[2024-08-05 08:22:26,880][00035] Saving configuration to /kaggle/working/train_dir/default_experiment/config.json... [2024-08-05 08:22:26,882][00035] Rollout worker 0 uses device cpu [2024-08-05 08:22:26,883][00035] Rollout worker 1 uses device cpu [2024-08-05 08:22:26,884][00035] Rollout worker 2 uses device cpu [2024-08-05 08:22:26,885][00035] Rollout worker 3 uses device cpu [2024-08-05 08:22:27,048][00035] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2024-08-05 08:22:27,051][00035] InferenceWorker_p0-w0: min num requests: 1 [2024-08-05 08:22:27,071][00035] Starting all processes... [2024-08-05 08:22:27,072][00035] Starting process learner_proc0 [2024-08-05 08:22:27,173][00035] Starting all processes... [2024-08-05 08:22:27,180][00035] Starting process inference_proc0-0 [2024-08-05 08:22:27,181][00035] Starting process rollout_proc0 [2024-08-05 08:22:27,181][00035] Starting process rollout_proc1 [2024-08-05 08:22:27,182][00035] Starting process rollout_proc2 [2024-08-05 08:22:27,182][00035] Starting process rollout_proc3 [2024-08-05 08:22:32,285][00137] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2024-08-05 08:22:32,286][00137] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 [2024-08-05 08:22:32,309][00137] Num visible devices: 1 [2024-08-05 08:22:32,346][00137] Setting fixed seed 0 [2024-08-05 08:22:32,350][00137] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2024-08-05 08:22:32,350][00137] Initializing actor-critic model on device cuda:0 [2024-08-05 08:22:32,351][00137] RunningMeanStd input shape: (23,) [2024-08-05 08:22:32,354][00137] RunningMeanStd input shape: (3, 72, 128) [2024-08-05 08:22:32,355][00137] RunningMeanStd input shape: (1,) [2024-08-05 08:22:32,373][00150] Worker 3 uses CPU cores [3] [2024-08-05 08:22:32,399][00137] ConvEncoder: input_channels=3 [2024-08-05 08:22:32,408][00147] Worker 0 uses CPU cores [0] [2024-08-05 08:22:32,422][00149] Worker 2 uses CPU cores [2] [2024-08-05 08:22:32,439][00148] Worker 1 uses CPU cores [1] [2024-08-05 08:22:32,552][00146] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2024-08-05 08:22:32,552][00146] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 [2024-08-05 08:22:32,570][00146] Num visible devices: 1 [2024-08-05 08:22:32,642][00137] Conv encoder output size: 512 [2024-08-05 08:22:32,643][00137] Policy head output size: 640 [2024-08-05 08:22:32,719][00137] Created Actor Critic model with architecture: [2024-08-05 08:22:32,720][00137] ActorCriticSharedWeights( (obs_normalizer): ObservationNormalizer( (running_mean_std): RunningMeanStdDictInPlace( (running_mean_std): ModuleDict( (measurements): RunningMeanStdInPlace() (obs): RunningMeanStdInPlace() ) ) ) (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) (encoder): VizdoomEncoder( (basic_encoder): ConvEncoder( (enc): RecursiveScriptModule( original_name=ConvEncoderImpl (conv_head): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Conv2d) (1): RecursiveScriptModule(original_name=ReLU) (2): RecursiveScriptModule(original_name=Conv2d) (3): RecursiveScriptModule(original_name=ReLU) (4): RecursiveScriptModule(original_name=Conv2d) (5): RecursiveScriptModule(original_name=ReLU) ) (mlp_layers): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Linear) (1): RecursiveScriptModule(original_name=ReLU) ) ) ) (measurements_head): Sequential( (0): Linear(in_features=23, out_features=128, bias=True) (1): ReLU() (2): Linear(in_features=128, out_features=128, bias=True) (3): ReLU() ) ) (core): ModelCoreRNN( (core): LSTM(640, 512) ) (decoder): MlpDecoder( (mlp): Identity() ) (critic_linear): Linear(in_features=512, out_features=1, bias=True) (action_parameterization): ActionParameterizationDefault( (distribution_linear): Linear(in_features=512, out_features=39, bias=True) ) ) [2024-08-05 08:22:32,969][00137] Using optimizer [2024-08-05 08:22:34,087][00137] No checkpoints found [2024-08-05 08:22:34,087][00137] Did not load from checkpoint, starting from scratch! [2024-08-05 08:22:34,087][00137] Initialized policy 0 weights for model version 0 [2024-08-05 08:22:34,092][00137] LearnerWorker_p0 finished initialization! [2024-08-05 08:22:34,093][00137] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2024-08-05 08:22:34,183][00146] RunningMeanStd input shape: (23,) [2024-08-05 08:22:34,184][00146] RunningMeanStd input shape: (3, 72, 128) [2024-08-05 08:22:34,185][00146] RunningMeanStd input shape: (1,) [2024-08-05 08:22:34,200][00146] ConvEncoder: input_channels=3 [2024-08-05 08:22:34,320][00146] Conv encoder output size: 512 [2024-08-05 08:22:34,321][00146] Policy head output size: 640 [2024-08-05 08:22:34,393][00035] Inference worker 0-0 is ready! [2024-08-05 08:22:34,394][00035] All inference workers are ready! Signal rollout workers to start! [2024-08-05 08:22:34,451][00147] Doom resolution: 160x120, resize resolution: (128, 72) [2024-08-05 08:22:34,452][00150] Doom resolution: 160x120, resize resolution: (128, 72) [2024-08-05 08:22:34,453][00148] Doom resolution: 160x120, resize resolution: (128, 72) [2024-08-05 08:22:34,454][00147] Port 40300 is available [2024-08-05 08:22:34,455][00147] Using port 40300 [2024-08-05 08:22:34,454][00149] Doom resolution: 160x120, resize resolution: (128, 72) [2024-08-05 08:22:34,455][00150] Port 40600 is available [2024-08-05 08:22:34,455][00150] Using port 40600 [2024-08-05 08:22:34,457][00148] Port 40400 is available [2024-08-05 08:22:34,457][00148] Using port 40400 [2024-08-05 08:22:34,459][00149] Port 40500 is available [2024-08-05 08:22:34,459][00149] Using port 40500 [2024-08-05 08:22:34,507][00147] Port 40301 is available [2024-08-05 08:22:34,507][00150] Port 40601 is available [2024-08-05 08:22:34,507][00147] Using port 40301 [2024-08-05 08:22:34,507][00150] Using port 40601 [2024-08-05 08:22:34,508][00148] Port 40401 is available [2024-08-05 08:22:34,508][00148] Using port 40401 [2024-08-05 08:22:34,509][00149] Port 40501 is available [2024-08-05 08:22:34,509][00149] Using port 40501 [2024-08-05 08:22:34,510][00147] Using port 40300 on host... [2024-08-05 08:22:34,511][00148] Using port 40400 on host... [2024-08-05 08:22:34,511][00150] Using port 40600 on host... [2024-08-05 08:22:34,512][00149] Using port 40500 on host... [2024-08-05 08:22:35,067][00147] Initialized w:0 v:0 player:0 [2024-08-05 08:22:35,067][00149] Initialized w:2 v:0 player:0 [2024-08-05 08:22:35,068][00148] Initialized w:1 v:0 player:0 [2024-08-05 08:22:35,067][00150] Initialized w:3 v:0 player:0 [2024-08-05 08:22:35,075][00148] Decorrelating experience for 0 frames... [2024-08-05 08:22:35,075][00149] Decorrelating experience for 0 frames... [2024-08-05 08:22:35,075][00147] Decorrelating experience for 0 frames... [2024-08-05 08:22:35,075][00150] Decorrelating experience for 0 frames... [2024-08-05 08:22:35,077][00148] Using port 40401 on host... [2024-08-05 08:22:35,077][00147] Using port 40301 on host... [2024-08-05 08:22:35,077][00149] Using port 40501 on host... [2024-08-05 08:22:35,077][00150] Using port 40601 on host... [2024-08-05 08:22:35,569][00147] Initialized w:0 v:1 player:0 [2024-08-05 08:22:35,572][00147] Decorrelating experience for 32 frames... [2024-08-05 08:22:35,574][00150] Initialized w:3 v:1 player:0 [2024-08-05 08:22:35,576][00150] Decorrelating experience for 32 frames... [2024-08-05 08:22:35,578][00149] Initialized w:2 v:1 player:0 [2024-08-05 08:22:35,578][00148] Initialized w:1 v:1 player:0 [2024-08-05 08:22:35,580][00149] Decorrelating experience for 32 frames... [2024-08-05 08:22:35,580][00148] Decorrelating experience for 32 frames... [2024-08-05 08:22:35,707][00147] Port 40302 is available [2024-08-05 08:22:35,707][00149] Port 40502 is available [2024-08-05 08:22:35,707][00147] Using port 40302 [2024-08-05 08:22:35,708][00149] Using port 40502 [2024-08-05 08:22:35,710][00150] Port 40602 is available [2024-08-05 08:22:35,711][00150] Using port 40602 [2024-08-05 08:22:35,712][00148] Port 40402 is available [2024-08-05 08:22:35,713][00148] Using port 40402 [2024-08-05 08:22:35,758][00149] Port 40503 is available [2024-08-05 08:22:35,759][00149] Using port 40503 [2024-08-05 08:22:35,760][00147] Port 40303 is available [2024-08-05 08:22:35,761][00147] Using port 40303 [2024-08-05 08:22:35,762][00149] Using port 40502 on host... [2024-08-05 08:22:35,762][00150] Port 40603 is available [2024-08-05 08:22:35,762][00150] Using port 40603 [2024-08-05 08:22:35,764][00148] Port 40403 is available [2024-08-05 08:22:35,764][00147] Using port 40302 on host... [2024-08-05 08:22:35,764][00148] Using port 40403 [2024-08-05 08:22:35,765][00150] Using port 40602 on host... [2024-08-05 08:22:35,767][00148] Using port 40402 on host... [2024-08-05 08:22:36,255][00149] Initialized w:2 v:2 player:0 [2024-08-05 08:22:36,257][00149] Decorrelating experience for 64 frames... [2024-08-05 08:22:36,260][00148] Initialized w:1 v:2 player:0 [2024-08-05 08:22:36,260][00150] Initialized w:3 v:2 player:0 [2024-08-05 08:22:36,262][00148] Decorrelating experience for 64 frames... [2024-08-05 08:22:36,262][00150] Decorrelating experience for 64 frames... [2024-08-05 08:22:36,278][00147] Initialized w:0 v:2 player:0 [2024-08-05 08:22:36,280][00147] Decorrelating experience for 64 frames... [2024-08-05 08:22:36,418][00148] Using port 40403 on host... [2024-08-05 08:22:36,419][00149] Using port 40503 on host... [2024-08-05 08:22:36,422][00150] Using port 40603 on host... [2024-08-05 08:22:36,455][00147] Using port 40303 on host... [2024-08-05 08:22:36,500][00035] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-05 08:22:36,990][00150] Initialized w:3 v:3 player:0 [2024-08-05 08:22:36,990][00148] Initialized w:1 v:3 player:0 [2024-08-05 08:22:36,993][00150] Decorrelating experience for 96 frames... [2024-08-05 08:22:36,993][00148] Decorrelating experience for 96 frames... [2024-08-05 08:22:37,002][00149] Initialized w:2 v:3 player:0 [2024-08-05 08:22:37,004][00149] Decorrelating experience for 96 frames... [2024-08-05 08:22:37,010][00147] Initialized w:0 v:3 player:0 [2024-08-05 08:22:37,012][00147] Decorrelating experience for 96 frames... [2024-08-05 08:22:41,500][00035] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 414.4. Samples: 2072. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-05 08:22:46,015][00137] Signal inference workers to stop experience collection... [2024-08-05 08:22:46,042][00146] InferenceWorker_p0-w0: stopping experience collection [2024-08-05 08:22:46,500][00035] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 450.0. Samples: 4500. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-05 08:22:46,589][00137] Signal inference workers to resume experience collection... [2024-08-05 08:22:46,590][00146] InferenceWorker_p0-w0: resuming experience collection [2024-08-05 08:22:47,040][00035] Heartbeat connected on Batcher_0 [2024-08-05 08:22:47,058][00035] Heartbeat connected on RolloutWorker_w0 [2024-08-05 08:22:47,065][00035] Heartbeat connected on InferenceWorker_p0-w0 [2024-08-05 08:22:47,071][00035] Heartbeat connected on RolloutWorker_w3 [2024-08-05 08:22:47,078][00035] Heartbeat connected on RolloutWorker_w1 [2024-08-05 08:22:47,091][00035] Heartbeat connected on RolloutWorker_w2 [2024-08-05 08:22:47,983][00035] Heartbeat connected on LearnerWorker_p0 [2024-08-05 08:22:51,500][00035] Fps is (10 sec: 2457.6, 60 sec: 1638.4, 300 sec: 1638.4). Total num frames: 24576. Throughput: 0: 425.3. Samples: 6380. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2024-08-05 08:22:56,500][00035] Fps is (10 sec: 4915.2, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 49152. Throughput: 0: 595.2. Samples: 11904. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:23:01,500][00035] Fps is (10 sec: 4096.0, 60 sec: 2621.4, 300 sec: 2621.4). Total num frames: 65536. Throughput: 0: 696.3. Samples: 17408. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:23:04,982][00146] Updated weights for policy 0, policy_version 10 (0.0224) [2024-08-05 08:23:06,501][00035] Fps is (10 sec: 3276.7, 60 sec: 2730.6, 300 sec: 2730.6). Total num frames: 81920. Throughput: 0: 675.5. Samples: 20264. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:23:11,500][00035] Fps is (10 sec: 3276.8, 60 sec: 2808.7, 300 sec: 2808.7). Total num frames: 98304. Throughput: 0: 736.7. Samples: 25786. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:23:16,500][00035] Fps is (10 sec: 4096.2, 60 sec: 3072.0, 300 sec: 3072.0). Total num frames: 122880. Throughput: 0: 784.0. Samples: 31360. Policy #0 lag: (min: 0.0, avg: 0.0, max: 1.0) [2024-08-05 08:23:16,631][00150] DAMAGECOUNT value on done: 30.0 [2024-08-05 08:23:16,633][00150] Sum rewards: -6.207, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.214', 'AMMO5': '0.005', 'AMMO2': '0.019', 'HITCOUNT': '0.030', 'weapon4': '0.070', 'ARMOR': '0.076', 'DAMAGECOUNT': '0.090', 'AMMO4': '0.094', 'WEAPON5': '0.100', 'AMMO3': '0.133', 'WEAPON4': '0.200', 'WEAPON3': '0.650', 'weapon3': '0.664', 'weapon2': '0.876', 'FRAGCOUNT': '1.000'} [2024-08-05 08:23:16,716][00149] DAMAGECOUNT value on done: 0.0 [2024-08-05 08:23:17,200][00150] DAMAGECOUNT value on done: 130.0 [2024-08-05 08:23:17,201][00150] Sum rewards: -6.632, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-2.006', 'AMMO2': '0.007', 'weapon4': '0.016', 'AMMO4': '0.036', 'WEAPON4': '0.100', 'HITCOUNT': '0.110', 'AMMO3': '0.148', 'DAMAGECOUNT': '0.390', 'ARMOR': '0.512', 'weapon3': '0.612', 'WEAPON3': '0.800', 'weapon2': '0.892', 'FRAGCOUNT': '3.000'} [2024-08-05 08:23:17,255][00149] DAMAGECOUNT value on done: 0.0 [2024-08-05 08:23:17,678][00147] DAMAGECOUNT value on done: 255.0 [2024-08-05 08:23:17,679][00147] Sum rewards: -5.243, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-2.012', 'AMMO2': '0.022', 'AMMO4': '0.107', 'ARMOR': '0.121', 'weapon4': '0.150', 'AMMO3': '0.168', 'HITCOUNT': '0.210', 'WEAPON4': '0.250', 'weapon3': '0.566', 'DAMAGECOUNT': '0.765', 'WEAPON3': '0.800', 'weapon2': '0.860', 'FRAGCOUNT': '1.000'} [2024-08-05 08:23:17,748][00148] DAMAGECOUNT value on done: 65.0 [2024-08-05 08:23:17,760][00150] DAMAGECOUNT value on done: 20.0 [2024-08-05 08:23:17,805][00149] DAMAGECOUNT value on done: 33.0 [2024-08-05 08:23:17,806][00149] Sum rewards: -5.750, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.862', 'HITCOUNT': '0.020', 'AMMO2': '0.026', 'ARMOR': '0.080', 'DAMAGECOUNT': '0.099', 'weapon4': '0.106', 'AMMO3': '0.113', 'AMMO4': '0.132', 'WEAPON4': '0.300', 'WEAPON3': '0.600', 'weapon3': '0.698', 'weapon2': '0.938', 'FRAGCOUNT': '1.000'} [2024-08-05 08:23:18,280][00147] DAMAGECOUNT value on done: 55.0 [2024-08-05 08:23:18,350][00148] DAMAGECOUNT value on done: 110.0 [2024-08-05 08:23:18,350][00148] Sum rewards: -5.800, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.678', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.003', 'weapon5': '0.008', 'AMMO2': '0.012', 'weapon4': '0.012', 'ARMOR': '0.048', 'WEAPON5': '0.050', 'AMMO4': '0.057', 'HITCOUNT': '0.060', 'AMMO3': '0.087', 'WEAPON4': '0.100', 'DAMAGECOUNT': '0.330', 'WEAPON3': '0.450', 'weapon3': '0.750', 'weapon2': '0.912'} [2024-08-05 08:23:18,370][00150] DAMAGECOUNT value on done: 120.0 [2024-08-05 08:23:18,441][00149] DAMAGECOUNT value on done: 0.0 [2024-08-05 08:23:18,442][00149] Sum rewards: -13.900, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-2.954', 'FRAGCOUNT': '-1.500', 'AMMO4': '-0.008', 'AMMO2': '-0.002', 'AMMO5': '0.010', 'weapon5': '0.020', 'ARMOR': '0.024', 'WEAPON5': '0.200', 'AMMO3': '0.245', 'weapon3': '0.722', 'weapon2': '0.792', 'WEAPON3': '1.300'} [2024-08-05 08:23:18,890][00148] DAMAGECOUNT value on done: 20.0 [2024-08-05 08:23:18,929][00147] DAMAGECOUNT value on done: 107.0 [2024-08-05 08:23:18,929][00147] Sum rewards: -5.751, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.664', 'AMMO2': '0.009', 'ARMOR': '0.020', 'AMMO4': '0.043', 'HITCOUNT': '0.080', 'WEAPON4': '0.100', 'AMMO3': '0.110', 'DAMAGECOUNT': '0.321', 'WEAPON3': '0.600', 'weapon3': '0.926', 'weapon2': '0.954', 'FRAGCOUNT': '1.000'} [2024-08-05 08:23:19,435][00148] DAMAGECOUNT value on done: 0.0 [2024-08-05 08:23:19,523][00147] DAMAGECOUNT value on done: 0.0 [2024-08-05 08:23:21,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3094.8, 300 sec: 3094.8). Total num frames: 139264. Throughput: 0: 756.2. Samples: 34028. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:23:21,502][00035] Avg episode reward: [(0, '-6.223')] [2024-08-05 08:23:21,505][00137] Saving new best policy, reward=-6.223! [2024-08-05 08:23:26,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3113.0, 300 sec: 3113.0). Total num frames: 155648. Throughput: 0: 823.2. Samples: 39116. Policy #0 lag: (min: 0.0, avg: 0.0, max: 1.0) [2024-08-05 08:23:26,502][00035] Avg episode reward: [(0, '-6.223')] [2024-08-05 08:23:27,583][00146] Updated weights for policy 0, policy_version 20 (0.0023) [2024-08-05 08:23:31,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3127.9, 300 sec: 3127.9). Total num frames: 172032. Throughput: 0: 892.4. Samples: 44656. Policy #0 lag: (min: 0.0, avg: 0.0, max: 1.0) [2024-08-05 08:23:31,501][00035] Avg episode reward: [(0, '-6.223')] [2024-08-05 08:23:36,500][00035] Fps is (10 sec: 3276.7, 60 sec: 3140.2, 300 sec: 3140.2). Total num frames: 188416. Throughput: 0: 912.6. Samples: 47446. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:23:36,503][00035] Avg episode reward: [(0, '-6.223')] [2024-08-05 08:23:41,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3276.8). Total num frames: 212992. Throughput: 0: 912.6. Samples: 52972. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:23:41,502][00035] Avg episode reward: [(0, '-6.223')] [2024-08-05 08:23:46,500][00035] Fps is (10 sec: 4096.2, 60 sec: 3822.9, 300 sec: 3276.8). Total num frames: 229376. Throughput: 0: 913.2. Samples: 58502. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:23:46,504][00035] Avg episode reward: [(0, '-6.223')] [2024-08-05 08:23:49,765][00146] Updated weights for policy 0, policy_version 30 (0.0027) [2024-08-05 08:23:51,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3276.8). Total num frames: 245760. Throughput: 0: 911.3. Samples: 61274. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:23:51,501][00035] Avg episode reward: [(0, '-6.223')] [2024-08-05 08:23:53,042][00150] DAMAGECOUNT value on done: 95.0 [2024-08-05 08:23:53,280][00149] DAMAGECOUNT value on done: 0.0 [2024-08-05 08:23:53,836][00150] DAMAGECOUNT value on done: 135.0 [2024-08-05 08:23:54,004][00149] DAMAGECOUNT value on done: 150.0 [2024-08-05 08:23:54,005][00149] Sum rewards: -4.574, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.661', 'AMMO2': '0.019', 'ARMOR': '0.036', 'weapon4': '0.040', 'HITCOUNT': '0.090', 'AMMO4': '0.096', 'AMMO3': '0.097', 'WEAPON4': '0.200', 'WEAPON3': '0.450', 'DAMAGECOUNT': '0.450', 'weapon3': '0.776', 'FRAGCOUNT': '1.000', 'weapon2': '1.082'} [2024-08-05 08:23:54,354][00150] DAMAGECOUNT value on done: 25.0 [2024-08-05 08:23:54,567][00149] DAMAGECOUNT value on done: 208.0 [2024-08-05 08:23:54,569][00149] Sum rewards: -2.385, reward structure: {'DEATHCOUNT': '-5.250', 'FRAGCOUNT': '-0.500', 'HEALTH': '-0.144', 'AMMO5': '0.007', 'HITCOUNT': '0.030', 'AMMO2': '0.036', 'AMMO3': '0.057', 'weapon5': '0.104', 'weapon4': '0.126', 'WEAPON5': '0.150', 'AMMO4': '0.178', 'WEAPON4': '0.200', 'WEAPON3': '0.300', 'weapon3': '0.426', 'ARMOR': '0.444', 'DAMAGECOUNT': '0.525', 'weapon2': '0.926'} [2024-08-05 08:23:54,976][00150] DAMAGECOUNT value on done: 125.0 [2024-08-05 08:23:55,168][00149] DAMAGECOUNT value on done: 0.0 [2024-08-05 08:23:55,584][00147] DAMAGECOUNT value on done: 270.0 [2024-08-05 08:23:55,975][00148] DAMAGECOUNT value on done: 180.0 [2024-08-05 08:23:55,976][00148] Sum rewards: -7.325, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.680', 'AMMO2': '0.016', 'AMMO4': '0.079', 'HITCOUNT': '0.110', 'ARMOR': '0.116', 'AMMO3': '0.137', 'WEAPON4': '0.200', 'weapon4': '0.288', 'DAMAGECOUNT': '0.345', 'weapon3': '0.452', 'WEAPON3': '0.500', 'weapon2': '0.862', 'FRAGCOUNT': '1.000'} [2024-08-05 08:23:56,127][00147] DAMAGECOUNT value on done: 62.0 [2024-08-05 08:23:56,500][00035] Fps is (10 sec: 3276.7, 60 sec: 3549.9, 300 sec: 3276.8). Total num frames: 262144. Throughput: 0: 902.5. Samples: 66400. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:23:56,502][00035] Avg episode reward: [(0, '-6.187')] [2024-08-05 08:23:56,503][00137] Saving new best policy, reward=-6.187! [2024-08-05 08:23:56,589][00148] DAMAGECOUNT value on done: 208.0 [2024-08-05 08:23:56,717][00147] DAMAGECOUNT value on done: 152.0 [2024-08-05 08:23:57,258][00148] DAMAGECOUNT value on done: 220.0 [2024-08-05 08:23:57,259][00148] Sum rewards: -5.480, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.183', 'AMMO5': '0.005', 'AMMO2': '0.010', 'ARMOR': '0.032', 'AMMO4': '0.050', 'weapon4': '0.080', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.109', 'HITCOUNT': '0.160', 'WEAPON3': '0.550', 'DAMAGECOUNT': '0.600', 'weapon3': '0.626', 'FRAGCOUNT': '1.000', 'weapon2': '1.030'} [2024-08-05 08:23:57,322][00147] DAMAGECOUNT value on done: 125.0 [2024-08-05 08:23:57,827][00148] DAMAGECOUNT value on done: 170.0 [2024-08-05 08:23:57,829][00148] Sum rewards: -3.916, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.980', 'weapon5': '0.002', 'AMMO5': '0.010', 'AMMO2': '0.029', 'ARMOR': '0.032', 'WEAPON5': '0.100', 'AMMO3': '0.106', 'HITCOUNT': '0.130', 'AMMO4': '0.143', 'weapon4': '0.206', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.510', 'WEAPON3': '0.550', 'weapon3': '0.552', 'weapon2': '0.894', 'FRAGCOUNT': '1.000'} [2024-08-05 08:24:01,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3373.2). Total num frames: 286720. Throughput: 0: 900.4. Samples: 71876. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:24:01,502][00035] Avg episode reward: [(0, '-6.267')] [2024-08-05 08:24:06,500][00035] Fps is (10 sec: 4096.1, 60 sec: 3686.4, 300 sec: 3367.8). Total num frames: 303104. Throughput: 0: 903.9. Samples: 74704. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:24:06,502][00035] Avg episode reward: [(0, '-6.267')] [2024-08-05 08:24:11,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3363.0). Total num frames: 319488. Throughput: 0: 914.8. Samples: 80280. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:24:11,502][00035] Avg episode reward: [(0, '-6.267')] [2024-08-05 08:24:12,463][00146] Updated weights for policy 0, policy_version 40 (0.0029) [2024-08-05 08:24:16,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3358.7). Total num frames: 335872. Throughput: 0: 917.6. Samples: 85946. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:24:16,502][00035] Avg episode reward: [(0, '-6.267')] [2024-08-05 08:24:17,280][00148] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-05 08:24:21,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3432.8). Total num frames: 360448. Throughput: 0: 916.0. Samples: 88668. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:24:21,502][00035] Avg episode reward: [(0, '-6.267')] [2024-08-05 08:24:21,507][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000044_360448.pth... [2024-08-05 08:24:26,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3425.7). Total num frames: 376832. Throughput: 0: 911.7. Samples: 93998. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:24:26,502][00035] Avg episode reward: [(0, '-6.267')] [2024-08-05 08:24:29,407][00150] DAMAGECOUNT value on done: 125.0 [2024-08-05 08:24:29,597][00149] DAMAGECOUNT value on done: 22.0 [2024-08-05 08:24:29,598][00149] Sum rewards: -10.994, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.050', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.014', 'AMMO2': '0.015', 'weapon5': '0.018', 'HITCOUNT': '0.030', 'ARMOR': '0.052', 'DAMAGECOUNT': '0.066', 'AMMO4': '0.076', 'weapon4': '0.078', 'AMMO3': '0.142', 'WEAPON4': '0.150', 'WEAPON5': '0.200', 'weapon3': '0.470', 'WEAPON3': '0.750', 'weapon2': '0.994'} [2024-08-05 08:24:29,934][00150] DAMAGECOUNT value on done: 260.0 [2024-08-05 08:24:29,935][00150] Sum rewards: -2.707, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-1.440', 'AMMO2': '0.023', 'ARMOR': '0.040', 'AMMO3': '0.057', 'HITCOUNT': '0.070', 'AMMO4': '0.116', 'weapon4': '0.244', 'WEAPON3': '0.300', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.375', 'weapon3': '0.444', 'FRAGCOUNT': '1.000', 'weapon2': '1.014'} [2024-08-05 08:24:30,152][00149] DAMAGECOUNT value on done: 379.0 [2024-08-05 08:24:30,153][00149] Sum rewards: -4.289, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.916', 'AMMO2': '0.004', 'AMMO5': '0.005', 'weapon5': '0.018', 'AMMO4': '0.021', 'weapon4': '0.026', 'HITCOUNT': '0.040', 'WEAPON4': '0.050', 'WEAPON5': '0.050', 'AMMO3': '0.117', 'ARMOR': '0.487', 'WEAPON3': '0.650', 'DAMAGECOUNT': '0.675', 'weapon3': '0.712', 'FRAGCOUNT': '1.000', 'weapon2': '1.022'} [2024-08-05 08:24:30,492][00150] DAMAGECOUNT value on done: 30.0 [2024-08-05 08:24:30,731][00149] DAMAGECOUNT value on done: 233.0 [2024-08-05 08:24:31,066][00150] DAMAGECOUNT value on done: 125.0 [2024-08-05 08:24:31,241][00149] DAMAGECOUNT value on done: 0.0 [2024-08-05 08:24:31,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3419.3). Total num frames: 393216. Throughput: 0: 907.6. Samples: 99344. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:24:31,502][00035] Avg episode reward: [(0, '-6.395')] [2024-08-05 08:24:32,691][00147] DAMAGECOUNT value on done: 385.0 [2024-08-05 08:24:32,692][00147] Sum rewards: -5.785, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.226', 'AMMO5': '0.007', 'AMMO2': '0.013', 'HITCOUNT': '0.060', 'AMMO4': '0.064', 'weapon5': '0.070', 'ARMOR': '0.072', 'WEAPON5': '0.150', 'AMMO3': '0.172', 'DAMAGECOUNT': '0.345', 'weapon2': '0.768', 'WEAPON3': '0.850', 'weapon3': '0.870', 'FRAGCOUNT': '1.000'} [2024-08-05 08:24:33,257][00147] DAMAGECOUNT value on done: 80.0 [2024-08-05 08:24:33,258][00147] Sum rewards: -5.696, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.024', 'HITCOUNT': '0.010', 'AMMO2': '0.021', 'ARMOR': '0.048', 'DAMAGECOUNT': '0.054', 'AMMO3': '0.082', 'AMMO4': '0.105', 'weapon4': '0.134', 'WEAPON4': '0.250', 'weapon3': '0.390', 'WEAPON3': '0.450', 'FRAGCOUNT': '1.000', 'weapon2': '1.034'} [2024-08-05 08:24:33,514][00148] DAMAGECOUNT value on done: 195.0 [2024-08-05 08:24:33,828][00147] DAMAGECOUNT value on done: 197.0 [2024-08-05 08:24:33,829][00147] Sum rewards: -10.512, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-1.804', 'AMMO2': '0.024', 'HITCOUNT': '0.040', 'ARMOR': '0.049', 'AMMO4': '0.120', 'weapon4': '0.134', 'DAMAGECOUNT': '0.135', 'AMMO3': '0.139', 'WEAPON4': '0.250', 'weapon3': '0.396', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon2': '1.054'} [2024-08-05 08:24:34,054][00148] DAMAGECOUNT value on done: 273.0 [2024-08-05 08:24:34,398][00147] DAMAGECOUNT value on done: 135.0 [2024-08-05 08:24:34,611][00148] DAMAGECOUNT value on done: 245.0 [2024-08-05 08:24:34,612][00148] Sum rewards: -6.974, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.748', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.005', 'AMMO2': '0.008', 'weapon5': '0.014', 'HITCOUNT': '0.020', 'AMMO4': '0.039', 'ARMOR': '0.040', 'DAMAGECOUNT': '0.075', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.129', 'weapon4': '0.132', 'weapon2': '0.724', 'WEAPON3': '0.750', 'weapon3': '0.888'} [2024-08-05 08:24:35,015][00146] Updated weights for policy 0, policy_version 50 (0.0019) [2024-08-05 08:24:35,228][00148] DAMAGECOUNT value on done: 240.0 [2024-08-05 08:24:36,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3413.3). Total num frames: 409600. Throughput: 0: 908.5. Samples: 102158. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:24:36,502][00035] Avg episode reward: [(0, '-6.533')] [2024-08-05 08:24:41,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3407.9). Total num frames: 425984. Throughput: 0: 916.2. Samples: 107628. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:24:41,502][00035] Avg episode reward: [(0, '-6.533')] [2024-08-05 08:24:46,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3465.8). Total num frames: 450560. Throughput: 0: 918.4. Samples: 113206. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:24:46,502][00035] Avg episode reward: [(0, '-6.533')] [2024-08-05 08:24:51,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3458.8). Total num frames: 466944. Throughput: 0: 916.6. Samples: 115950. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:24:51,502][00035] Avg episode reward: [(0, '-6.533')] [2024-08-05 08:24:56,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3452.3). Total num frames: 483328. Throughput: 0: 916.4. Samples: 121518. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:24:56,502][00035] Avg episode reward: [(0, '-6.533')] [2024-08-05 08:24:57,668][00146] Updated weights for policy 0, policy_version 60 (0.0019) [2024-08-05 08:25:01,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3446.3). Total num frames: 499712. Throughput: 0: 904.5. Samples: 126650. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:25:01,504][00035] Avg episode reward: [(0, '-6.533')] [2024-08-05 08:25:05,654][00149] DAMAGECOUNT value on done: 22.0 [2024-08-05 08:25:05,779][00150] DAMAGECOUNT value on done: 150.0 [2024-08-05 08:25:06,208][00149] DAMAGECOUNT value on done: 394.0 [2024-08-05 08:25:06,289][00150] DAMAGECOUNT value on done: 455.0 [2024-08-05 08:25:06,500][00035] Fps is (10 sec: 3276.7, 60 sec: 3549.8, 300 sec: 3440.6). Total num frames: 516096. Throughput: 0: 907.1. Samples: 129488. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:25:06,502][00035] Avg episode reward: [(0, '-6.417')] [2024-08-05 08:25:06,830][00149] DAMAGECOUNT value on done: 238.0 [2024-08-05 08:25:06,931][00150] DAMAGECOUNT value on done: 74.0 [2024-08-05 08:25:07,384][00149] DAMAGECOUNT value on done: 34.0 [2024-08-05 08:25:07,494][00150] DAMAGECOUNT value on done: 132.0 [2024-08-05 08:25:10,255][00147] DAMAGECOUNT value on done: 497.0 [2024-08-05 08:25:10,256][00147] Sum rewards: -5.499, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.840', 'AMMO2': '0.005', 'AMMO5': '0.014', 'weapon5': '0.020', 'AMMO4': '0.023', 'ARMOR': '0.032', 'weapon4': '0.076', 'WEAPON4': '0.100', 'HITCOUNT': '0.120', 'AMMO3': '0.137', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.336', 'WEAPON3': '0.650', 'weapon3': '0.818', 'FRAGCOUNT': '1.000', 'weapon2': '1.060'} [2024-08-05 08:25:10,712][00148] DAMAGECOUNT value on done: 225.0 [2024-08-05 08:25:10,811][00147] DAMAGECOUNT value on done: 115.0 [2024-08-05 08:25:11,329][00148] DAMAGECOUNT value on done: 308.0 [2024-08-05 08:25:11,330][00148] Sum rewards: -4.260, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.543', 'AMMO2': '0.012', 'HITCOUNT': '0.030', 'AMMO4': '0.061', 'AMMO3': '0.069', 'WEAPON4': '0.100', 'DAMAGECOUNT': '0.105', 'ARMOR': '0.152', 'weapon4': '0.228', 'WEAPON3': '0.350', 'weapon3': '0.350', 'FRAGCOUNT': '1.000', 'weapon2': '1.326'} [2024-08-05 08:25:11,444][00147] DAMAGECOUNT value on done: 307.0 [2024-08-05 08:25:11,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3488.2). Total num frames: 540672. Throughput: 0: 911.3. Samples: 135006. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:25:11,502][00035] Avg episode reward: [(0, '-6.604')] [2024-08-05 08:25:11,878][00148] DAMAGECOUNT value on done: 320.0 [2024-08-05 08:25:11,879][00148] Sum rewards: -4.353, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.054', 'AMMO5': '0.003', 'AMMO2': '0.011', 'weapon5': '0.018', 'WEAPON5': '0.050', 'AMMO4': '0.054', 'ARMOR': '0.068', 'HITCOUNT': '0.080', 'WEAPON4': '0.100', 'AMMO3': '0.117', 'weapon4': '0.144', 'DAMAGECOUNT': '0.225', 'WEAPON3': '0.600', 'weapon3': '0.628', 'weapon2': '0.854', 'FRAGCOUNT': '1.000'} [2024-08-05 08:25:11,977][00147] DAMAGECOUNT value on done: 135.0 [2024-08-05 08:25:12,462][00148] DAMAGECOUNT value on done: 275.0 [2024-08-05 08:25:12,463][00148] Sum rewards: -4.482, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.035', 'AMMO5': '0.005', 'AMMO2': '0.028', 'ARMOR': '0.036', 'HITCOUNT': '0.040', 'weapon4': '0.088', 'WEAPON5': '0.100', 'DAMAGECOUNT': '0.105', 'AMMO3': '0.109', 'AMMO4': '0.138', 'WEAPON4': '0.300', 'weapon3': '0.578', 'WEAPON3': '0.600', 'weapon2': '0.926', 'FRAGCOUNT': '1.000'} [2024-08-05 08:25:16,500][00035] Fps is (10 sec: 4096.1, 60 sec: 3686.4, 300 sec: 3481.6). Total num frames: 557056. Throughput: 0: 915.9. Samples: 140560. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:25:16,501][00035] Avg episode reward: [(0, '-6.599')] [2024-08-05 08:25:19,675][00146] Updated weights for policy 0, policy_version 70 (0.0023) [2024-08-05 08:25:21,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3475.4). Total num frames: 573440. Throughput: 0: 916.0. Samples: 143380. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:25:21,502][00035] Avg episode reward: [(0, '-6.599')] [2024-08-05 08:25:26,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3517.7). Total num frames: 598016. Throughput: 0: 918.1. Samples: 148942. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:25:26,502][00035] Avg episode reward: [(0, '-6.599')] [2024-08-05 08:25:31,500][00035] Fps is (10 sec: 4095.9, 60 sec: 3686.4, 300 sec: 3510.9). Total num frames: 614400. Throughput: 0: 907.0. Samples: 154020. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:25:31,502][00035] Avg episode reward: [(0, '-6.599')] [2024-08-05 08:25:36,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3504.4). Total num frames: 630784. Throughput: 0: 908.0. Samples: 156808. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:25:36,502][00035] Avg episode reward: [(0, '-6.599')] [2024-08-05 08:25:41,500][00035] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3498.2). Total num frames: 647168. Throughput: 0: 906.4. Samples: 162306. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:25:41,501][00035] Avg episode reward: [(0, '-6.599')] [2024-08-05 08:25:41,830][00150] DAMAGECOUNT value on done: 150.0 [2024-08-05 08:25:41,849][00149] DAMAGECOUNT value on done: 97.0 [2024-08-05 08:25:41,849][00149] Sum rewards: -8.881, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-2.431', 'AMMO4': '-0.022', 'AMMO2': '-0.004', 'AMMO5': '0.008', 'weapon5': '0.026', 'HITCOUNT': '0.080', 'WEAPON5': '0.150', 'AMMO3': '0.171', 'DAMAGECOUNT': '0.225', 'ARMOR': '0.472', 'weapon3': '0.726', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '1.168'} [2024-08-05 08:25:42,387][00146] Updated weights for policy 0, policy_version 80 (0.0020) [2024-08-05 08:25:42,417][00150] DAMAGECOUNT value on done: 520.0 [2024-08-05 08:25:42,418][00150] Sum rewards: -8.780, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-1.025', 'ARMOR': '0.004', 'AMMO2': '0.018', 'HITCOUNT': '0.070', 'AMMO4': '0.088', 'WEAPON4': '0.100', 'AMMO3': '0.182', 'DAMAGECOUNT': '0.195', 'weapon3': '0.734', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '1.054'} [2024-08-05 08:25:42,445][00149] DAMAGECOUNT value on done: 457.0 [2024-08-05 08:25:42,959][00149] DAMAGECOUNT value on done: 353.0 [2024-08-05 08:25:42,961][00149] Sum rewards: -5.644, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.414', 'AMMO5': '0.005', 'AMMO2': '0.019', 'weapon5': '0.024', 'ARMOR': '0.056', 'HITCOUNT': '0.070', 'AMMO4': '0.093', 'WEAPON5': '0.100', 'weapon4': '0.114', 'AMMO3': '0.182', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.345', 'weapon3': '0.792', 'weapon2': '0.820', 'WEAPON3': '0.950', 'FRAGCOUNT': '1.000'} [2024-08-05 08:25:43,015][00150] DAMAGECOUNT value on done: 89.0 [2024-08-05 08:25:43,506][00149] DAMAGECOUNT value on done: 160.0 [2024-08-05 08:25:43,507][00149] Sum rewards: -5.882, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.910', 'AMMO5': '0.010', 'AMMO2': '0.014', 'HITCOUNT': '0.040', 'AMMO4': '0.068', 'AMMO3': '0.078', 'weapon5': '0.124', 'weapon4': '0.134', 'WEAPON4': '0.150', 'WEAPON5': '0.200', 'WEAPON3': '0.300', 'DAMAGECOUNT': '0.378', 'weapon3': '0.496', 'FRAGCOUNT': '1.000', 'weapon2': '1.036'} [2024-08-05 08:25:43,540][00150] DAMAGECOUNT value on done: 232.0 [2024-08-05 08:25:43,541][00150] Sum rewards: -4.695, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.094', 'AMMO5': '0.005', 'weapon5': '0.008', 'AMMO2': '0.009', 'weapon4': '0.042', 'AMMO4': '0.042', 'WEAPON4': '0.050', 'HITCOUNT': '0.050', 'AMMO3': '0.095', 'WEAPON5': '0.100', 'DAMAGECOUNT': '0.300', 'WEAPON3': '0.500', 'weapon3': '0.718', 'weapon2': '0.980', 'FRAGCOUNT': '1.000'} [2024-08-05 08:25:46,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3492.4). Total num frames: 663552. Throughput: 0: 916.8. Samples: 167904. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:25:46,502][00035] Avg episode reward: [(0, '-6.729')] [2024-08-05 08:25:47,970][00147] DAMAGECOUNT value on done: 650.0 [2024-08-05 08:25:47,971][00147] Sum rewards: -2.391, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-0.560', 'AMMO4': '-0.009', 'AMMO2': '-0.002', 'weapon5': '0.002', 'AMMO5': '0.003', 'ARMOR': '0.036', 'WEAPON5': '0.050', 'AMMO3': '0.092', 'HITCOUNT': '0.120', 'WEAPON3': '0.450', 'DAMAGECOUNT': '0.459', 'weapon3': '0.716', 'FRAGCOUNT': '1.000', 'weapon2': '1.252'} [2024-08-05 08:25:48,045][00148] DAMAGECOUNT value on done: 260.0 [2024-08-05 08:25:48,046][00148] Sum rewards: -8.510, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.843', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.005', 'weapon5': '0.008', 'AMMO2': '0.011', 'HITCOUNT': '0.030', 'AMMO4': '0.053', 'AMMO3': '0.099', 'WEAPON5': '0.100', 'DAMAGECOUNT': '0.105', 'weapon4': '0.132', 'WEAPON4': '0.150', 'WEAPON3': '0.550', 'weapon3': '0.676', 'weapon2': '0.914'} [2024-08-05 08:25:48,538][00147] DAMAGECOUNT value on done: 190.0 [2024-08-05 08:25:48,539][00147] Sum rewards: -6.257, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-2.009', 'AMMO2': '0.003', 'AMMO4': '0.013', 'WEAPON4': '0.050', 'weapon4': '0.050', 'HITCOUNT': '0.060', 'AMMO3': '0.193', 'DAMAGECOUNT': '0.225', 'weapon3': '0.496', 'ARMOR': '0.554', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '1.308'} [2024-08-05 08:25:48,585][00148] DAMAGECOUNT value on done: 513.0 [2024-08-05 08:25:48,586][00148] Sum rewards: 0.071, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-0.578', 'AMMO2': '0.010', 'AMMO4': '0.049', 'AMMO3': '0.081', 'WEAPON4': '0.100', 'weapon4': '0.100', 'HITCOUNT': '0.170', 'ARMOR': '0.428', 'WEAPON3': '0.450', 'DAMAGECOUNT': '0.615', 'weapon3': '0.668', 'weapon2': '0.978', 'FRAGCOUNT': '3.000'} [2024-08-05 08:25:49,122][00147] DAMAGECOUNT value on done: 307.0 [2024-08-05 08:25:49,205][00148] DAMAGECOUNT value on done: 482.0 [2024-08-05 08:25:49,206][00148] Sum rewards: -2.165, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.085', 'AMMO5': '0.003', 'WEAPON1': '0.010', 'weapon4': '0.018', 'AMMO2': '0.021', 'WEAPON5': '0.050', 'weapon5': '0.080', 'AMMO3': '0.090', 'HITCOUNT': '0.090', 'AMMO4': '0.103', 'WEAPON4': '0.150', 'WEAPON3': '0.450', 'DAMAGECOUNT': '0.486', 'weapon3': '0.832', 'weapon2': '1.038', 'FRAGCOUNT': '2.000'} [2024-08-05 08:25:49,687][00147] DAMAGECOUNT value on done: 335.0 [2024-08-05 08:25:49,687][00147] Sum rewards: -5.649, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-0.794', 'weapon5': '0.006', 'AMMO5': '0.010', 'AMMO2': '0.022', 'WEAPON5': '0.050', 'AMMO4': '0.108', 'AMMO3': '0.119', 'HITCOUNT': '0.120', 'weapon4': '0.184', 'WEAPON4': '0.250', 'WEAPON3': '0.500', 'weapon3': '0.542', 'DAMAGECOUNT': '0.600', 'weapon2': '1.134', 'FRAGCOUNT': '2.000'} [2024-08-05 08:25:49,764][00148] DAMAGECOUNT value on done: 295.0 [2024-08-05 08:25:51,500][00035] Fps is (10 sec: 4095.9, 60 sec: 3686.4, 300 sec: 3528.9). Total num frames: 688128. Throughput: 0: 914.2. Samples: 170628. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:25:51,502][00035] Avg episode reward: [(0, '-6.560')] [2024-08-05 08:25:56,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3522.6). Total num frames: 704512. Throughput: 0: 916.4. Samples: 176242. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:25:56,502][00035] Avg episode reward: [(0, '-6.560')] [2024-08-05 08:26:01,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3516.6). Total num frames: 720896. Throughput: 0: 906.7. Samples: 181362. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:26:01,502][00035] Avg episode reward: [(0, '-6.560')] [2024-08-05 08:26:05,020][00146] Updated weights for policy 0, policy_version 90 (0.0024) [2024-08-05 08:26:06,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3510.9). Total num frames: 737280. Throughput: 0: 903.9. Samples: 184056. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:26:06,503][00035] Avg episode reward: [(0, '-6.560')] [2024-08-05 08:26:11,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3505.4). Total num frames: 753664. Throughput: 0: 901.6. Samples: 189514. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:26:11,502][00035] Avg episode reward: [(0, '-6.560')] [2024-08-05 08:26:16,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3537.5). Total num frames: 778240. Throughput: 0: 912.0. Samples: 195060. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:26:16,502][00035] Avg episode reward: [(0, '-6.560')] [2024-08-05 08:26:17,977][00149] DAMAGECOUNT value on done: 177.0 [2024-08-05 08:26:17,979][00149] Sum rewards: -5.450, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.528', 'AMMO2': '0.024', 'HITCOUNT': '0.050', 'ARMOR': '0.052', 'AMMO3': '0.098', 'AMMO4': '0.118', 'weapon4': '0.158', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.240', 'WEAPON3': '0.400', 'weapon3': '0.538', 'FRAGCOUNT': '1.000', 'weapon2': '1.200'} [2024-08-05 08:26:18,452][00150] DAMAGECOUNT value on done: 175.0 [2024-08-05 08:26:18,572][00149] DAMAGECOUNT value on done: 502.0 [2024-08-05 08:26:18,573][00149] Sum rewards: -5.482, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.305', 'WEAPON1': '0.010', 'ARMOR': '0.012', 'AMMO2': '0.025', 'HITCOUNT': '0.030', 'weapon4': '0.066', 'AMMO3': '0.112', 'AMMO4': '0.125', 'DAMAGECOUNT': '0.135', 'WEAPON4': '0.200', 'weapon3': '0.406', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon2': '1.352'} [2024-08-05 08:26:18,974][00150] DAMAGECOUNT value on done: 565.0 [2024-08-05 08:26:18,974][00150] Sum rewards: -4.658, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.044', 'AMMO5': '0.005', 'AMMO2': '0.010', 'HITCOUNT': '0.040', 'ARMOR': '0.040', 'AMMO4': '0.050', 'WEAPON4': '0.100', 'weapon4': '0.110', 'AMMO3': '0.118', 'DAMAGECOUNT': '0.135', 'WEAPON3': '0.550', 'weapon3': '0.776', 'weapon2': '0.952', 'FRAGCOUNT': '1.000'} [2024-08-05 08:26:19,122][00149] DAMAGECOUNT value on done: 403.0 [2024-08-05 08:26:19,580][00150] DAMAGECOUNT value on done: 104.0 [2024-08-05 08:26:19,650][00149] DAMAGECOUNT value on done: 230.0 [2024-08-05 08:26:20,112][00150] DAMAGECOUNT value on done: 237.0 [2024-08-05 08:26:21,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3531.7). Total num frames: 794624. Throughput: 0: 910.8. Samples: 197792. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:26:21,502][00035] Avg episode reward: [(0, '-6.461')] [2024-08-05 08:26:21,508][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000097_794624.pth... [2024-08-05 08:26:25,238][00148] DAMAGECOUNT value on done: 300.0 [2024-08-05 08:26:25,271][00149] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-05 08:26:25,777][00148] DAMAGECOUNT value on done: 513.0 [2024-08-05 08:26:25,826][00147] DAMAGECOUNT value on done: 730.0 [2024-08-05 08:26:26,335][00148] DAMAGECOUNT value on done: 497.0 [2024-08-05 08:26:26,398][00147] DAMAGECOUNT value on done: 365.0 [2024-08-05 08:26:26,398][00147] Sum rewards: -10.223, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-2.228', 'AMMO2': '0.011', 'ARMOR': '0.036', 'AMMO4': '0.054', 'WEAPON4': '0.150', 'HITCOUNT': '0.150', 'weapon4': '0.152', 'AMMO3': '0.191', 'DAMAGECOUNT': '0.525', 'weapon3': '0.616', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '1.070'} [2024-08-05 08:26:26,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3526.1). Total num frames: 811008. Throughput: 0: 912.5. Samples: 203368. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:26:26,502][00035] Avg episode reward: [(0, '-6.519')] [2024-08-05 08:26:26,919][00148] DAMAGECOUNT value on done: 330.0 [2024-08-05 08:26:26,962][00147] DAMAGECOUNT value on done: 355.0 [2024-08-05 08:26:26,962][00147] Sum rewards: -8.407, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.164', 'AMMO5': '0.004', 'weapon4': '0.006', 'AMMO2': '0.022', 'ARMOR': '0.040', 'weapon5': '0.040', 'HITCOUNT': '0.050', 'WEAPON4': '0.050', 'WEAPON5': '0.100', 'AMMO4': '0.108', 'DAMAGECOUNT': '0.144', 'AMMO3': '0.161', 'weapon3': '0.498', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '1.234'} [2024-08-05 08:26:27,259][00146] Updated weights for policy 0, policy_version 100 (0.0025) [2024-08-05 08:26:27,601][00147] DAMAGECOUNT value on done: 444.0 [2024-08-05 08:26:27,603][00147] Sum rewards: -1.635, reward structure: {'DEATHCOUNT': '-6.000', 'AMMO5': '0.003', 'AMMO2': '0.012', 'ARMOR': '0.050', 'WEAPON5': '0.050', 'AMMO4': '0.059', 'HITCOUNT': '0.060', 'weapon4': '0.084', 'WEAPON4': '0.100', 'AMMO3': '0.105', 'HEALTH': '0.154', 'DAMAGECOUNT': '0.327', 'WEAPON3': '0.550', 'weapon2': '0.854', 'weapon3': '0.958', 'FRAGCOUNT': '1.000'} [2024-08-05 08:26:31,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3520.8). Total num frames: 827392. Throughput: 0: 911.9. Samples: 208938. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:26:31,502][00035] Avg episode reward: [(0, '-6.510')] [2024-08-05 08:26:36,506][00035] Fps is (10 sec: 3275.0, 60 sec: 3549.5, 300 sec: 3515.7). Total num frames: 843776. Throughput: 0: 903.0. Samples: 211270. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:26:36,511][00035] Avg episode reward: [(0, '-6.510')] [2024-08-05 08:26:41,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3544.3). Total num frames: 868352. Throughput: 0: 903.8. Samples: 216912. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:26:41,504][00035] Avg episode reward: [(0, '-6.510')] [2024-08-05 08:26:46,500][00035] Fps is (10 sec: 4098.2, 60 sec: 3686.4, 300 sec: 3538.9). Total num frames: 884736. Throughput: 0: 914.4. Samples: 222510. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:26:46,502][00035] Avg episode reward: [(0, '-6.510')] [2024-08-05 08:26:49,605][00146] Updated weights for policy 0, policy_version 110 (0.0028) [2024-08-05 08:26:51,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3533.8). Total num frames: 901120. Throughput: 0: 916.7. Samples: 225306. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:26:51,501][00035] Avg episode reward: [(0, '-6.510')] [2024-08-05 08:26:53,782][00149] DAMAGECOUNT value on done: 228.0 [2024-08-05 08:26:54,391][00149] DAMAGECOUNT value on done: 667.0 [2024-08-05 08:26:54,392][00149] Sum rewards: -7.416, reward structure: {'DEATHCOUNT': '-8.250', 'FRAGCOUNT': '-1.500', 'HEALTH': '-1.285', 'AMMO5': '0.005', 'weapon5': '0.014', 'AMMO2': '0.019', 'WEAPON1': '0.020', 'ARMOR': '0.044', 'AMMO4': '0.094', 'WEAPON5': '0.100', 'AMMO3': '0.104', 'HITCOUNT': '0.110', 'weapon4': '0.164', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.495', 'WEAPON3': '0.550', 'weapon3': '0.732', 'weapon2': '0.968'} [2024-08-05 08:26:54,513][00150] DAMAGECOUNT value on done: 271.0 [2024-08-05 08:26:54,931][00149] DAMAGECOUNT value on done: 418.0 [2024-08-05 08:26:55,060][00150] DAMAGECOUNT value on done: 630.0 [2024-08-05 08:26:55,508][00149] DAMAGECOUNT value on done: 230.0 [2024-08-05 08:26:55,617][00150] DAMAGECOUNT value on done: 184.0 [2024-08-05 08:26:55,617][00150] Sum rewards: -4.446, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.080', 'AMMO5': '0.009', 'weapon5': '0.018', 'AMMO2': '0.018', 'HITCOUNT': '0.070', 'AMMO3': '0.073', 'AMMO4': '0.091', 'WEAPON5': '0.100', 'weapon4': '0.140', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.240', 'WEAPON3': '0.400', 'weapon3': '0.836', 'weapon2': '0.938', 'FRAGCOUNT': '1.000'} [2024-08-05 08:26:56,141][00150] DAMAGECOUNT value on done: 291.0 [2024-08-05 08:26:56,500][00035] Fps is (10 sec: 4096.1, 60 sec: 3686.4, 300 sec: 3560.4). Total num frames: 925696. Throughput: 0: 919.0. Samples: 230870. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:26:56,501][00035] Avg episode reward: [(0, '-6.598')] [2024-08-05 08:27:01,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3555.0). Total num frames: 942080. Throughput: 0: 919.2. Samples: 236422. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:27:01,502][00035] Avg episode reward: [(0, '-6.598')] [2024-08-05 08:27:02,362][00148] DAMAGECOUNT value on done: 415.0 [2024-08-05 08:27:02,363][00148] Sum rewards: -3.296, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-0.630', 'AMMO5': '0.003', 'AMMO2': '0.019', 'WEAPON5': '0.050', 'AMMO3': '0.055', 'ARMOR': '0.068', 'HITCOUNT': '0.080', 'AMMO4': '0.092', 'weapon4': '0.110', 'WEAPON4': '0.200', 'WEAPON3': '0.300', 'DAMAGECOUNT': '0.345', 'weapon3': '0.662', 'FRAGCOUNT': '1.000', 'weapon2': '1.100'} [2024-08-05 08:27:02,992][00148] DAMAGECOUNT value on done: 653.0 [2024-08-05 08:27:03,068][00147] DAMAGECOUNT value on done: 850.0 [2024-08-05 08:27:03,069][00147] Sum rewards: -5.252, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.272', 'AMMO5': '0.003', 'AMMO2': '0.019', 'weapon4': '0.022', 'WEAPON5': '0.050', 'HITCOUNT': '0.060', 'ARMOR': '0.092', 'AMMO4': '0.095', 'WEAPON4': '0.100', 'AMMO3': '0.111', 'DAMAGECOUNT': '0.360', 'WEAPON3': '0.600', 'weapon3': '0.802', 'weapon2': '0.956', 'FRAGCOUNT': '1.000'} [2024-08-05 08:27:03,541][00148] DAMAGECOUNT value on done: 637.0 [2024-08-05 08:27:03,541][00148] Sum rewards: -10.131, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-1.090', 'AMMO2': '0.011', 'AMMO4': '0.054', 'ARMOR': '0.068', 'HITCOUNT': '0.090', 'AMMO3': '0.124', 'WEAPON4': '0.150', 'weapon4': '0.198', 'DAMAGECOUNT': '0.420', 'weapon3': '0.634', 'WEAPON3': '0.650', 'FRAGCOUNT': '1.000', 'weapon2': '1.060'} [2024-08-05 08:27:03,595][00147] DAMAGECOUNT value on done: 500.0 [2024-08-05 08:27:03,595][00147] Sum rewards: -4.877, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.338', 'AMMO2': '0.022', 'HITCOUNT': '0.090', 'weapon4': '0.098', 'AMMO4': '0.108', 'AMMO3': '0.124', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.405', 'WEAPON3': '0.650', 'weapon3': '0.848', 'weapon2': '0.916', 'FRAGCOUNT': '2.000'} [2024-08-05 08:27:04,073][00148] DAMAGECOUNT value on done: 345.0 [2024-08-05 08:27:04,173][00147] DAMAGECOUNT value on done: 435.0 [2024-08-05 08:27:04,985][00147] DAMAGECOUNT value on done: 599.0 [2024-08-05 08:27:04,986][00147] Sum rewards: -8.463, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-1.586', 'ARMOR': '0.004', 'AMMO2': '0.042', 'AMMO3': '0.167', 'HITCOUNT': '0.170', 'AMMO4': '0.211', 'weapon4': '0.220', 'WEAPON4': '0.350', 'DAMAGECOUNT': '0.465', 'weapon3': '0.610', 'WEAPON3': '0.900', 'weapon2': '0.984', 'FRAGCOUNT': '1.000'} [2024-08-05 08:27:06,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3549.9). Total num frames: 958464. Throughput: 0: 918.6. Samples: 239128. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:27:06,502][00035] Avg episode reward: [(0, '-6.563')] [2024-08-05 08:27:11,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3544.9). Total num frames: 974848. Throughput: 0: 909.3. Samples: 244286. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:27:11,502][00035] Avg episode reward: [(0, '-6.563')] [2024-08-05 08:27:12,328][00146] Updated weights for policy 0, policy_version 120 (0.0027) [2024-08-05 08:27:16,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3540.1). Total num frames: 991232. Throughput: 0: 910.7. Samples: 249920. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:27:16,502][00035] Avg episode reward: [(0, '-6.563')] [2024-08-05 08:27:21,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3564.2). Total num frames: 1015808. Throughput: 0: 919.9. Samples: 252660. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:27:21,502][00035] Avg episode reward: [(0, '-6.563')] [2024-08-05 08:27:26,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3559.3). Total num frames: 1032192. Throughput: 0: 920.0. Samples: 258314. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:27:26,504][00035] Avg episode reward: [(0, '-6.563')] [2024-08-05 08:27:29,761][00149] DAMAGECOUNT value on done: 273.0 [2024-08-05 08:27:30,322][00149] DAMAGECOUNT value on done: 767.0 [2024-08-05 08:27:30,324][00149] Sum rewards: -5.104, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.612', 'AMMO5': '0.004', 'ARMOR': '0.004', 'AMMO2': '0.005', 'HITCOUNT': '0.010', 'AMMO4': '0.027', 'WEAPON5': '0.100', 'weapon5': '0.104', 'AMMO3': '0.142', 'DAMAGECOUNT': '0.300', 'weapon3': '0.400', 'WEAPON3': '0.750', 'FRAGCOUNT': '1.000', 'weapon2': '1.162'} [2024-08-05 08:27:30,895][00150] DAMAGECOUNT value on done: 351.0 [2024-08-05 08:27:30,938][00149] DAMAGECOUNT value on done: 445.0 [2024-08-05 08:27:31,466][00150] DAMAGECOUNT value on done: 715.0 [2024-08-05 08:27:31,467][00150] Sum rewards: -3.039, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-1.261', 'AMMO5': '0.007', 'weapon7': '0.008', 'AMMO2': '0.008', 'AMMO4': '0.040', 'HITCOUNT': '0.060', 'weapon5': '0.066', 'ARMOR': '0.072', 'AMMO3': '0.087', 'WEAPON4': '0.100', 'WEAPON5': '0.150', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'weapon4': '0.250', 'DAMAGECOUNT': '0.255', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.500', 'weapon3': '0.598', 'weapon2': '0.920'} [2024-08-05 08:27:31,473][00149] DAMAGECOUNT value on done: 250.0 [2024-08-05 08:27:31,474][00149] Sum rewards: -6.432, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.797', 'AMMO2': '0.013', 'HITCOUNT': '0.030', 'DAMAGECOUNT': '0.060', 'AMMO4': '0.064', 'AMMO3': '0.098', 'WEAPON4': '0.150', 'weapon4': '0.174', 'WEAPON3': '0.500', 'weapon3': '0.538', 'weapon2': '0.988', 'FRAGCOUNT': '1.000'} [2024-08-05 08:27:31,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3554.5). Total num frames: 1048576. Throughput: 0: 917.2. Samples: 263786. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:27:31,502][00035] Avg episode reward: [(0, '-6.484')] [2024-08-05 08:27:32,133][00150] DAMAGECOUNT value on done: 453.0 [2024-08-05 08:27:32,134][00150] Sum rewards: -5.523, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.844', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.006', 'AMMO2': '0.019', 'ARMOR': '0.052', 'weapon5': '0.092', 'AMMO4': '0.097', 'weapon4': '0.102', 'HITCOUNT': '0.150', 'WEAPON5': '0.150', 'AMMO3': '0.162', 'WEAPON4': '0.200', 'weapon3': '0.682', 'WEAPON3': '0.750', 'DAMAGECOUNT': '0.807', 'weapon2': '1.052'} [2024-08-05 08:27:32,666][00150] DAMAGECOUNT value on done: 306.0 [2024-08-05 08:27:34,223][00146] Updated weights for policy 0, policy_version 130 (0.0024) [2024-08-05 08:27:36,501][00035] Fps is (10 sec: 3276.5, 60 sec: 3686.7, 300 sec: 3610.0). Total num frames: 1064960. Throughput: 0: 917.5. Samples: 266596. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:27:36,502][00035] Avg episode reward: [(0, '-6.445')] [2024-08-05 08:27:40,358][00148] DAMAGECOUNT value on done: 430.0 [2024-08-05 08:27:40,662][00147] DAMAGECOUNT value on done: 885.0 [2024-08-05 08:27:40,926][00148] DAMAGECOUNT value on done: 653.0 [2024-08-05 08:27:41,198][00147] DAMAGECOUNT value on done: 500.0 [2024-08-05 08:27:41,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 1089536. Throughput: 0: 908.2. Samples: 271738. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:27:41,502][00035] Avg episode reward: [(0, '-6.555')] [2024-08-05 08:27:41,514][00148] DAMAGECOUNT value on done: 740.0 [2024-08-05 08:27:41,801][00147] DAMAGECOUNT value on done: 532.0 [2024-08-05 08:27:42,062][00148] DAMAGECOUNT value on done: 350.0 [2024-08-05 08:27:42,361][00147] DAMAGECOUNT value on done: 614.0 [2024-08-05 08:27:46,500][00035] Fps is (10 sec: 4096.3, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1105920. Throughput: 0: 909.4. Samples: 277346. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:27:46,502][00035] Avg episode reward: [(0, '-6.432')] [2024-08-05 08:27:51,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 1122304. Throughput: 0: 911.3. Samples: 280136. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:27:51,502][00035] Avg episode reward: [(0, '-6.432')] [2024-08-05 08:27:56,500][00035] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 1138688. Throughput: 0: 920.9. Samples: 285728. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:27:56,502][00035] Avg episode reward: [(0, '-6.432')] [2024-08-05 08:27:56,771][00146] Updated weights for policy 0, policy_version 140 (0.0023) [2024-08-05 08:28:01,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1163264. Throughput: 0: 919.1. Samples: 291278. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:28:01,502][00035] Avg episode reward: [(0, '-6.432')] [2024-08-05 08:28:05,716][00149] DAMAGECOUNT value on done: 273.0 [2024-08-05 08:28:06,257][00149] DAMAGECOUNT value on done: 802.0 [2024-08-05 08:28:06,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1179648. Throughput: 0: 921.0. Samples: 294104. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:28:06,504][00035] Avg episode reward: [(0, '-6.430')] [2024-08-05 08:28:06,852][00149] DAMAGECOUNT value on done: 505.0 [2024-08-05 08:28:06,853][00149] Sum rewards: -5.833, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.666', 'AMMO5': '0.010', 'AMMO2': '0.011', 'weapon5': '0.012', 'weapon4': '0.024', 'HITCOUNT': '0.050', 'AMMO4': '0.054', 'AMMO3': '0.084', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'ARMOR': '0.140', 'DAMAGECOUNT': '0.180', 'WEAPON3': '0.400', 'weapon3': '0.844', 'FRAGCOUNT': '1.000', 'weapon2': '1.074'} [2024-08-05 08:28:07,055][00150] DAMAGECOUNT value on done: 373.0 [2024-08-05 08:28:07,420][00149] DAMAGECOUNT value on done: 346.0 [2024-08-05 08:28:07,421][00149] Sum rewards: -7.738, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.040', 'AMMO2': '0.009', 'AMMO5': '0.009', 'weapon5': '0.022', 'AMMO4': '0.044', 'ARMOR': '0.061', 'weapon4': '0.078', 'HITCOUNT': '0.100', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.181', 'DAMAGECOUNT': '0.288', 'weapon3': '0.700', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '1.210'} [2024-08-05 08:28:07,648][00150] DAMAGECOUNT value on done: 816.0 [2024-08-05 08:28:07,649][00150] Sum rewards: -5.920, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.312', 'AMMO2': '0.011', 'WEAPON1': '0.020', 'ARMOR': '0.044', 'AMMO4': '0.054', 'weapon4': '0.066', 'AMMO3': '0.084', 'HITCOUNT': '0.100', 'WEAPON4': '0.100', 'DAMAGECOUNT': '0.303', 'WEAPON3': '0.450', 'weapon3': '0.870', 'FRAGCOUNT': '1.000', 'weapon2': '1.040'} [2024-08-05 08:28:08,243][00150] DAMAGECOUNT value on done: 664.0 [2024-08-05 08:28:08,243][00150] Sum rewards: -6.640, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-0.990', 'ARMOR': '0.004', 'AMMO2': '0.017', 'AMMO4': '0.084', 'weapon4': '0.102', 'WEAPON4': '0.150', 'AMMO3': '0.170', 'HITCOUNT': '0.170', 'DAMAGECOUNT': '0.633', 'WEAPON3': '0.850', 'weapon3': '0.874', 'weapon2': '1.296', 'FRAGCOUNT': '2.000'} [2024-08-05 08:28:09,047][00150] DAMAGECOUNT value on done: 331.0 [2024-08-05 08:28:11,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 1196032. Throughput: 0: 907.6. Samples: 299154. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:28:11,504][00035] Avg episode reward: [(0, '-6.606')] [2024-08-05 08:28:16,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 1212416. Throughput: 0: 909.3. Samples: 304706. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:28:16,502][00035] Avg episode reward: [(0, '-6.606')] [2024-08-05 08:28:17,807][00148] DAMAGECOUNT value on done: 460.0 [2024-08-05 08:28:17,966][00147] DAMAGECOUNT value on done: 980.0 [2024-08-05 08:28:17,967][00147] Sum rewards: -7.888, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.672', 'AMMO4': '-0.000', 'AMMO2': '0.000', 'AMMO5': '0.010', 'weapon5': '0.024', 'ARMOR': '0.078', 'HITCOUNT': '0.090', 'AMMO3': '0.099', 'WEAPON5': '0.100', 'DAMAGECOUNT': '0.285', 'WEAPON3': '0.550', 'weapon3': '0.556', 'FRAGCOUNT': '1.000', 'weapon2': '1.492'} [2024-08-05 08:28:18,432][00148] DAMAGECOUNT value on done: 693.0 [2024-08-05 08:28:18,572][00147] DAMAGECOUNT value on done: 515.0 [2024-08-05 08:28:19,009][00148] DAMAGECOUNT value on done: 770.0 [2024-08-05 08:28:19,138][00147] DAMAGECOUNT value on done: 537.0 [2024-08-05 08:28:19,470][00146] Updated weights for policy 0, policy_version 150 (0.0027) [2024-08-05 08:28:19,670][00148] DAMAGECOUNT value on done: 563.0 [2024-08-05 08:28:19,671][00148] Sum rewards: -5.158, reward structure: {'DEATHCOUNT': '-11.250', 'AMMO5': '0.005', 'AMMO2': '0.008', 'weapon5': '0.012', 'weapon4': '0.014', 'ARMOR': '0.032', 'AMMO4': '0.038', 'WEAPON4': '0.050', 'WEAPON5': '0.050', 'HITCOUNT': '0.070', 'AMMO3': '0.156', 'HEALTH': '0.372', 'DAMAGECOUNT': '0.639', 'weapon3': '0.652', 'WEAPON3': '0.800', 'weapon2': '1.194', 'FRAGCOUNT': '2.000'} [2024-08-05 08:28:19,730][00147] DAMAGECOUNT value on done: 716.0 [2024-08-05 08:28:21,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 1228800. Throughput: 0: 906.1. Samples: 307370. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:28:21,502][00035] Avg episode reward: [(0, '-6.441')] [2024-08-05 08:28:21,514][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000150_1228800.pth... [2024-08-05 08:28:21,614][00137] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000044_360448.pth [2024-08-05 08:28:26,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1253376. Throughput: 0: 914.6. Samples: 312894. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:28:26,502][00035] Avg episode reward: [(0, '-6.441')] [2024-08-05 08:28:31,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1269760. Throughput: 0: 914.7. Samples: 318506. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:28:31,502][00035] Avg episode reward: [(0, '-6.441')] [2024-08-05 08:28:36,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.5, 300 sec: 3637.8). Total num frames: 1286144. Throughput: 0: 914.9. Samples: 321306. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:28:36,502][00035] Avg episode reward: [(0, '-6.441')] [2024-08-05 08:28:41,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 1302528. Throughput: 0: 910.7. Samples: 326708. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:28:41,504][00035] Avg episode reward: [(0, '-6.441')] [2024-08-05 08:28:42,158][00146] Updated weights for policy 0, policy_version 160 (0.0026) [2024-08-05 08:28:42,530][00149] DAMAGECOUNT value on done: 333.0 [2024-08-05 08:28:42,531][00149] Sum rewards: -6.546, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.975', 'AMMO2': '0.013', 'HITCOUNT': '0.050', 'ARMOR': '0.056', 'AMMO4': '0.063', 'WEAPON4': '0.100', 'AMMO3': '0.113', 'DAMAGECOUNT': '0.180', 'WEAPON3': '0.500', 'weapon3': '0.530', 'FRAGCOUNT': '1.000', 'weapon2': '1.574'} [2024-08-05 08:28:43,053][00149] DAMAGECOUNT value on done: 824.0 [2024-08-05 08:28:43,615][00149] DAMAGECOUNT value on done: 578.0 [2024-08-05 08:28:43,616][00149] Sum rewards: -8.477, reward structure: {'DEATHCOUNT': '-8.250', 'FRAGCOUNT': '-3.000', 'HEALTH': '-0.380', 'ARMOR': '0.004', 'AMMO5': '0.007', 'AMMO2': '0.015', 'weapon4': '0.054', 'weapon5': '0.056', 'HITCOUNT': '0.060', 'AMMO4': '0.073', 'WEAPON5': '0.100', 'AMMO3': '0.117', 'WEAPON4': '0.150', 'DAMAGECOUNT': '0.219', 'WEAPON3': '0.500', 'weapon3': '0.748', 'weapon2': '1.050'} [2024-08-05 08:28:43,901][00150] DAMAGECOUNT value on done: 503.0 [2024-08-05 08:28:43,902][00150] Sum rewards: -2.701, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-1.280', 'AMMO2': '0.009', 'ARMOR': '0.040', 'AMMO4': '0.046', 'HITCOUNT': '0.070', 'AMMO3': '0.125', 'WEAPON4': '0.150', 'weapon4': '0.176', 'DAMAGECOUNT': '0.390', 'WEAPON3': '0.700', 'weapon3': '0.836', 'FRAGCOUNT': '1.000', 'weapon2': '1.036'} [2024-08-05 08:28:44,154][00149] DAMAGECOUNT value on done: 356.0 [2024-08-05 08:28:44,494][00150] DAMAGECOUNT value on done: 886.0 [2024-08-05 08:28:45,074][00150] DAMAGECOUNT value on done: 859.0 [2024-08-05 08:28:45,075][00150] Sum rewards: -7.831, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.482', 'AMMO5': '0.005', 'weapon5': '0.008', 'AMMO2': '0.018', 'weapon4': '0.036', 'WEAPON4': '0.050', 'AMMO4': '0.090', 'WEAPON5': '0.100', 'HITCOUNT': '0.140', 'AMMO3': '0.150', 'DAMAGECOUNT': '0.585', 'WEAPON3': '0.650', 'weapon3': '0.656', 'FRAGCOUNT': '1.000', 'weapon2': '1.412'} [2024-08-05 08:28:45,587][00150] DAMAGECOUNT value on done: 756.0 [2024-08-05 08:28:45,589][00150] Sum rewards: -1.873, reward structure: {'DEATHCOUNT': '-8.250', 'AMMO2': '0.006', 'WEAPON1': '0.010', 'AMMO5': '0.012', 'AMMO4': '0.028', 'ARMOR': '0.028', 'AMMO3': '0.088', 'HITCOUNT': '0.110', 'WEAPON5': '0.200', 'weapon5': '0.204', 'WEAPON3': '0.400', 'HEALTH': '0.664', 'weapon3': '0.700', 'weapon2': '1.152', 'DAMAGECOUNT': '1.275', 'FRAGCOUNT': '1.500'} [2024-08-05 08:28:46,500][00035] Fps is (10 sec: 3276.7, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 1318912. Throughput: 0: 903.1. Samples: 331916. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:28:46,502][00035] Avg episode reward: [(0, '-6.453')] [2024-08-05 08:28:51,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1343488. Throughput: 0: 901.2. Samples: 334656. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:28:51,502][00035] Avg episode reward: [(0, '-6.453')] [2024-08-05 08:28:55,167][00148] DAMAGECOUNT value on done: 490.0 [2024-08-05 08:28:55,262][00147] DAMAGECOUNT value on done: 1075.0 [2024-08-05 08:28:55,263][00147] Sum rewards: -4.347, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.120', 'AMMO2': '0.011', 'AMMO5': '0.012', 'AMMO4': '0.056', 'HITCOUNT': '0.070', 'weapon5': '0.074', 'weapon4': '0.078', 'AMMO3': '0.133', 'WEAPON5': '0.150', 'WEAPON4': '0.150', 'DAMAGECOUNT': '0.285', 'ARMOR': '0.491', 'WEAPON3': '0.600', 'weapon3': '0.652', 'FRAGCOUNT': '1.000', 'weapon2': '1.260'} [2024-08-05 08:28:55,784][00148] DAMAGECOUNT value on done: 883.0 [2024-08-05 08:28:55,785][00148] Sum rewards: -3.460, reward structure: {'DEATHCOUNT': '-6.000', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.003', 'ARMOR': '0.008', 'weapon5': '0.016', 'AMMO2': '0.017', 'WEAPON5': '0.050', 'AMMO3': '0.075', 'HITCOUNT': '0.080', 'AMMO4': '0.085', 'WEAPON4': '0.150', 'weapon4': '0.180', 'WEAPON3': '0.400', 'HEALTH': '0.570', 'DAMAGECOUNT': '0.570', 'weapon3': '0.782', 'weapon2': '1.054'} [2024-08-05 08:28:55,806][00147] DAMAGECOUNT value on done: 555.0 [2024-08-05 08:28:56,399][00147] DAMAGECOUNT value on done: 562.0 [2024-08-05 08:28:56,412][00148] DAMAGECOUNT value on done: 805.0 [2024-08-05 08:28:56,500][00035] Fps is (10 sec: 4096.1, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 1359872. Throughput: 0: 913.5. Samples: 340262. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:28:56,501][00035] Avg episode reward: [(0, '-6.261')] [2024-08-05 08:28:56,993][00147] DAMAGECOUNT value on done: 847.0 [2024-08-05 08:28:56,994][00147] Sum rewards: -8.593, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.965', 'AMMO2': '0.009', 'AMMO4': '0.045', 'HITCOUNT': '0.060', 'weapon7': '0.070', 'AMMO6': '0.100', 'AMMO7': '0.100', 'WEAPON7': '0.100', 'AMMO3': '0.102', 'DAMAGECOUNT': '0.393', 'WEAPON3': '0.550', 'weapon3': '0.844', 'FRAGCOUNT': '1.000', 'weapon2': '1.248'} [2024-08-05 08:28:57,053][00148] DAMAGECOUNT value on done: 568.0 [2024-08-05 08:29:01,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 1376256. Throughput: 0: 913.7. Samples: 345824. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:29:01,502][00035] Avg episode reward: [(0, '-6.284')] [2024-08-05 08:29:04,190][00146] Updated weights for policy 0, policy_version 170 (0.0023) [2024-08-05 08:29:06,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1400832. Throughput: 0: 917.1. Samples: 348640. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:29:06,502][00035] Avg episode reward: [(0, '-6.284')] [2024-08-05 08:29:11,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1417216. Throughput: 0: 920.1. Samples: 354298. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:29:11,502][00035] Avg episode reward: [(0, '-6.284')] [2024-08-05 08:29:16,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 1433600. Throughput: 0: 909.5. Samples: 359434. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:29:16,502][00035] Avg episode reward: [(0, '-6.284')] [2024-08-05 08:29:18,502][00149] DAMAGECOUNT value on done: 423.0 [2024-08-05 08:29:19,033][00149] DAMAGECOUNT value on done: 973.0 [2024-08-05 08:29:19,562][00149] DAMAGECOUNT value on done: 738.0 [2024-08-05 08:29:19,563][00149] Sum rewards: -3.190, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.290', 'AMMO2': '0.011', 'ARMOR': '0.016', 'AMMO4': '0.053', 'HITCOUNT': '0.090', 'AMMO3': '0.122', 'WEAPON4': '0.200', 'weapon4': '0.206', 'DAMAGECOUNT': '0.480', 'WEAPON3': '0.550', 'weapon3': '0.806', 'weapon2': '1.066', 'FRAGCOUNT': '3.000'} [2024-08-05 08:29:19,870][00150] DAMAGECOUNT value on done: 533.0 [2024-08-05 08:29:20,149][00149] DAMAGECOUNT value on done: 371.0 [2024-08-05 08:29:20,478][00150] DAMAGECOUNT value on done: 1262.0 [2024-08-05 08:29:20,479][00150] Sum rewards: -3.873, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.980', 'AMMO5': '0.004', 'AMMO2': '0.015', 'weapon5': '0.058', 'AMMO4': '0.074', 'HITCOUNT': '0.080', 'ARMOR': '0.080', 'weapon4': '0.092', 'WEAPON5': '0.100', 'AMMO3': '0.112', 'WEAPON4': '0.200', 'WEAPON3': '0.600', 'weapon3': '0.650', 'DAMAGECOUNT': '1.128', 'weapon2': '1.164', 'FRAGCOUNT': '2.000'} [2024-08-05 08:29:21,002][00150] DAMAGECOUNT value on done: 915.0 [2024-08-05 08:29:21,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 1449984. Throughput: 0: 909.2. Samples: 362220. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:29:21,502][00035] Avg episode reward: [(0, '-6.140')] [2024-08-05 08:29:21,510][00137] Saving new best policy, reward=-6.140! [2024-08-05 08:29:21,590][00150] DAMAGECOUNT value on done: 866.0 [2024-08-05 08:29:26,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 1466368. Throughput: 0: 910.0. Samples: 367658. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:29:26,502][00035] Avg episode reward: [(0, '-6.131')] [2024-08-05 08:29:26,504][00137] Saving new best policy, reward=-6.131! [2024-08-05 08:29:26,788][00146] Updated weights for policy 0, policy_version 180 (0.0022) [2024-08-05 08:29:31,501][00035] Fps is (10 sec: 4095.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1490944. Throughput: 0: 914.9. Samples: 373086. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:29:31,502][00035] Avg episode reward: [(0, '-6.131')] [2024-08-05 08:29:32,639][00147] DAMAGECOUNT value on done: 1188.0 [2024-08-05 08:29:32,846][00148] DAMAGECOUNT value on done: 530.0 [2024-08-05 08:29:32,847][00148] Sum rewards: -4.423, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.602', 'AMMO5': '0.003', 'AMMO2': '0.014', 'WEAPON1': '0.020', 'HITCOUNT': '0.040', 'weapon4': '0.048', 'WEAPON4': '0.050', 'WEAPON5': '0.050', 'weapon5': '0.054', 'AMMO4': '0.072', 'AMMO3': '0.096', 'DAMAGECOUNT': '0.120', 'weapon3': '0.288', 'WEAPON3': '0.300', 'FRAGCOUNT': '2.000', 'weapon2': '2.024'} [2024-08-05 08:29:33,193][00147] DAMAGECOUNT value on done: 555.0 [2024-08-05 08:29:33,443][00148] DAMAGECOUNT value on done: 963.0 [2024-08-05 08:29:33,801][00147] DAMAGECOUNT value on done: 621.0 [2024-08-05 08:29:33,801][00147] Sum rewards: -8.892, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-2.730', 'AMMO2': '0.049', 'HITCOUNT': '0.050', 'ARMOR': '0.072', 'AMMO3': '0.141', 'DAMAGECOUNT': '0.177', 'AMMO4': '0.245', 'weapon4': '0.246', 'weapon3': '0.404', 'WEAPON4': '0.600', 'WEAPON3': '0.650', 'FRAGCOUNT': '1.000', 'weapon2': '1.454'} [2024-08-05 08:29:34,066][00148] DAMAGECOUNT value on done: 845.0 [2024-08-05 08:29:34,067][00148] Sum rewards: -4.346, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.084', 'AMMO2': '0.003', 'AMMO4': '0.015', 'HITCOUNT': '0.030', 'ARMOR': '0.036', 'weapon4': '0.058', 'WEAPON4': '0.100', 'AMMO3': '0.120', 'DAMAGECOUNT': '0.120', 'WEAPON3': '0.550', 'weapon3': '0.710', 'FRAGCOUNT': '1.000', 'weapon2': '1.496'} [2024-08-05 08:29:34,387][00147] DAMAGECOUNT value on done: 899.0 [2024-08-05 08:29:34,636][00148] DAMAGECOUNT value on done: 677.0 [2024-08-05 08:29:34,637][00148] Sum rewards: -4.618, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.200', 'AMMO5': '0.003', 'AMMO2': '0.003', 'AMMO4': '0.014', 'WEAPON1': '0.020', 'WEAPON5': '0.050', 'weapon5': '0.050', 'weapon4': '0.060', 'AMMO3': '0.095', 'HITCOUNT': '0.100', 'WEAPON4': '0.100', 'DAMAGECOUNT': '0.327', 'WEAPON3': '0.550', 'weapon3': '0.768', 'FRAGCOUNT': '1.000', 'weapon2': '1.192'} [2024-08-05 08:29:36,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1507328. Throughput: 0: 914.7. Samples: 375818. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:29:36,504][00035] Avg episode reward: [(0, '-6.138')] [2024-08-05 08:29:41,500][00035] Fps is (10 sec: 3277.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 1523712. Throughput: 0: 912.3. Samples: 381314. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:29:41,502][00035] Avg episode reward: [(0, '-6.138')] [2024-08-05 08:29:46,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 1540096. Throughput: 0: 904.2. Samples: 386514. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:29:46,501][00035] Avg episode reward: [(0, '-6.138')] [2024-08-05 08:29:49,435][00146] Updated weights for policy 0, policy_version 190 (0.0035) [2024-08-05 08:29:51,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 1556480. Throughput: 0: 903.2. Samples: 389286. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:29:51,502][00035] Avg episode reward: [(0, '-6.138')] [2024-08-05 08:29:54,924][00149] DAMAGECOUNT value on done: 486.0 [2024-08-05 08:29:55,460][00149] DAMAGECOUNT value on done: 973.0 [2024-08-05 08:29:56,071][00149] DAMAGECOUNT value on done: 808.0 [2024-08-05 08:29:56,194][00150] DAMAGECOUNT value on done: 607.0 [2024-08-05 08:29:56,195][00150] Sum rewards: -6.276, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-2.800', 'AMMO2': '0.005', 'weapon4': '0.006', 'AMMO4': '0.024', 'WEAPON4': '0.050', 'HITCOUNT': '0.080', 'AMMO3': '0.134', 'DAMAGECOUNT': '0.222', 'ARMOR': '0.481', 'WEAPON3': '0.650', 'weapon3': '0.732', 'FRAGCOUNT': '1.000', 'weapon2': '1.390'} [2024-08-05 08:29:56,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1581056. Throughput: 0: 902.8. Samples: 394924. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:29:56,502][00035] Avg episode reward: [(0, '-6.129')] [2024-08-05 08:29:56,506][00137] Saving new best policy, reward=-6.129! [2024-08-05 08:29:56,682][00149] DAMAGECOUNT value on done: 404.0 [2024-08-05 08:29:56,826][00150] DAMAGECOUNT value on done: 1357.0 [2024-08-05 08:29:57,400][00150] DAMAGECOUNT value on done: 1000.0 [2024-08-05 08:29:57,966][00150] DAMAGECOUNT value on done: 998.0 [2024-08-05 08:29:57,967][00150] Sum rewards: -4.811, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.170', 'AMMO5': '0.003', 'AMMO2': '0.015', 'ARMOR': '0.044', 'weapon4': '0.046', 'WEAPON5': '0.050', 'AMMO4': '0.076', 'AMMO3': '0.091', 'HITCOUNT': '0.120', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.396', 'WEAPON3': '0.500', 'weapon3': '0.748', 'FRAGCOUNT': '1.000', 'weapon2': '1.320'} [2024-08-05 08:30:01,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1597440. Throughput: 0: 911.6. Samples: 400454. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:30:01,502][00035] Avg episode reward: [(0, '-6.214')] [2024-08-05 08:30:06,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 1613824. Throughput: 0: 912.6. Samples: 403288. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:30:06,502][00035] Avg episode reward: [(0, '-6.214')] [2024-08-05 08:30:09,892][00147] DAMAGECOUNT value on done: 1197.0 [2024-08-05 08:30:10,175][00148] DAMAGECOUNT value on done: 540.0 [2024-08-05 08:30:10,472][00147] DAMAGECOUNT value on done: 581.0 [2024-08-05 08:30:10,778][00148] DAMAGECOUNT value on done: 1117.0 [2024-08-05 08:30:10,779][00148] Sum rewards: -6.215, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.708', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.003', 'AMMO2': '0.011', 'weapon4': '0.042', 'weapon5': '0.048', 'WEAPON4': '0.050', 'WEAPON5': '0.050', 'AMMO4': '0.056', 'HITCOUNT': '0.100', 'AMMO3': '0.109', 'DAMAGECOUNT': '0.462', 'WEAPON3': '0.500', 'ARMOR': '0.580', 'weapon3': '0.644', 'weapon2': '1.338'} [2024-08-05 08:30:11,025][00147] DAMAGECOUNT value on done: 752.0 [2024-08-05 08:30:11,353][00148] DAMAGECOUNT value on done: 930.0 [2024-08-05 08:30:11,354][00148] Sum rewards: -5.493, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.089', 'AMMO2': '0.012', 'ARMOR': '0.028', 'AMMO4': '0.058', 'HITCOUNT': '0.080', 'weapon4': '0.080', 'AMMO3': '0.127', 'WEAPON4': '0.150', 'DAMAGECOUNT': '0.255', 'WEAPON3': '0.700', 'weapon3': '0.944', 'FRAGCOUNT': '1.000', 'weapon2': '1.162'} [2024-08-05 08:30:11,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 1630208. Throughput: 0: 913.9. Samples: 408784. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:30:11,502][00035] Avg episode reward: [(0, '-6.214')] [2024-08-05 08:30:11,594][00146] Updated weights for policy 0, policy_version 200 (0.0019) [2024-08-05 08:30:11,621][00147] DAMAGECOUNT value on done: 1044.0 [2024-08-05 08:30:11,622][00147] Sum rewards: -3.977, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.498', 'AMMO5': '0.010', 'AMMO2': '0.012', 'HITCOUNT': '0.020', 'weapon5': '0.020', 'ARMOR': '0.040', 'weapon4': '0.048', 'AMMO4': '0.057', 'AMMO3': '0.080', 'WEAPON4': '0.100', 'WEAPON5': '0.200', 'WEAPON3': '0.250', 'DAMAGECOUNT': '0.435', 'weapon3': '0.444', 'FRAGCOUNT': '1.000', 'weapon2': '1.556'} [2024-08-05 08:30:11,939][00148] DAMAGECOUNT value on done: 777.0 [2024-08-05 08:30:16,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1654784. Throughput: 0: 913.5. Samples: 414194. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:30:16,504][00035] Avg episode reward: [(0, '-6.138')] [2024-08-05 08:30:21,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 1671168. Throughput: 0: 906.2. Samples: 416598. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:30:21,502][00035] Avg episode reward: [(0, '-6.138')] [2024-08-05 08:30:21,508][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000204_1671168.pth... [2024-08-05 08:30:21,607][00137] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000097_794624.pth [2024-08-05 08:30:26,501][00035] Fps is (10 sec: 3276.5, 60 sec: 3686.3, 300 sec: 3637.8). Total num frames: 1687552. Throughput: 0: 908.4. Samples: 422194. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:30:26,502][00035] Avg episode reward: [(0, '-6.138')] [2024-08-05 08:30:31,204][00149] DAMAGECOUNT value on done: 560.0 [2024-08-05 08:30:31,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 1703936. Throughput: 0: 915.9. Samples: 427730. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:30:31,505][00035] Avg episode reward: [(0, '-6.090')] [2024-08-05 08:30:31,513][00137] Saving new best policy, reward=-6.090! [2024-08-05 08:30:31,802][00149] DAMAGECOUNT value on done: 1053.0 [2024-08-05 08:30:31,803][00149] Sum rewards: -6.693, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.398', 'AMMO2': '0.004', 'AMMO4': '0.019', 'WEAPON1': '0.020', 'WEAPON4': '0.050', 'weapon4': '0.058', 'ARMOR': '0.072', 'HITCOUNT': '0.100', 'AMMO3': '0.156', 'DAMAGECOUNT': '0.240', 'WEAPON3': '0.600', 'weapon3': '0.692', 'FRAGCOUNT': '1.000', 'weapon2': '1.444'} [2024-08-05 08:30:32,398][00149] DAMAGECOUNT value on done: 844.0 [2024-08-05 08:30:32,753][00150] DAMAGECOUNT value on done: 767.0 [2024-08-05 08:30:32,754][00150] Sum rewards: -3.647, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.225', 'AMMO5': '0.003', 'AMMO2': '0.006', 'AMMO4': '0.029', 'WEAPON5': '0.050', 'HITCOUNT': '0.110', 'AMMO3': '0.124', 'DAMAGECOUNT': '0.480', 'WEAPON3': '0.650', 'FRAGCOUNT': '1.000', 'weapon3': '1.112', 'weapon2': '1.264'} [2024-08-05 08:30:32,928][00149] DAMAGECOUNT value on done: 604.0 [2024-08-05 08:30:32,929][00149] Sum rewards: -5.139, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.645', 'AMMO2': '0.002', 'weapon4': '0.004', 'AMMO5': '0.005', 'AMMO4': '0.011', 'WEAPON4': '0.050', 'WEAPON5': '0.050', 'ARMOR': '0.080', 'AMMO3': '0.152', 'HITCOUNT': '0.170', 'DAMAGECOUNT': '0.600', 'WEAPON3': '0.850', 'weapon3': '1.100', 'weapon2': '1.182', 'FRAGCOUNT': '2.000'} [2024-08-05 08:30:33,280][00150] DAMAGECOUNT value on done: 1372.0 [2024-08-05 08:30:33,840][00150] DAMAGECOUNT value on done: 1045.0 [2024-08-05 08:30:34,436][00146] Updated weights for policy 0, policy_version 210 (0.0025) [2024-08-05 08:30:34,468][00150] DAMAGECOUNT value on done: 1128.0 [2024-08-05 08:30:36,500][00035] Fps is (10 sec: 3277.1, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 1720320. Throughput: 0: 914.3. Samples: 430428. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:30:36,502][00035] Avg episode reward: [(0, '-6.075')] [2024-08-05 08:30:36,574][00137] Saving new best policy, reward=-6.075! [2024-08-05 08:30:41,501][00035] Fps is (10 sec: 4095.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1744896. Throughput: 0: 909.6. Samples: 435858. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:30:41,502][00035] Avg episode reward: [(0, '-6.075')] [2024-08-05 08:30:46,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 1761280. Throughput: 0: 909.6. Samples: 441388. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:30:46,501][00035] Avg episode reward: [(0, '-6.075')] [2024-08-05 08:30:47,497][00147] DAMAGECOUNT value on done: 1214.0 [2024-08-05 08:30:47,605][00148] DAMAGECOUNT value on done: 658.0 [2024-08-05 08:30:47,606][00148] Sum rewards: -5.617, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.844', 'ARMOR': '0.004', 'AMMO2': '0.013', 'weapon4': '0.036', 'AMMO4': '0.062', 'WEAPON4': '0.100', 'HITCOUNT': '0.110', 'AMMO3': '0.150', 'DAMAGECOUNT': '0.354', 'WEAPON3': '0.750', 'FRAGCOUNT': '1.000', 'weapon3': '1.058', 'weapon2': '1.340'} [2024-08-05 08:30:48,133][00147] DAMAGECOUNT value on done: 633.0 [2024-08-05 08:30:48,255][00148] DAMAGECOUNT value on done: 1132.0 [2024-08-05 08:30:48,795][00147] DAMAGECOUNT value on done: 774.0 [2024-08-05 08:30:49,011][00148] DAMAGECOUNT value on done: 1035.0 [2024-08-05 08:30:49,581][00147] DAMAGECOUNT value on done: 1254.0 [2024-08-05 08:30:49,583][00147] Sum rewards: -5.731, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-0.730', 'weapon4': '0.002', 'AMMO2': '0.010', 'WEAPON4': '0.050', 'AMMO4': '0.052', 'AMMO3': '0.097', 'HITCOUNT': '0.150', 'ARMOR': '0.436', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.630', 'weapon3': '0.702', 'FRAGCOUNT': '1.000', 'weapon2': '1.870'} [2024-08-05 08:30:49,677][00148] DAMAGECOUNT value on done: 797.0 [2024-08-05 08:30:49,678][00148] Sum rewards: -4.660, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.114', 'AMMO2': '0.014', 'HITCOUNT': '0.020', 'WEAPON4': '0.050', 'DAMAGECOUNT': '0.060', 'weapon4': '0.068', 'AMMO4': '0.069', 'AMMO3': '0.085', 'ARMOR': '0.400', 'WEAPON3': '0.400', 'weapon3': '0.720', 'FRAGCOUNT': '1.000', 'weapon2': '1.568'} [2024-08-05 08:30:51,500][00035] Fps is (10 sec: 3277.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 1777664. Throughput: 0: 900.0. Samples: 443786. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:30:51,502][00035] Avg episode reward: [(0, '-6.099')] [2024-08-05 08:30:56,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 1794048. Throughput: 0: 901.3. Samples: 449342. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:30:56,502][00035] Avg episode reward: [(0, '-6.099')] [2024-08-05 08:30:57,019][00146] Updated weights for policy 0, policy_version 220 (0.0026) [2024-08-05 08:31:01,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1818624. Throughput: 0: 904.4. Samples: 454890. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:31:01,503][00035] Avg episode reward: [(0, '-6.099')] [2024-08-05 08:31:03,966][00148] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-05 08:31:06,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1835008. Throughput: 0: 913.5. Samples: 457704. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:31:06,502][00035] Avg episode reward: [(0, '-6.099')] [2024-08-05 08:31:07,636][00149] DAMAGECOUNT value on done: 735.0 [2024-08-05 08:31:07,636][00149] Sum rewards: -8.762, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-1.348', 'AMMO2': '0.028', 'ARMOR': '0.034', 'weapon4': '0.084', 'HITCOUNT': '0.110', 'AMMO3': '0.129', 'AMMO4': '0.138', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.525', 'WEAPON3': '0.650', 'FRAGCOUNT': '1.000', 'weapon3': '1.132', 'weapon2': '1.306'} [2024-08-05 08:31:08,219][00149] DAMAGECOUNT value on done: 1078.0 [2024-08-05 08:31:08,777][00149] DAMAGECOUNT value on done: 848.0 [2024-08-05 08:31:09,303][00149] DAMAGECOUNT value on done: 774.0 [2024-08-05 08:31:09,304][00149] Sum rewards: -6.095, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.158', 'AMMO5': '0.003', 'WEAPON1': '0.010', 'AMMO2': '0.013', 'weapon5': '0.016', 'WEAPON5': '0.050', 'AMMO4': '0.062', 'HITCOUNT': '0.120', 'AMMO3': '0.190', 'DAMAGECOUNT': '0.510', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.050', 'weapon2': '1.158', 'weapon3': '1.382'} [2024-08-05 08:31:09,385][00150] DAMAGECOUNT value on done: 837.0 [2024-08-05 08:31:09,386][00150] Sum rewards: -8.756, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-2.613', 'AMMO2': '0.020', 'ARMOR': '0.036', 'HITCOUNT': '0.060', 'AMMO4': '0.100', 'AMMO3': '0.153', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.210', 'weapon4': '0.222', 'weapon3': '0.782', 'WEAPON3': '0.850', 'FRAGCOUNT': '1.000', 'weapon2': '1.474'} [2024-08-05 08:31:09,904][00150] DAMAGECOUNT value on done: 1477.0 [2024-08-05 08:31:10,519][00150] DAMAGECOUNT value on done: 1060.0 [2024-08-05 08:31:10,520][00150] Sum rewards: -8.951, reward structure: {'DEATHCOUNT': '-9.750', 'FRAGCOUNT': '-1.500', 'HEALTH': '-1.005', 'AMMO5': '0.003', 'AMMO2': '0.013', 'weapon5': '0.028', 'HITCOUNT': '0.030', 'DAMAGECOUNT': '0.045', 'WEAPON5': '0.050', 'AMMO4': '0.063', 'AMMO3': '0.094', 'WEAPON3': '0.500', 'weapon3': '1.104', 'weapon2': '1.374'} [2024-08-05 08:31:11,105][00150] DAMAGECOUNT value on done: 1193.0 [2024-08-05 08:31:11,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 1851392. Throughput: 0: 911.2. Samples: 463196. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:31:11,501][00035] Avg episode reward: [(0, '-6.208')] [2024-08-05 08:31:16,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 1867776. Throughput: 0: 913.4. Samples: 468832. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:31:16,502][00035] Avg episode reward: [(0, '-6.208')] [2024-08-05 08:31:19,229][00146] Updated weights for policy 0, policy_version 230 (0.0029) [2024-08-05 08:31:21,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 1884160. Throughput: 0: 913.5. Samples: 471536. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:31:21,504][00035] Avg episode reward: [(0, '-6.208')] [2024-08-05 08:31:25,027][00147] DAMAGECOUNT value on done: 1349.0 [2024-08-05 08:31:25,146][00148] DAMAGECOUNT value on done: 693.0 [2024-08-05 08:31:25,147][00148] Sum rewards: -10.216, reward structure: {'DEATHCOUNT': '-11.250', 'FRAGCOUNT': '-1.500', 'HEALTH': '-1.080', 'AMMO5': '0.005', 'weapon5': '0.006', 'AMMO2': '0.010', 'HITCOUNT': '0.040', 'ARMOR': '0.048', 'AMMO4': '0.052', 'WEAPON5': '0.100', 'DAMAGECOUNT': '0.105', 'WEAPON4': '0.150', 'AMMO3': '0.156', 'weapon4': '0.220', 'WEAPON3': '0.600', 'weapon3': '0.848', 'weapon2': '1.274'} [2024-08-05 08:31:25,586][00147] DAMAGECOUNT value on done: 712.0 [2024-08-05 08:31:25,721][00148] DAMAGECOUNT value on done: 1147.0 [2024-08-05 08:31:25,722][00148] Sum rewards: -7.903, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.640', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.003', 'HITCOUNT': '0.010', 'AMMO2': '0.015', 'ARMOR': '0.036', 'DAMAGECOUNT': '0.045', 'weapon5': '0.064', 'AMMO4': '0.072', 'WEAPON5': '0.100', 'AMMO3': '0.128', 'weapon4': '0.246', 'WEAPON4': '0.300', 'WEAPON3': '0.650', 'weapon3': '0.886', 'weapon2': '1.182'} [2024-08-05 08:31:26,115][00147] DAMAGECOUNT value on done: 814.0 [2024-08-05 08:31:26,314][00148] DAMAGECOUNT value on done: 1045.0 [2024-08-05 08:31:26,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1908736. Throughput: 0: 907.4. Samples: 476690. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:31:26,504][00035] Avg episode reward: [(0, '-6.300')] [2024-08-05 08:31:26,757][00147] DAMAGECOUNT value on done: 1339.0 [2024-08-05 08:31:26,757][00147] Sum rewards: -6.805, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.400', 'WEAPON1': '0.020', 'AMMO2': '0.023', 'HITCOUNT': '0.100', 'AMMO4': '0.115', 'weapon4': '0.134', 'AMMO3': '0.148', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.255', 'WEAPON3': '0.850', 'FRAGCOUNT': '1.000', 'weapon3': '1.076', 'weapon2': '1.174'} [2024-08-05 08:31:26,958][00148] DAMAGECOUNT value on done: 827.0 [2024-08-05 08:31:31,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1925120. Throughput: 0: 908.8. Samples: 482286. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:31:31,502][00035] Avg episode reward: [(0, '-6.265')] [2024-08-05 08:31:36,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 1941504. Throughput: 0: 919.0. Samples: 485140. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:31:36,501][00035] Avg episode reward: [(0, '-6.265')] [2024-08-05 08:31:41,486][00146] Updated weights for policy 0, policy_version 240 (0.0021) [2024-08-05 08:31:41,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1966080. Throughput: 0: 919.4. Samples: 490716. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:31:41,504][00035] Avg episode reward: [(0, '-6.265')] [2024-08-05 08:31:43,721][00149] DAMAGECOUNT value on done: 860.0 [2024-08-05 08:31:44,237][00149] DAMAGECOUNT value on done: 1206.0 [2024-08-05 08:31:44,238][00149] Sum rewards: -7.758, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.802', 'AMMO5': '0.010', 'AMMO2': '0.018', 'weapon5': '0.018', 'HITCOUNT': '0.070', 'AMMO4': '0.087', 'AMMO3': '0.137', 'WEAPON5': '0.150', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.384', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.650', 'weapon3': '1.082', 'weapon2': '1.238'} [2024-08-05 08:31:44,788][00149] DAMAGECOUNT value on done: 883.0 [2024-08-05 08:31:45,344][00149] DAMAGECOUNT value on done: 934.0 [2024-08-05 08:31:45,345][00149] Sum rewards: -1.449, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-1.077', 'AMMO4': '-0.007', 'AMMO2': '-0.001', 'AMMO5': '0.003', 'ARMOR': '0.024', 'AMMO3': '0.038', 'weapon4': '0.038', 'HITCOUNT': '0.040', 'WEAPON4': '0.050', 'weapon5': '0.080', 'weapon3': '0.094', 'WEAPON5': '0.100', 'WEAPON3': '0.200', 'DAMAGECOUNT': '0.480', 'weapon2': '1.740', 'FRAGCOUNT': '2.000'} [2024-08-05 08:31:45,583][00150] DAMAGECOUNT value on done: 845.0 [2024-08-05 08:31:46,148][00150] DAMAGECOUNT value on done: 1481.0 [2024-08-05 08:31:46,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1982464. Throughput: 0: 919.8. Samples: 496280. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:31:46,504][00035] Avg episode reward: [(0, '-6.249')] [2024-08-05 08:31:46,737][00150] DAMAGECOUNT value on done: 1060.0 [2024-08-05 08:31:47,281][00150] DAMAGECOUNT value on done: 1313.0 [2024-08-05 08:31:47,282][00150] Sum rewards: -6.476, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.292', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.022', 'AMMO2': '-0.004', 'AMMO5': '0.005', 'WEAPON1': '0.010', 'HITCOUNT': '0.030', 'ARMOR': '0.036', 'WEAPON5': '0.100', 'weapon5': '0.128', 'AMMO3': '0.141', 'DAMAGECOUNT': '0.360', 'WEAPON3': '0.750', 'weapon3': '0.876', 'weapon2': '1.156'} [2024-08-05 08:31:51,501][00035] Fps is (10 sec: 3276.5, 60 sec: 3686.3, 300 sec: 3637.8). Total num frames: 1998848. Throughput: 0: 917.9. Samples: 499012. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:31:51,503][00035] Avg episode reward: [(0, '-6.201')] [2024-08-05 08:31:56,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2015232. Throughput: 0: 910.0. Samples: 504148. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:31:56,502][00035] Avg episode reward: [(0, '-6.201')] [2024-08-05 08:32:01,500][00035] Fps is (10 sec: 3277.1, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 2031616. Throughput: 0: 908.5. Samples: 509716. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:32:01,502][00035] Avg episode reward: [(0, '-6.201')] [2024-08-05 08:32:02,192][00148] DAMAGECOUNT value on done: 808.0 [2024-08-05 08:32:02,193][00148] Sum rewards: -4.960, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.544', 'AMMO5': '0.003', 'WEAPON1': '0.010', 'AMMO2': '0.011', 'weapon5': '0.022', 'weapon4': '0.044', 'WEAPON5': '0.050', 'AMMO4': '0.055', 'HITCOUNT': '0.060', 'WEAPON4': '0.100', 'AMMO3': '0.128', 'DAMAGECOUNT': '0.345', 'WEAPON3': '0.600', 'weapon3': '0.946', 'FRAGCOUNT': '1.000', 'weapon2': '1.210'} [2024-08-05 08:32:02,256][00147] DAMAGECOUNT value on done: 1514.0 [2024-08-05 08:32:02,257][00147] Sum rewards: -1.074, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-0.026', 'AMMO2': '0.032', 'AMMO3': '0.077', 'ARMOR': '0.094', 'HITCOUNT': '0.100', 'AMMO4': '0.161', 'WEAPON4': '0.200', 'weapon4': '0.304', 'WEAPON3': '0.400', 'DAMAGECOUNT': '0.495', 'weapon3': '0.550', 'weapon2': '1.288', 'FRAGCOUNT': '2.000'} [2024-08-05 08:32:02,719][00148] DAMAGECOUNT value on done: 1252.0 [2024-08-05 08:32:02,825][00147] DAMAGECOUNT value on done: 732.0 [2024-08-05 08:32:02,826][00147] Sum rewards: -6.779, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.274', 'AMMO2': '0.009', 'HITCOUNT': '0.030', 'AMMO4': '0.046', 'DAMAGECOUNT': '0.060', 'WEAPON4': '0.100', 'weapon4': '0.130', 'AMMO3': '0.138', 'ARMOR': '0.513', 'WEAPON3': '0.750', 'weapon3': '0.864', 'FRAGCOUNT': '1.000', 'weapon2': '1.354'} [2024-08-05 08:32:03,275][00148] DAMAGECOUNT value on done: 1110.0 [2024-08-05 08:32:03,408][00147] DAMAGECOUNT value on done: 894.0 [2024-08-05 08:32:03,813][00148] DAMAGECOUNT value on done: 922.0 [2024-08-05 08:32:04,009][00147] DAMAGECOUNT value on done: 1357.0 [2024-08-05 08:32:04,276][00146] Updated weights for policy 0, policy_version 250 (0.0030) [2024-08-05 08:32:06,500][00035] Fps is (10 sec: 4095.9, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 2056192. Throughput: 0: 908.8. Samples: 512434. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:32:06,502][00035] Avg episode reward: [(0, '-6.028')] [2024-08-05 08:32:06,504][00137] Saving new best policy, reward=-6.028! [2024-08-05 08:32:11,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 2072576. Throughput: 0: 917.6. Samples: 517982. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:32:11,503][00035] Avg episode reward: [(0, '-6.028')] [2024-08-05 08:32:16,500][00035] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2088960. Throughput: 0: 918.0. Samples: 523598. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:32:16,502][00035] Avg episode reward: [(0, '-6.028')] [2024-08-05 08:32:20,486][00149] DAMAGECOUNT value on done: 860.0 [2024-08-05 08:32:21,011][00149] DAMAGECOUNT value on done: 1211.0 [2024-08-05 08:32:21,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2105344. Throughput: 0: 916.4. Samples: 526378. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:32:21,501][00035] Avg episode reward: [(0, '-6.044')] [2024-08-05 08:32:21,508][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000257_2105344.pth... [2024-08-05 08:32:21,600][00149] DAMAGECOUNT value on done: 948.0 [2024-08-05 08:32:21,617][00137] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000150_1228800.pth [2024-08-05 08:32:21,632][00150] DAMAGECOUNT value on done: 860.0 [2024-08-05 08:32:22,195][00149] DAMAGECOUNT value on done: 1029.0 [2024-08-05 08:32:22,196][00149] Sum rewards: -4.262, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.218', 'AMMO2': '0.003', 'AMMO4': '0.013', 'HITCOUNT': '0.090', 'AMMO3': '0.115', 'DAMAGECOUNT': '0.285', 'ARMOR': '0.428', 'WEAPON3': '0.700', 'weapon3': '1.026', 'weapon2': '1.296', 'FRAGCOUNT': '2.000'} [2024-08-05 08:32:22,206][00150] DAMAGECOUNT value on done: 1506.0 [2024-08-05 08:32:22,736][00150] DAMAGECOUNT value on done: 1080.0 [2024-08-05 08:32:23,274][00150] DAMAGECOUNT value on done: 1496.0 [2024-08-05 08:32:26,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 2121728. Throughput: 0: 905.9. Samples: 531480. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:32:26,502][00035] Avg episode reward: [(0, '-6.172')] [2024-08-05 08:32:26,794][00146] Updated weights for policy 0, policy_version 260 (0.0021) [2024-08-05 08:32:31,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 2146304. Throughput: 0: 903.6. Samples: 536942. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:32:31,502][00035] Avg episode reward: [(0, '-6.172')] [2024-08-05 08:32:36,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2162688. Throughput: 0: 905.9. Samples: 539778. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:32:36,502][00035] Avg episode reward: [(0, '-6.172')] [2024-08-05 08:32:39,609][00147] DAMAGECOUNT value on done: 1634.0 [2024-08-05 08:32:39,660][00148] DAMAGECOUNT value on done: 952.0 [2024-08-05 08:32:39,661][00148] Sum rewards: -10.536, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-2.012', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.004', 'weapon5': '0.020', 'AMMO2': '0.027', 'HITCOUNT': '0.070', 'WEAPON5': '0.100', 'AMMO3': '0.106', 'AMMO4': '0.136', 'weapon4': '0.138', 'DAMAGECOUNT': '0.192', 'WEAPON4': '0.300', 'ARMOR': '0.424', 'WEAPON3': '0.600', 'weapon3': '0.730', 'weapon2': '1.378'} [2024-08-05 08:32:40,187][00147] DAMAGECOUNT value on done: 777.0 [2024-08-05 08:32:40,236][00148] DAMAGECOUNT value on done: 1309.0 [2024-08-05 08:32:40,237][00148] Sum rewards: -3.843, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.894', 'AMMO5': '0.003', 'AMMO2': '0.010', 'weapon5': '0.018', 'weapon4': '0.030', 'WEAPON5': '0.050', 'AMMO4': '0.051', 'HITCOUNT': '0.060', 'AMMO3': '0.092', 'WEAPON4': '0.100', 'DAMAGECOUNT': '0.171', 'ARMOR': '0.400', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon3': '1.098', 'weapon2': '1.118'} [2024-08-05 08:32:40,773][00148] DAMAGECOUNT value on done: 1240.0 [2024-08-05 08:32:40,820][00147] DAMAGECOUNT value on done: 1065.0 [2024-08-05 08:32:40,821][00147] Sum rewards: -5.028, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-0.032', 'AMMO5': '0.005', 'AMMO2': '0.014', 'weapon5': '0.022', 'WEAPON1': '0.040', 'ARMOR': '0.048', 'WEAPON5': '0.050', 'AMMO4': '0.070', 'AMMO3': '0.138', 'HITCOUNT': '0.140', 'WEAPON4': '0.150', 'weapon4': '0.154', 'DAMAGECOUNT': '0.513', 'WEAPON3': '0.600', 'weapon3': '0.794', 'weapon2': '1.516', 'FRAGCOUNT': '2.000'} [2024-08-05 08:32:41,308][00148] DAMAGECOUNT value on done: 1022.0 [2024-08-05 08:32:41,309][00148] Sum rewards: -4.029, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.096', 'AMMO5': '0.005', 'weapon5': '0.012', 'AMMO2': '0.016', 'AMMO3': '0.056', 'ARMOR': '0.057', 'HITCOUNT': '0.060', 'AMMO4': '0.081', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'weapon4': '0.190', 'WEAPON3': '0.300', 'DAMAGECOUNT': '0.300', 'weapon3': '0.594', 'FRAGCOUNT': '1.000', 'weapon2': '1.446'} [2024-08-05 08:32:41,438][00147] DAMAGECOUNT value on done: 1357.0 [2024-08-05 08:32:41,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 2179072. Throughput: 0: 913.6. Samples: 545262. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:32:41,501][00035] Avg episode reward: [(0, '-6.288')] [2024-08-05 08:32:46,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 2195456. Throughput: 0: 915.1. Samples: 550896. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:32:46,504][00035] Avg episode reward: [(0, '-6.288')] [2024-08-05 08:32:48,823][00146] Updated weights for policy 0, policy_version 270 (0.0020) [2024-08-05 08:32:51,500][00035] Fps is (10 sec: 4095.9, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 2220032. Throughput: 0: 916.2. Samples: 553662. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:32:51,502][00035] Avg episode reward: [(0, '-6.288')] [2024-08-05 08:32:56,508][00035] Fps is (10 sec: 4092.7, 60 sec: 3685.9, 300 sec: 3637.7). Total num frames: 2236416. Throughput: 0: 918.9. Samples: 559340. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:32:56,512][00035] Avg episode reward: [(0, '-6.288')] [2024-08-05 08:32:56,629][00149] DAMAGECOUNT value on done: 964.0 [2024-08-05 08:32:56,635][00149] Sum rewards: -5.287, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.820', 'AMMO4': '-0.003', 'AMMO2': '-0.001', 'ARMOR': '0.048', 'HITCOUNT': '0.100', 'AMMO3': '0.112', 'DAMAGECOUNT': '0.312', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon2': '1.076', 'weapon3': '1.288'} [2024-08-05 08:32:57,477][00149] DAMAGECOUNT value on done: 1251.0 [2024-08-05 08:32:58,148][00149] DAMAGECOUNT value on done: 978.0 [2024-08-05 08:32:58,291][00150] DAMAGECOUNT value on done: 860.0 [2024-08-05 08:32:58,679][00149] DAMAGECOUNT value on done: 1034.0 [2024-08-05 08:32:58,907][00150] DAMAGECOUNT value on done: 1601.0 [2024-08-05 08:32:58,907][00150] Sum rewards: -7.049, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.819', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.007', 'AMMO2': '0.016', 'ARMOR': '0.020', 'weapon4': '0.078', 'AMMO4': '0.079', 'HITCOUNT': '0.080', 'weapon5': '0.088', 'AMMO3': '0.122', 'WEAPON4': '0.150', 'WEAPON5': '0.150', 'DAMAGECOUNT': '0.285', 'WEAPON3': '0.550', 'weapon3': '0.558', 'weapon2': '1.336'} [2024-08-05 08:32:59,519][00150] DAMAGECOUNT value on done: 1117.0 [2024-08-05 08:33:00,053][00150] DAMAGECOUNT value on done: 1620.0 [2024-08-05 08:33:01,500][00035] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2252800. Throughput: 0: 904.5. Samples: 564302. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:33:01,502][00035] Avg episode reward: [(0, '-6.397')] [2024-08-05 08:33:06,500][00035] Fps is (10 sec: 3279.5, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 2269184. Throughput: 0: 904.7. Samples: 567090. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:33:06,502][00035] Avg episode reward: [(0, '-6.397')] [2024-08-05 08:33:11,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 2285568. Throughput: 0: 912.8. Samples: 572554. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:33:11,502][00035] Avg episode reward: [(0, '-6.397')] [2024-08-05 08:33:11,655][00146] Updated weights for policy 0, policy_version 280 (0.0036) [2024-08-05 08:33:16,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 2310144. Throughput: 0: 914.8. Samples: 578110. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:33:16,502][00035] Avg episode reward: [(0, '-6.397')] [2024-08-05 08:33:16,975][00148] DAMAGECOUNT value on done: 1145.0 [2024-08-05 08:33:16,976][00148] Sum rewards: -1.780, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.592', 'AMMO5': '0.003', 'AMMO2': '0.018', 'ARMOR': '0.035', 'WEAPON5': '0.050', 'weapon4': '0.086', 'AMMO4': '0.088', 'HITCOUNT': '0.120', 'AMMO3': '0.139', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.579', 'WEAPON3': '0.600', 'weapon2': '1.120', 'weapon3': '1.274', 'FRAGCOUNT': '2.000'} [2024-08-05 08:33:17,176][00147] DAMAGECOUNT value on done: 1673.0 [2024-08-05 08:33:17,523][00148] DAMAGECOUNT value on done: 1341.0 [2024-08-05 08:33:17,710][00147] DAMAGECOUNT value on done: 924.0 [2024-08-05 08:33:18,080][00148] DAMAGECOUNT value on done: 1390.0 [2024-08-05 08:33:18,081][00148] Sum rewards: -1.444, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-0.916', 'AMMO2': '0.004', 'AMMO5': '0.005', 'AMMO4': '0.018', 'weapon5': '0.030', 'WEAPON4': '0.050', 'ARMOR': '0.080', 'AMMO3': '0.097', 'WEAPON5': '0.100', 'HITCOUNT': '0.130', 'weapon4': '0.190', 'DAMAGECOUNT': '0.450', 'WEAPON3': '0.550', 'weapon2': '0.858', 'FRAGCOUNT': '1.000', 'weapon3': '1.160'} [2024-08-05 08:33:18,276][00147] DAMAGECOUNT value on done: 1275.0 [2024-08-05 08:33:18,276][00147] Sum rewards: -4.328, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.792', 'AMMO2': '0.029', 'ARMOR': '0.108', 'weapon4': '0.124', 'AMMO3': '0.132', 'AMMO4': '0.146', 'HITCOUNT': '0.150', 'WEAPON4': '0.350', 'DAMAGECOUNT': '0.630', 'WEAPON3': '0.650', 'weapon3': '0.960', 'weapon2': '1.184', 'FRAGCOUNT': '2.000'} [2024-08-05 08:33:18,685][00148] DAMAGECOUNT value on done: 1209.0 [2024-08-05 08:33:18,686][00148] Sum rewards: -6.105, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.575', 'AMMO5': '0.003', 'ARMOR': '0.004', 'AMMO2': '0.008', 'WEAPON1': '0.010', 'AMMO4': '0.039', 'WEAPON4': '0.050', 'WEAPON5': '0.050', 'weapon4': '0.072', 'weapon5': '0.086', 'HITCOUNT': '0.110', 'AMMO3': '0.178', 'DAMAGECOUNT': '0.561', 'weapon3': '0.754', 'WEAPON3': '0.800', 'weapon2': '1.246', 'FRAGCOUNT': '2.000'} [2024-08-05 08:33:18,863][00147] DAMAGECOUNT value on done: 1464.0 [2024-08-05 08:33:21,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2326528. Throughput: 0: 912.6. Samples: 580846. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:33:21,502][00035] Avg episode reward: [(0, '-6.410')] [2024-08-05 08:33:26,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2342912. Throughput: 0: 914.5. Samples: 586416. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:33:26,502][00035] Avg episode reward: [(0, '-6.410')] [2024-08-05 08:33:31,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 2359296. Throughput: 0: 903.8. Samples: 591568. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:33:31,502][00035] Avg episode reward: [(0, '-6.410')] [2024-08-05 08:33:33,291][00149] DAMAGECOUNT value on done: 1025.0 [2024-08-05 08:33:33,292][00149] Sum rewards: -11.953, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-2.020', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.005', 'AMMO2': '0.016', 'ARMOR': '0.052', 'weapon5': '0.054', 'HITCOUNT': '0.060', 'AMMO4': '0.078', 'WEAPON5': '0.100', 'weapon4': '0.138', 'AMMO3': '0.163', 'DAMAGECOUNT': '0.183', 'WEAPON4': '0.200', 'WEAPON3': '0.850', 'weapon3': '0.888', 'weapon2': '1.530'} [2024-08-05 08:33:33,858][00149] DAMAGECOUNT value on done: 1319.0 [2024-08-05 08:33:34,226][00146] Updated weights for policy 0, policy_version 290 (0.0019) [2024-08-05 08:33:34,458][00149] DAMAGECOUNT value on done: 1348.0 [2024-08-05 08:33:34,459][00149] Sum rewards: -3.120, reward structure: {'DEATHCOUNT': '-9.000', 'AMMO5': '0.007', 'AMMO2': '0.011', 'WEAPON4': '0.050', 'AMMO4': '0.054', 'AMMO3': '0.085', 'weapon4': '0.090', 'weapon5': '0.108', 'WEAPON5': '0.150', 'HITCOUNT': '0.180', 'HEALTH': '0.344', 'WEAPON3': '0.400', 'FRAGCOUNT': '1.000', 'weapon3': '1.014', 'DAMAGECOUNT': '1.110', 'weapon2': '1.276'} [2024-08-05 08:33:34,851][00150] DAMAGECOUNT value on done: 924.0 [2024-08-05 08:33:34,852][00150] Sum rewards: -6.464, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-0.340', 'AMMO5': '0.005', 'ARMOR': '0.024', 'AMMO2': '0.024', 'HITCOUNT': '0.070', 'WEAPON5': '0.100', 'AMMO4': '0.122', 'AMMO3': '0.151', 'weapon4': '0.152', 'DAMAGECOUNT': '0.192', 'WEAPON4': '0.200', 'WEAPON3': '0.750', 'FRAGCOUNT': '1.000', 'weapon3': '1.100', 'weapon2': '1.236'} [2024-08-05 08:33:35,034][00149] DAMAGECOUNT value on done: 1194.0 [2024-08-05 08:33:35,035][00149] Sum rewards: -7.194, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.756', 'FRAGCOUNT': '-1.000', 'AMMO5': '0.007', 'WEAPON1': '0.010', 'AMMO2': '0.047', 'ARMOR': '0.076', 'weapon5': '0.078', 'HITCOUNT': '0.090', 'AMMO3': '0.094', 'WEAPON5': '0.150', 'AMMO4': '0.234', 'weapon4': '0.330', 'WEAPON4': '0.450', 'DAMAGECOUNT': '0.480', 'WEAPON3': '0.500', 'weapon3': '0.734', 'weapon2': '1.282'} [2024-08-05 08:33:35,385][00150] DAMAGECOUNT value on done: 1634.0 [2024-08-05 08:33:35,941][00150] DAMAGECOUNT value on done: 1302.0 [2024-08-05 08:33:35,942][00150] Sum rewards: -1.673, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.461', 'AMMO5': '0.003', 'AMMO2': '0.003', 'AMMO4': '0.016', 'weapon5': '0.040', 'weapon4': '0.042', 'WEAPON5': '0.050', 'WEAPON4': '0.050', 'AMMO3': '0.129', 'HITCOUNT': '0.130', 'DAMAGECOUNT': '0.555', 'WEAPON3': '0.700', 'weapon2': '1.244', 'weapon3': '1.326', 'FRAGCOUNT': '2.000'} [2024-08-05 08:33:36,507][00035] Fps is (10 sec: 4093.0, 60 sec: 3685.9, 300 sec: 3665.5). Total num frames: 2383872. Throughput: 0: 902.0. Samples: 594260. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:33:36,513][00035] Avg episode reward: [(0, '-6.430')] [2024-08-05 08:33:36,558][00150] DAMAGECOUNT value on done: 1730.0 [2024-08-05 08:33:41,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 2400256. Throughput: 0: 897.6. Samples: 599724. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:33:41,501][00035] Avg episode reward: [(0, '-6.420')] [2024-08-05 08:33:46,500][00035] Fps is (10 sec: 3279.2, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2416640. Throughput: 0: 910.0. Samples: 605254. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:33:46,502][00035] Avg episode reward: [(0, '-6.420')] [2024-08-05 08:33:51,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 2433024. Throughput: 0: 909.1. Samples: 607998. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:33:51,502][00035] Avg episode reward: [(0, '-6.420')] [2024-08-05 08:33:54,613][00148] DAMAGECOUNT value on done: 1289.0 [2024-08-05 08:33:54,614][00148] Sum rewards: -6.720, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-1.074', 'AMMO2': '0.007', 'ARMOR': '0.024', 'AMMO4': '0.035', 'WEAPON4': '0.100', 'weapon4': '0.108', 'HITCOUNT': '0.130', 'AMMO3': '0.145', 'DAMAGECOUNT': '0.432', 'WEAPON3': '0.700', 'weapon3': '1.064', 'weapon2': '1.608', 'FRAGCOUNT': '2.000'} [2024-08-05 08:33:54,647][00147] DAMAGECOUNT value on done: 1698.0 [2024-08-05 08:33:55,161][00148] DAMAGECOUNT value on done: 1376.0 [2024-08-05 08:33:55,225][00147] DAMAGECOUNT value on done: 954.0 [2024-08-05 08:33:55,760][00148] DAMAGECOUNT value on done: 1601.0 [2024-08-05 08:33:55,761][00148] Sum rewards: -5.073, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.906', 'AMMO5': '0.005', 'ARMOR': '0.012', 'AMMO2': '0.027', 'WEAPON5': '0.100', 'AMMO3': '0.116', 'AMMO4': '0.135', 'HITCOUNT': '0.140', 'weapon4': '0.166', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.633', 'WEAPON3': '0.650', 'weapon3': '0.894', 'weapon2': '1.404', 'FRAGCOUNT': '2.000'} [2024-08-05 08:33:55,792][00147] DAMAGECOUNT value on done: 1300.0 [2024-08-05 08:33:56,368][00148] DAMAGECOUNT value on done: 1319.0 [2024-08-05 08:33:56,389][00147] DAMAGECOUNT value on done: 1518.0 [2024-08-05 08:33:56,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3550.4, 300 sec: 3637.8). Total num frames: 2449408. Throughput: 0: 911.2. Samples: 613556. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:33:56,502][00035] Avg episode reward: [(0, '-6.351')] [2024-08-05 08:33:56,736][00146] Updated weights for policy 0, policy_version 300 (0.0022) [2024-08-05 08:34:01,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2473984. Throughput: 0: 901.9. Samples: 618694. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:34:01,502][00035] Avg episode reward: [(0, '-6.351')] [2024-08-05 08:34:06,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2490368. Throughput: 0: 901.6. Samples: 621420. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:34:06,502][00035] Avg episode reward: [(0, '-6.351')] [2024-08-05 08:34:09,998][00149] DAMAGECOUNT value on done: 1030.0 [2024-08-05 08:34:10,610][00149] DAMAGECOUNT value on done: 1411.0 [2024-08-05 08:34:11,150][00149] DAMAGECOUNT value on done: 1367.0 [2024-08-05 08:34:11,152][00149] Sum rewards: -7.631, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.550', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.003', 'AMMO2': '0.007', 'WEAPON1': '0.010', 'weapon5': '0.018', 'ARMOR': '0.028', 'HITCOUNT': '0.030', 'AMMO4': '0.033', 'WEAPON5': '0.050', 'WEAPON4': '0.050', 'DAMAGECOUNT': '0.057', 'weapon4': '0.058', 'AMMO3': '0.092', 'WEAPON3': '0.450', 'weapon3': '0.742', 'weapon2': '2.042'} [2024-08-05 08:34:11,298][00150] DAMAGECOUNT value on done: 979.0 [2024-08-05 08:34:11,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2506752. Throughput: 0: 898.8. Samples: 626862. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:34:11,502][00035] Avg episode reward: [(0, '-6.499')] [2024-08-05 08:34:11,725][00149] DAMAGECOUNT value on done: 1395.0 [2024-08-05 08:34:11,726][00149] Sum rewards: -3.513, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.710', 'AMMO2': '0.014', 'AMMO5': '0.022', 'AMMO4': '0.071', 'weapon5': '0.086', 'AMMO3': '0.091', 'HITCOUNT': '0.130', 'weapon4': '0.130', 'WEAPON4': '0.150', 'WEAPON5': '0.350', 'WEAPON3': '0.550', 'DAMAGECOUNT': '0.603', 'weapon3': '1.074', 'weapon2': '1.426', 'FRAGCOUNT': '2.500'} [2024-08-05 08:34:11,859][00150] DAMAGECOUNT value on done: 1669.0 [2024-08-05 08:34:12,404][00150] DAMAGECOUNT value on done: 1405.0 [2024-08-05 08:34:13,007][00150] DAMAGECOUNT value on done: 1895.0 [2024-08-05 08:34:16,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 2523136. Throughput: 0: 905.6. Samples: 632320. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:34:16,502][00035] Avg episode reward: [(0, '-6.479')] [2024-08-05 08:34:19,475][00146] Updated weights for policy 0, policy_version 310 (0.0029) [2024-08-05 08:34:21,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 2539520. Throughput: 0: 907.2. Samples: 635076. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:34:21,502][00035] Avg episode reward: [(0, '-6.479')] [2024-08-05 08:34:21,511][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000310_2539520.pth... [2024-08-05 08:34:21,619][00137] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000204_1671168.pth [2024-08-05 08:34:26,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2564096. Throughput: 0: 908.8. Samples: 640622. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:34:26,502][00035] Avg episode reward: [(0, '-6.479')] [2024-08-05 08:34:31,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2580480. Throughput: 0: 908.5. Samples: 646138. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:34:31,502][00035] Avg episode reward: [(0, '-6.479')] [2024-08-05 08:34:32,242][00147] DAMAGECOUNT value on done: 1818.0 [2024-08-05 08:34:32,590][00148] DAMAGECOUNT value on done: 1534.0 [2024-08-05 08:34:32,591][00148] Sum rewards: -1.546, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.372', 'AMMO5': '0.007', 'AMMO2': '0.011', 'weapon5': '0.046', 'AMMO4': '0.055', 'AMMO3': '0.063', 'WEAPON5': '0.150', 'HITCOUNT': '0.160', 'weapon4': '0.194', 'WEAPON4': '0.250', 'WEAPON3': '0.450', 'ARMOR': '0.500', 'DAMAGECOUNT': '0.735', 'weapon3': '1.056', 'weapon2': '1.648', 'FRAGCOUNT': '2.000'} [2024-08-05 08:34:32,948][00147] DAMAGECOUNT value on done: 1083.0 [2024-08-05 08:34:33,335][00148] DAMAGECOUNT value on done: 1416.0 [2024-08-05 08:34:33,727][00147] DAMAGECOUNT value on done: 1345.0 [2024-08-05 08:34:33,946][00148] DAMAGECOUNT value on done: 1714.0 [2024-08-05 08:34:33,946][00148] Sum rewards: 1.004, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-0.325', 'AMMO5': '0.005', 'AMMO2': '0.020', 'WEAPON5': '0.050', 'weapon4': '0.054', 'weapon5': '0.058', 'ARMOR': '0.064', 'AMMO3': '0.069', 'HITCOUNT': '0.090', 'AMMO4': '0.102', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.339', 'WEAPON3': '0.400', 'weapon3': '1.120', 'weapon2': '1.758', 'FRAGCOUNT': '3.000'} [2024-08-05 08:34:34,289][00147] DAMAGECOUNT value on done: 1620.0 [2024-08-05 08:34:34,494][00148] DAMAGECOUNT value on done: 1330.0 [2024-08-05 08:34:36,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3550.3, 300 sec: 3637.8). Total num frames: 2596864. Throughput: 0: 899.8. Samples: 648490. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:34:36,502][00035] Avg episode reward: [(0, '-6.361')] [2024-08-05 08:34:41,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 2613248. Throughput: 0: 897.9. Samples: 653960. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:34:41,502][00035] Avg episode reward: [(0, '-6.361')] [2024-08-05 08:34:42,238][00146] Updated weights for policy 0, policy_version 320 (0.0025) [2024-08-05 08:34:46,235][00149] DAMAGECOUNT value on done: 1100.0 [2024-08-05 08:34:46,500][00035] Fps is (10 sec: 3276.7, 60 sec: 3549.8, 300 sec: 3637.8). Total num frames: 2629632. Throughput: 0: 909.9. Samples: 659638. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:34:46,502][00035] Avg episode reward: [(0, '-6.336')] [2024-08-05 08:34:46,878][00149] DAMAGECOUNT value on done: 1541.0 [2024-08-05 08:34:46,879][00149] Sum rewards: -7.050, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-2.124', 'AMMO2': '0.001', 'AMMO4': '0.005', 'WEAPON1': '0.020', 'WEAPON4': '0.100', 'AMMO3': '0.115', 'HITCOUNT': '0.140', 'DAMAGECOUNT': '0.390', 'WEAPON3': '0.650', 'weapon3': '1.118', 'weapon2': '1.784', 'FRAGCOUNT': '2.000'} [2024-08-05 08:34:47,421][00149] DAMAGECOUNT value on done: 1519.0 [2024-08-05 08:34:47,793][00150] DAMAGECOUNT value on done: 1268.0 [2024-08-05 08:34:47,794][00150] Sum rewards: -0.448, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.288', 'AMMO5': '0.005', 'WEAPON1': '0.010', 'AMMO2': '0.014', 'weapon7': '0.016', 'WEAPON5': '0.050', 'ARMOR': '0.060', 'weapon5': '0.060', 'AMMO4': '0.069', 'weapon4': '0.090', 'AMMO3': '0.097', 'AMMO6': '0.100', 'WEAPON7': '0.100', 'AMMO7': '0.100', 'WEAPON4': '0.200', 'HITCOUNT': '0.210', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.867', 'weapon2': '1.214', 'weapon3': '1.228', 'FRAGCOUNT': '2.500'} [2024-08-05 08:34:48,008][00149] DAMAGECOUNT value on done: 1667.0 [2024-08-05 08:34:48,009][00149] Sum rewards: 0.654, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.097', 'AMMO2': '0.004', 'AMMO5': '0.007', 'AMMO4': '0.018', 'weapon5': '0.062', 'ARMOR': '0.086', 'AMMO3': '0.131', 'WEAPON5': '0.150', 'WEAPON4': '0.200', 'HITCOUNT': '0.220', 'weapon4': '0.234', 'WEAPON3': '0.750', 'DAMAGECOUNT': '0.816', 'weapon3': '1.264', 'weapon2': '1.308', 'FRAGCOUNT': '4.000'} [2024-08-05 08:34:48,354][00150] DAMAGECOUNT value on done: 1748.0 [2024-08-05 08:34:48,929][00150] DAMAGECOUNT value on done: 1447.0 [2024-08-05 08:34:49,476][00150] DAMAGECOUNT value on done: 1935.0 [2024-08-05 08:34:51,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2654208. Throughput: 0: 908.2. Samples: 662290. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:34:51,502][00035] Avg episode reward: [(0, '-6.189')] [2024-08-05 08:34:56,500][00035] Fps is (10 sec: 4096.1, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2670592. Throughput: 0: 912.5. Samples: 667924. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:34:56,502][00035] Avg episode reward: [(0, '-6.189')] [2024-08-05 08:35:01,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 2686976. Throughput: 0: 916.1. Samples: 673546. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:35:01,502][00035] Avg episode reward: [(0, '-6.189')] [2024-08-05 08:35:04,191][00146] Updated weights for policy 0, policy_version 330 (0.0027) [2024-08-05 08:35:06,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 2703360. Throughput: 0: 914.7. Samples: 676238. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:35:06,504][00035] Avg episode reward: [(0, '-6.189')] [2024-08-05 08:35:09,798][00147] DAMAGECOUNT value on done: 1983.0 [2024-08-05 08:35:09,800][00147] Sum rewards: -9.253, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-2.530', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.019', 'AMMO2': '-0.004', 'AMMO5': '0.008', 'WEAPON1': '0.020', 'ARMOR': '0.036', 'weapon5': '0.042', 'HITCOUNT': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.202', 'DAMAGECOUNT': '0.495', 'WEAPON3': '1.150', 'weapon2': '1.370', 'weapon3': '1.526'} [2024-08-05 08:35:10,179][00148] DAMAGECOUNT value on done: 1576.0 [2024-08-05 08:35:10,356][00147] DAMAGECOUNT value on done: 1181.0 [2024-08-05 08:35:10,709][00148] DAMAGECOUNT value on done: 1701.0 [2024-08-05 08:35:10,710][00148] Sum rewards: -1.703, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.070', 'WEAPON1': '0.010', 'AMMO2': '0.012', 'ARMOR': '0.032', 'AMMO4': '0.061', 'AMMO3': '0.144', 'HITCOUNT': '0.200', 'WEAPON3': '0.850', 'DAMAGECOUNT': '0.855', 'weapon2': '1.272', 'weapon3': '1.430', 'FRAGCOUNT': '2.000'} [2024-08-05 08:35:10,923][00147] DAMAGECOUNT value on done: 1535.0 [2024-08-05 08:35:10,924][00147] Sum rewards: -3.372, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.248', 'AMMO2': '0.005', 'AMMO4': '0.023', 'ARMOR': '0.048', 'WEAPON4': '0.100', 'AMMO3': '0.108', 'HITCOUNT': '0.140', 'weapon4': '0.192', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.570', 'FRAGCOUNT': '1.000', 'weapon3': '1.112', 'weapon2': '1.578'} [2024-08-05 08:35:11,280][00148] DAMAGECOUNT value on done: 1859.0 [2024-08-05 08:35:11,281][00148] Sum rewards: -6.269, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-2.388', 'AMMO2': '0.005', 'AMMO4': '0.025', 'weapon4': '0.028', 'ARMOR': '0.056', 'WEAPON4': '0.100', 'HITCOUNT': '0.120', 'AMMO3': '0.147', 'DAMAGECOUNT': '0.435', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon3': '1.466', 'weapon2': '1.586'} [2024-08-05 08:35:11,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2727936. Throughput: 0: 907.6. Samples: 681466. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:35:11,502][00035] Avg episode reward: [(0, '-6.025')] [2024-08-05 08:35:11,509][00137] Saving new best policy, reward=-6.025! [2024-08-05 08:35:11,544][00147] DAMAGECOUNT value on done: 1760.0 [2024-08-05 08:35:11,545][00147] Sum rewards: -6.108, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-0.251', 'AMMO5': '0.003', 'weapon5': '0.022', 'AMMO2': '0.023', 'ARMOR': '0.040', 'WEAPON5': '0.050', 'AMMO3': '0.087', 'HITCOUNT': '0.100', 'AMMO4': '0.115', 'weapon4': '0.124', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.420', 'WEAPON3': '0.450', 'weapon3': '0.732', 'FRAGCOUNT': '1.000', 'weapon2': '2.028'} [2024-08-05 08:35:11,885][00148] DAMAGECOUNT value on done: 1441.0 [2024-08-05 08:35:16,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2744320. Throughput: 0: 910.0. Samples: 687088. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:35:16,501][00035] Avg episode reward: [(0, '-5.988')] [2024-08-05 08:35:16,503][00137] Saving new best policy, reward=-5.988! [2024-08-05 08:35:21,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2760704. Throughput: 0: 918.3. Samples: 689812. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:35:21,502][00035] Avg episode reward: [(0, '-5.988')] [2024-08-05 08:35:22,276][00149] DAMAGECOUNT value on done: 1132.0 [2024-08-05 08:35:22,277][00149] Sum rewards: -2.760, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-0.795', 'AMMO2': '0.006', 'AMMO5': '0.010', 'weapon4': '0.010', 'WEAPON1': '0.020', 'AMMO4': '0.028', 'HITCOUNT': '0.030', 'ARMOR': '0.036', 'weapon5': '0.036', 'AMMO3': '0.085', 'DAMAGECOUNT': '0.096', 'WEAPON4': '0.100', 'WEAPON5': '0.200', 'WEAPON3': '0.550', 'FRAGCOUNT': '1.000', 'weapon3': '1.144', 'weapon2': '1.434'} [2024-08-05 08:35:22,783][00149] DAMAGECOUNT value on done: 1705.0 [2024-08-05 08:35:22,784][00149] Sum rewards: -5.457, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.664', 'AMMO2': '0.012', 'AMMO4': '0.059', 'ARMOR': '0.090', 'HITCOUNT': '0.140', 'weapon4': '0.144', 'AMMO3': '0.148', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.492', 'WEAPON3': '0.750', 'weapon3': '1.256', 'weapon2': '1.416', 'FRAGCOUNT': '2.000'} [2024-08-05 08:35:23,334][00149] DAMAGECOUNT value on done: 1704.0 [2024-08-05 08:35:23,336][00149] Sum rewards: -6.394, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-0.872', 'AMMO2': '0.013', 'ARMOR': '0.056', 'AMMO4': '0.063', 'HITCOUNT': '0.130', 'weapon4': '0.140', 'AMMO3': '0.143', 'WEAPON4': '0.150', 'DAMAGECOUNT': '0.555', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '1.226', 'weapon3': '1.452'} [2024-08-05 08:35:23,876][00149] DAMAGECOUNT value on done: 1815.0 [2024-08-05 08:35:23,877][00149] Sum rewards: -6.829, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-0.906', 'AMMO2': '0.024', 'ARMOR': '0.036', 'AMMO3': '0.067', 'HITCOUNT': '0.110', 'AMMO4': '0.121', 'WEAPON4': '0.200', 'weapon4': '0.272', 'WEAPON3': '0.400', 'DAMAGECOUNT': '0.444', 'weapon3': '0.648', 'FRAGCOUNT': '1.000', 'weapon2': '2.004'} [2024-08-05 08:35:23,919][00150] DAMAGECOUNT value on done: 1345.0 [2024-08-05 08:35:24,508][00150] DAMAGECOUNT value on done: 1933.0 [2024-08-05 08:35:24,509][00150] Sum rewards: -9.299, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-1.168', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.007', 'WEAPON1': '0.010', 'AMMO2': '0.011', 'AMMO4': '0.056', 'ARMOR': '0.072', 'weapon5': '0.078', 'AMMO3': '0.107', 'HITCOUNT': '0.110', 'WEAPON5': '0.150', 'WEAPON3': '0.550', 'DAMAGECOUNT': '0.555', 'weapon3': '0.598', 'weapon2': '2.064'} [2024-08-05 08:35:25,057][00150] DAMAGECOUNT value on done: 1707.0 [2024-08-05 08:35:25,058][00150] Sum rewards: -8.364, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-2.716', 'ARMOR': '0.004', 'AMMO5': '0.005', 'weapon5': '0.008', 'AMMO2': '0.015', 'weapon4': '0.034', 'WEAPON5': '0.050', 'AMMO4': '0.077', 'AMMO3': '0.191', 'WEAPON4': '0.200', 'HITCOUNT': '0.220', 'DAMAGECOUNT': '0.780', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon2': '1.290', 'weapon3': '1.378'} [2024-08-05 08:35:25,612][00150] DAMAGECOUNT value on done: 2035.0 [2024-08-05 08:35:25,613][00150] Sum rewards: -6.648, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-2.460', 'weapon5': '0.004', 'AMMO5': '0.005', 'AMMO2': '0.022', 'HITCOUNT': '0.090', 'WEAPON5': '0.100', 'AMMO4': '0.108', 'weapon4': '0.116', 'AMMO3': '0.143', 'WEAPON4': '0.150', 'DAMAGECOUNT': '0.300', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '1.328', 'weapon3': '1.396'} [2024-08-05 08:35:26,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 2777088. Throughput: 0: 920.2. Samples: 695368. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:35:26,502][00035] Avg episode reward: [(0, '-6.028')] [2024-08-05 08:35:26,785][00146] Updated weights for policy 0, policy_version 340 (0.0030) [2024-08-05 08:35:31,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 2801664. Throughput: 0: 918.3. Samples: 700962. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:35:31,504][00035] Avg episode reward: [(0, '-6.028')] [2024-08-05 08:35:36,500][00035] Fps is (10 sec: 4095.9, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2818048. Throughput: 0: 923.4. Samples: 703844. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:35:36,502][00035] Avg episode reward: [(0, '-6.028')] [2024-08-05 08:35:41,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2834432. Throughput: 0: 911.9. Samples: 708960. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:35:41,502][00035] Avg episode reward: [(0, '-6.028')] [2024-08-05 08:35:46,500][00035] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2850816. Throughput: 0: 913.4. Samples: 714650. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:35:46,501][00035] Avg episode reward: [(0, '-6.028')] [2024-08-05 08:35:47,208][00147] DAMAGECOUNT value on done: 2311.0 [2024-08-05 08:35:47,209][00147] Sum rewards: -6.937, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-2.394', 'AMMO5': '0.007', 'ARMOR': '0.008', 'WEAPON1': '0.020', 'weapon4': '0.020', 'AMMO2': '0.028', 'weapon5': '0.058', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO4': '0.140', 'AMMO3': '0.227', 'HITCOUNT': '0.250', 'weapon2': '0.886', 'DAMAGECOUNT': '0.984', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.150', 'weapon3': '1.728'} [2024-08-05 08:35:47,288][00148] DAMAGECOUNT value on done: 1821.0 [2024-08-05 08:35:47,289][00148] Sum rewards: -2.518, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.546', 'AMMO2': '0.020', 'ARMOR': '0.036', 'WEAPON4': '0.100', 'AMMO4': '0.102', 'AMMO3': '0.113', 'HITCOUNT': '0.190', 'weapon4': '0.298', 'WEAPON3': '0.650', 'DAMAGECOUNT': '0.735', 'weapon3': '1.044', 'weapon2': '1.490', 'FRAGCOUNT': '3.000'} [2024-08-05 08:35:47,736][00147] DAMAGECOUNT value on done: 1317.0 [2024-08-05 08:35:47,737][00147] Sum rewards: -2.920, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.732', 'AMMO2': '0.002', 'AMMO5': '0.003', 'weapon5': '0.008', 'AMMO4': '0.009', 'ARMOR': '0.048', 'WEAPON5': '0.050', 'HITCOUNT': '0.090', 'AMMO3': '0.098', 'DAMAGECOUNT': '0.408', 'WEAPON3': '0.600', 'weapon2': '1.244', 'weapon3': '1.502', 'FRAGCOUNT': '2.000'} [2024-08-05 08:35:47,847][00148] DAMAGECOUNT value on done: 1786.0 [2024-08-05 08:35:48,294][00147] DAMAGECOUNT value on done: 1545.0 [2024-08-05 08:35:48,448][00148] DAMAGECOUNT value on done: 1976.0 [2024-08-05 08:35:48,448][00148] Sum rewards: -3.809, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.202', 'AMMO2': '0.023', 'ARMOR': '0.072', 'AMMO4': '0.113', 'AMMO3': '0.114', 'HITCOUNT': '0.120', 'weapon4': '0.236', 'WEAPON4': '0.250', 'DAMAGECOUNT': '0.351', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon2': '1.254', 'weapon3': '1.260'} [2024-08-05 08:35:48,847][00147] DAMAGECOUNT value on done: 1825.0 [2024-08-05 08:35:49,054][00148] DAMAGECOUNT value on done: 1471.0 [2024-08-05 08:35:49,054][00148] Sum rewards: -10.801, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-1.971', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.005', 'weapon5': '0.012', 'AMMO2': '0.020', 'HITCOUNT': '0.030', 'weapon4': '0.054', 'DAMAGECOUNT': '0.090', 'AMMO4': '0.098', 'WEAPON5': '0.100', 'WEAPON4': '0.150', 'AMMO3': '0.167', 'ARMOR': '0.460', 'WEAPON3': '0.800', 'weapon3': '0.930', 'weapon2': '1.754'} [2024-08-05 08:35:49,069][00146] Updated weights for policy 0, policy_version 350 (0.0019) [2024-08-05 08:35:51,500][00035] Fps is (10 sec: 4095.9, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 2875392. Throughput: 0: 913.2. Samples: 717334. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:35:51,507][00035] Avg episode reward: [(0, '-5.994')] [2024-08-05 08:35:56,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2891776. Throughput: 0: 921.3. Samples: 722926. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:35:56,502][00035] Avg episode reward: [(0, '-5.994')] [2024-08-05 08:35:57,940][00149] DAMAGECOUNT value on done: 1152.0 [2024-08-05 08:35:58,494][00149] DAMAGECOUNT value on done: 1764.0 [2024-08-05 08:35:58,495][00149] Sum rewards: -8.176, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-1.358', 'weapon5': '0.002', 'AMMO5': '0.003', 'AMMO2': '0.011', 'ARMOR': '0.040', 'WEAPON5': '0.050', 'AMMO4': '0.056', 'HITCOUNT': '0.060', 'weapon4': '0.098', 'WEAPON4': '0.100', 'AMMO3': '0.151', 'DAMAGECOUNT': '0.177', 'WEAPON3': '0.850', 'FRAGCOUNT': '1.000', 'weapon3': '1.140', 'weapon2': '1.444'} [2024-08-05 08:35:59,043][00149] DAMAGECOUNT value on done: 1742.0 [2024-08-05 08:35:59,569][00149] DAMAGECOUNT value on done: 1910.0 [2024-08-05 08:35:59,936][00150] DAMAGECOUNT value on done: 1420.0 [2024-08-05 08:35:59,938][00150] Sum rewards: -2.935, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.312', 'AMMO2': '0.004', 'AMMO5': '0.005', 'AMMO4': '0.021', 'weapon5': '0.026', 'weapon4': '0.048', 'HITCOUNT': '0.090', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'ARMOR': '0.120', 'AMMO3': '0.167', 'DAMAGECOUNT': '0.225', 'WEAPON3': '0.950', 'weapon2': '1.118', 'weapon3': '1.652', 'FRAGCOUNT': '2.000'} [2024-08-05 08:36:00,575][00150] DAMAGECOUNT value on done: 2095.0 [2024-08-05 08:36:00,576][00150] Sum rewards: -8.238, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-2.200', 'AMMO5': '0.005', 'AMMO2': '0.019', 'weapon4': '0.028', 'ARMOR': '0.044', 'AMMO4': '0.097', 'WEAPON5': '0.100', 'HITCOUNT': '0.110', 'AMMO3': '0.175', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.486', 'WEAPON3': '0.950', 'FRAGCOUNT': '1.000', 'weapon3': '1.346', 'weapon2': '1.402'} [2024-08-05 08:36:01,160][00150] DAMAGECOUNT value on done: 1707.0 [2024-08-05 08:36:01,500][00035] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2908160. Throughput: 0: 918.0. Samples: 728400. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:36:01,504][00035] Avg episode reward: [(0, '-5.986')] [2024-08-05 08:36:01,517][00137] Saving new best policy, reward=-5.986! [2024-08-05 08:36:01,720][00150] DAMAGECOUNT value on done: 2170.0 [2024-08-05 08:36:01,721][00150] Sum rewards: -8.100, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-2.330', 'AMMO2': '0.006', 'AMMO4': '0.029', 'HITCOUNT': '0.110', 'AMMO3': '0.145', 'DAMAGECOUNT': '0.405', 'WEAPON3': '0.800', 'ARMOR': '0.893', 'FRAGCOUNT': '1.000', 'weapon3': '1.020', 'weapon2': '1.822'} [2024-08-05 08:36:06,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2924544. Throughput: 0: 919.3. Samples: 731180. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:36:06,504][00035] Avg episode reward: [(0, '-6.013')] [2024-08-05 08:36:11,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 2940928. Throughput: 0: 908.1. Samples: 736234. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:36:11,502][00035] Avg episode reward: [(0, '-6.013')] [2024-08-05 08:36:11,766][00146] Updated weights for policy 0, policy_version 360 (0.0029) [2024-08-05 08:36:16,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 2965504. Throughput: 0: 908.2. Samples: 741830. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:36:16,501][00035] Avg episode reward: [(0, '-6.013')] [2024-08-05 08:36:19,926][00148] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-05 08:36:21,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2981888. Throughput: 0: 905.5. Samples: 744590. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:36:21,502][00035] Avg episode reward: [(0, '-6.013')] [2024-08-05 08:36:21,511][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000364_2981888.pth... [2024-08-05 08:36:21,624][00137] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000257_2105344.pth [2024-08-05 08:36:24,843][00147] DAMAGECOUNT value on done: 2446.0 [2024-08-05 08:36:24,843][00147] Sum rewards: -4.528, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.032', 'AMMO5': '0.007', 'AMMO2': '0.012', 'weapon5': '0.034', 'ARMOR': '0.040', 'AMMO4': '0.062', 'HITCOUNT': '0.070', 'AMMO3': '0.095', 'WEAPON4': '0.150', 'WEAPON5': '0.150', 'weapon4': '0.246', 'DAMAGECOUNT': '0.405', 'WEAPON3': '0.450', 'weapon3': '0.920', 'FRAGCOUNT': '1.000', 'weapon2': '1.362'} [2024-08-05 08:36:24,871][00148] DAMAGECOUNT value on done: 1852.0 [2024-08-05 08:36:25,440][00148] DAMAGECOUNT value on done: 1853.0 [2024-08-05 08:36:25,456][00147] DAMAGECOUNT value on done: 1507.0 [2024-08-05 08:36:25,457][00147] Sum rewards: -5.067, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.315', 'AMMO2': '0.007', 'AMMO5': '0.007', 'AMMO4': '0.035', 'HITCOUNT': '0.070', 'WEAPON5': '0.100', 'AMMO3': '0.126', 'weapon5': '0.148', 'weapon4': '0.190', 'WEAPON4': '0.200', 'ARMOR': '0.516', 'DAMAGECOUNT': '0.570', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon3': '1.048', 'weapon2': '1.380'} [2024-08-05 08:36:25,987][00147] DAMAGECOUNT value on done: 1580.0 [2024-08-05 08:36:26,004][00148] DAMAGECOUNT value on done: 2085.0 [2024-08-05 08:36:26,005][00148] Sum rewards: -9.738, reward structure: {'DEATHCOUNT': '-9.000', 'FRAGCOUNT': '-3.500', 'HEALTH': '-1.916', 'WEAPON1': '0.010', 'AMMO2': '0.010', 'AMMO5': '0.011', 'ARMOR': '0.012', 'AMMO4': '0.051', 'weapon5': '0.102', 'HITCOUNT': '0.110', 'AMMO3': '0.124', 'WEAPON4': '0.150', 'weapon4': '0.162', 'WEAPON5': '0.250', 'DAMAGECOUNT': '0.327', 'WEAPON3': '0.650', 'weapon3': '1.238', 'weapon2': '1.470'} [2024-08-05 08:36:26,501][00035] Fps is (10 sec: 3276.5, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2998272. Throughput: 0: 912.9. Samples: 750042. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:36:26,503][00035] Avg episode reward: [(0, '-5.845')] [2024-08-05 08:36:26,508][00137] Saving new best policy, reward=-5.845! [2024-08-05 08:36:26,530][00148] DAMAGECOUNT value on done: 1696.0 [2024-08-05 08:36:26,531][00148] Sum rewards: -0.131, reward structure: {'DEATHCOUNT': '-8.250', 'weapon4': '0.004', 'AMMO2': '0.022', 'WEAPON4': '0.050', 'ARMOR': '0.080', 'AMMO3': '0.090', 'AMMO4': '0.112', 'HITCOUNT': '0.170', 'WEAPON3': '0.450', 'HEALTH': '0.674', 'DAMAGECOUNT': '0.675', 'weapon3': '1.122', 'weapon2': '1.670', 'FRAGCOUNT': '3.000'} [2024-08-05 08:36:26,626][00147] DAMAGECOUNT value on done: 1885.0 [2024-08-05 08:36:31,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 3014656. Throughput: 0: 904.9. Samples: 755372. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:36:31,501][00035] Avg episode reward: [(0, '-5.762')] [2024-08-05 08:36:31,510][00137] Saving new best policy, reward=-5.762! [2024-08-05 08:36:34,314][00146] Updated weights for policy 0, policy_version 370 (0.0019) [2024-08-05 08:36:34,698][00149] DAMAGECOUNT value on done: 1197.0 [2024-08-05 08:36:35,246][00149] DAMAGECOUNT value on done: 1883.0 [2024-08-05 08:36:35,824][00149] DAMAGECOUNT value on done: 1792.0 [2024-08-05 08:36:35,825][00149] Sum rewards: -9.512, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.762', 'FRAGCOUNT': '-1.500', 'AMMO2': '0.006', 'AMMO5': '0.007', 'AMMO4': '0.030', 'ARMOR': '0.034', 'HITCOUNT': '0.050', 'weapon5': '0.084', 'AMMO3': '0.126', 'DAMAGECOUNT': '0.150', 'weapon4': '0.154', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'WEAPON3': '0.650', 'weapon3': '1.188', 'weapon2': '1.370'} [2024-08-05 08:36:36,418][00149] DAMAGECOUNT value on done: 2150.0 [2024-08-05 08:36:36,419][00149] Sum rewards: -5.356, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.288', 'AMMO4': '-0.004', 'AMMO2': '-0.001', 'AMMO5': '0.003', 'WEAPON1': '0.010', 'weapon5': '0.022', 'WEAPON5': '0.050', 'weapon4': '0.096', 'WEAPON4': '0.100', 'AMMO3': '0.116', 'ARMOR': '0.122', 'HITCOUNT': '0.190', 'WEAPON3': '0.650', 'DAMAGECOUNT': '0.720', 'FRAGCOUNT': '1.000', 'weapon3': '1.114', 'weapon2': '1.494'} [2024-08-05 08:36:36,500][00035] Fps is (10 sec: 3277.1, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 3031040. Throughput: 0: 905.8. Samples: 758096. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:36:36,502][00035] Avg episode reward: [(0, '-5.806')] [2024-08-05 08:36:36,632][00150] DAMAGECOUNT value on done: 1564.0 [2024-08-05 08:36:36,636][00150] Sum rewards: -5.400, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.488', 'AMMO2': '0.007', 'AMMO4': '0.036', 'ARMOR': '0.056', 'WEAPON4': '0.100', 'AMMO3': '0.113', 'HITCOUNT': '0.140', 'weapon4': '0.152', 'DAMAGECOUNT': '0.432', 'WEAPON3': '0.550', 'FRAGCOUNT': '1.000', 'weapon3': '1.208', 'weapon2': '1.294'} [2024-08-05 08:36:37,248][00150] DAMAGECOUNT value on done: 2135.0 [2024-08-05 08:36:37,793][00150] DAMAGECOUNT value on done: 1846.0 [2024-08-05 08:36:38,378][00150] DAMAGECOUNT value on done: 2287.0 [2024-08-05 08:36:38,379][00150] Sum rewards: -5.320, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.534', 'AMMO4': '-0.011', 'AMMO2': '-0.002', 'weapon4': '0.038', 'HITCOUNT': '0.070', 'WEAPON4': '0.100', 'ARMOR': '0.100', 'AMMO3': '0.158', 'DAMAGECOUNT': '0.351', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon3': '1.160', 'weapon2': '1.450'} [2024-08-05 08:36:41,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 3047424. Throughput: 0: 898.5. Samples: 763360. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:36:41,502][00035] Avg episode reward: [(0, '-5.756')] [2024-08-05 08:36:41,508][00137] Saving new best policy, reward=-5.756! [2024-08-05 08:36:46,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3072000. Throughput: 0: 892.4. Samples: 768556. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:36:46,502][00035] Avg episode reward: [(0, '-5.756')] [2024-08-05 08:36:51,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 3088384. Throughput: 0: 891.6. Samples: 771304. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:36:51,502][00035] Avg episode reward: [(0, '-5.756')] [2024-08-05 08:36:56,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 3104768. Throughput: 0: 904.4. Samples: 776934. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:36:56,502][00035] Avg episode reward: [(0, '-5.756')] [2024-08-05 08:36:57,159][00146] Updated weights for policy 0, policy_version 380 (0.0023) [2024-08-05 08:37:01,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 3121152. Throughput: 0: 905.0. Samples: 782556. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:37:01,501][00035] Avg episode reward: [(0, '-5.756')] [2024-08-05 08:37:02,780][00148] DAMAGECOUNT value on done: 2017.0 [2024-08-05 08:37:02,781][00148] Sum rewards: -8.787, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.312', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.003', 'AMMO2': '0.006', 'AMMO4': '0.029', 'weapon5': '0.036', 'weapon4': '0.044', 'WEAPON4': '0.050', 'WEAPON5': '0.050', 'ARMOR': '0.056', 'AMMO3': '0.091', 'HITCOUNT': '0.100', 'DAMAGECOUNT': '0.495', 'WEAPON3': '0.550', 'weapon3': '1.078', 'weapon2': '1.688'} [2024-08-05 08:37:02,799][00147] DAMAGECOUNT value on done: 2726.0 [2024-08-05 08:37:02,799][00147] Sum rewards: -0.821, reward structure: {'DEATHCOUNT': '-5.250', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.005', 'WEAPON1': '0.010', 'AMMO2': '0.025', 'WEAPON4': '0.050', 'AMMO3': '0.059', 'WEAPON5': '0.100', 'AMMO4': '0.126', 'weapon4': '0.152', 'weapon5': '0.164', 'HITCOUNT': '0.230', 'WEAPON3': '0.300', 'HEALTH': '0.412', 'DAMAGECOUNT': '0.840', 'weapon3': '1.208', 'weapon2': '1.248'} [2024-08-05 08:37:03,306][00148] DAMAGECOUNT value on done: 1907.0 [2024-08-05 08:37:03,307][00148] Sum rewards: -9.778, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-2.074', 'AMMO2': '0.028', 'HITCOUNT': '0.050', 'AMMO4': '0.138', 'AMMO3': '0.148', 'WEAPON4': '0.150', 'DAMAGECOUNT': '0.162', 'weapon4': '0.174', 'WEAPON3': '0.750', 'FRAGCOUNT': '1.000', 'weapon3': '1.010', 'weapon2': '1.436'} [2024-08-05 08:37:03,370][00147] DAMAGECOUNT value on done: 1662.0 [2024-08-05 08:37:03,371][00147] Sum rewards: -6.898, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-2.694', 'AMMO5': '0.015', 'AMMO2': '0.018', 'WEAPON1': '0.020', 'weapon4': '0.028', 'ARMOR': '0.040', 'weapon5': '0.044', 'AMMO4': '0.089', 'HITCOUNT': '0.090', 'WEAPON4': '0.150', 'AMMO3': '0.185', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.465', 'WEAPON3': '1.000', 'weapon2': '1.002', 'weapon3': '1.600', 'FRAGCOUNT': '2.000'} [2024-08-05 08:37:03,934][00148] DAMAGECOUNT value on done: 2172.0 [2024-08-05 08:37:03,943][00147] DAMAGECOUNT value on done: 1605.0 [2024-08-05 08:37:04,481][00147] DAMAGECOUNT value on done: 1992.0 [2024-08-05 08:37:04,494][00148] DAMAGECOUNT value on done: 1793.0 [2024-08-05 08:37:04,495][00148] Sum rewards: -0.823, reward structure: {'DEATHCOUNT': '-4.500', 'HEALTH': '-0.086', 'AMMO2': '0.006', 'AMMO4': '0.030', 'ARMOR': '0.032', 'AMMO3': '0.053', 'HITCOUNT': '0.060', 'WEAPON3': '0.250', 'DAMAGECOUNT': '0.291', 'weapon2': '0.966', 'FRAGCOUNT': '1.000', 'weapon3': '1.074'} [2024-08-05 08:37:06,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3145728. Throughput: 0: 905.6. Samples: 785344. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:37:06,502][00035] Avg episode reward: [(0, '-5.685')] [2024-08-05 08:37:06,504][00137] Saving new best policy, reward=-5.685! [2024-08-05 08:37:06,698][00150] Large shaping reward -2.534 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.28500000000000003, -95.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-05 08:37:10,838][00149] DAMAGECOUNT value on done: 1247.0 [2024-08-05 08:37:10,838][00149] Sum rewards: -7.557, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.422', 'AMMO2': '0.024', 'ARMOR': '0.044', 'HITCOUNT': '0.050', 'AMMO4': '0.118', 'AMMO3': '0.129', 'DAMAGECOUNT': '0.150', 'weapon4': '0.160', 'WEAPON4': '0.200', 'WEAPON3': '0.750', 'FRAGCOUNT': '1.000', 'weapon3': '1.130', 'weapon2': '1.360'} [2024-08-05 08:37:11,359][00149] DAMAGECOUNT value on done: 2008.0 [2024-08-05 08:37:11,360][00149] Sum rewards: -4.737, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.863', 'AMMO2': '0.021', 'weapon4': '0.064', 'ARMOR': '0.088', 'HITCOUNT': '0.090', 'AMMO4': '0.103', 'AMMO3': '0.147', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.375', 'WEAPON3': '0.750', 'FRAGCOUNT': '1.000', 'weapon2': '1.122', 'weapon3': '1.416'} [2024-08-05 08:37:11,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3162112. Throughput: 0: 908.1. Samples: 790906. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:37:11,504][00035] Avg episode reward: [(0, '-5.750')] [2024-08-05 08:37:11,932][00149] DAMAGECOUNT value on done: 1852.0 [2024-08-05 08:37:11,933][00149] Sum rewards: -4.197, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.560', 'AMMO4': '-0.026', 'AMMO2': '-0.005', 'HITCOUNT': '0.060', 'AMMO3': '0.120', 'DAMAGECOUNT': '0.180', 'ARMOR': '0.530', 'WEAPON3': '0.550', 'FRAGCOUNT': '1.000', 'weapon2': '1.272', 'weapon3': '1.682'} [2024-08-05 08:37:12,608][00149] DAMAGECOUNT value on done: 2281.0 [2024-08-05 08:37:12,609][00149] Sum rewards: -6.763, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.650', 'AMMO5': '0.005', 'ARMOR': '0.012', 'weapon5': '0.016', 'AMMO2': '0.029', 'WEAPON5': '0.100', 'HITCOUNT': '0.110', 'AMMO3': '0.136', 'AMMO4': '0.147', 'WEAPON4': '0.200', 'weapon4': '0.250', 'DAMAGECOUNT': '0.393', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon2': '1.058', 'weapon3': '1.230'} [2024-08-05 08:37:12,841][00150] DAMAGECOUNT value on done: 1743.0 [2024-08-05 08:37:12,841][00150] Sum rewards: -8.915, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-3.175', 'AMMO2': '0.011', 'WEAPON1': '0.020', 'AMMO4': '0.056', 'ARMOR': '0.072', 'weapon4': '0.088', 'AMMO3': '0.122', 'HITCOUNT': '0.130', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.537', 'WEAPON3': '0.600', 'weapon3': '0.970', 'weapon2': '1.454', 'FRAGCOUNT': '2.000'} [2024-08-05 08:37:13,614][00150] DAMAGECOUNT value on done: 2345.0 [2024-08-05 08:37:13,615][00150] Sum rewards: -3.478, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.544', 'AMMO4': '-0.012', 'AMMO2': '-0.002', 'ARMOR': '0.064', 'AMMO3': '0.166', 'HITCOUNT': '0.190', 'DAMAGECOUNT': '0.630', 'WEAPON3': '0.850', 'weapon2': '1.436', 'weapon3': '1.494', 'FRAGCOUNT': '2.000'} [2024-08-05 08:37:14,178][00150] DAMAGECOUNT value on done: 2028.0 [2024-08-05 08:37:14,179][00150] Sum rewards: -3.554, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.436', 'AMMO5': '0.003', 'AMMO2': '0.023', 'HITCOUNT': '0.070', 'WEAPON5': '0.100', 'weapon5': '0.102', 'AMMO4': '0.115', 'AMMO3': '0.125', 'WEAPON4': '0.200', 'weapon4': '0.236', 'DAMAGECOUNT': '0.546', 'WEAPON3': '0.600', 'weapon3': '0.934', 'weapon2': '1.578', 'FRAGCOUNT': '2.000'} [2024-08-05 08:37:14,735][00150] DAMAGECOUNT value on done: 2337.0 [2024-08-05 08:37:14,736][00150] Sum rewards: -5.682, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.568', 'AMMO5': '0.013', 'AMMO2': '0.017', 'WEAPON1': '0.020', 'HITCOUNT': '0.050', 'ARMOR': '0.068', 'AMMO4': '0.086', 'WEAPON4': '0.100', 'weapon5': '0.108', 'AMMO3': '0.115', 'weapon4': '0.122', 'DAMAGECOUNT': '0.150', 'WEAPON5': '0.200', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.650', 'weapon2': '1.184', 'weapon3': '1.252'} [2024-08-05 08:37:16,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 3178496. Throughput: 0: 903.8. Samples: 796042. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:37:16,502][00035] Avg episode reward: [(0, '-5.671')] [2024-08-05 08:37:16,503][00137] Saving new best policy, reward=-5.671! [2024-08-05 08:37:19,541][00146] Updated weights for policy 0, policy_version 390 (0.0023) [2024-08-05 08:37:21,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 3194880. Throughput: 0: 905.6. Samples: 798848. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:37:21,502][00035] Avg episode reward: [(0, '-5.671')] [2024-08-05 08:37:26,500][00035] Fps is (10 sec: 4095.9, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3219456. Throughput: 0: 913.9. Samples: 804488. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:37:26,503][00035] Avg episode reward: [(0, '-5.671')] [2024-08-05 08:37:31,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3235840. Throughput: 0: 922.7. Samples: 810078. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:37:31,502][00035] Avg episode reward: [(0, '-5.671')] [2024-08-05 08:37:36,500][00035] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3252224. Throughput: 0: 925.2. Samples: 812936. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:37:36,502][00035] Avg episode reward: [(0, '-5.671')] [2024-08-05 08:37:39,961][00148] DAMAGECOUNT value on done: 2152.0 [2024-08-05 08:37:39,962][00148] Sum rewards: -0.546, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-0.591', 'AMMO5': '0.005', 'AMMO2': '0.007', 'ARMOR': '0.024', 'AMMO4': '0.036', 'AMMO3': '0.093', 'WEAPON5': '0.100', 'HITCOUNT': '0.120', 'DAMAGECOUNT': '0.405', 'WEAPON3': '0.500', 'weapon2': '1.256', 'weapon3': '1.498', 'FRAGCOUNT': '2.000'} [2024-08-05 08:37:39,994][00147] DAMAGECOUNT value on done: 2796.0 [2024-08-05 08:37:40,553][00148] DAMAGECOUNT value on done: 1922.0 [2024-08-05 08:37:40,605][00147] DAMAGECOUNT value on done: 1857.0 [2024-08-05 08:37:40,606][00147] Sum rewards: -1.330, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.238', 'AMMO4': '-0.045', 'AMMO2': '-0.009', 'AMMO3': '0.113', 'ARMOR': '0.120', 'HITCOUNT': '0.170', 'DAMAGECOUNT': '0.585', 'WEAPON3': '0.600', 'weapon3': '1.416', 'weapon2': '1.458', 'FRAGCOUNT': '3.000'} [2024-08-05 08:37:41,075][00148] DAMAGECOUNT value on done: 2207.0 [2024-08-05 08:37:41,157][00147] DAMAGECOUNT value on done: 1680.0 [2024-08-05 08:37:41,158][00147] Sum rewards: -10.043, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.572', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.009', 'AMMO2': '0.016', 'WEAPON1': '0.020', 'weapon5': '0.036', 'AMMO4': '0.079', 'HITCOUNT': '0.080', 'weapon4': '0.094', 'AMMO3': '0.118', 'WEAPON5': '0.150', 'WEAPON4': '0.150', 'DAMAGECOUNT': '0.225', 'WEAPON3': '0.600', 'weapon3': '0.944', 'weapon2': '1.758'} [2024-08-05 08:37:41,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3268608. Throughput: 0: 922.5. Samples: 818448. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:37:41,506][00035] Avg episode reward: [(0, '-5.556')] [2024-08-05 08:37:41,517][00137] Saving new best policy, reward=-5.556! [2024-08-05 08:37:41,716][00146] Updated weights for policy 0, policy_version 400 (0.0027) [2024-08-05 08:37:41,753][00148] DAMAGECOUNT value on done: 1901.0 [2024-08-05 08:37:41,754][00148] Sum rewards: -4.209, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.211', 'AMMO2': '0.007', 'AMMO4': '0.034', 'HITCOUNT': '0.070', 'weapon4': '0.088', 'AMMO3': '0.107', 'WEAPON4': '0.150', 'DAMAGECOUNT': '0.324', 'WEAPON3': '0.500', 'ARMOR': '0.506', 'FRAGCOUNT': '1.000', 'weapon3': '1.120', 'weapon2': '1.346'} [2024-08-05 08:37:41,820][00147] DAMAGECOUNT value on done: 2047.0 [2024-08-05 08:37:41,821][00147] Sum rewards: -0.472, reward structure: {'DEATHCOUNT': '-4.500', 'HEALTH': '-1.025', 'AMMO4': '-0.024', 'AMMO2': '-0.005', 'AMMO5': '0.005', 'WEAPON1': '0.010', 'weapon5': '0.018', 'WEAPON5': '0.050', 'HITCOUNT': '0.060', 'AMMO3': '0.094', 'DAMAGECOUNT': '0.165', 'WEAPON3': '0.450', 'ARMOR': '0.500', 'FRAGCOUNT': '1.000', 'weapon2': '1.126', 'weapon3': '1.604'} [2024-08-05 08:37:46,500][00035] Fps is (10 sec: 4095.9, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3293184. Throughput: 0: 912.4. Samples: 823614. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:37:46,502][00035] Avg episode reward: [(0, '-5.481')] [2024-08-05 08:37:46,503][00137] Saving new best policy, reward=-5.481! [2024-08-05 08:37:47,275][00149] DAMAGECOUNT value on done: 1502.0 [2024-08-05 08:37:47,276][00149] Sum rewards: -6.682, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-0.824', 'AMMO2': '0.010', 'AMMO4': '0.049', 'AMMO3': '0.118', 'HITCOUNT': '0.190', 'WEAPON3': '0.650', 'DAMAGECOUNT': '0.765', 'weapon3': '0.894', 'FRAGCOUNT': '1.000', 'weapon2': '1.716'} [2024-08-05 08:37:47,808][00149] DAMAGECOUNT value on done: 2252.0 [2024-08-05 08:37:47,809][00149] Sum rewards: -1.106, reward structure: {'DEATHCOUNT': '-5.250', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.006', 'WEAPON1': '0.010', 'ARMOR': '0.016', 'AMMO2': '0.041', 'HEALTH': '0.053', 'AMMO3': '0.070', 'weapon5': '0.128', 'WEAPON4': '0.150', 'WEAPON5': '0.150', 'AMMO4': '0.202', 'weapon4': '0.208', 'HITCOUNT': '0.210', 'WEAPON3': '0.350', 'DAMAGECOUNT': '0.732', 'weapon2': '0.962', 'weapon3': '1.356'} [2024-08-05 08:37:48,351][00149] DAMAGECOUNT value on done: 2004.0 [2024-08-05 08:37:48,352][00149] Sum rewards: -3.436, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.857', 'AMMO4': '-0.002', 'AMMO2': '-0.000', 'weapon4': '0.052', 'ARMOR': '0.056', 'AMMO3': '0.073', 'HITCOUNT': '0.090', 'WEAPON4': '0.100', 'DAMAGECOUNT': '0.456', 'WEAPON3': '0.500', 'FRAGCOUNT': '1.000', 'weapon2': '1.402', 'weapon3': '1.444'} [2024-08-05 08:37:48,888][00149] DAMAGECOUNT value on done: 2438.0 [2024-08-05 08:37:48,889][00149] Sum rewards: -4.624, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.976', 'WEAPON1': '0.010', 'AMMO2': '0.018', 'ARMOR': '0.052', 'AMMO4': '0.090', 'AMMO3': '0.112', 'HITCOUNT': '0.130', 'weapon4': '0.338', 'WEAPON4': '0.350', 'DAMAGECOUNT': '0.471', 'WEAPON3': '0.550', 'weapon3': '0.946', 'FRAGCOUNT': '1.000', 'weapon2': '1.534'} [2024-08-05 08:37:48,953][00150] DAMAGECOUNT value on done: 1782.0 [2024-08-05 08:37:49,503][00150] DAMAGECOUNT value on done: 2647.0 [2024-08-05 08:37:49,504][00150] Sum rewards: -6.644, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-1.970', 'AMMO5': '0.005', 'AMMO2': '0.011', 'weapon5': '0.020', 'weapon4': '0.034', 'ARMOR': '0.040', 'AMMO4': '0.056', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.165', 'HITCOUNT': '0.240', 'WEAPON3': '0.900', 'DAMAGECOUNT': '0.906', 'weapon3': '1.168', 'weapon2': '1.580', 'FRAGCOUNT': '2.000'} [2024-08-05 08:37:50,019][00150] DAMAGECOUNT value on done: 2107.0 [2024-08-05 08:37:50,568][00150] DAMAGECOUNT value on done: 2387.0 [2024-08-05 08:37:51,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.9). Total num frames: 3309568. Throughput: 0: 911.0. Samples: 826340. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:37:51,502][00035] Avg episode reward: [(0, '-5.398')] [2024-08-05 08:37:51,508][00137] Saving new best policy, reward=-5.398! [2024-08-05 08:37:56,500][00035] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3325952. Throughput: 0: 913.1. Samples: 831994. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:37:56,502][00035] Avg episode reward: [(0, '-5.398')] [2024-08-05 08:38:01,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3342336. Throughput: 0: 925.3. Samples: 837680. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:38:01,502][00035] Avg episode reward: [(0, '-5.398')] [2024-08-05 08:38:03,777][00146] Updated weights for policy 0, policy_version 410 (0.0026) [2024-08-05 08:38:06,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3366912. Throughput: 0: 926.8. Samples: 840554. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:38:06,501][00035] Avg episode reward: [(0, '-5.398')] [2024-08-05 08:38:11,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3383296. Throughput: 0: 928.1. Samples: 846254. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:38:11,502][00035] Avg episode reward: [(0, '-5.398')] [2024-08-05 08:38:16,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3399680. Throughput: 0: 927.7. Samples: 851824. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:38:16,504][00035] Avg episode reward: [(0, '-5.398')] [2024-08-05 08:38:17,051][00147] DAMAGECOUNT value on done: 2926.0 [2024-08-05 08:38:17,052][00147] Sum rewards: -4.695, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-2.140', 'AMMO2': '0.011', 'ARMOR': '0.040', 'AMMO4': '0.055', 'HITCOUNT': '0.070', 'AMMO3': '0.158', 'WEAPON4': '0.200', 'weapon4': '0.240', 'DAMAGECOUNT': '0.390', 'WEAPON3': '0.950', 'FRAGCOUNT': '1.000', 'weapon2': '1.034', 'weapon3': '1.546'} [2024-08-05 08:38:17,229][00148] DAMAGECOUNT value on done: 2237.0 [2024-08-05 08:38:17,230][00148] Sum rewards: -5.354, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-2.495', 'AMMO5': '0.009', 'AMMO2': '0.019', 'ARMOR': '0.040', 'weapon5': '0.058', 'AMMO4': '0.093', 'WEAPON5': '0.100', 'HITCOUNT': '0.110', 'AMMO3': '0.117', 'weapon4': '0.144', 'WEAPON4': '0.250', 'DAMAGECOUNT': '0.255', 'WEAPON3': '0.700', 'weapon3': '0.930', 'FRAGCOUNT': '1.000', 'weapon2': '1.566'} [2024-08-05 08:38:17,745][00147] DAMAGECOUNT value on done: 1884.0 [2024-08-05 08:38:17,877][00148] DAMAGECOUNT value on done: 2073.0 [2024-08-05 08:38:17,878][00148] Sum rewards: -4.079, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.550', 'AMMO5': '0.003', 'WEAPON1': '0.010', 'AMMO2': '0.022', 'weapon4': '0.030', 'weapon5': '0.036', 'WEAPON5': '0.050', 'ARMOR': '0.092', 'HITCOUNT': '0.110', 'AMMO4': '0.111', 'AMMO3': '0.120', 'WEAPON4': '0.150', 'DAMAGECOUNT': '0.453', 'WEAPON3': '0.750', 'FRAGCOUNT': '1.000', 'weapon2': '1.168', 'weapon3': '1.616'} [2024-08-05 08:38:18,281][00147] DAMAGECOUNT value on done: 1690.0 [2024-08-05 08:38:18,414][00148] DAMAGECOUNT value on done: 2257.0 [2024-08-05 08:38:18,822][00147] DAMAGECOUNT value on done: 2087.0 [2024-08-05 08:38:18,966][00148] DAMAGECOUNT value on done: 2016.0 [2024-08-05 08:38:18,966][00148] Sum rewards: -5.172, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.275', 'AMMO4': '-0.001', 'AMMO2': '-0.000', 'AMMO5': '0.003', 'WEAPON5': '0.050', 'HITCOUNT': '0.080', 'weapon5': '0.094', 'AMMO3': '0.147', 'DAMAGECOUNT': '0.345', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '1.294', 'weapon2': '1.392'} [2024-08-05 08:38:21,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3416064. Throughput: 0: 918.4. Samples: 854264. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:38:21,505][00035] Avg episode reward: [(0, '-5.431')] [2024-08-05 08:38:21,576][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000418_3424256.pth... [2024-08-05 08:38:21,682][00137] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000310_2539520.pth [2024-08-05 08:38:22,862][00149] DAMAGECOUNT value on done: 1537.0 [2024-08-05 08:38:22,863][00149] Sum rewards: -6.558, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.968', 'AMMO4': '-0.024', 'AMMO2': '-0.005', 'AMMO5': '0.005', 'weapon5': '0.022', 'HITCOUNT': '0.040', 'ARMOR': '0.064', 'WEAPON5': '0.100', 'DAMAGECOUNT': '0.105', 'AMMO3': '0.144', 'WEAPON3': '0.650', 'weapon3': '1.044', 'weapon2': '1.764', 'FRAGCOUNT': '2.000'} [2024-08-05 08:38:23,392][00149] DAMAGECOUNT value on done: 2267.0 [2024-08-05 08:38:23,980][00149] DAMAGECOUNT value on done: 2159.0 [2024-08-05 08:38:23,980][00149] Sum rewards: -7.515, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-1.278', 'AMMO5': '0.003', 'AMMO2': '0.007', 'weapon5': '0.010', 'ARMOR': '0.032', 'AMMO4': '0.036', 'WEAPON4': '0.050', 'WEAPON5': '0.050', 'HITCOUNT': '0.110', 'weapon4': '0.124', 'AMMO3': '0.192', 'DAMAGECOUNT': '0.465', 'WEAPON3': '0.950', 'FRAGCOUNT': '1.000', 'weapon2': '1.072', 'weapon3': '1.662'} [2024-08-05 08:38:24,377][00150] DAMAGECOUNT value on done: 1942.0 [2024-08-05 08:38:24,378][00150] Sum rewards: -4.933, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.145', 'AMMO5': '0.007', 'AMMO2': '0.023', 'weapon5': '0.072', 'weapon4': '0.078', 'HITCOUNT': '0.100', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO4': '0.114', 'AMMO3': '0.127', 'DAMAGECOUNT': '0.480', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.750', 'weapon2': '0.944', 'weapon3': '1.816'} [2024-08-05 08:38:24,537][00149] DAMAGECOUNT value on done: 2473.0 [2024-08-05 08:38:24,538][00149] Sum rewards: -8.029, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.690', 'AMMO4': '-0.035', 'AMMO2': '-0.007', 'ARMOR': '0.016', 'WEAPON1': '0.020', 'HITCOUNT': '0.040', 'DAMAGECOUNT': '0.105', 'AMMO3': '0.197', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon3': '1.338', 'weapon2': '1.386'} [2024-08-05 08:38:24,910][00150] DAMAGECOUNT value on done: 2722.0 [2024-08-05 08:38:24,911][00150] Sum rewards: -3.638, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.992', 'AMMO2': '0.004', 'AMMO4': '0.021', 'ARMOR': '0.055', 'HITCOUNT': '0.060', 'WEAPON4': '0.100', 'AMMO3': '0.124', 'weapon4': '0.144', 'DAMAGECOUNT': '0.225', 'WEAPON3': '0.550', 'FRAGCOUNT': '1.000', 'weapon2': '1.198', 'weapon3': '1.372'} [2024-08-05 08:38:25,446][00150] DAMAGECOUNT value on done: 2262.0 [2024-08-05 08:38:25,447][00150] Sum rewards: 0.019, reward structure: {'DEATHCOUNT': '-4.500', 'HEALTH': '-0.360', 'AMMO2': '0.004', 'AMMO4': '0.018', 'ARMOR': '0.036', 'AMMO3': '0.064', 'HITCOUNT': '0.100', 'WEAPON4': '0.100', 'weapon4': '0.114', 'WEAPON3': '0.350', 'DAMAGECOUNT': '0.465', 'FRAGCOUNT': '1.000', 'weapon3': '1.306', 'weapon2': '1.322'} [2024-08-05 08:38:25,963][00146] Updated weights for policy 0, policy_version 420 (0.0021) [2024-08-05 08:38:26,020][00150] DAMAGECOUNT value on done: 2616.0 [2024-08-05 08:38:26,021][00150] Sum rewards: -4.420, reward structure: {'DEATHCOUNT': '-7.500', 'FRAGCOUNT': '-1.500', 'HEALTH': '-0.616', 'AMMO2': '0.004', 'AMMO5': '0.005', 'WEAPON1': '0.010', 'AMMO4': '0.020', 'weapon4': '0.042', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.107', 'weapon5': '0.164', 'HITCOUNT': '0.230', 'WEAPON3': '0.500', 'ARMOR': '0.510', 'DAMAGECOUNT': '0.687', 'weapon3': '1.312', 'weapon2': '1.404'} [2024-08-05 08:38:26,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3440640. Throughput: 0: 921.0. Samples: 859892. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:38:26,501][00035] Avg episode reward: [(0, '-5.444')] [2024-08-05 08:38:31,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.9). Total num frames: 3457024. Throughput: 0: 931.9. Samples: 865550. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:38:31,502][00035] Avg episode reward: [(0, '-5.444')] [2024-08-05 08:38:36,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3473408. Throughput: 0: 935.4. Samples: 868432. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:38:36,504][00035] Avg episode reward: [(0, '-5.444')] [2024-08-05 08:38:41,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3665.6). Total num frames: 3497984. Throughput: 0: 934.3. Samples: 874036. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:38:41,502][00035] Avg episode reward: [(0, '-5.444')] [2024-08-05 08:38:46,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3514368. Throughput: 0: 933.6. Samples: 879690. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:38:46,503][00035] Avg episode reward: [(0, '-5.444')] [2024-08-05 08:38:47,778][00146] Updated weights for policy 0, policy_version 430 (0.0025) [2024-08-05 08:38:51,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3530752. Throughput: 0: 922.9. Samples: 882084. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:38:51,503][00035] Avg episode reward: [(0, '-5.444')] [2024-08-05 08:38:53,796][00147] DAMAGECOUNT value on done: 3035.0 [2024-08-05 08:38:53,797][00147] Sum rewards: -2.507, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.478', 'AMMO2': '0.009', 'WEAPON1': '0.010', 'weapon4': '0.018', 'AMMO4': '0.045', 'WEAPON4': '0.050', 'AMMO3': '0.104', 'HITCOUNT': '0.110', 'ARMOR': '0.126', 'DAMAGECOUNT': '0.327', 'WEAPON3': '0.550', 'FRAGCOUNT': '1.000', 'weapon3': '1.332', 'weapon2': '1.790'} [2024-08-05 08:38:54,080][00148] DAMAGECOUNT value on done: 2412.0 [2024-08-05 08:38:54,081][00148] Sum rewards: -2.632, reward structure: {'DEATHCOUNT': '-9.000', 'AMMO5': '0.005', 'AMMO2': '0.018', 'ARMOR': '0.040', 'weapon5': '0.040', 'HEALTH': '0.048', 'AMMO4': '0.091', 'HITCOUNT': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.115', 'DAMAGECOUNT': '0.525', 'WEAPON3': '0.550', 'weapon3': '1.414', 'FRAGCOUNT': '1.500', 'weapon2': '1.822'} [2024-08-05 08:38:54,357][00147] DAMAGECOUNT value on done: 2034.0 [2024-08-05 08:38:54,358][00147] Sum rewards: -2.979, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.600', 'AMMO2': '0.012', 'ARMOR': '0.040', 'AMMO4': '0.057', 'weapon4': '0.076', 'WEAPON4': '0.100', 'AMMO3': '0.134', 'HITCOUNT': '0.160', 'DAMAGECOUNT': '0.450', 'WEAPON3': '0.700', 'weapon3': '1.562', 'weapon2': '1.580', 'FRAGCOUNT': '2.000'} [2024-08-05 08:38:54,661][00148] DAMAGECOUNT value on done: 2178.0 [2024-08-05 08:38:54,662][00148] Sum rewards: -9.063, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-3.125', 'AMMO5': '0.005', 'AMMO2': '0.012', 'ARMOR': '0.056', 'HITCOUNT': '0.060', 'AMMO4': '0.062', 'WEAPON5': '0.100', 'AMMO3': '0.194', 'DAMAGECOUNT': '0.315', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.150', 'weapon2': '1.376', 'weapon3': '1.732'} [2024-08-05 08:38:54,992][00147] DAMAGECOUNT value on done: 1755.0 [2024-08-05 08:38:55,251][00148] DAMAGECOUNT value on done: 2277.0 [2024-08-05 08:38:55,628][00147] DAMAGECOUNT value on done: 2302.0 [2024-08-05 08:38:55,830][00148] DAMAGECOUNT value on done: 2151.0 [2024-08-05 08:38:56,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3547136. Throughput: 0: 920.2. Samples: 887664. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:38:56,502][00035] Avg episode reward: [(0, '-5.407')] [2024-08-05 08:38:58,420][00149] DAMAGECOUNT value on done: 1656.0 [2024-08-05 08:38:58,421][00149] Sum rewards: -2.489, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.200', 'AMMO5': '0.005', 'WEAPON1': '0.010', 'weapon5': '0.012', 'AMMO2': '0.024', 'weapon7': '0.050', 'ARMOR': '0.060', 'HITCOUNT': '0.070', 'AMMO3': '0.088', 'AMMO6': '0.100', 'AMMO7': '0.100', 'WEAPON7': '0.100', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'AMMO4': '0.117', 'weapon4': '0.238', 'DAMAGECOUNT': '0.357', 'WEAPON3': '0.550', 'FRAGCOUNT': '1.000', 'weapon3': '1.056', 'weapon2': '1.324'} [2024-08-05 08:38:58,969][00149] DAMAGECOUNT value on done: 2333.0 [2024-08-05 08:38:59,508][00149] DAMAGECOUNT value on done: 2419.0 [2024-08-05 08:38:59,509][00149] Sum rewards: -6.038, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-0.850', 'AMMO5': '0.003', 'AMMO2': '0.003', 'AMMO4': '0.017', 'ARMOR': '0.028', 'WEAPON5': '0.050', 'AMMO3': '0.129', 'HITCOUNT': '0.220', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.780', 'FRAGCOUNT': '1.000', 'weapon3': '1.372', 'weapon2': '1.860'} [2024-08-05 08:39:00,014][00149] DAMAGECOUNT value on done: 2553.0 [2024-08-05 08:39:00,015][00149] Sum rewards: -7.997, reward structure: {'DEATHCOUNT': '-9.750', 'FRAGCOUNT': '-1.500', 'HEALTH': '-1.046', 'AMMO2': '0.001', 'AMMO4': '0.003', 'AMMO5': '0.006', 'weapon5': '0.062', 'HITCOUNT': '0.070', 'WEAPON5': '0.100', 'AMMO3': '0.131', 'DAMAGECOUNT': '0.240', 'WEAPON3': '0.700', 'weapon2': '1.310', 'weapon3': '1.676'} [2024-08-05 08:39:00,251][00150] DAMAGECOUNT value on done: 2267.0 [2024-08-05 08:39:00,252][00150] Sum rewards: -3.969, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.772', 'AMMO2': '0.001', 'AMMO4': '0.006', 'AMMO3': '0.177', 'HITCOUNT': '0.230', 'WEAPON3': '0.950', 'DAMAGECOUNT': '0.975', 'weapon2': '1.266', 'weapon3': '1.698', 'FRAGCOUNT': '3.000'} [2024-08-05 08:39:00,830][00150] DAMAGECOUNT value on done: 2797.0 [2024-08-05 08:39:00,830][00150] Sum rewards: -5.728, reward structure: {'DEATHCOUNT': '-7.500', 'FRAGCOUNT': '-1.500', 'HEALTH': '-1.101', 'AMMO5': '0.005', 'AMMO2': '0.016', 'WEAPON5': '0.050', 'HITCOUNT': '0.070', 'AMMO4': '0.078', 'ARMOR': '0.084', 'AMMO3': '0.091', 'weapon5': '0.094', 'weapon4': '0.152', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.225', 'WEAPON3': '0.550', 'weapon3': '1.004', 'weapon2': '1.754'} [2024-08-05 08:39:01,365][00150] DAMAGECOUNT value on done: 2366.0 [2024-08-05 08:39:01,365][00150] Sum rewards: -6.769, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.294', 'AMMO2': '0.007', 'AMMO4': '0.035', 'WEAPON4': '0.050', 'HITCOUNT': '0.110', 'AMMO3': '0.124', 'DAMAGECOUNT': '0.312', 'ARMOR': '0.472', 'WEAPON3': '0.550', 'FRAGCOUNT': '1.000', 'weapon3': '1.022', 'weapon2': '2.092'} [2024-08-05 08:39:01,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3563520. Throughput: 0: 918.8. Samples: 893168. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:39:01,504][00035] Avg episode reward: [(0, '-5.429')] [2024-08-05 08:39:01,978][00150] DAMAGECOUNT value on done: 2687.0 [2024-08-05 08:39:01,979][00150] Sum rewards: -6.061, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.038', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.003', 'AMMO2': '0.017', 'weapon5': '0.018', 'WEAPON5': '0.050', 'HITCOUNT': '0.080', 'AMMO4': '0.087', 'AMMO3': '0.107', 'ARMOR': '0.120', 'weapon4': '0.126', 'WEAPON4': '0.150', 'DAMAGECOUNT': '0.213', 'WEAPON3': '0.500', 'weapon3': '0.930', 'weapon2': '1.576'} [2024-08-05 08:39:06,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3588096. Throughput: 0: 926.9. Samples: 895976. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:39:06,502][00035] Avg episode reward: [(0, '-5.421')] [2024-08-05 08:39:10,096][00146] Updated weights for policy 0, policy_version 440 (0.0028) [2024-08-05 08:39:11,500][00035] Fps is (10 sec: 4095.9, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3604480. Throughput: 0: 926.7. Samples: 901596. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:39:11,502][00035] Avg episode reward: [(0, '-5.421')] [2024-08-05 08:39:16,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3620864. Throughput: 0: 928.1. Samples: 907314. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:39:16,503][00035] Avg episode reward: [(0, '-5.421')] [2024-08-05 08:39:21,500][00035] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3665.6). Total num frames: 3645440. Throughput: 0: 926.8. Samples: 910136. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:39:21,502][00035] Avg episode reward: [(0, '-5.421')] [2024-08-05 08:39:25,365][00150] Large shaping reward -2.504 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.255, -85.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-05 08:39:26,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3661824. Throughput: 0: 920.0. Samples: 915436. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:39:26,502][00035] Avg episode reward: [(0, '-5.421')] [2024-08-05 08:39:30,718][00147] DAMAGECOUNT value on done: 3182.0 [2024-08-05 08:39:31,286][00147] DAMAGECOUNT value on done: 2248.0 [2024-08-05 08:39:31,287][00147] Sum rewards: 0.580, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-0.470', 'AMMO5': '0.003', 'AMMO2': '0.003', 'ARMOR': '0.016', 'AMMO4': '0.016', 'WEAPON1': '0.020', 'AMMO3': '0.078', 'WEAPON4': '0.100', 'weapon4': '0.112', 'HITCOUNT': '0.150', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.642', 'weapon3': '1.168', 'weapon2': '1.492', 'FRAGCOUNT': '2.000'} [2024-08-05 08:39:31,334][00148] DAMAGECOUNT value on done: 2552.0 [2024-08-05 08:39:31,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3678208. Throughput: 0: 917.7. Samples: 920986. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:39:31,504][00035] Avg episode reward: [(0, '-5.285')] [2024-08-05 08:39:31,514][00137] Saving new best policy, reward=-5.285! [2024-08-05 08:39:31,896][00147] DAMAGECOUNT value on done: 1795.0 [2024-08-05 08:39:31,942][00148] DAMAGECOUNT value on done: 2228.0 [2024-08-05 08:39:31,942][00148] Sum rewards: -6.829, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.530', 'AMMO2': '0.002', 'AMMO5': '0.005', 'AMMO4': '0.012', 'weapon5': '0.028', 'HITCOUNT': '0.050', 'AMMO3': '0.092', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'weapon4': '0.126', 'DAMAGECOUNT': '0.150', 'WEAPON3': '0.550', 'FRAGCOUNT': '1.000', 'weapon3': '1.302', 'weapon2': '1.684'} [2024-08-05 08:39:32,413][00146] Updated weights for policy 0, policy_version 450 (0.0038) [2024-08-05 08:39:32,491][00147] DAMAGECOUNT value on done: 2467.0 [2024-08-05 08:39:32,492][00147] Sum rewards: -5.671, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.180', 'AMMO4': '-0.023', 'AMMO2': '-0.004', 'AMMO5': '0.003', 'ARMOR': '0.040', 'HITCOUNT': '0.120', 'AMMO3': '0.161', 'DAMAGECOUNT': '0.495', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '1.316', 'weapon3': '2.002'} [2024-08-05 08:39:32,568][00148] DAMAGECOUNT value on done: 2332.0 [2024-08-05 08:39:32,569][00148] Sum rewards: -6.422, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.476', 'AMMO5': '0.005', 'AMMO2': '0.011', 'ARMOR': '0.040', 'AMMO4': '0.056', 'HITCOUNT': '0.060', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.110', 'weapon4': '0.130', 'DAMAGECOUNT': '0.165', 'WEAPON3': '0.650', 'FRAGCOUNT': '1.000', 'weapon3': '1.340', 'weapon2': '1.786'} [2024-08-05 08:39:33,183][00148] DAMAGECOUNT value on done: 2466.0 [2024-08-05 08:39:33,184][00148] Sum rewards: -1.426, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.058', 'AMMO5': '0.003', 'weapon5': '0.012', 'AMMO2': '0.025', 'WEAPON5': '0.050', 'ARMOR': '0.060', 'AMMO3': '0.117', 'AMMO4': '0.124', 'weapon4': '0.144', 'WEAPON4': '0.200', 'HITCOUNT': '0.270', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.945', 'weapon3': '1.534', 'weapon2': '1.548', 'FRAGCOUNT': '2.000'} [2024-08-05 08:39:33,967][00149] DAMAGECOUNT value on done: 1822.0 [2024-08-05 08:39:34,864][00149] DAMAGECOUNT value on done: 2423.0 [2024-08-05 08:39:35,418][00149] DAMAGECOUNT value on done: 2714.0 [2024-08-05 08:39:35,419][00149] Sum rewards: -3.332, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.318', 'AMMO5': '0.003', 'AMMO2': '0.004', 'weapon5': '0.004', 'AMMO4': '0.019', 'WEAPON1': '0.020', 'WEAPON5': '0.050', 'weapon4': '0.054', 'WEAPON4': '0.100', 'AMMO3': '0.113', 'HITCOUNT': '0.320', 'ARMOR': '0.496', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.885', 'weapon3': '1.196', 'weapon2': '1.872', 'FRAGCOUNT': '2.000'} [2024-08-05 08:39:36,001][00149] DAMAGECOUNT value on done: 2763.0 [2024-08-05 08:39:36,002][00149] Sum rewards: -5.287, reward structure: {'DEATHCOUNT': '-9.750', 'FRAGCOUNT': '-1.000', 'HEALTH': '-0.079', 'AMMO5': '0.007', 'AMMO2': '0.024', 'weapon5': '0.062', 'weapon7': '0.068', 'HITCOUNT': '0.080', 'AMMO6': '0.100', 'AMMO7': '0.100', 'WEAPON7': '0.100', 'AMMO4': '0.117', 'AMMO3': '0.134', 'WEAPON5': '0.150', 'DAMAGECOUNT': '0.630', 'WEAPON3': '0.800', 'weapon3': '1.518', 'weapon2': '1.652'} [2024-08-05 08:39:36,180][00150] DAMAGECOUNT value on done: 2307.0 [2024-08-05 08:39:36,181][00150] Sum rewards: -6.569, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.545', 'FRAGCOUNT': '-1.500', 'AMMO2': '0.002', 'AMMO5': '0.007', 'AMMO4': '0.009', 'ARMOR': '0.040', 'HITCOUNT': '0.050', 'AMMO3': '0.086', 'weapon5': '0.098', 'WEAPON4': '0.100', 'weapon4': '0.116', 'DAMAGECOUNT': '0.120', 'WEAPON5': '0.150', 'WEAPON3': '0.450', 'weapon3': '1.298', 'weapon2': '1.450'} [2024-08-05 08:39:36,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3694592. Throughput: 0: 920.9. Samples: 923526. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:39:36,502][00035] Avg episode reward: [(0, '-5.276')] [2024-08-05 08:39:36,504][00137] Saving new best policy, reward=-5.276! [2024-08-05 08:39:36,840][00150] DAMAGECOUNT value on done: 2924.0 [2024-08-05 08:39:36,841][00150] Sum rewards: -6.583, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-0.624', 'AMMO2': '0.012', 'weapon4': '0.020', 'WEAPON1': '0.030', 'AMMO4': '0.059', 'HITCOUNT': '0.070', 'WEAPON4': '0.100', 'AMMO3': '0.173', 'DAMAGECOUNT': '0.381', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '1.494', 'weapon3': '1.802'} [2024-08-05 08:39:37,426][00150] DAMAGECOUNT value on done: 2443.0 [2024-08-05 08:39:37,428][00150] Sum rewards: -3.396, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.696', 'AMMO2': '0.026', 'HITCOUNT': '0.080', 'ARMOR': '0.100', 'AMMO3': '0.105', 'AMMO4': '0.132', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.231', 'weapon4': '0.342', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon3': '1.230', 'weapon2': '1.504'} [2024-08-05 08:39:38,004][00150] DAMAGECOUNT value on done: 2832.0 [2024-08-05 08:39:38,005][00150] Sum rewards: -4.288, reward structure: {'DEATHCOUNT': '-11.250', 'AMMO2': '0.018', 'AMMO4': '0.089', 'HITCOUNT': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.150', 'HEALTH': '0.216', 'weapon4': '0.262', 'DAMAGECOUNT': '0.435', 'WEAPON3': '0.750', 'ARMOR': '0.860', 'FRAGCOUNT': '1.000', 'weapon3': '1.306', 'weapon2': '1.676'} [2024-08-05 08:39:41,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3665.6). Total num frames: 3710976. Throughput: 0: 914.6. Samples: 928822. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:39:41,502][00035] Avg episode reward: [(0, '-5.216')] [2024-08-05 08:39:41,512][00137] Saving new best policy, reward=-5.216! [2024-08-05 08:39:46,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3735552. Throughput: 0: 913.4. Samples: 934270. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:39:46,502][00035] Avg episode reward: [(0, '-5.216')] [2024-08-05 08:39:51,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3751936. Throughput: 0: 911.8. Samples: 937006. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:39:51,501][00035] Avg episode reward: [(0, '-5.216')] [2024-08-05 08:39:55,726][00146] Updated weights for policy 0, policy_version 460 (0.0021) [2024-08-05 08:39:56,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3768320. Throughput: 0: 901.6. Samples: 942166. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:39:56,502][00035] Avg episode reward: [(0, '-5.216')] [2024-08-05 08:40:01,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3784704. Throughput: 0: 896.7. Samples: 947666. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:40:01,502][00035] Avg episode reward: [(0, '-5.216')] [2024-08-05 08:40:03,584][00150] Large shaping reward 2.632 for [('FRAGCOUNT', 2.0, 2.0), ('HITCOUNT', 0.03, 3.0), ('DAMAGECOUNT', 0.6, 200), ('weapon7', 0.002)] [2024-08-05 08:40:06,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 3801088. Throughput: 0: 896.4. Samples: 950474. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:40:06,502][00035] Avg episode reward: [(0, '-5.216')] [2024-08-05 08:40:08,852][00147] DAMAGECOUNT value on done: 3252.0 [2024-08-05 08:40:09,203][00148] DAMAGECOUNT value on done: 2737.0 [2024-08-05 08:40:09,204][00148] Sum rewards: -0.973, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.206', 'weapon5': '0.002', 'AMMO5': '0.003', 'AMMO2': '0.011', 'WEAPON5': '0.050', 'AMMO4': '0.052', 'ARMOR': '0.080', 'AMMO3': '0.104', 'HITCOUNT': '0.130', 'WEAPON3': '0.550', 'DAMAGECOUNT': '0.555', 'weapon3': '1.526', 'weapon2': '1.670', 'FRAGCOUNT': '2.000'} [2024-08-05 08:40:09,443][00147] DAMAGECOUNT value on done: 2400.0 [2024-08-05 08:40:09,444][00147] Sum rewards: -6.068, reward structure: {'DEATHCOUNT': '-10.500', 'FRAGCOUNT': '-0.500', 'HEALTH': '-0.306', 'AMMO5': '0.005', 'weapon5': '0.016', 'AMMO2': '0.025', 'WEAPON5': '0.050', 'ARMOR': '0.092', 'WEAPON4': '0.100', 'AMMO3': '0.104', 'AMMO4': '0.124', 'HITCOUNT': '0.170', 'weapon4': '0.188', 'WEAPON3': '0.450', 'DAMAGECOUNT': '0.456', 'weapon3': '0.826', 'weapon2': '2.632'} [2024-08-05 08:40:09,758][00148] DAMAGECOUNT value on done: 2386.0 [2024-08-05 08:40:09,759][00148] Sum rewards: -5.947, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-2.375', 'AMMO2': '0.001', 'AMMO5': '0.003', 'AMMO4': '0.004', 'weapon5': '0.058', 'HITCOUNT': '0.070', 'WEAPON5': '0.100', 'ARMOR': '0.112', 'AMMO3': '0.140', 'WEAPON4': '0.200', 'weapon4': '0.330', 'DAMAGECOUNT': '0.474', 'WEAPON3': '0.750', 'FRAGCOUNT': '1.000', 'weapon3': '1.340', 'weapon2': '1.596'} [2024-08-05 08:40:10,011][00147] DAMAGECOUNT value on done: 1875.0 [2024-08-05 08:40:10,299][00148] DAMAGECOUNT value on done: 2521.0 [2024-08-05 08:40:10,300][00148] Sum rewards: -2.831, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.690', 'AMMO4': '-0.033', 'AMMO2': '-0.007', 'AMMO5': '0.005', 'ARMOR': '0.033', 'weapon4': '0.094', 'WEAPON4': '0.100', 'AMMO3': '0.160', 'HITCOUNT': '0.190', 'DAMAGECOUNT': '0.567', 'WEAPON3': '0.850', 'weapon3': '1.520', 'weapon2': '1.630', 'FRAGCOUNT': '2.000'} [2024-08-05 08:40:10,539][00147] DAMAGECOUNT value on done: 2771.0 [2024-08-05 08:40:10,541][00147] Sum rewards: -1.610, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.776', 'AMMO5': '0.003', 'AMMO2': '0.006', 'WEAPON1': '0.010', 'ARMOR': '0.020', 'AMMO4': '0.028', 'WEAPON5': '0.050', 'AMMO3': '0.128', 'HITCOUNT': '0.150', 'weapon5': '0.222', 'WEAPON3': '0.450', 'DAMAGECOUNT': '0.912', 'weapon3': '1.440', 'weapon2': '1.748', 'FRAGCOUNT': '3.000'} [2024-08-05 08:40:10,867][00148] DAMAGECOUNT value on done: 2664.0 [2024-08-05 08:40:10,868][00148] Sum rewards: -2.492, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.346', 'weapon5': '0.002', 'AMMO2': '0.004', 'AMMO5': '0.013', 'AMMO4': '0.022', 'WEAPON5': '0.050', 'AMMO3': '0.097', 'ARMOR': '0.104', 'HITCOUNT': '0.170', 'weapon4': '0.178', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.594', 'WEAPON3': '0.650', 'FRAGCOUNT': '1.000', 'weapon3': '1.582', 'weapon2': '1.688'} [2024-08-05 08:40:11,156][00149] DAMAGECOUNT value on done: 1972.0 [2024-08-05 08:40:11,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3825664. Throughput: 0: 900.9. Samples: 955976. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:40:11,502][00035] Avg episode reward: [(0, '-5.122')] [2024-08-05 08:40:11,514][00137] Saving new best policy, reward=-5.122! [2024-08-05 08:40:11,735][00149] DAMAGECOUNT value on done: 2701.0 [2024-08-05 08:40:11,736][00149] Sum rewards: -1.001, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.025', 'AMMO4': '-0.007', 'AMMO2': '-0.001', 'AMMO3': '0.105', 'HITCOUNT': '0.240', 'ARMOR': '0.505', 'WEAPON3': '0.750', 'DAMAGECOUNT': '0.834', 'FRAGCOUNT': '1.000', 'weapon3': '1.666', 'weapon2': '1.682'} [2024-08-05 08:40:12,255][00149] DAMAGECOUNT value on done: 3131.0 [2024-08-05 08:40:12,256][00149] Sum rewards: -0.623, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.430', 'AMMO4': '-0.027', 'AMMO2': '-0.005', 'ARMOR': '0.048', 'AMMO3': '0.118', 'HITCOUNT': '0.330', 'WEAPON3': '0.600', 'DAMAGECOUNT': '1.251', 'weapon3': '1.264', 'weapon2': '2.228', 'FRAGCOUNT': '4.000'} [2024-08-05 08:40:12,795][00150] DAMAGECOUNT value on done: 2511.0 [2024-08-05 08:40:12,796][00150] Sum rewards: -6.586, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.952', 'AMMO2': '0.001', 'AMMO4': '0.006', 'AMMO5': '0.010', 'ARMOR': '0.072', 'HITCOUNT': '0.130', 'AMMO3': '0.138', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.612', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '1.794', 'weapon3': '1.852'} [2024-08-05 08:40:12,809][00149] DAMAGECOUNT value on done: 2787.0 [2024-08-05 08:40:12,810][00149] Sum rewards: -7.544, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-2.072', 'AMMO4': '-0.024', 'AMMO2': '-0.005', 'AMMO5': '0.003', 'weapon5': '0.018', 'HITCOUNT': '0.030', 'WEAPON5': '0.050', 'DAMAGECOUNT': '0.072', 'AMMO3': '0.178', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.050', 'weapon2': '1.674', 'weapon3': '1.732'} [2024-08-05 08:40:13,427][00150] DAMAGECOUNT value on done: 2934.0 [2024-08-05 08:40:13,963][00150] DAMAGECOUNT value on done: 2963.0 [2024-08-05 08:40:13,964][00150] Sum rewards: 1.115, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.028', 'AMMO2': '0.004', 'AMMO5': '0.008', 'AMMO4': '0.022', 'weapon7': '0.076', 'AMMO6': '0.120', 'AMMO7': '0.120', 'AMMO3': '0.138', 'weapon5': '0.152', 'WEAPON5': '0.200', 'WEAPON7': '0.200', 'HITCOUNT': '0.220', 'WEAPON3': '0.850', 'weapon2': '1.510', 'DAMAGECOUNT': '1.530', 'weapon3': '1.742', 'FRAGCOUNT': '3.500'} [2024-08-05 08:40:14,495][00150] DAMAGECOUNT value on done: 3062.0 [2024-08-05 08:40:14,496][00150] Sum rewards: -7.484, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-2.020', 'AMMO5': '0.003', 'WEAPON1': '0.010', 'AMMO2': '0.025', 'WEAPON5': '0.050', 'ARMOR': '0.073', 'weapon5': '0.088', 'AMMO4': '0.124', 'AMMO3': '0.142', 'HITCOUNT': '0.250', 'weapon4': '0.298', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.690', 'WEAPON3': '0.800', 'weapon3': '1.534', 'weapon2': '1.650', 'FRAGCOUNT': '2.000'} [2024-08-05 08:40:16,501][00035] Fps is (10 sec: 4095.7, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3842048. Throughput: 0: 898.9. Samples: 961438. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:40:16,503][00035] Avg episode reward: [(0, '-4.912')] [2024-08-05 08:40:16,506][00137] Saving new best policy, reward=-4.912! [2024-08-05 08:40:17,857][00146] Updated weights for policy 0, policy_version 470 (0.0023) [2024-08-05 08:40:21,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3665.6). Total num frames: 3858432. Throughput: 0: 903.4. Samples: 964180. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:40:21,502][00035] Avg episode reward: [(0, '-4.912')] [2024-08-05 08:40:21,511][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000471_3858432.pth... [2024-08-05 08:40:21,617][00137] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000364_2981888.pth [2024-08-05 08:40:26,500][00035] Fps is (10 sec: 3277.0, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 3874816. Throughput: 0: 901.0. Samples: 969368. Policy #0 lag: (min: 0.0, avg: 0.0, max: 1.0) [2024-08-05 08:40:26,504][00035] Avg episode reward: [(0, '-4.912')] [2024-08-05 08:40:31,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 3891200. Throughput: 0: 903.0. Samples: 974904. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:40:31,502][00035] Avg episode reward: [(0, '-4.912')] [2024-08-05 08:40:36,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3915776. Throughput: 0: 904.0. Samples: 977688. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:40:36,502][00035] Avg episode reward: [(0, '-4.912')] [2024-08-05 08:40:40,585][00146] Updated weights for policy 0, policy_version 480 (0.0017) [2024-08-05 08:40:41,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3932160. Throughput: 0: 912.9. Samples: 983246. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:40:41,502][00035] Avg episode reward: [(0, '-4.912')] [2024-08-05 08:40:46,246][00147] DAMAGECOUNT value on done: 3622.0 [2024-08-05 08:40:46,247][00147] Sum rewards: 0.285, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.786', 'AMMO4': '-0.019', 'AMMO2': '-0.004', 'AMMO5': '0.007', 'WEAPON5': '0.050', 'weapon5': '0.058', 'AMMO3': '0.090', 'HITCOUNT': '0.250', 'WEAPON3': '0.350', 'DAMAGECOUNT': '1.110', 'weapon3': '1.240', 'weapon2': '2.188', 'FRAGCOUNT': '4.000'} [2024-08-05 08:40:46,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 3948544. Throughput: 0: 914.2. Samples: 988806. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:40:46,502][00035] Avg episode reward: [(0, '-4.855')] [2024-08-05 08:40:46,504][00137] Saving new best policy, reward=-4.855! [2024-08-05 08:40:46,894][00147] DAMAGECOUNT value on done: 2488.0 [2024-08-05 08:40:46,895][00147] Sum rewards: -1.349, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.171', 'AMMO5': '0.003', 'AMMO2': '0.008', 'AMMO4': '0.038', 'weapon5': '0.044', 'weapon4': '0.058', 'ARMOR': '0.088', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.104', 'HITCOUNT': '0.110', 'DAMAGECOUNT': '0.264', 'WEAPON3': '0.700', 'weapon2': '1.668', 'weapon3': '1.788', 'FRAGCOUNT': '2.000'} [2024-08-05 08:40:46,988][00148] DAMAGECOUNT value on done: 2972.0 [2024-08-05 08:40:46,988][00148] Sum rewards: -1.804, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-0.940', 'AMMO4': '-0.011', 'AMMO2': '-0.002', 'ARMOR': '0.040', 'WEAPON4': '0.050', 'AMMO3': '0.092', 'HITCOUNT': '0.180', 'weapon4': '0.214', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.705', 'FRAGCOUNT': '1.000', 'weapon2': '1.544', 'weapon3': '1.574'} [2024-08-05 08:40:47,137][00149] DAMAGECOUNT value on done: 2232.0 [2024-08-05 08:40:47,137][00149] Sum rewards: -1.059, reward structure: {'DEATHCOUNT': '-8.250', 'AMMO2': '0.004', 'AMMO4': '0.018', 'ARMOR': '0.028', 'WEAPON4': '0.100', 'AMMO3': '0.115', 'HITCOUNT': '0.180', 'weapon4': '0.230', 'HEALTH': '0.276', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.780', 'weapon2': '0.922', 'weapon3': '1.938', 'FRAGCOUNT': '2.000'} [2024-08-05 08:40:47,474][00147] DAMAGECOUNT value on done: 2033.0 [2024-08-05 08:40:47,475][00147] Sum rewards: -3.072, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.400', 'weapon5': '0.006', 'AMMO5': '0.015', 'WEAPON1': '0.020', 'AMMO2': '0.026', 'AMMO6': '0.100', 'AMMO7': '0.100', 'WEAPON7': '0.100', 'WEAPON4': '0.100', 'weapon4': '0.100', 'weapon7': '0.110', 'AMMO3': '0.117', 'AMMO4': '0.128', 'HITCOUNT': '0.160', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.474', 'WEAPON3': '0.650', 'FRAGCOUNT': '1.000', 'weapon2': '1.430', 'weapon3': '1.642'} [2024-08-05 08:40:47,621][00148] DAMAGECOUNT value on done: 2436.0 [2024-08-05 08:40:47,622][00148] Sum rewards: -1.775, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.736', 'AMMO2': '0.023', 'ARMOR': '0.032', 'HITCOUNT': '0.050', 'WEAPON4': '0.100', 'AMMO4': '0.114', 'DAMAGECOUNT': '0.150', 'AMMO3': '0.172', 'weapon4': '0.274', 'WEAPON3': '0.650', 'weapon3': '1.526', 'weapon2': '1.870', 'FRAGCOUNT': '3.000'} [2024-08-05 08:40:47,751][00149] DAMAGECOUNT value on done: 3123.0 [2024-08-05 08:40:47,752][00149] Sum rewards: -1.929, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.426', 'AMMO4': '-0.008', 'AMMO2': '-0.002', 'ARMOR': '0.032', 'WEAPON4': '0.100', 'AMMO3': '0.116', 'weapon4': '0.196', 'HITCOUNT': '0.440', 'WEAPON3': '0.600', 'DAMAGECOUNT': '1.266', 'weapon3': '1.324', 'weapon2': '1.432', 'FRAGCOUNT': '3.000'} [2024-08-05 08:40:48,023][00147] DAMAGECOUNT value on done: 3124.0 [2024-08-05 08:40:48,024][00147] Sum rewards: -3.060, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.675', 'AMMO2': '0.007', 'ARMOR': '0.032', 'AMMO4': '0.035', 'weapon7': '0.096', 'AMMO6': '0.120', 'AMMO7': '0.120', 'WEAPON4': '0.150', 'AMMO3': '0.151', 'WEAPON7': '0.200', 'HITCOUNT': '0.220', 'weapon4': '0.368', 'weapon2': '0.758', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.059', 'weapon3': '1.798', 'FRAGCOUNT': '4.000'} [2024-08-05 08:40:48,171][00148] DAMAGECOUNT value on done: 2646.0 [2024-08-05 08:40:48,171][00148] Sum rewards: -5.514, reward structure: {'DEATHCOUNT': '-9.750', 'FRAGCOUNT': '-0.500', 'HEALTH': '-0.354', 'AMMO2': '0.001', 'weapon4': '0.004', 'AMMO4': '0.007', 'AMMO5': '0.007', 'WEAPON4': '0.050', 'HITCOUNT': '0.070', 'ARMOR': '0.085', 'WEAPON5': '0.100', 'weapon5': '0.110', 'AMMO3': '0.135', 'DAMAGECOUNT': '0.375', 'WEAPON3': '0.750', 'weapon3': '1.614', 'weapon2': '1.780'} [2024-08-05 08:40:48,292][00149] DAMAGECOUNT value on done: 3273.0 [2024-08-05 08:40:48,293][00149] Sum rewards: -4.491, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-0.418', 'AMMO5': '0.003', 'WEAPON1': '0.010', 'AMMO2': '0.021', 'ARMOR': '0.040', 'WEAPON4': '0.050', 'AMMO4': '0.105', 'weapon4': '0.124', 'HITCOUNT': '0.160', 'AMMO3': '0.176', 'DAMAGECOUNT': '0.426', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '1.468', 'weapon3': '1.944'} [2024-08-05 08:40:48,723][00148] DAMAGECOUNT value on done: 2856.0 [2024-08-05 08:40:48,859][00149] DAMAGECOUNT value on done: 3089.0 [2024-08-05 08:40:48,859][00149] Sum rewards: -1.879, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.846', 'AMMO4': '-0.051', 'AMMO2': '-0.010', 'AMMO5': '0.015', 'ARMOR': '0.040', 'weapon5': '0.088', 'AMMO3': '0.161', 'HITCOUNT': '0.240', 'WEAPON5': '0.300', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.906', 'FRAGCOUNT': '1.000', 'weapon2': '1.430', 'weapon3': '1.998'} [2024-08-05 08:40:49,322][00150] DAMAGECOUNT value on done: 2667.0 [2024-08-05 08:40:49,323][00150] Sum rewards: -5.791, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.430', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.075', 'AMMO2': '-0.015', 'AMMO5': '0.009', 'HITCOUNT': '0.050', 'weapon5': '0.080', 'AMMO3': '0.144', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.468', 'WEAPON3': '0.600', 'weapon3': '1.136', 'weapon2': '2.042'} [2024-08-05 08:40:49,890][00150] DAMAGECOUNT value on done: 3180.0 [2024-08-05 08:40:49,891][00150] Sum rewards: -1.147, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-0.705', 'AMMO2': '0.014', 'WEAPON1': '0.020', 'AMMO4': '0.070', 'ARMOR': '0.096', 'AMMO3': '0.125', 'WEAPON4': '0.150', 'weapon4': '0.240', 'HITCOUNT': '0.280', 'WEAPON3': '0.550', 'DAMAGECOUNT': '0.738', 'FRAGCOUNT': '1.000', 'weapon3': '1.326', 'weapon2': '1.698'} [2024-08-05 08:40:50,452][00150] DAMAGECOUNT value on done: 3141.0 [2024-08-05 08:40:51,029][00150] DAMAGECOUNT value on done: 3176.0 [2024-08-05 08:40:51,030][00150] Sum rewards: -1.134, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-0.160', 'AMMO5': '0.003', 'WEAPON1': '0.010', 'AMMO2': '0.023', 'ARMOR': '0.036', 'weapon5': '0.044', 'WEAPON5': '0.050', 'AMMO3': '0.108', 'HITCOUNT': '0.110', 'AMMO4': '0.113', 'WEAPON4': '0.150', 'weapon4': '0.288', 'DAMAGECOUNT': '0.342', 'WEAPON3': '0.550', 'FRAGCOUNT': '1.000', 'weapon3': '1.368', 'weapon2': '1.582'} [2024-08-05 08:40:51,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 3964928. Throughput: 0: 910.3. Samples: 991438. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:40:51,505][00035] Avg episode reward: [(0, '-4.415')] [2024-08-05 08:40:51,513][00137] Saving new best policy, reward=-4.415! [2024-08-05 08:40:56,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3989504. Throughput: 0: 907.0. Samples: 996792. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:40:56,502][00035] Avg episode reward: [(0, '-4.415')] [2024-08-05 08:41:01,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 4005888. Throughput: 0: 894.7. Samples: 1001698. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:41:01,502][00035] Avg episode reward: [(0, '-4.415')] [2024-08-05 08:41:03,602][00146] Updated weights for policy 0, policy_version 490 (0.0038) [2024-08-05 08:41:06,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 4022272. Throughput: 0: 894.6. Samples: 1004436. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:41:06,504][00035] Avg episode reward: [(0, '-4.415')] [2024-08-05 08:41:11,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 4038656. Throughput: 0: 899.1. Samples: 1009828. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:41:11,502][00035] Avg episode reward: [(0, '-4.415')] [2024-08-05 08:41:16,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 4055040. Throughput: 0: 898.5. Samples: 1015336. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:41:16,503][00035] Avg episode reward: [(0, '-4.415')] [2024-08-05 08:41:21,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 4071424. Throughput: 0: 897.6. Samples: 1018080. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:41:21,502][00035] Avg episode reward: [(0, '-4.415')] [2024-08-05 08:41:24,283][00149] DAMAGECOUNT value on done: 2446.0 [2024-08-05 08:41:24,284][00149] Sum rewards: -0.998, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-0.908', 'AMMO4': '-0.032', 'AMMO2': '-0.006', 'weapon4': '0.018', 'ARMOR': '0.036', 'WEAPON4': '0.050', 'AMMO3': '0.086', 'weapon7': '0.092', 'AMMO6': '0.120', 'AMMO7': '0.120', 'WEAPON7': '0.200', 'HITCOUNT': '0.200', 'DAMAGECOUNT': '0.642', 'WEAPON3': '0.650', 'FRAGCOUNT': '1.000', 'weapon3': '1.728', 'weapon2': '1.756'} [2024-08-05 08:41:24,287][00147] DAMAGECOUNT value on done: 3916.0 [2024-08-05 08:41:24,287][00147] Sum rewards: -5.184, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.968', 'ARMOR': '0.004', 'AMMO5': '0.008', 'AMMO2': '0.009', 'AMMO4': '0.046', 'WEAPON5': '0.050', 'weapon5': '0.104', 'AMMO3': '0.163', 'HITCOUNT': '0.280', 'DAMAGECOUNT': '0.882', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.500', 'weapon3': '1.592', 'weapon2': '1.746'} [2024-08-05 08:41:24,823][00147] DAMAGECOUNT value on done: 2655.0 [2024-08-05 08:41:24,824][00147] Sum rewards: -4.772, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-2.755', 'AMMO2': '0.001', 'AMMO4': '0.007', 'weapon5': '0.016', 'AMMO5': '0.018', 'ARMOR': '0.056', 'AMMO3': '0.130', 'HITCOUNT': '0.160', 'WEAPON4': '0.200', 'weapon4': '0.262', 'WEAPON5': '0.350', 'DAMAGECOUNT': '0.501', 'WEAPON3': '0.850', 'FRAGCOUNT': '1.000', 'weapon2': '1.576', 'weapon3': '1.856'} [2024-08-05 08:41:24,887][00149] DAMAGECOUNT value on done: 3418.0 [2024-08-05 08:41:24,887][00149] Sum rewards: -2.856, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-0.258', 'AMMO2': '0.003', 'AMMO5': '0.006', 'AMMO4': '0.015', 'ARMOR': '0.036', 'weapon5': '0.080', 'WEAPON5': '0.100', 'AMMO3': '0.169', 'HITCOUNT': '0.190', 'WEAPON3': '0.850', 'DAMAGECOUNT': '0.885', 'weapon2': '1.496', 'FRAGCOUNT': '2.000', 'weapon3': '2.072'} [2024-08-05 08:41:25,162][00148] DAMAGECOUNT value on done: 3411.0 [2024-08-05 08:41:25,163][00148] Sum rewards: -2.550, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-0.959', 'AMMO2': '0.009', 'AMMO4': '0.045', 'ARMOR': '0.048', 'AMMO3': '0.178', 'WEAPON4': '0.200', 'weapon4': '0.328', 'HITCOUNT': '0.330', 'WEAPON3': '0.850', 'DAMAGECOUNT': '1.317', 'weapon2': '1.492', 'weapon3': '1.862', 'FRAGCOUNT': '3.000'} [2024-08-05 08:41:25,375][00147] DAMAGECOUNT value on done: 2239.0 [2024-08-05 08:41:25,421][00149] DAMAGECOUNT value on done: 3389.0 [2024-08-05 08:41:25,764][00148] DAMAGECOUNT value on done: 2612.0 [2024-08-05 08:41:25,764][00148] Sum rewards: -6.264, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-3.193', 'AMMO4': '-0.013', 'AMMO2': '-0.003', 'AMMO5': '0.010', 'weapon5': '0.020', 'weapon7': '0.048', 'ARMOR': '0.052', 'AMMO6': '0.160', 'AMMO7': '0.160', 'AMMO3': '0.167', 'HITCOUNT': '0.170', 'weapon4': '0.190', 'WEAPON4': '0.200', 'WEAPON7': '0.200', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.528', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '1.574', 'weapon3': '1.866'} [2024-08-05 08:41:25,957][00149] DAMAGECOUNT value on done: 3312.0 [2024-08-05 08:41:25,957][00149] Sum rewards: -4.619, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.837', 'AMMO4': '-0.031', 'AMMO2': '-0.006', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'ARMOR': '0.024', 'WEAPON4': '0.050', 'HITCOUNT': '0.110', 'weapon5': '0.136', 'AMMO3': '0.145', 'WEAPON5': '0.150', 'weapon4': '0.234', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.669', 'WEAPON3': '0.900', 'weapon2': '1.566', 'weapon3': '1.744'} [2024-08-05 08:41:25,977][00147] DAMAGECOUNT value on done: 3383.0 [2024-08-05 08:41:25,978][00147] Sum rewards: -3.014, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.096', 'AMMO5': '0.005', 'WEAPON1': '0.020', 'AMMO2': '0.025', 'ARMOR': '0.040', 'weapon4': '0.068', 'WEAPON5': '0.100', 'AMMO3': '0.120', 'AMMO4': '0.127', 'HITCOUNT': '0.190', 'WEAPON4': '0.200', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.777', 'weapon3': '1.634', 'weapon2': '1.926', 'FRAGCOUNT': '2.000'} [2024-08-05 08:41:26,247][00146] Updated weights for policy 0, policy_version 500 (0.0030) [2024-08-05 08:41:26,348][00148] DAMAGECOUNT value on done: 2842.0 [2024-08-05 08:41:26,349][00148] Sum rewards: -4.110, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.685', 'AMMO4': '-0.034', 'AMMO2': '-0.007', 'weapon5': '0.002', 'AMMO5': '0.010', 'ARMOR': '0.055', 'HITCOUNT': '0.130', 'AMMO3': '0.139', 'WEAPON5': '0.150', 'DAMAGECOUNT': '0.588', 'WEAPON3': '0.950', 'FRAGCOUNT': '1.000', 'weapon2': '1.682', 'weapon3': '1.910'} [2024-08-05 08:41:26,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 4096000. Throughput: 0: 896.0. Samples: 1023566. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:41:26,502][00035] Avg episode reward: [(0, '-4.355')] [2024-08-05 08:41:26,503][00137] Saving new best policy, reward=-4.355! [2024-08-05 08:41:26,682][00150] DAMAGECOUNT value on done: 3037.0 [2024-08-05 08:41:26,683][00150] Sum rewards: -1.753, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.597', 'AMMO2': '0.003', 'AMMO5': '0.014', 'AMMO4': '0.016', 'WEAPON4': '0.050', 'weapon7': '0.090', 'AMMO6': '0.100', 'WEAPON7': '0.100', 'AMMO7': '0.100', 'AMMO3': '0.141', 'weapon4': '0.146', 'WEAPON5': '0.200', 'HITCOUNT': '0.300', 'weapon5': '0.314', 'ARMOR': '0.457', 'weapon2': '0.720', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.110', 'weapon3': '2.332', 'FRAGCOUNT': '2.500'} [2024-08-05 08:41:27,010][00148] DAMAGECOUNT value on done: 3046.0 [2024-08-05 08:41:27,220][00150] DAMAGECOUNT value on done: 3280.0 [2024-08-05 08:41:27,768][00150] DAMAGECOUNT value on done: 3412.0 [2024-08-05 08:41:27,768][00150] Sum rewards: -6.268, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-2.221', 'AMMO5': '0.011', 'AMMO2': '0.019', 'ARMOR': '0.052', 'AMMO4': '0.094', 'HITCOUNT': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.142', 'weapon5': '0.164', 'weapon4': '0.194', 'WEAPON5': '0.200', 'WEAPON3': '0.750', 'DAMAGECOUNT': '0.813', 'weapon3': '1.648', 'weapon2': '1.666', 'FRAGCOUNT': '2.000'} [2024-08-05 08:41:28,475][00150] DAMAGECOUNT value on done: 3436.0 [2024-08-05 08:41:28,476][00150] Sum rewards: -2.488, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.120', 'AMMO4': '-0.062', 'AMMO2': '-0.012', 'ARMOR': '0.080', 'AMMO3': '0.150', 'HITCOUNT': '0.230', 'DAMAGECOUNT': '0.780', 'WEAPON3': '0.950', 'weapon2': '1.468', 'weapon3': '1.548', 'FRAGCOUNT': '2.000'} [2024-08-05 08:41:31,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 4112384. Throughput: 0: 882.0. Samples: 1028498. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:41:31,502][00035] Avg episode reward: [(0, '-4.398')] [2024-08-05 08:41:36,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3665.6). Total num frames: 4128768. Throughput: 0: 886.7. Samples: 1031340. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:41:36,502][00035] Avg episode reward: [(0, '-4.398')] [2024-08-05 08:41:41,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 4145152. Throughput: 0: 890.6. Samples: 1036870. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:41:41,502][00035] Avg episode reward: [(0, '-4.398')] [2024-08-05 08:41:46,501][00035] Fps is (10 sec: 3276.6, 60 sec: 3549.8, 300 sec: 3637.8). Total num frames: 4161536. Throughput: 0: 906.9. Samples: 1042510. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:41:46,502][00035] Avg episode reward: [(0, '-4.398')] [2024-08-05 08:41:48,872][00146] Updated weights for policy 0, policy_version 510 (0.0025) [2024-08-05 08:41:51,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 4186112. Throughput: 0: 908.1. Samples: 1045300. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:41:51,502][00035] Avg episode reward: [(0, '-4.398')] [2024-08-05 08:41:56,500][00035] Fps is (10 sec: 4096.3, 60 sec: 3549.9, 300 sec: 3665.6). Total num frames: 4202496. Throughput: 0: 913.7. Samples: 1050944. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:41:56,502][00035] Avg episode reward: [(0, '-4.398')] [2024-08-05 08:42:00,595][00149] DAMAGECOUNT value on done: 2686.0 [2024-08-05 08:42:01,369][00149] DAMAGECOUNT value on done: 3638.0 [2024-08-05 08:42:01,370][00149] Sum rewards: -7.618, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-2.204', 'AMMO4': '-0.086', 'AMMO2': '-0.017', 'AMMO5': '0.003', 'weapon5': '0.018', 'ARMOR': '0.020', 'WEAPON1': '0.020', 'WEAPON5': '0.050', 'HITCOUNT': '0.170', 'AMMO3': '0.179', 'DAMAGECOUNT': '0.660', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.500', 'weapon3': '1.622', 'weapon2': '1.648'} [2024-08-05 08:42:01,503][00035] Fps is (10 sec: 3275.8, 60 sec: 3549.7, 300 sec: 3637.8). Total num frames: 4218880. Throughput: 0: 905.1. Samples: 1056068. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:42:01,509][00035] Avg episode reward: [(0, '-4.358')] [2024-08-05 08:42:02,063][00149] DAMAGECOUNT value on done: 3514.0 [2024-08-05 08:42:02,064][00149] Sum rewards: -0.101, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-0.396', 'AMMO5': '0.003', 'AMMO2': '0.017', 'weapon4': '0.036', 'ARMOR': '0.044', 'WEAPON5': '0.050', 'weapon5': '0.052', 'HITCOUNT': '0.070', 'AMMO4': '0.086', 'WEAPON4': '0.100', 'AMMO3': '0.130', 'DAMAGECOUNT': '0.375', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon2': '1.306', 'weapon3': '1.676'} [2024-08-05 08:42:02,276][00147] DAMAGECOUNT value on done: 4213.0 [2024-08-05 08:42:02,277][00147] Sum rewards: -0.922, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.440', 'AMMO5': '0.010', 'weapon5': '0.010', 'AMMO2': '0.020', 'ARMOR': '0.072', 'weapon7': '0.080', 'AMMO4': '0.097', 'AMMO6': '0.100', 'AMMO7': '0.100', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'WEAPON7': '0.100', 'AMMO3': '0.114', 'HITCOUNT': '0.250', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.891', 'weapon3': '1.296', 'weapon2': '1.728', 'FRAGCOUNT': '3.000'} [2024-08-05 08:42:02,657][00149] DAMAGECOUNT value on done: 3785.0 [2024-08-05 08:42:02,658][00149] Sum rewards: -5.074, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-1.972', 'AMMO5': '0.003', 'AMMO2': '0.007', 'weapon4': '0.016', 'AMMO4': '0.036', 'WEAPON5': '0.050', 'WEAPON4': '0.050', 'weapon5': '0.054', 'ARMOR': '0.096', 'AMMO3': '0.199', 'HITCOUNT': '0.280', 'WEAPON3': '1.050', 'DAMAGECOUNT': '1.419', 'weapon2': '1.446', 'weapon3': '1.942', 'FRAGCOUNT': '3.000'} [2024-08-05 08:42:02,815][00148] DAMAGECOUNT value on done: 3703.0 [2024-08-05 08:42:02,816][00148] Sum rewards: -6.707, reward structure: {'DEATHCOUNT': '-10.500', 'FRAGCOUNT': '-1.500', 'HEALTH': '-1.010', 'AMMO5': '0.010', 'AMMO2': '0.014', 'ARMOR': '0.048', 'weapon7': '0.048', 'weapon5': '0.058', 'AMMO4': '0.068', 'AMMO6': '0.120', 'AMMO7': '0.120', 'AMMO3': '0.143', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'WEAPON7': '0.200', 'weapon4': '0.262', 'HITCOUNT': '0.290', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.876', 'weapon2': '1.430', 'weapon3': '1.616'} [2024-08-05 08:42:02,849][00147] DAMAGECOUNT value on done: 2853.0 [2024-08-05 08:42:02,849][00147] Sum rewards: -7.368, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.762', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.014', 'AMMO2': '0.017', 'WEAPON1': '0.040', 'weapon5': '0.062', 'AMMO4': '0.086', 'AMMO3': '0.132', 'WEAPON4': '0.150', 'HITCOUNT': '0.200', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.594', 'WEAPON3': '0.850', 'weapon2': '1.406', 'weapon3': '1.792'} [2024-08-05 08:42:03,289][00150] DAMAGECOUNT value on done: 3077.0 [2024-08-05 08:42:03,290][00150] Sum rewards: -1.964, reward structure: {'DEATHCOUNT': '-4.500', 'FRAGCOUNT': '-1.500', 'HEALTH': '-0.496', 'AMMO2': '0.012', 'AMMO5': '0.019', 'HITCOUNT': '0.030', 'AMMO4': '0.060', 'ARMOR': '0.080', 'AMMO3': '0.086', 'weapon5': '0.100', 'DAMAGECOUNT': '0.120', 'WEAPON4': '0.200', 'WEAPON5': '0.300', 'weapon4': '0.404', 'WEAPON3': '0.500', 'weapon2': '1.120', 'weapon3': '1.500'} [2024-08-05 08:42:03,394][00148] DAMAGECOUNT value on done: 2863.0 [2024-08-05 08:42:03,405][00147] DAMAGECOUNT value on done: 2716.0 [2024-08-05 08:42:03,406][00147] Sum rewards: -4.413, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.624', 'AMMO4': '-0.056', 'AMMO2': '-0.011', 'AMMO5': '0.005', 'WEAPON5': '0.100', 'ARMOR': '0.102', 'weapon5': '0.108', 'HITCOUNT': '0.180', 'AMMO3': '0.212', 'WEAPON3': '0.950', 'DAMAGECOUNT': '1.431', 'weapon3': '1.716', 'weapon2': '1.724', 'FRAGCOUNT': '2.000'} [2024-08-05 08:42:03,843][00150] DAMAGECOUNT value on done: 3515.0 [2024-08-05 08:42:03,844][00150] Sum rewards: -4.794, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.050', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.005', 'AMMO2': '0.015', 'weapon5': '0.018', 'WEAPON5': '0.050', 'ARMOR': '0.072', 'AMMO4': '0.072', 'AMMO3': '0.135', 'WEAPON4': '0.150', 'weapon4': '0.208', 'HITCOUNT': '0.220', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.705', 'weapon2': '1.506', 'weapon3': '1.900'} [2024-08-05 08:42:03,960][00148] DAMAGECOUNT value on done: 3172.0 [2024-08-05 08:42:03,961][00148] Sum rewards: -2.400, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.392', 'AMMO2': '0.008', 'AMMO5': '0.023', 'AMMO4': '0.037', 'weapon5': '0.102', 'AMMO3': '0.106', 'HITCOUNT': '0.260', 'WEAPON5': '0.350', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.990', 'weapon3': '1.656', 'weapon2': '1.760', 'FRAGCOUNT': '2.000'} [2024-08-05 08:42:03,962][00147] DAMAGECOUNT value on done: 3637.0 [2024-08-05 08:42:03,963][00147] Sum rewards: -1.565, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-0.396', 'AMMO4': '-0.030', 'AMMO2': '-0.006', 'AMMO5': '0.010', 'WEAPON1': '0.010', 'ARMOR': '0.040', 'AMMO3': '0.100', 'WEAPON5': '0.100', 'weapon5': '0.148', 'HITCOUNT': '0.180', 'WEAPON3': '0.400', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.762', 'weapon2': '0.880', 'weapon3': '1.736'} [2024-08-05 08:42:04,422][00150] DAMAGECOUNT value on done: 3661.0 [2024-08-05 08:42:04,423][00150] Sum rewards: 0.210, reward structure: {'DEATHCOUNT': '-8.250', 'AMMO2': '0.004', 'AMMO5': '0.018', 'AMMO4': '0.019', 'WEAPON1': '0.020', 'WEAPON4': '0.050', 'HEALTH': '0.052', 'ARMOR': '0.082', 'weapon4': '0.108', 'AMMO3': '0.118', 'weapon5': '0.124', 'HITCOUNT': '0.170', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.747', 'WEAPON3': '0.750', 'weapon2': '1.234', 'weapon3': '1.764', 'FRAGCOUNT': '3.000'} [2024-08-05 08:42:04,535][00148] DAMAGECOUNT value on done: 3070.0 [2024-08-05 08:42:04,536][00148] Sum rewards: -2.930, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.411', 'AMMO2': '0.005', 'AMMO5': '0.013', 'weapon4': '0.020', 'AMMO4': '0.025', 'HITCOUNT': '0.030', 'weapon5': '0.044', 'ARMOR': '0.060', 'DAMAGECOUNT': '0.072', 'WEAPON5': '0.150', 'WEAPON4': '0.150', 'AMMO3': '0.173', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '1.322', 'weapon3': '2.118'} [2024-08-05 08:42:05,008][00150] DAMAGECOUNT value on done: 3579.0 [2024-08-05 08:42:06,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 4235264. Throughput: 0: 904.0. Samples: 1058758. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:42:06,501][00035] Avg episode reward: [(0, '-3.999')] [2024-08-05 08:42:06,503][00137] Saving new best policy, reward=-3.999! [2024-08-05 08:42:11,500][00035] Fps is (10 sec: 3277.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 4251648. Throughput: 0: 904.9. Samples: 1064286. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:42:11,501][00035] Avg episode reward: [(0, '-3.999')] [2024-08-05 08:42:11,523][00146] Updated weights for policy 0, policy_version 520 (0.0033) [2024-08-05 08:42:16,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 4276224. Throughput: 0: 921.3. Samples: 1069958. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:42:16,501][00035] Avg episode reward: [(0, '-3.999')] [2024-08-05 08:42:21,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 4292608. Throughput: 0: 920.7. Samples: 1072772. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:42:21,501][00035] Avg episode reward: [(0, '-3.999')] [2024-08-05 08:42:21,509][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000524_4292608.pth... [2024-08-05 08:42:21,617][00137] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000418_3424256.pth [2024-08-05 08:42:26,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 4308992. Throughput: 0: 922.7. Samples: 1078390. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:42:26,504][00035] Avg episode reward: [(0, '-3.999')] [2024-08-05 08:42:31,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 4333568. Throughput: 0: 920.9. Samples: 1083952. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:42:31,502][00035] Avg episode reward: [(0, '-3.999')] [2024-08-05 08:42:33,823][00146] Updated weights for policy 0, policy_version 530 (0.0026) [2024-08-05 08:42:36,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 4349952. Throughput: 0: 911.6. Samples: 1086324. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:42:36,502][00035] Avg episode reward: [(0, '-3.999')] [2024-08-05 08:42:36,886][00149] DAMAGECOUNT value on done: 3212.0 [2024-08-05 08:42:36,887][00149] Sum rewards: -1.051, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-0.746', 'AMMO5': '0.007', 'AMMO2': '0.011', 'ARMOR': '0.032', 'AMMO4': '0.053', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'weapon5': '0.110', 'AMMO3': '0.189', 'HITCOUNT': '0.190', 'WEAPON3': '0.850', 'weapon2': '1.438', 'weapon3': '1.536', 'DAMAGECOUNT': '1.578', 'FRAGCOUNT': '4.000'} [2024-08-05 08:42:37,452][00149] DAMAGECOUNT value on done: 3738.0 [2024-08-05 08:42:37,452][00149] Sum rewards: -4.403, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.186', 'AMMO5': '0.003', 'AMMO2': '0.006', 'AMMO4': '0.029', 'weapon5': '0.046', 'ARMOR': '0.078', 'AMMO3': '0.090', 'WEAPON5': '0.100', 'HITCOUNT': '0.110', 'weapon4': '0.146', 'WEAPON4': '0.150', 'DAMAGECOUNT': '0.300', 'WEAPON3': '0.550', 'FRAGCOUNT': '1.000', 'weapon3': '1.276', 'weapon2': '1.900'} [2024-08-05 08:42:37,994][00149] DAMAGECOUNT value on done: 3814.0 [2024-08-05 08:42:37,994][00149] Sum rewards: 0.168, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.513', 'AMMO5': '0.007', 'AMMO2': '0.011', 'WEAPON1': '0.020', 'AMMO4': '0.054', 'weapon5': '0.056', 'ARMOR': '0.085', 'WEAPON4': '0.100', 'AMMO3': '0.113', 'weapon4': '0.182', 'WEAPON5': '0.200', 'HITCOUNT': '0.230', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.900', 'weapon3': '1.290', 'weapon2': '1.682', 'FRAGCOUNT': '3.000'} [2024-08-05 08:42:38,646][00149] DAMAGECOUNT value on done: 3929.0 [2024-08-05 08:42:38,647][00149] Sum rewards: -6.663, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-2.090', 'AMMO5': '0.003', 'weapon5': '0.008', 'AMMO2': '0.018', 'WEAPON5': '0.050', 'ARMOR': '0.068', 'AMMO4': '0.089', 'HITCOUNT': '0.160', 'AMMO3': '0.204', 'WEAPON4': '0.250', 'weapon4': '0.272', 'DAMAGECOUNT': '0.432', 'WEAPON3': '1.250', 'weapon2': '1.348', 'FRAGCOUNT': '2.000', 'weapon3': '2.026'} [2024-08-05 08:42:39,043][00147] DAMAGECOUNT value on done: 4367.0 [2024-08-05 08:42:39,044][00147] Sum rewards: -3.146, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.970', 'AMMO2': '0.013', 'ARMOR': '0.036', 'AMMO4': '0.066', 'AMMO3': '0.098', 'HITCOUNT': '0.110', 'WEAPON4': '0.200', 'weapon4': '0.272', 'DAMAGECOUNT': '0.462', 'WEAPON3': '0.650', 'FRAGCOUNT': '1.000', 'weapon2': '1.188', 'weapon3': '1.978'} [2024-08-05 08:42:39,549][00150] DAMAGECOUNT value on done: 3322.0 [2024-08-05 08:42:39,550][00150] Sum rewards: -3.994, reward structure: {'DEATHCOUNT': '-9.000', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.005', 'AMMO2': '0.007', 'AMMO4': '0.033', 'WEAPON5': '0.050', 'weapon5': '0.050', 'ARMOR': '0.064', 'HEALTH': '0.097', 'AMMO3': '0.137', 'HITCOUNT': '0.170', 'DAMAGECOUNT': '0.735', 'WEAPON3': '0.750', 'weapon2': '1.486', 'weapon3': '1.922'} [2024-08-05 08:42:39,560][00147] DAMAGECOUNT value on done: 2998.0 [2024-08-05 08:42:39,561][00147] Sum rewards: -4.656, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-1.586', 'AMMO5': '0.017', 'AMMO2': '0.021', 'ARMOR': '0.056', 'weapon5': '0.064', 'HITCOUNT': '0.100', 'AMMO4': '0.104', 'AMMO3': '0.175', 'WEAPON5': '0.250', 'weapon4': '0.284', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.435', 'weapon2': '0.956', 'WEAPON3': '1.050', 'weapon3': '2.118', 'FRAGCOUNT': '3.000'} [2024-08-05 08:42:39,885][00148] DAMAGECOUNT value on done: 3890.0 [2024-08-05 08:42:40,091][00150] DAMAGECOUNT value on done: 3921.0 [2024-08-05 08:42:40,092][00150] Sum rewards: -2.367, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.320', 'AMMO2': '0.027', 'ARMOR': '0.076', 'AMMO4': '0.135', 'AMMO3': '0.138', 'weapon4': '0.166', 'WEAPON4': '0.250', 'HITCOUNT': '0.300', 'WEAPON3': '0.650', 'DAMAGECOUNT': '1.218', 'weapon2': '1.398', 'weapon3': '1.594', 'FRAGCOUNT': '2.000'} [2024-08-05 08:42:40,129][00147] DAMAGECOUNT value on done: 3227.0 [2024-08-05 08:42:40,130][00147] Sum rewards: 1.837, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.058', 'AMMO2': '0.000', 'AMMO4': '0.001', 'ARMOR': '0.043', 'weapon7': '0.056', 'AMMO6': '0.100', 'AMMO7': '0.100', 'WEAPON7': '0.100', 'AMMO3': '0.105', 'HITCOUNT': '0.160', 'WEAPON3': '0.700', 'weapon2': '1.152', 'DAMAGECOUNT': '1.233', 'weapon3': '1.894', 'FRAGCOUNT': '4.000'} [2024-08-05 08:42:40,466][00148] DAMAGECOUNT value on done: 2905.0 [2024-08-05 08:42:40,467][00148] Sum rewards: -8.441, reward structure: {'DEATHCOUNT': '-10.500', 'FRAGCOUNT': '-1.500', 'HEALTH': '-1.046', 'AMMO5': '0.005', 'AMMO2': '0.012', 'weapon5': '0.022', 'HITCOUNT': '0.040', 'ARMOR': '0.045', 'AMMO4': '0.058', 'WEAPON5': '0.100', 'AMMO3': '0.114', 'DAMAGECOUNT': '0.126', 'WEAPON4': '0.150', 'weapon4': '0.222', 'WEAPON3': '0.600', 'weapon2': '1.480', 'weapon3': '1.632'} [2024-08-05 08:42:40,698][00150] DAMAGECOUNT value on done: 3821.0 [2024-08-05 08:42:40,698][00150] Sum rewards: -7.750, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.013', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.007', 'AMMO2': '0.009', 'weapon5': '0.028', 'ARMOR': '0.031', 'AMMO4': '0.045', 'AMMO3': '0.132', 'HITCOUNT': '0.140', 'WEAPON5': '0.150', 'DAMAGECOUNT': '0.480', 'WEAPON3': '0.850', 'weapon2': '1.254', 'weapon3': '1.886'} [2024-08-05 08:42:40,739][00147] DAMAGECOUNT value on done: 3797.0 [2024-08-05 08:42:40,740][00147] Sum rewards: -5.974, reward structure: {'DEATHCOUNT': '-8.250', 'FRAGCOUNT': '-1.500', 'HEALTH': '-1.038', 'AMMO5': '0.005', 'weapon5': '0.008', 'ARMOR': '0.016', 'AMMO2': '0.018', 'WEAPON5': '0.050', 'AMMO3': '0.070', 'AMMO4': '0.091', 'WEAPON4': '0.150', 'HITCOUNT': '0.180', 'weapon4': '0.206', 'WEAPON3': '0.400', 'DAMAGECOUNT': '0.480', 'weapon3': '0.966', 'weapon2': '2.174'} [2024-08-05 08:42:41,009][00148] DAMAGECOUNT value on done: 3397.0 [2024-08-05 08:42:41,010][00148] Sum rewards: 1.729, reward structure: {'DEATHCOUNT': '-6.750', 'AMMO2': '0.002', 'AMMO5': '0.008', 'weapon5': '0.008', 'AMMO4': '0.012', 'WEAPON5': '0.100', 'AMMO3': '0.108', 'HITCOUNT': '0.170', 'HEALTH': '0.323', 'ARMOR': '0.493', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.675', 'weapon2': '1.426', 'weapon3': '1.654', 'FRAGCOUNT': '3.000'} [2024-08-05 08:42:41,254][00150] DAMAGECOUNT value on done: 3954.0 [2024-08-05 08:42:41,255][00150] Sum rewards: -7.107, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-2.812', 'AMMO4': '-0.014', 'AMMO2': '-0.003', 'AMMO5': '0.005', 'WEAPON5': '0.050', 'ARMOR': '0.069', 'WEAPON4': '0.100', 'AMMO3': '0.211', 'HITCOUNT': '0.280', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.125', 'weapon3': '1.488', 'weapon2': '1.994', 'FRAGCOUNT': '3.000'} [2024-08-05 08:42:41,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 4366336. Throughput: 0: 909.4. Samples: 1091866. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:42:41,503][00035] Avg episode reward: [(0, '-3.898')] [2024-08-05 08:42:41,509][00137] Saving new best policy, reward=-3.898! [2024-08-05 08:42:41,546][00148] DAMAGECOUNT value on done: 3125.0 [2024-08-05 08:42:46,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 4382720. Throughput: 0: 919.1. Samples: 1097424. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:42:46,502][00035] Avg episode reward: [(0, '-3.813')] [2024-08-05 08:42:46,506][00137] Saving new best policy, reward=-3.813! [2024-08-05 08:42:51,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 4407296. Throughput: 0: 920.8. Samples: 1100192. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:42:51,502][00035] Avg episode reward: [(0, '-3.813')] [2024-08-05 08:42:55,635][00146] Updated weights for policy 0, policy_version 540 (0.0019) [2024-08-05 08:42:56,500][00035] Fps is (10 sec: 4096.1, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 4423680. Throughput: 0: 924.0. Samples: 1105868. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:42:56,504][00035] Avg episode reward: [(0, '-3.813')] [2024-08-05 08:43:01,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.6, 300 sec: 3637.8). Total num frames: 4440064. Throughput: 0: 920.8. Samples: 1111396. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:43:01,502][00035] Avg episode reward: [(0, '-3.813')] [2024-08-05 08:43:06,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 4456448. Throughput: 0: 918.2. Samples: 1114092. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:43:06,502][00035] Avg episode reward: [(0, '-3.813')] [2024-08-05 08:43:11,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 4472832. Throughput: 0: 909.4. Samples: 1119314. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:43:11,502][00035] Avg episode reward: [(0, '-3.813')] [2024-08-05 08:43:13,092][00149] DAMAGECOUNT value on done: 3357.0 [2024-08-05 08:43:13,093][00149] Sum rewards: -7.573, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.200', 'AMMO4': '-0.010', 'AMMO2': '-0.002', 'AMMO5': '0.005', 'ARMOR': '0.040', 'weapon5': '0.048', 'WEAPON5': '0.050', 'WEAPON4': '0.050', 'weapon4': '0.066', 'AMMO3': '0.122', 'HITCOUNT': '0.160', 'DAMAGECOUNT': '0.435', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.650', 'weapon2': '1.360', 'weapon3': '1.652'} [2024-08-05 08:43:13,621][00149] DAMAGECOUNT value on done: 3817.0 [2024-08-05 08:43:13,622][00149] Sum rewards: -5.461, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.645', 'weapon5': '0.002', 'AMMO5': '0.005', 'AMMO2': '0.011', 'AMMO4': '0.052', 'ARMOR': '0.093', 'HITCOUNT': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.140', 'DAMAGECOUNT': '0.237', 'WEAPON4': '0.250', 'weapon4': '0.438', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon2': '1.342', 'weapon3': '1.464'} [2024-08-05 08:43:14,223][00149] DAMAGECOUNT value on done: 4081.0 [2024-08-05 08:43:14,224][00149] Sum rewards: -3.863, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.183', 'AMMO5': '0.003', 'AMMO2': '0.011', 'weapon5': '0.036', 'WEAPON5': '0.050', 'AMMO4': '0.057', 'ARMOR': '0.068', 'AMMO3': '0.150', 'WEAPON4': '0.150', 'HITCOUNT': '0.220', 'weapon4': '0.384', 'DAMAGECOUNT': '0.801', 'WEAPON3': '0.850', 'weapon2': '1.182', 'weapon3': '1.608', 'FRAGCOUNT': '3.000'} [2024-08-05 08:43:14,782][00149] DAMAGECOUNT value on done: 4087.0 [2024-08-05 08:43:15,859][00150] DAMAGECOUNT value on done: 3588.0 [2024-08-05 08:43:15,860][00150] Sum rewards: -0.369, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-0.830', 'AMMO5': '0.003', 'WEAPON1': '0.010', 'ARMOR': '0.013', 'AMMO2': '0.016', 'WEAPON5': '0.050', 'AMMO3': '0.077', 'AMMO4': '0.082', 'HITCOUNT': '0.110', 'weapon5': '0.110', 'WEAPON4': '0.400', 'WEAPON3': '0.500', 'weapon4': '0.594', 'DAMAGECOUNT': '0.798', 'weapon2': '0.900', 'FRAGCOUNT': '1.000', 'weapon3': '1.048'} [2024-08-05 08:43:16,471][00150] DAMAGECOUNT value on done: 4074.0 [2024-08-05 08:43:16,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 4497408. Throughput: 0: 905.1. Samples: 1124682. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:43:16,502][00035] Avg episode reward: [(0, '-3.861')] [2024-08-05 08:43:16,703][00147] DAMAGECOUNT value on done: 4604.0 [2024-08-05 08:43:16,703][00147] Sum rewards: 1.454, reward structure: {'DEATHCOUNT': '-4.500', 'HEALTH': '-0.502', 'AMMO5': '0.005', 'AMMO2': '0.006', 'AMMO4': '0.031', 'WEAPON4': '0.050', 'AMMO3': '0.092', 'WEAPON5': '0.100', 'weapon5': '0.120', 'weapon4': '0.210', 'HITCOUNT': '0.220', 'WEAPON3': '0.450', 'DAMAGECOUNT': '0.711', 'weapon2': '0.762', 'ARMOR': '0.857', 'weapon3': '1.342', 'FRAGCOUNT': '1.500'} [2024-08-05 08:43:17,116][00150] DAMAGECOUNT value on done: 4230.0 [2024-08-05 08:43:17,117][00150] Sum rewards: -2.338, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.261', 'AMMO4': '-0.013', 'AMMO2': '-0.002', 'AMMO5': '0.003', 'ARMOR': '0.036', 'WEAPON4': '0.050', 'WEAPON5': '0.050', 'weapon5': '0.064', 'AMMO3': '0.108', 'HITCOUNT': '0.150', 'weapon4': '0.190', 'WEAPON3': '0.550', 'FRAGCOUNT': '1.000', 'DAMAGECOUNT': '1.227', 'weapon2': '1.468', 'weapon3': '1.542'} [2024-08-05 08:43:17,226][00148] DAMAGECOUNT value on done: 4522.0 [2024-08-05 08:43:17,227][00148] Sum rewards: -2.289, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.743', 'AMMO2': '0.007', 'WEAPON1': '0.010', 'AMMO5': '0.013', 'AMMO4': '0.033', 'weapon5': '0.070', 'AMMO3': '0.126', 'weapon4': '0.134', 'WEAPON4': '0.150', 'WEAPON5': '0.200', 'HITCOUNT': '0.290', 'ARMOR': '0.480', 'WEAPON3': '0.800', 'weapon2': '1.226', 'DAMAGECOUNT': '1.680', 'weapon3': '1.736', 'FRAGCOUNT': '4.000'} [2024-08-05 08:43:17,263][00147] DAMAGECOUNT value on done: 3349.0 [2024-08-05 08:43:17,263][00147] Sum rewards: -9.287, reward structure: {'DEATHCOUNT': '-14.250', 'HEALTH': '-3.500', 'AMMO2': '0.003', 'WEAPON1': '0.010', 'AMMO5': '0.012', 'AMMO4': '0.017', 'weapon5': '0.114', 'AMMO3': '0.203', 'WEAPON5': '0.250', 'HITCOUNT': '0.260', 'DAMAGECOUNT': '1.053', 'weapon2': '1.228', 'WEAPON3': '1.250', 'FRAGCOUNT': '2.000', 'weapon3': '2.062'} [2024-08-05 08:43:17,677][00150] DAMAGECOUNT value on done: 4004.0 [2024-08-05 08:43:17,792][00148] DAMAGECOUNT value on done: 3050.0 [2024-08-05 08:43:17,792][00148] Sum rewards: -2.630, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.974', 'AMMO5': '0.003', 'AMMO2': '0.010', 'ARMOR': '0.016', 'weapon5': '0.018', 'AMMO4': '0.049', 'WEAPON5': '0.050', 'AMMO3': '0.103', 'HITCOUNT': '0.140', 'WEAPON4': '0.150', 'weapon4': '0.154', 'DAMAGECOUNT': '0.435', 'WEAPON3': '0.650', 'FRAGCOUNT': '1.000', 'weapon2': '1.032', 'weapon3': '2.034'} [2024-08-05 08:43:17,813][00147] DAMAGECOUNT value on done: 3322.0 [2024-08-05 08:43:17,814][00147] Sum rewards: -10.600, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-1.750', 'FRAGCOUNT': '-1.500', 'AMMO2': '0.006', 'ARMOR': '0.016', 'AMMO5': '0.018', 'AMMO4': '0.029', 'weapon4': '0.088', 'HITCOUNT': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.102', 'weapon5': '0.152', 'DAMAGECOUNT': '0.285', 'WEAPON5': '0.300', 'WEAPON3': '0.650', 'weapon3': '1.302', 'weapon2': '1.502'} [2024-08-05 08:43:18,351][00148] DAMAGECOUNT value on done: 3677.0 [2024-08-05 08:43:18,352][00148] Sum rewards: -5.407, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.817', 'AMMO5': '0.005', 'AMMO2': '0.005', 'AMMO4': '0.027', 'WEAPON5': '0.100', 'AMMO3': '0.173', 'HITCOUNT': '0.280', 'DAMAGECOUNT': '0.840', 'weapon2': '0.970', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.050', 'weapon3': '2.460'} [2024-08-05 08:43:18,465][00147] DAMAGECOUNT value on done: 4072.0 [2024-08-05 08:43:18,465][00147] Sum rewards: -7.201, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-2.700', 'weapon5': '0.002', 'AMMO5': '0.005', 'AMMO2': '0.007', 'AMMO4': '0.037', 'WEAPON5': '0.100', 'AMMO3': '0.217', 'HITCOUNT': '0.250', 'DAMAGECOUNT': '0.825', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.150', 'weapon2': '1.286', 'weapon3': '1.870'} [2024-08-05 08:43:18,746][00146] Updated weights for policy 0, policy_version 550 (0.0020) [2024-08-05 08:43:18,985][00148] DAMAGECOUNT value on done: 3390.0 [2024-08-05 08:43:18,986][00148] Sum rewards: -3.926, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.916', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.005', 'AMMO2': '-0.001', 'AMMO5': '0.005', 'ARMOR': '0.040', 'WEAPON4': '0.050', 'weapon5': '0.070', 'WEAPON5': '0.100', 'AMMO3': '0.123', 'HITCOUNT': '0.140', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.795', 'weapon2': '0.968', 'weapon3': '2.004'} [2024-08-05 08:43:21,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 4513792. Throughput: 0: 910.8. Samples: 1127308. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:43:21,502][00035] Avg episode reward: [(0, '-3.884')] [2024-08-05 08:43:26,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 4530176. Throughput: 0: 911.7. Samples: 1132894. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:43:26,502][00035] Avg episode reward: [(0, '-3.884')] [2024-08-05 08:43:31,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 4546560. Throughput: 0: 908.6. Samples: 1138310. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:43:31,502][00035] Avg episode reward: [(0, '-3.884')] [2024-08-05 08:43:36,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 4562944. Throughput: 0: 906.7. Samples: 1140992. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:43:36,504][00035] Avg episode reward: [(0, '-3.884')] [2024-08-05 08:43:41,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 4579328. Throughput: 0: 891.7. Samples: 1145996. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:43:41,502][00035] Avg episode reward: [(0, '-3.884')] [2024-08-05 08:43:41,574][00146] Updated weights for policy 0, policy_version 560 (0.0020) [2024-08-05 08:43:46,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 4603904. Throughput: 0: 892.2. Samples: 1151546. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:43:46,501][00035] Avg episode reward: [(0, '-3.884')] [2024-08-05 08:43:50,218][00149] DAMAGECOUNT value on done: 3556.0 [2024-08-05 08:43:50,219][00149] Sum rewards: -8.907, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-2.348', 'FRAGCOUNT': '-1.000', 'AMMO5': '0.005', 'AMMO2': '0.019', 'ARMOR': '0.036', 'weapon4': '0.054', 'weapon5': '0.062', 'AMMO4': '0.097', 'WEAPON5': '0.150', 'HITCOUNT': '0.160', 'AMMO3': '0.186', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.597', 'WEAPON3': '1.000', 'weapon2': '1.204', 'weapon3': '1.920'} [2024-08-05 08:43:50,820][00149] DAMAGECOUNT value on done: 3989.0 [2024-08-05 08:43:50,821][00149] Sum rewards: -1.741, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-0.879', 'AMMO5': '0.005', 'AMMO2': '0.012', 'WEAPON1': '0.020', 'weapon5': '0.038', 'AMMO4': '0.059', 'AMMO3': '0.080', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'ARMOR': '0.120', 'HITCOUNT': '0.190', 'weapon4': '0.220', 'WEAPON3': '0.400', 'DAMAGECOUNT': '0.516', 'weapon2': '0.934', 'FRAGCOUNT': '1.000', 'weapon3': '1.344'} [2024-08-05 08:43:51,360][00149] DAMAGECOUNT value on done: 4327.0 [2024-08-05 08:43:51,361][00149] Sum rewards: -1.492, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.784', 'AMMO2': '0.001', 'AMMO4': '0.005', 'WEAPON4': '0.050', 'weapon4': '0.072', 'AMMO3': '0.090', 'HITCOUNT': '0.260', 'ARMOR': '0.500', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.738', 'weapon3': '1.356', 'weapon2': '1.720', 'FRAGCOUNT': '3.000'} [2024-08-05 08:43:51,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 4620288. Throughput: 0: 893.2. Samples: 1154286. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:43:51,502][00035] Avg episode reward: [(0, '-3.840')] [2024-08-05 08:43:51,958][00149] DAMAGECOUNT value on done: 4367.0 [2024-08-05 08:43:52,782][00150] DAMAGECOUNT value on done: 3888.0 [2024-08-05 08:43:52,783][00150] Sum rewards: 0.363, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.025', 'AMMO5': '0.008', 'AMMO2': '0.012', 'AMMO4': '0.060', 'weapon5': '0.076', 'AMMO3': '0.111', 'WEAPON5': '0.150', 'HITCOUNT': '0.200', 'WEAPON4': '0.200', 'weapon4': '0.344', 'ARMOR': '0.540', 'WEAPON3': '0.700', 'weapon2': '0.892', 'DAMAGECOUNT': '0.900', 'weapon3': '1.944', 'FRAGCOUNT': '2.000'} [2024-08-05 08:43:53,351][00150] DAMAGECOUNT value on done: 4374.0 [2024-08-05 08:43:53,352][00150] Sum rewards: -3.762, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-2.018', 'AMMO2': '0.013', 'AMMO5': '0.020', 'AMMO4': '0.067', 'ARMOR': '0.068', 'weapon5': '0.094', 'AMMO3': '0.192', 'WEAPON4': '0.200', 'HITCOUNT': '0.230', 'WEAPON5': '0.250', 'weapon4': '0.418', 'WEAPON3': '0.900', 'DAMAGECOUNT': '0.900', 'weapon2': '1.152', 'weapon3': '1.502', 'FRAGCOUNT': '2.000'} [2024-08-05 08:43:53,932][00150] DAMAGECOUNT value on done: 4693.0 [2024-08-05 08:43:53,933][00150] Sum rewards: -0.586, reward structure: {'DEATHCOUNT': '-8.250', 'AMMO5': '0.005', 'HEALTH': '0.024', 'AMMO2': '0.028', 'ARMOR': '0.072', 'AMMO3': '0.094', 'WEAPON5': '0.100', 'weapon5': '0.120', 'AMMO4': '0.138', 'WEAPON4': '0.150', 'weapon4': '0.190', 'HITCOUNT': '0.240', 'WEAPON3': '0.500', 'weapon3': '0.958', 'DAMAGECOUNT': '1.389', 'weapon2': '1.656', 'FRAGCOUNT': '2.000'} [2024-08-05 08:43:54,471][00147] DAMAGECOUNT value on done: 4863.0 [2024-08-05 08:43:54,473][00147] Sum rewards: -0.864, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.884', 'AMMO5': '0.005', 'AMMO2': '0.015', 'ARMOR': '0.028', 'WEAPON4': '0.050', 'AMMO4': '0.075', 'weapon4': '0.104', 'AMMO3': '0.140', 'WEAPON5': '0.150', 'weapon5': '0.182', 'HITCOUNT': '0.190', 'WEAPON3': '0.750', 'DAMAGECOUNT': '0.777', 'weapon3': '1.242', 'weapon2': '1.562', 'FRAGCOUNT': '3.000'} [2024-08-05 08:43:54,535][00150] DAMAGECOUNT value on done: 4204.0 [2024-08-05 08:43:55,069][00147] DAMAGECOUNT value on done: 3609.0 [2024-08-05 08:43:55,070][00147] Sum rewards: -0.161, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.106', 'AMMO5': '0.012', 'AMMO2': '0.023', 'ARMOR': '0.032', 'weapon5': '0.078', 'AMMO3': '0.100', 'WEAPON4': '0.100', 'AMMO4': '0.114', 'WEAPON5': '0.200', 'HITCOUNT': '0.210', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.780', 'weapon2': '1.306', 'weapon3': '1.640', 'FRAGCOUNT': '3.000'} [2024-08-05 08:43:55,131][00148] DAMAGECOUNT value on done: 4617.0 [2024-08-05 08:43:55,132][00148] Sum rewards: -8.713, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.778', 'FRAGCOUNT': '-1.500', 'AMMO2': '0.002', 'AMMO5': '0.005', 'AMMO4': '0.008', 'ARMOR': '0.040', 'WEAPON5': '0.050', 'weapon5': '0.066', 'HITCOUNT': '0.080', 'weapon4': '0.096', 'WEAPON4': '0.150', 'AMMO3': '0.171', 'DAMAGECOUNT': '0.285', 'WEAPON3': '1.050', 'weapon2': '1.102', 'weapon3': '1.960'} [2024-08-05 08:43:55,660][00147] DAMAGECOUNT value on done: 3660.0 [2024-08-05 08:43:55,661][00147] Sum rewards: -4.455, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-0.939', 'AMMO5': '0.003', 'AMMO2': '0.011', 'ARMOR': '0.016', 'WEAPON4': '0.050', 'WEAPON5': '0.050', 'weapon5': '0.052', 'AMMO4': '0.056', 'weapon4': '0.090', 'AMMO3': '0.174', 'HITCOUNT': '0.220', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.014', 'weapon3': '1.452', 'weapon2': '1.496', 'FRAGCOUNT': '3.000'} [2024-08-05 08:43:55,689][00148] DAMAGECOUNT value on done: 3151.0 [2024-08-05 08:43:56,269][00147] DAMAGECOUNT value on done: 4284.0 [2024-08-05 08:43:56,270][00147] Sum rewards: -6.829, reward structure: {'DEATHCOUNT': '-10.500', 'FRAGCOUNT': '-1.500', 'HEALTH': '-0.275', 'AMMO5': '0.007', 'WEAPON1': '0.010', 'AMMO2': '0.050', 'ARMOR': '0.072', 'weapon5': '0.114', 'AMMO3': '0.117', 'WEAPON5': '0.150', 'HITCOUNT': '0.180', 'AMMO4': '0.252', 'WEAPON4': '0.350', 'WEAPON3': '0.550', 'weapon4': '0.560', 'DAMAGECOUNT': '0.636', 'weapon3': '1.138', 'weapon2': '1.260'} [2024-08-05 08:43:56,317][00148] DAMAGECOUNT value on done: 3848.0 [2024-08-05 08:43:56,318][00148] Sum rewards: -3.098, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.628', 'weapon5': '0.002', 'AMMO5': '0.005', 'AMMO2': '0.008', 'ARMOR': '0.032', 'AMMO4': '0.042', 'WEAPON5': '0.050', 'AMMO3': '0.157', 'HITCOUNT': '0.160', 'DAMAGECOUNT': '0.513', 'WEAPON3': '0.950', 'weapon2': '0.964', 'FRAGCOUNT': '2.000', 'weapon3': '2.396'} [2024-08-05 08:43:56,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 4636672. Throughput: 0: 896.8. Samples: 1159672. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:43:56,502][00035] Avg episode reward: [(0, '-3.910')] [2024-08-05 08:43:56,942][00148] DAMAGECOUNT value on done: 3615.0 [2024-08-05 08:43:56,943][00148] Sum rewards: -5.896, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.892', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.017', 'AMMO2': '-0.003', 'AMMO5': '0.010', 'ARMOR': '0.032', 'AMMO3': '0.139', 'weapon5': '0.150', 'WEAPON5': '0.200', 'HITCOUNT': '0.210', 'DAMAGECOUNT': '0.675', 'WEAPON3': '0.700', 'weapon2': '1.562', 'weapon3': '1.588'} [2024-08-05 08:44:01,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 4653056. Throughput: 0: 898.6. Samples: 1165120. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:44:01,501][00035] Avg episode reward: [(0, '-3.903')] [2024-08-05 08:44:04,115][00146] Updated weights for policy 0, policy_version 570 (0.0019) [2024-08-05 08:44:06,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 4677632. Throughput: 0: 900.8. Samples: 1167846. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:44:06,504][00035] Avg episode reward: [(0, '-3.903')] [2024-08-05 08:44:11,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 4694016. Throughput: 0: 887.0. Samples: 1172808. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:44:11,502][00035] Avg episode reward: [(0, '-3.903')] [2024-08-05 08:44:16,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 4710400. Throughput: 0: 889.0. Samples: 1178314. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:44:16,502][00035] Avg episode reward: [(0, '-3.903')] [2024-08-05 08:44:21,500][00035] Fps is (10 sec: 3276.7, 60 sec: 3549.8, 300 sec: 3610.0). Total num frames: 4726784. Throughput: 0: 890.3. Samples: 1181058. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:44:21,502][00035] Avg episode reward: [(0, '-3.903')] [2024-08-05 08:44:21,511][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000577_4726784.pth... [2024-08-05 08:44:21,615][00137] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000471_3858432.pth [2024-08-05 08:44:26,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 4743168. Throughput: 0: 900.6. Samples: 1186522. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:44:26,502][00035] Avg episode reward: [(0, '-3.903')] [2024-08-05 08:44:26,643][00149] DAMAGECOUNT value on done: 3624.0 [2024-08-05 08:44:27,198][00146] Updated weights for policy 0, policy_version 580 (0.0035) [2024-08-05 08:44:27,276][00149] DAMAGECOUNT value on done: 4154.0 [2024-08-05 08:44:27,812][00149] DAMAGECOUNT value on done: 4487.0 [2024-08-05 08:44:27,813][00149] Sum rewards: -4.131, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-2.241', 'AMMO2': '0.013', 'WEAPON4': '0.050', 'AMMO4': '0.065', 'ARMOR': '0.112', 'HITCOUNT': '0.150', 'AMMO3': '0.169', 'weapon4': '0.178', 'DAMAGECOUNT': '0.480', 'WEAPON3': '0.900', 'weapon2': '1.428', 'weapon3': '1.564', 'FRAGCOUNT': '2.000'} [2024-08-05 08:44:28,380][00149] DAMAGECOUNT value on done: 4612.0 [2024-08-05 08:44:28,381][00149] Sum rewards: -8.360, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-2.067', 'AMMO5': '0.003', 'AMMO2': '0.008', 'AMMO4': '0.040', 'ARMOR': '0.048', 'WEAPON5': '0.050', 'weapon5': '0.054', 'AMMO6': '0.100', 'WEAPON7': '0.100', 'AMMO7': '0.100', 'weapon4': '0.140', 'WEAPON4': '0.150', 'HITCOUNT': '0.190', 'AMMO3': '0.256', 'FRAGCOUNT': '0.500', 'weapon2': '0.722', 'DAMAGECOUNT': '0.735', 'WEAPON3': '1.150', 'weapon3': '2.112'} [2024-08-05 08:44:29,670][00150] DAMAGECOUNT value on done: 4128.0 [2024-08-05 08:44:29,671][00150] Sum rewards: -4.732, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.780', 'ARMOR': '0.004', 'AMMO5': '0.005', 'AMMO2': '0.012', 'AMMO4': '0.059', 'AMMO3': '0.164', 'WEAPON4': '0.200', 'weapon4': '0.214', 'HITCOUNT': '0.220', 'DAMAGECOUNT': '0.720', 'WEAPON3': '0.750', 'weapon2': '1.314', 'weapon3': '1.886', 'FRAGCOUNT': '2.000'} [2024-08-05 08:44:30,211][00150] DAMAGECOUNT value on done: 4419.0 [2024-08-05 08:44:30,212][00150] Sum rewards: -7.162, reward structure: {'DEATHCOUNT': '-9.000', 'FRAGCOUNT': '-1.500', 'HEALTH': '-1.134', 'AMMO4': '-0.025', 'AMMO2': '-0.005', 'AMMO5': '0.007', 'ARMOR': '0.032', 'HITCOUNT': '0.050', 'weapon5': '0.058', 'DAMAGECOUNT': '0.135', 'AMMO3': '0.139', 'WEAPON5': '0.150', 'WEAPON3': '0.700', 'weapon3': '1.580', 'weapon2': '1.650'} [2024-08-05 08:44:30,745][00150] DAMAGECOUNT value on done: 5078.0 [2024-08-05 08:44:30,746][00150] Sum rewards: -3.971, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.192', 'AMMO5': '0.003', 'weapon5': '0.018', 'AMMO2': '0.022', 'WEAPON1': '0.030', 'WEAPON5': '0.050', 'AMMO4': '0.109', 'AMMO3': '0.113', 'weapon4': '0.148', 'WEAPON4': '0.300', 'HITCOUNT': '0.360', 'ARMOR': '0.457', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.750', 'DAMAGECOUNT': '1.155', 'weapon2': '1.296', 'weapon3': '1.660'} [2024-08-05 08:44:31,337][00150] DAMAGECOUNT value on done: 4626.0 [2024-08-05 08:44:31,338][00150] Sum rewards: -2.532, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.933', 'AMMO5': '0.006', 'AMMO2': '0.019', 'WEAPON1': '0.020', 'ARMOR': '0.024', 'weapon7': '0.078', 'weapon5': '0.088', 'AMMO3': '0.094', 'AMMO4': '0.095', 'AMMO6': '0.100', 'AMMO7': '0.100', 'WEAPON7': '0.100', 'weapon4': '0.148', 'WEAPON4': '0.150', 'WEAPON5': '0.150', 'HITCOUNT': '0.290', 'WEAPON3': '0.600', 'weapon2': '0.996', 'FRAGCOUNT': '1.000', 'DAMAGECOUNT': '1.266', 'weapon3': '2.076'} [2024-08-05 08:44:31,500][00035] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 4759552. Throughput: 0: 899.4. Samples: 1192018. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:44:31,504][00035] Avg episode reward: [(0, '-4.104')] [2024-08-05 08:44:32,999][00147] DAMAGECOUNT value on done: 4953.0 [2024-08-05 08:44:33,000][00147] Sum rewards: -3.179, reward structure: {'DEATHCOUNT': '-6.750', 'FRAGCOUNT': '-0.500', 'HEALTH': '-0.020', 'AMMO5': '0.003', 'AMMO2': '0.020', 'ARMOR': '0.040', 'WEAPON5': '0.050', 'weapon5': '0.064', 'weapon4': '0.084', 'AMMO3': '0.089', 'HITCOUNT': '0.100', 'WEAPON4': '0.100', 'AMMO4': '0.101', 'DAMAGECOUNT': '0.270', 'WEAPON3': '0.400', 'weapon3': '1.106', 'weapon2': '1.664'} [2024-08-05 08:44:33,279][00148] DAMAGECOUNT value on done: 4766.0 [2024-08-05 08:44:33,280][00148] Sum rewards: -5.270, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.270', 'AMMO2': '0.005', 'AMMO4': '0.027', 'weapon4': '0.034', 'WEAPON4': '0.100', 'AMMO3': '0.113', 'HITCOUNT': '0.140', 'DAMAGECOUNT': '0.447', 'WEAPON3': '0.750', 'FRAGCOUNT': '1.000', 'weapon2': '1.314', 'weapon3': '1.820'} [2024-08-05 08:44:33,552][00147] DAMAGECOUNT value on done: 4000.0 [2024-08-05 08:44:33,553][00147] Sum rewards: 0.776, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.166', 'AMMO5': '0.009', 'AMMO2': '0.028', 'ARMOR': '0.100', 'AMMO3': '0.102', 'AMMO4': '0.137', 'WEAPON5': '0.200', 'weapon4': '0.210', 'weapon5': '0.224', 'HITCOUNT': '0.240', 'WEAPON4': '0.300', 'WEAPON3': '0.650', 'DAMAGECOUNT': '1.173', 'weapon2': '1.492', 'weapon3': '1.576', 'FRAGCOUNT': '3.000'} [2024-08-05 08:44:33,829][00148] DAMAGECOUNT value on done: 3548.0 [2024-08-05 08:44:33,829][00148] Sum rewards: 2.205, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-0.869', 'AMMO2': '0.005', 'weapon4': '0.022', 'AMMO4': '0.023', 'ARMOR': '0.028', 'AMMO3': '0.085', 'WEAPON4': '0.100', 'weapon7': '0.144', 'HITCOUNT': '0.310', 'AMMO6': '0.320', 'AMMO7': '0.320', 'WEAPON7': '0.400', 'WEAPON3': '0.550', 'DAMAGECOUNT': '1.191', 'weapon3': '1.224', 'weapon2': '1.602', 'FRAGCOUNT': '2.000'} [2024-08-05 08:44:34,150][00147] DAMAGECOUNT value on done: 3825.0 [2024-08-05 08:44:34,150][00147] Sum rewards: -6.761, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-2.085', 'AMMO5': '0.013', 'weapon5': '0.016', 'AMMO2': '0.018', 'weapon4': '0.062', 'ARMOR': '0.076', 'AMMO4': '0.089', 'HITCOUNT': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.206', 'WEAPON5': '0.250', 'DAMAGECOUNT': '0.495', 'WEAPON3': '1.150', 'weapon2': '1.294', 'FRAGCOUNT': '2.000', 'weapon3': '2.206'} [2024-08-05 08:44:34,458][00148] DAMAGECOUNT value on done: 4447.0 [2024-08-05 08:44:34,459][00148] Sum rewards: 1.513, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.691', 'AMMO5': '0.016', 'weapon7': '0.020', 'AMMO2': '0.037', 'AMMO3': '0.076', 'WEAPON4': '0.150', 'weapon5': '0.180', 'AMMO4': '0.186', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'weapon4': '0.212', 'HITCOUNT': '0.260', 'WEAPON5': '0.400', 'WEAPON3': '0.600', 'weapon2': '1.058', 'weapon3': '1.612', 'DAMAGECOUNT': '1.797', 'FRAGCOUNT': '4.000'} [2024-08-05 08:44:34,714][00147] DAMAGECOUNT value on done: 4569.0 [2024-08-05 08:44:34,715][00147] Sum rewards: -0.787, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.052', 'AMMO5': '0.005', 'AMMO2': '0.006', 'WEAPON1': '0.010', 'AMMO4': '0.031', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.113', 'weapon4': '0.228', 'HITCOUNT': '0.260', 'ARMOR': '0.416', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.855', 'FRAGCOUNT': '1.000', 'weapon3': '1.400', 'weapon2': '1.790'} [2024-08-05 08:44:35,025][00148] DAMAGECOUNT value on done: 4007.0 [2024-08-05 08:44:35,026][00148] Sum rewards: -2.892, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.288', 'AMMO2': '0.002', 'AMMO5': '0.007', 'AMMO4': '0.009', 'weapon4': '0.010', 'ARMOR': '0.052', 'WEAPON4': '0.100', 'AMMO3': '0.109', 'WEAPON5': '0.150', 'weapon5': '0.186', 'HITCOUNT': '0.190', 'WEAPON3': '0.650', 'DAMAGECOUNT': '1.176', 'weapon2': '1.254', 'FRAGCOUNT': '1.500', 'weapon3': '2.000'} [2024-08-05 08:44:36,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 4784128. Throughput: 0: 897.8. Samples: 1194686. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:44:36,503][00035] Avg episode reward: [(0, '-3.966')] [2024-08-05 08:44:41,506][00035] Fps is (10 sec: 4093.4, 60 sec: 3686.0, 300 sec: 3610.0). Total num frames: 4800512. Throughput: 0: 895.8. Samples: 1199988. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:44:41,508][00035] Avg episode reward: [(0, '-3.966')] [2024-08-05 08:44:46,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 4816896. Throughput: 0: 888.4. Samples: 1205098. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:44:46,501][00035] Avg episode reward: [(0, '-3.966')] [2024-08-05 08:44:50,171][00146] Updated weights for policy 0, policy_version 590 (0.0027) [2024-08-05 08:44:51,500][00035] Fps is (10 sec: 3278.9, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 4833280. Throughput: 0: 887.9. Samples: 1207802. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:44:51,502][00035] Avg episode reward: [(0, '-3.966')] [2024-08-05 08:44:56,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 4849664. Throughput: 0: 901.2. Samples: 1213360. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:44:56,502][00035] Avg episode reward: [(0, '-3.966')] [2024-08-05 08:45:01,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 4874240. Throughput: 0: 900.4. Samples: 1218832. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:45:01,502][00035] Avg episode reward: [(0, '-3.966')] [2024-08-05 08:45:03,245][00149] DAMAGECOUNT value on done: 3958.0 [2024-08-05 08:45:03,246][00149] Sum rewards: -0.626, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.378', 'AMMO5': '0.007', 'WEAPON1': '0.010', 'AMMO2': '0.017', 'ARMOR': '0.056', 'AMMO4': '0.083', 'AMMO3': '0.122', 'WEAPON5': '0.150', 'HITCOUNT': '0.270', 'WEAPON3': '0.750', 'DAMAGECOUNT': '1.002', 'weapon2': '1.214', 'weapon3': '2.070', 'FRAGCOUNT': '4.000'} [2024-08-05 08:45:03,848][00149] DAMAGECOUNT value on done: 4264.0 [2024-08-05 08:45:03,849][00149] Sum rewards: -3.102, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.960', 'AMMO2': '0.000', 'AMMO4': '0.000', 'AMMO5': '0.003', 'ARMOR': '0.036', 'WEAPON1': '0.040', 'WEAPON5': '0.050', 'HITCOUNT': '0.110', 'AMMO3': '0.113', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.330', 'weapon4': '0.372', 'WEAPON3': '0.800', 'weapon2': '1.286', 'weapon3': '1.668', 'FRAGCOUNT': '2.000'} [2024-08-05 08:45:04,404][00149] DAMAGECOUNT value on done: 4657.0 [2024-08-05 08:45:04,988][00149] DAMAGECOUNT value on done: 4927.0 [2024-08-05 08:45:04,989][00149] Sum rewards: -9.206, reward structure: {'DEATHCOUNT': '-14.250', 'HEALTH': '-3.344', 'AMMO2': '0.006', 'AMMO4': '0.030', 'ARMOR': '0.040', 'AMMO3': '0.182', 'WEAPON4': '0.250', 'HITCOUNT': '0.270', 'weapon4': '0.446', 'DAMAGECOUNT': '0.945', 'WEAPON3': '0.950', 'weapon3': '1.186', 'FRAGCOUNT': '2.000', 'weapon2': '2.082'} [2024-08-05 08:45:06,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 4890624. Throughput: 0: 899.5. Samples: 1221534. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:45:06,502][00035] Avg episode reward: [(0, '-4.007')] [2024-08-05 08:45:06,692][00150] DAMAGECOUNT value on done: 4228.0 [2024-08-05 08:45:06,694][00150] Sum rewards: -5.023, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.798', 'FRAGCOUNT': '-0.500', 'WEAPON1': '0.010', 'HITCOUNT': '0.010', 'AMMO5': '0.019', 'AMMO2': '0.031', 'ARMOR': '0.052', 'AMMO3': '0.145', 'AMMO4': '0.154', 'WEAPON4': '0.200', 'WEAPON5': '0.250', 'weapon4': '0.264', 'DAMAGECOUNT': '0.300', 'weapon5': '0.380', 'WEAPON3': '0.650', 'weapon3': '1.226', 'weapon2': '1.584'} [2024-08-05 08:45:07,244][00150] DAMAGECOUNT value on done: 4544.0 [2024-08-05 08:45:07,245][00150] Sum rewards: -2.450, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-0.512', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.005', 'WEAPON1': '0.010', 'AMMO2': '0.013', 'AMMO4': '0.064', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'weapon4': '0.104', 'HITCOUNT': '0.140', 'AMMO3': '0.151', 'weapon5': '0.198', 'DAMAGECOUNT': '0.375', 'ARMOR': '0.420', 'WEAPON3': '0.650', 'weapon2': '1.416', 'weapon3': '1.566'} [2024-08-05 08:45:07,801][00150] DAMAGECOUNT value on done: 5268.0 [2024-08-05 08:45:07,802][00150] Sum rewards: -2.746, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.089', 'AMMO4': '-0.026', 'AMMO2': '-0.005', 'ARMOR': '0.040', 'AMMO3': '0.104', 'HITCOUNT': '0.190', 'WEAPON4': '0.200', 'weapon4': '0.340', 'DAMAGECOUNT': '0.570', 'WEAPON3': '0.600', 'weapon3': '1.448', 'weapon2': '1.632', 'FRAGCOUNT': '3.000'} [2024-08-05 08:45:08,449][00150] DAMAGECOUNT value on done: 4761.0 [2024-08-05 08:45:08,450][00150] Sum rewards: -4.057, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.744', 'AMMO2': '0.007', 'WEAPON1': '0.010', 'AMMO4': '0.037', 'ARMOR': '0.112', 'HITCOUNT': '0.120', 'AMMO3': '0.172', 'DAMAGECOUNT': '0.405', 'WEAPON3': '0.850', 'FRAGCOUNT': '1.000', 'weapon2': '1.478', 'weapon3': '2.246'} [2024-08-05 08:45:11,004][00147] DAMAGECOUNT value on done: 5251.0 [2024-08-05 08:45:11,005][00147] Sum rewards: -7.718, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.264', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.027', 'AMMO2': '-0.005', 'AMMO5': '0.003', 'WEAPON5': '0.050', 'WEAPON4': '0.100', 'HITCOUNT': '0.110', 'weapon5': '0.110', 'AMMO3': '0.168', 'weapon4': '0.200', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.894', 'weapon3': '1.422', 'weapon2': '1.722'} [2024-08-05 08:45:11,402][00148] DAMAGECOUNT value on done: 4920.0 [2024-08-05 08:45:11,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 4907008. Throughput: 0: 899.4. Samples: 1226994. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:45:11,503][00035] Avg episode reward: [(0, '-4.065')] [2024-08-05 08:45:11,586][00147] DAMAGECOUNT value on done: 4290.0 [2024-08-05 08:45:11,587][00147] Sum rewards: -1.471, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.118', 'AMMO5': '0.010', 'AMMO2': '0.012', 'ARMOR': '0.016', 'AMMO4': '0.059', 'WEAPON4': '0.100', 'AMMO3': '0.116', 'weapon5': '0.196', 'WEAPON5': '0.200', 'HITCOUNT': '0.220', 'weapon4': '0.388', 'WEAPON3': '0.550', 'DAMAGECOUNT': '0.870', 'weapon2': '1.402', 'weapon3': '1.508', 'FRAGCOUNT': '3.000'} [2024-08-05 08:45:11,981][00148] DAMAGECOUNT value on done: 3803.0 [2024-08-05 08:45:11,982][00148] Sum rewards: -2.898, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.290', 'AMMO5': '0.005', 'weapon5': '0.010', 'AMMO2': '0.023', 'ARMOR': '0.036', 'WEAPON5': '0.100', 'AMMO4': '0.114', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.148', 'AMMO3': '0.167', 'WEAPON4': '0.200', 'WEAPON7': '0.200', 'HITCOUNT': '0.210', 'weapon4': '0.424', 'DAMAGECOUNT': '0.765', 'weapon2': '1.038', 'WEAPON3': '1.050', 'weapon3': '1.912', 'FRAGCOUNT': '3.000'} [2024-08-05 08:45:12,185][00147] DAMAGECOUNT value on done: 3938.0 [2024-08-05 08:45:12,722][00148] DAMAGECOUNT value on done: 4587.0 [2024-08-05 08:45:12,723][00148] Sum rewards: -1.566, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.980', 'AMMO5': '0.012', 'AMMO2': '0.024', 'weapon4': '0.028', 'weapon5': '0.064', 'WEAPON4': '0.100', 'AMMO4': '0.119', 'HITCOUNT': '0.140', 'AMMO3': '0.158', 'WEAPON5': '0.250', 'DAMAGECOUNT': '0.420', 'WEAPON3': '0.850', 'weapon2': '1.362', 'weapon3': '1.886', 'FRAGCOUNT': '4.000'} [2024-08-05 08:45:12,889][00147] DAMAGECOUNT value on done: 4664.0 [2024-08-05 08:45:13,072][00146] Updated weights for policy 0, policy_version 600 (0.0026) [2024-08-05 08:45:13,514][00148] DAMAGECOUNT value on done: 4213.0 [2024-08-05 08:45:13,515][00148] Sum rewards: -2.514, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.432', 'AMMO5': '0.007', 'AMMO2': '0.018', 'WEAPON1': '0.020', 'AMMO4': '0.088', 'ARMOR': '0.121', 'WEAPON5': '0.150', 'AMMO3': '0.159', 'HITCOUNT': '0.170', 'WEAPON4': '0.200', 'weapon4': '0.310', 'DAMAGECOUNT': '0.618', 'WEAPON3': '0.850', 'FRAGCOUNT': '1.000', 'weapon2': '1.216', 'weapon3': '1.990'} [2024-08-05 08:45:16,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 4923392. Throughput: 0: 887.7. Samples: 1231966. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:45:16,504][00035] Avg episode reward: [(0, '-3.966')] [2024-08-05 08:45:21,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 4939776. Throughput: 0: 887.8. Samples: 1234636. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:45:21,502][00035] Avg episode reward: [(0, '-3.966')] [2024-08-05 08:45:26,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 4956160. Throughput: 0: 893.7. Samples: 1240198. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:45:26,502][00035] Avg episode reward: [(0, '-3.966')] [2024-08-05 08:45:31,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 4980736. Throughput: 0: 901.6. Samples: 1245670. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:45:31,502][00035] Avg episode reward: [(0, '-3.966')] [2024-08-05 08:45:35,689][00146] Updated weights for policy 0, policy_version 610 (0.0026) [2024-08-05 08:45:36,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 4997120. Throughput: 0: 902.4. Samples: 1248412. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:45:36,501][00035] Avg episode reward: [(0, '-3.966')] [2024-08-05 08:45:40,011][00149] DAMAGECOUNT value on done: 4253.0 [2024-08-05 08:45:40,013][00149] Sum rewards: -2.581, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-2.204', 'AMMO2': '0.003', 'AMMO4': '0.015', 'AMMO3': '0.101', 'WEAPON4': '0.150', 'weapon4': '0.216', 'HITCOUNT': '0.260', 'ARMOR': '0.528', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.885', 'weapon2': '1.324', 'weapon3': '1.690', 'FRAGCOUNT': '2.000'} [2024-08-05 08:45:40,586][00149] DAMAGECOUNT value on done: 4374.0 [2024-08-05 08:45:40,587][00149] Sum rewards: -2.051, reward structure: {'DEATHCOUNT': '-6.750', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.005', 'weapon5': '0.016', 'AMMO2': '0.020', 'WEAPON4': '0.050', 'WEAPON5': '0.050', 'ARMOR': '0.072', 'AMMO3': '0.093', 'AMMO4': '0.099', 'HITCOUNT': '0.120', 'weapon4': '0.196', 'DAMAGECOUNT': '0.330', 'HEALTH': '0.394', 'WEAPON3': '0.500', 'weapon2': '1.450', 'weapon3': '1.804'} [2024-08-05 08:45:41,122][00149] DAMAGECOUNT value on done: 5012.0 [2024-08-05 08:45:41,123][00149] Sum rewards: 1.710, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.344', 'AMMO5': '0.007', 'weapon5': '0.010', 'AMMO2': '0.020', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO4': '0.100', 'AMMO3': '0.125', 'weapon4': '0.176', 'HITCOUNT': '0.220', 'WEAPON3': '0.650', 'DAMAGECOUNT': '1.065', 'weapon3': '1.464', 'weapon2': '1.516', 'FRAGCOUNT': '4.000'} [2024-08-05 08:45:41,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3550.2, 300 sec: 3610.0). Total num frames: 5013504. Throughput: 0: 900.4. Samples: 1253878. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:45:41,502][00035] Avg episode reward: [(0, '-3.832')] [2024-08-05 08:45:41,718][00149] DAMAGECOUNT value on done: 5108.0 [2024-08-05 08:45:41,718][00149] Sum rewards: -3.890, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.402', 'AMMO4': '-0.006', 'AMMO2': '-0.001', 'AMMO5': '0.010', 'weapon5': '0.028', 'WEAPON5': '0.050', 'ARMOR': '0.064', 'AMMO3': '0.148', 'HITCOUNT': '0.180', 'DAMAGECOUNT': '0.543', 'WEAPON3': '0.950', 'FRAGCOUNT': '1.000', 'weapon2': '1.374', 'weapon3': '2.172'} [2024-08-05 08:45:43,950][00150] DAMAGECOUNT value on done: 4251.0 [2024-08-05 08:45:44,685][00150] DAMAGECOUNT value on done: 4713.0 [2024-08-05 08:45:44,685][00150] Sum rewards: -2.595, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.519', 'ARMOR': '0.016', 'AMMO2': '0.030', 'weapon4': '0.040', 'AMMO3': '0.145', 'AMMO4': '0.151', 'HITCOUNT': '0.190', 'WEAPON4': '0.250', 'DAMAGECOUNT': '0.507', 'WEAPON3': '0.750', 'weapon2': '1.262', 'FRAGCOUNT': '2.000', 'weapon3': '2.332'} [2024-08-05 08:45:45,501][00150] DAMAGECOUNT value on done: 5369.0 [2024-08-05 08:45:45,503][00150] Sum rewards: -2.848, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.560', 'AMMO2': '0.000', 'AMMO4': '0.002', 'WEAPON1': '0.010', 'AMMO5': '0.015', 'weapon5': '0.094', 'HITCOUNT': '0.130', 'AMMO3': '0.186', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.303', 'WEAPON3': '0.850', 'FRAGCOUNT': '1.000', 'weapon2': '1.252', 'weapon3': '1.970'} [2024-08-05 08:45:46,147][00150] DAMAGECOUNT value on done: 5121.0 [2024-08-05 08:45:46,148][00150] Sum rewards: -3.921, reward structure: {'DEATHCOUNT': '-8.250', 'FRAGCOUNT': '-1.000', 'HEALTH': '-0.545', 'AMMO2': '0.006', 'AMMO5': '0.020', 'AMMO4': '0.028', 'ARMOR': '0.040', 'weapon5': '0.096', 'AMMO3': '0.130', 'HITCOUNT': '0.230', 'WEAPON5': '0.300', 'WEAPON3': '0.700', 'DAMAGECOUNT': '1.080', 'weapon2': '1.128', 'weapon3': '2.116'} [2024-08-05 08:45:46,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 5029888. Throughput: 0: 892.0. Samples: 1258974. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:45:46,502][00035] Avg episode reward: [(0, '-3.831')] [2024-08-05 08:45:49,187][00147] DAMAGECOUNT value on done: 5569.0 [2024-08-05 08:45:49,189][00147] Sum rewards: -2.869, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.622', 'AMMO5': '0.003', 'ARMOR': '0.004', 'weapon5': '0.012', 'AMMO2': '0.023', 'weapon4': '0.044', 'WEAPON5': '0.050', 'AMMO4': '0.113', 'AMMO3': '0.134', 'WEAPON4': '0.150', 'HITCOUNT': '0.270', 'WEAPON3': '0.750', 'DAMAGECOUNT': '0.954', 'weapon3': '1.574', 'weapon2': '1.672', 'FRAGCOUNT': '2.000'} [2024-08-05 08:45:49,318][00148] DAMAGECOUNT value on done: 5155.0 [2024-08-05 08:45:49,817][00147] DAMAGECOUNT value on done: 4457.0 [2024-08-05 08:45:49,817][00147] Sum rewards: -1.762, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.858', 'AMMO4': '-0.014', 'AMMO2': '-0.003', 'AMMO5': '0.010', 'weapon4': '0.020', 'weapon5': '0.022', 'WEAPON4': '0.050', 'AMMO3': '0.100', 'WEAPON5': '0.100', 'HITCOUNT': '0.170', 'DAMAGECOUNT': '0.501', 'ARMOR': '0.508', 'WEAPON3': '0.550', 'FRAGCOUNT': '1.000', 'weapon2': '1.754', 'weapon3': '1.828'} [2024-08-05 08:45:49,920][00148] DAMAGECOUNT value on done: 4113.0 [2024-08-05 08:45:50,390][00147] DAMAGECOUNT value on done: 4280.0 [2024-08-05 08:45:50,391][00147] Sum rewards: 1.820, reward structure: {'DEATHCOUNT': '-6.000', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'AMMO2': '0.037', 'ARMOR': '0.076', 'weapon5': '0.084', 'AMMO3': '0.099', 'WEAPON4': '0.100', 'WEAPON5': '0.150', 'AMMO4': '0.187', 'HITCOUNT': '0.230', 'HEALTH': '0.396', 'weapon4': '0.460', 'WEAPON3': '0.500', 'weapon2': '0.812', 'DAMAGECOUNT': '1.026', 'weapon3': '1.632', 'FRAGCOUNT': '2.000'} [2024-08-05 08:45:50,498][00148] DAMAGECOUNT value on done: 4657.0 [2024-08-05 08:45:50,969][00147] DAMAGECOUNT value on done: 4909.0 [2024-08-05 08:45:50,969][00147] Sum rewards: -1.112, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-0.720', 'AMMO5': '0.005', 'AMMO2': '0.009', 'AMMO4': '0.043', 'WEAPON5': '0.050', 'AMMO3': '0.082', 'weapon7': '0.092', 'weapon5': '0.096', 'AMMO6': '0.100', 'AMMO7': '0.100', 'WEAPON7': '0.100', 'HITCOUNT': '0.190', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.735', 'FRAGCOUNT': '1.000', 'weapon2': '1.088', 'weapon3': '1.318'} [2024-08-05 08:45:51,063][00148] DAMAGECOUNT value on done: 4353.0 [2024-08-05 08:45:51,064][00148] Sum rewards: -4.016, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-2.227', 'AMMO5': '0.007', 'AMMO2': '0.012', 'weapon5': '0.024', 'AMMO4': '0.060', 'HITCOUNT': '0.110', 'AMMO3': '0.129', 'ARMOR': '0.134', 'WEAPON4': '0.150', 'WEAPON5': '0.150', 'weapon4': '0.224', 'DAMAGECOUNT': '0.420', 'WEAPON3': '0.950', 'FRAGCOUNT': '1.000', 'weapon2': '1.014', 'weapon3': '2.076'} [2024-08-05 08:45:51,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 5046272. Throughput: 0: 893.0. Samples: 1261720. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:45:51,502][00035] Avg episode reward: [(0, '-3.588')] [2024-08-05 08:45:51,511][00137] Saving new best policy, reward=-3.588! [2024-08-05 08:45:56,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 5070848. Throughput: 0: 891.3. Samples: 1267104. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:45:56,504][00035] Avg episode reward: [(0, '-3.588')] [2024-08-05 08:45:58,569][00146] Updated weights for policy 0, policy_version 620 (0.0019) [2024-08-05 08:46:01,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 5087232. Throughput: 0: 904.0. Samples: 1272648. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:46:01,502][00035] Avg episode reward: [(0, '-3.588')] [2024-08-05 08:46:06,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 5103616. Throughput: 0: 907.4. Samples: 1275470. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:46:06,502][00035] Avg episode reward: [(0, '-3.588')] [2024-08-05 08:46:11,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 5120000. Throughput: 0: 902.8. Samples: 1280824. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:46:11,502][00035] Avg episode reward: [(0, '-3.588')] [2024-08-05 08:46:16,504][00035] Fps is (10 sec: 3275.4, 60 sec: 3549.6, 300 sec: 3610.0). Total num frames: 5136384. Throughput: 0: 901.7. Samples: 1286252. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:46:16,508][00035] Avg episode reward: [(0, '-3.588')] [2024-08-05 08:46:17,143][00149] DAMAGECOUNT value on done: 4383.0 [2024-08-05 08:46:17,143][00149] Sum rewards: -5.805, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.060', 'AMMO5': '0.005', 'weapon5': '0.008', 'WEAPON1': '0.020', 'AMMO2': '0.031', 'WEAPON5': '0.050', 'HITCOUNT': '0.140', 'AMMO4': '0.153', 'AMMO3': '0.176', 'weapon4': '0.192', 'WEAPON4': '0.250', 'DAMAGECOUNT': '0.390', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.050', 'weapon2': '1.448', 'weapon3': '1.842'} [2024-08-05 08:46:17,891][00149] DAMAGECOUNT value on done: 4544.0 [2024-08-05 08:46:17,892][00149] Sum rewards: -6.474, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.524', 'FRAGCOUNT': '-0.500', 'AMMO2': '0.010', 'AMMO5': '0.019', 'AMMO4': '0.048', 'WEAPON4': '0.100', 'HITCOUNT': '0.150', 'AMMO3': '0.161', 'weapon4': '0.198', 'weapon5': '0.204', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.510', 'WEAPON3': '0.750', 'weapon3': '1.360', 'weapon2': '1.490'} [2024-08-05 08:46:18,461][00149] DAMAGECOUNT value on done: 5201.0 [2024-08-05 08:46:19,017][00149] DAMAGECOUNT value on done: 5393.0 [2024-08-05 08:46:19,019][00149] Sum rewards: -5.035, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-1.152', 'AMMO5': '0.007', 'AMMO2': '0.020', 'weapon5': '0.058', 'AMMO4': '0.099', 'WEAPON5': '0.150', 'WEAPON4': '0.150', 'AMMO3': '0.191', 'weapon4': '0.208', 'HITCOUNT': '0.220', 'ARMOR': '0.490', 'weapon2': '0.556', 'DAMAGECOUNT': '0.855', 'WEAPON3': '1.200', 'FRAGCOUNT': '1.500', 'weapon3': '2.412'} [2024-08-05 08:46:21,215][00150] DAMAGECOUNT value on done: 4501.0 [2024-08-05 08:46:21,216][00150] Sum rewards: -3.649, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-0.878', 'AMMO5': '0.010', 'AMMO2': '0.014', 'weapon5': '0.030', 'ARMOR': '0.052', 'AMMO4': '0.070', 'WEAPON5': '0.100', 'WEAPON4': '0.150', 'AMMO3': '0.156', 'HITCOUNT': '0.200', 'weapon4': '0.234', 'DAMAGECOUNT': '0.750', 'WEAPON3': '0.800', 'weapon2': '1.250', 'weapon3': '1.912', 'FRAGCOUNT': '2.000'} [2024-08-05 08:46:21,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 5152768. Throughput: 0: 891.4. Samples: 1288526. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:46:21,504][00035] Avg episode reward: [(0, '-3.771')] [2024-08-05 08:46:21,513][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000629_5152768.pth... [2024-08-05 08:46:21,634][00137] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000524_4292608.pth [2024-08-05 08:46:21,724][00146] Updated weights for policy 0, policy_version 630 (0.0023) [2024-08-05 08:46:21,867][00150] DAMAGECOUNT value on done: 4948.0 [2024-08-05 08:46:21,868][00150] Sum rewards: -5.596, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.716', 'FRAGCOUNT': '-1.000', 'AMMO2': '0.008', 'AMMO5': '0.010', 'WEAPON1': '0.010', 'AMMO4': '0.038', 'WEAPON4': '0.100', 'weapon5': '0.118', 'WEAPON5': '0.150', 'HITCOUNT': '0.160', 'AMMO3': '0.171', 'weapon4': '0.206', 'ARMOR': '0.540', 'DAMAGECOUNT': '0.705', 'WEAPON3': '0.950', 'weapon2': '1.384', 'weapon3': '1.570'} [2024-08-05 08:46:22,390][00150] DAMAGECOUNT value on done: 5760.0 [2024-08-05 08:46:22,392][00150] Sum rewards: -5.605, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-1.920', 'AMMO5': '0.005', 'WEAPON1': '0.010', 'AMMO2': '0.019', 'WEAPON5': '0.050', 'ARMOR': '0.072', 'weapon4': '0.074', 'AMMO4': '0.095', 'HITCOUNT': '0.130', 'AMMO3': '0.169', 'WEAPON4': '0.200', 'weapon5': '0.212', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.164', 'weapon3': '1.548', 'weapon2': '1.666', 'FRAGCOUNT': '2.000'} [2024-08-05 08:46:22,947][00150] DAMAGECOUNT value on done: 5566.0 [2024-08-05 08:46:26,500][00035] Fps is (10 sec: 4097.8, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 5177344. Throughput: 0: 892.3. Samples: 1294032. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:46:26,502][00035] Avg episode reward: [(0, '-3.831')] [2024-08-05 08:46:27,134][00147] DAMAGECOUNT value on done: 5791.0 [2024-08-05 08:46:27,135][00147] Sum rewards: -6.795, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-2.665', 'AMMO4': '-0.013', 'AMMO2': '-0.002', 'ARMOR': '0.040', 'HITCOUNT': '0.190', 'AMMO3': '0.199', 'DAMAGECOUNT': '0.666', 'WEAPON3': '1.100', 'weapon3': '1.694', 'weapon2': '1.746', 'FRAGCOUNT': '3.000'} [2024-08-05 08:46:27,478][00148] DAMAGECOUNT value on done: 5515.0 [2024-08-05 08:46:27,479][00148] Sum rewards: 1.588, reward structure: {'DEATHCOUNT': '-7.500', 'weapon4': '0.012', 'AMMO2': '0.014', 'ARMOR': '0.028', 'WEAPON4': '0.050', 'AMMO4': '0.072', 'AMMO3': '0.122', 'HITCOUNT': '0.230', 'WEAPON3': '0.500', 'HEALTH': '0.736', 'DAMAGECOUNT': '1.080', 'weapon2': '1.188', 'weapon3': '2.056', 'FRAGCOUNT': '3.000'} [2024-08-05 08:46:27,701][00147] DAMAGECOUNT value on done: 5011.0 [2024-08-05 08:46:27,702][00147] Sum rewards: -6.491, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-2.200', 'AMMO5': '0.010', 'AMMO2': '0.026', 'ARMOR': '0.052', 'weapon5': '0.076', 'AMMO4': '0.132', 'WEAPON5': '0.150', 'AMMO3': '0.169', 'WEAPON4': '0.300', 'HITCOUNT': '0.430', 'weapon4': '0.456', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.950', 'weapon2': '1.232', 'weapon3': '1.564', 'DAMAGECOUNT': '1.662'} [2024-08-05 08:46:28,059][00148] DAMAGECOUNT value on done: 4448.0 [2024-08-05 08:46:28,060][00148] Sum rewards: -1.272, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.187', 'weapon4': '0.002', 'AMMO5': '0.007', 'ARMOR': '0.008', 'AMMO2': '0.012', 'weapon5': '0.026', 'WEAPON4': '0.050', 'AMMO4': '0.057', 'AMMO3': '0.127', 'WEAPON5': '0.150', 'HITCOUNT': '0.220', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.005', 'weapon2': '1.210', 'weapon3': '1.990', 'FRAGCOUNT': '4.000'} [2024-08-05 08:46:28,256][00147] DAMAGECOUNT value on done: 4493.0 [2024-08-05 08:46:28,256][00147] Sum rewards: -9.011, reward structure: {'DEATHCOUNT': '-14.250', 'HEALTH': '-1.762', 'AMMO5': '0.005', 'AMMO2': '0.008', 'AMMO4': '0.038', 'ARMOR': '0.056', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'weapon4': '0.144', 'weapon5': '0.158', 'HITCOUNT': '0.190', 'AMMO3': '0.207', 'DAMAGECOUNT': '0.639', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.150', 'weapon2': '1.426', 'weapon3': '1.780'} [2024-08-05 08:46:28,670][00148] DAMAGECOUNT value on done: 4847.0 [2024-08-05 08:46:28,670][00148] Sum rewards: -6.802, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-2.165', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.028', 'AMMO2': '-0.006', 'weapon5': '0.010', 'AMMO5': '0.019', 'ARMOR': '0.040', 'HITCOUNT': '0.180', 'AMMO3': '0.197', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.570', 'WEAPON3': '0.800', 'weapon3': '1.466', 'weapon2': '2.164'} [2024-08-05 08:46:28,822][00147] DAMAGECOUNT value on done: 5112.0 [2024-08-05 08:46:28,822][00147] Sum rewards: -6.553, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.820', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.000', 'AMMO2': '-0.000', 'AMMO5': '0.009', 'WEAPON1': '0.020', 'WEAPON4': '0.050', 'weapon4': '0.050', 'ARMOR': '0.080', 'WEAPON5': '0.150', 'HITCOUNT': '0.160', 'AMMO3': '0.181', 'weapon5': '0.250', 'DAMAGECOUNT': '0.609', 'WEAPON3': '0.950', 'weapon2': '1.224', 'weapon3': '1.784'} [2024-08-05 08:46:29,240][00148] DAMAGECOUNT value on done: 4778.0 [2024-08-05 08:46:29,241][00148] Sum rewards: -0.516, reward structure: {'DEATHCOUNT': '-9.750', 'AMMO5': '0.010', 'WEAPON1': '0.010', 'AMMO2': '0.011', 'weapon5': '0.026', 'ARMOR': '0.040', 'AMMO4': '0.054', 'AMMO3': '0.170', 'WEAPON5': '0.200', 'HITCOUNT': '0.330', 'WEAPON3': '0.750', 'weapon2': '0.952', 'HEALTH': '1.034', 'DAMAGECOUNT': '1.275', 'FRAGCOUNT': '2.000', 'weapon3': '2.372'} [2024-08-05 08:46:31,501][00035] Fps is (10 sec: 4095.7, 60 sec: 3549.8, 300 sec: 3610.0). Total num frames: 5193728. Throughput: 0: 900.4. Samples: 1299494. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:46:31,502][00035] Avg episode reward: [(0, '-3.842')] [2024-08-05 08:46:36,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 5210112. Throughput: 0: 901.9. Samples: 1302306. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:46:36,504][00035] Avg episode reward: [(0, '-3.842')] [2024-08-05 08:46:41,500][00035] Fps is (10 sec: 3277.0, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 5226496. Throughput: 0: 902.9. Samples: 1307736. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:46:41,502][00035] Avg episode reward: [(0, '-3.842')] [2024-08-05 08:46:43,862][00146] Updated weights for policy 0, policy_version 640 (0.0021) [2024-08-05 08:46:46,500][00035] Fps is (10 sec: 4095.9, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 5251072. Throughput: 0: 900.2. Samples: 1313156. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:46:46,502][00035] Avg episode reward: [(0, '-3.842')] [2024-08-05 08:46:51,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 5267456. Throughput: 0: 890.5. Samples: 1315544. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:46:51,502][00035] Avg episode reward: [(0, '-3.842')] [2024-08-05 08:46:54,386][00149] DAMAGECOUNT value on done: 4731.0 [2024-08-05 08:46:54,386][00149] Sum rewards: -0.690, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.210', 'AMMO4': '-0.003', 'AMMO2': '-0.001', 'AMMO3': '0.078', 'HITCOUNT': '0.220', 'WEAPON3': '0.400', 'DAMAGECOUNT': '1.044', 'weapon3': '1.162', 'weapon2': '1.870', 'FRAGCOUNT': '4.000'} [2024-08-05 08:46:54,937][00149] DAMAGECOUNT value on done: 4639.0 [2024-08-05 08:46:54,938][00149] Sum rewards: -12.085, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-2.790', 'FRAGCOUNT': '-1.500', 'weapon4': '0.010', 'AMMO2': '0.012', 'AMMO5': '0.012', 'WEAPON1': '0.020', 'weapon5': '0.032', 'ARMOR': '0.036', 'AMMO4': '0.058', 'HITCOUNT': '0.100', 'WEAPON4': '0.100', 'WEAPON5': '0.150', 'AMMO3': '0.242', 'DAMAGECOUNT': '0.285', 'WEAPON3': '1.400', 'weapon2': '1.412', 'weapon3': '1.836'} [2024-08-05 08:46:55,497][00149] DAMAGECOUNT value on done: 5445.0 [2024-08-05 08:46:55,498][00149] Sum rewards: -7.886, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-2.616', 'AMMO5': '0.005', 'AMMO2': '0.014', 'ARMOR': '0.064', 'AMMO4': '0.068', 'WEAPON5': '0.100', 'weapon5': '0.132', 'AMMO3': '0.145', 'HITCOUNT': '0.150', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.732', 'WEAPON3': '0.850', 'weapon3': '1.380', 'weapon2': '1.840'} [2024-08-05 08:46:56,090][00149] DAMAGECOUNT value on done: 5483.0 [2024-08-05 08:46:56,091][00149] Sum rewards: -5.471, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-2.750', 'AMMO5': '0.005', 'AMMO2': '0.020', 'ARMOR': '0.028', 'weapon4': '0.050', 'HITCOUNT': '0.080', 'AMMO4': '0.099', 'AMMO3': '0.145', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.270', 'WEAPON3': '0.900', 'weapon2': '1.380', 'weapon3': '1.852', 'FRAGCOUNT': '2.000'} [2024-08-05 08:46:56,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.1). Total num frames: 5283840. Throughput: 0: 891.2. Samples: 1320928. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:46:56,502][00035] Avg episode reward: [(0, '-3.995')] [2024-08-05 08:46:58,141][00150] DAMAGECOUNT value on done: 4673.0 [2024-08-05 08:46:58,142][00150] Sum rewards: 1.782, reward structure: {'DEATHCOUNT': '-4.500', 'HEALTH': '-0.958', 'AMMO2': '0.005', 'AMMO5': '0.012', 'AMMO4': '0.027', 'AMMO3': '0.084', 'weapon5': '0.134', 'HITCOUNT': '0.180', 'WEAPON4': '0.200', 'WEAPON5': '0.250', 'weapon4': '0.252', 'WEAPON3': '0.500', 'ARMOR': '0.511', 'DAMAGECOUNT': '0.516', 'weapon2': '0.966', 'weapon3': '1.602', 'FRAGCOUNT': '2.000'} [2024-08-05 08:46:58,749][00150] DAMAGECOUNT value on done: 5094.0 [2024-08-05 08:46:59,310][00150] DAMAGECOUNT value on done: 5930.0 [2024-08-05 08:46:59,311][00150] Sum rewards: -3.839, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-0.199', 'ARMOR': '0.004', 'AMMO2': '0.012', 'weapon5': '0.016', 'AMMO5': '0.018', 'AMMO4': '0.059', 'AMMO3': '0.172', 'HITCOUNT': '0.190', 'WEAPON5': '0.350', 'DAMAGECOUNT': '0.510', 'WEAPON3': '0.950', 'weapon2': '1.286', 'FRAGCOUNT': '2.000', 'weapon3': '2.044'} [2024-08-05 08:46:59,877][00150] DAMAGECOUNT value on done: 5855.0 [2024-08-05 08:46:59,881][00150] Sum rewards: -1.543, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.914', 'AMMO4': '-0.002', 'AMMO2': '-0.000', 'AMMO5': '0.003', 'weapon5': '0.004', 'ARMOR': '0.044', 'WEAPON5': '0.050', 'WEAPON4': '0.050', 'weapon4': '0.118', 'AMMO3': '0.127', 'HITCOUNT': '0.210', 'WEAPON3': '0.850', 'DAMAGECOUNT': '0.867', 'weapon2': '1.142', 'FRAGCOUNT': '2.000', 'weapon3': '2.158'} [2024-08-05 08:47:01,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 5300224. Throughput: 0: 890.5. Samples: 1326320. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:47:01,504][00035] Avg episode reward: [(0, '-3.879')] [2024-08-05 08:47:04,519][00147] DAMAGECOUNT value on done: 6171.0 [2024-08-05 08:47:04,520][00147] Sum rewards: -3.711, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.339', 'AMMO2': '0.005', 'AMMO5': '0.013', 'AMMO4': '0.024', 'ARMOR': '0.040', 'AMMO3': '0.100', 'WEAPON4': '0.100', 'weapon4': '0.120', 'WEAPON5': '0.150', 'weapon5': '0.192', 'HITCOUNT': '0.400', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.700', 'DAMAGECOUNT': '1.140', 'weapon2': '1.344', 'weapon3': '1.800'} [2024-08-05 08:47:05,129][00147] DAMAGECOUNT value on done: 5293.0 [2024-08-05 08:47:05,130][00147] Sum rewards: -4.708, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-0.887', 'AMMO4': '-0.007', 'AMMO2': '-0.001', 'AMMO5': '0.005', 'ARMOR': '0.032', 'WEAPON5': '0.050', 'weapon5': '0.058', 'AMMO3': '0.140', 'HITCOUNT': '0.160', 'WEAPON3': '0.550', 'DAMAGECOUNT': '0.846', 'FRAGCOUNT': '1.500', 'weapon2': '1.548', 'weapon3': '1.798'} [2024-08-05 08:47:05,534][00148] DAMAGECOUNT value on done: 5590.0 [2024-08-05 08:47:05,666][00147] DAMAGECOUNT value on done: 4718.0 [2024-08-05 08:47:05,667][00147] Sum rewards: 0.202, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.685', 'AMMO5': '0.010', 'AMMO2': '0.020', 'ARMOR': '0.048', 'AMMO3': '0.095', 'weapon5': '0.096', 'AMMO4': '0.099', 'WEAPON4': '0.100', 'weapon4': '0.140', 'HITCOUNT': '0.190', 'WEAPON5': '0.200', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.675', 'weapon2': '1.532', 'weapon3': '1.582', 'FRAGCOUNT': '3.000'} [2024-08-05 08:47:06,095][00148] DAMAGECOUNT value on done: 4633.0 [2024-08-05 08:47:06,096][00148] Sum rewards: -5.790, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.476', 'AMMO2': '0.007', 'AMMO4': '0.032', 'AMMO3': '0.162', 'WEAPON4': '0.200', 'HITCOUNT': '0.200', 'weapon4': '0.274', 'ARMOR': '0.520', 'DAMAGECOUNT': '0.555', 'weapon2': '0.878', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon3': '2.108'} [2024-08-05 08:47:06,236][00147] DAMAGECOUNT value on done: 5246.0 [2024-08-05 08:47:06,237][00147] Sum rewards: -2.552, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.814', 'AMMO5': '0.005', 'AMMO2': '0.018', 'ARMOR': '0.044', 'weapon5': '0.066', 'AMMO4': '0.091', 'WEAPON5': '0.100', 'AMMO3': '0.122', 'HITCOUNT': '0.140', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.402', 'WEAPON3': '0.450', 'weapon4': '0.612', 'FRAGCOUNT': '1.000', 'weapon3': '1.100', 'weapon2': '1.312'} [2024-08-05 08:47:06,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 5316608. Throughput: 0: 902.2. Samples: 1329126. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:47:06,502][00035] Avg episode reward: [(0, '-3.932')] [2024-08-05 08:47:06,690][00148] DAMAGECOUNT value on done: 4966.0 [2024-08-05 08:47:06,691][00148] Sum rewards: -5.855, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.233', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.002', 'AMMO2': '-0.000', 'AMMO5': '0.003', 'weapon5': '0.014', 'ARMOR': '0.040', 'WEAPON5': '0.050', 'HITCOUNT': '0.060', 'AMMO3': '0.151', 'DAMAGECOUNT': '0.357', 'WEAPON3': '0.850', 'weapon2': '1.282', 'weapon3': '2.074'} [2024-08-05 08:47:07,163][00146] Updated weights for policy 0, policy_version 650 (0.0023) [2024-08-05 08:47:07,340][00148] DAMAGECOUNT value on done: 4923.0 [2024-08-05 08:47:07,340][00148] Sum rewards: -2.485, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.628', 'AMMO4': '-0.019', 'AMMO2': '-0.004', 'AMMO5': '0.003', 'WEAPON1': '0.020', 'weapon5': '0.044', 'WEAPON4': '0.050', 'weapon4': '0.062', 'ARMOR': '0.090', 'WEAPON5': '0.100', 'AMMO3': '0.106', 'HITCOUNT': '0.130', 'DAMAGECOUNT': '0.435', 'WEAPON3': '0.500', 'FRAGCOUNT': '1.000', 'weapon2': '1.550', 'weapon3': '1.576'} [2024-08-05 08:47:11,500][00035] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 5332992. Throughput: 0: 900.3. Samples: 1334544. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:47:11,502][00035] Avg episode reward: [(0, '-3.936')] [2024-08-05 08:47:16,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.7, 300 sec: 3610.0). Total num frames: 5357568. Throughput: 0: 900.3. Samples: 1340008. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:47:16,502][00035] Avg episode reward: [(0, '-3.936')] [2024-08-05 08:47:21,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 5373952. Throughput: 0: 898.9. Samples: 1342756. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:47:21,502][00035] Avg episode reward: [(0, '-3.936')] [2024-08-05 08:47:26,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 5390336. Throughput: 0: 891.6. Samples: 1347856. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:47:26,502][00035] Avg episode reward: [(0, '-3.936')] [2024-08-05 08:47:29,762][00146] Updated weights for policy 0, policy_version 660 (0.0021) [2024-08-05 08:47:31,028][00149] DAMAGECOUNT value on done: 4824.0 [2024-08-05 08:47:31,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 5406720. Throughput: 0: 895.1. Samples: 1353436. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:47:31,502][00035] Avg episode reward: [(0, '-3.876')] [2024-08-05 08:47:31,566][00149] DAMAGECOUNT value on done: 4963.0 [2024-08-05 08:47:31,567][00149] Sum rewards: -0.012, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.992', 'ARMOR': '0.020', 'AMMO2': '0.025', 'weapon7': '0.084', 'AMMO6': '0.100', 'AMMO7': '0.100', 'WEAPON7': '0.100', 'AMMO4': '0.124', 'WEAPON4': '0.150', 'AMMO3': '0.151', 'weapon4': '0.208', 'HITCOUNT': '0.260', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.972', 'weapon2': '1.364', 'weapon3': '1.522', 'FRAGCOUNT': '4.000'} [2024-08-05 08:47:32,177][00149] DAMAGECOUNT value on done: 5524.0 [2024-08-05 08:47:32,179][00149] Sum rewards: -5.870, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.017', 'AMMO4': '-0.048', 'AMMO2': '-0.010', 'ARMOR': '0.048', 'HITCOUNT': '0.080', 'WEAPON4': '0.100', 'weapon4': '0.122', 'AMMO3': '0.197', 'DAMAGECOUNT': '0.237', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.200', 'weapon2': '1.318', 'weapon3': '1.902'} [2024-08-05 08:47:32,715][00149] DAMAGECOUNT value on done: 5691.0 [2024-08-05 08:47:32,717][00149] Sum rewards: -4.656, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.091', 'AMMO5': '0.007', 'AMMO2': '0.015', 'WEAPON1': '0.020', 'ARMOR': '0.044', 'weapon5': '0.052', 'AMMO4': '0.072', 'WEAPON5': '0.100', 'weapon4': '0.106', 'AMMO3': '0.149', 'WEAPON4': '0.150', 'HITCOUNT': '0.190', 'DAMAGECOUNT': '0.624', 'WEAPON3': '0.900', 'weapon2': '1.070', 'FRAGCOUNT': '2.000', 'weapon3': '2.186'} [2024-08-05 08:47:34,769][00150] DAMAGECOUNT value on done: 4823.0 [2024-08-05 08:47:34,770][00150] Sum rewards: -6.720, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.500', 'weapon5': '0.002', 'AMMO5': '0.005', 'AMMO2': '0.012', 'WEAPON1': '0.020', 'ARMOR': '0.040', 'AMMO4': '0.059', 'WEAPON5': '0.100', 'AMMO3': '0.178', 'HITCOUNT': '0.180', 'DAMAGECOUNT': '0.450', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '1.554', 'weapon3': '1.780'} [2024-08-05 08:47:35,295][00150] DAMAGECOUNT value on done: 5421.0 [2024-08-05 08:47:35,295][00150] Sum rewards: -1.246, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.348', 'AMMO4': '-0.046', 'AMMO2': '-0.009', 'weapon4': '0.032', 'WEAPON4': '0.050', 'ARMOR': '0.056', 'AMMO3': '0.122', 'HITCOUNT': '0.250', 'WEAPON3': '0.750', 'DAMAGECOUNT': '0.981', 'weapon2': '1.544', 'weapon3': '1.622', 'FRAGCOUNT': '3.000'} [2024-08-05 08:47:35,868][00150] DAMAGECOUNT value on done: 6080.0 [2024-08-05 08:47:36,425][00150] DAMAGECOUNT value on done: 6245.0 [2024-08-05 08:47:36,426][00150] Sum rewards: 0.078, reward structure: {'DEATHCOUNT': '-9.750', 'AMMO5': '0.005', 'AMMO2': '0.007', 'AMMO4': '0.036', 'HEALTH': '0.065', 'WEAPON5': '0.100', 'AMMO3': '0.150', 'HITCOUNT': '0.290', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.170', 'weapon2': '1.222', 'weapon3': '1.982', 'FRAGCOUNT': '4.000'} [2024-08-05 08:47:36,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 5423104. Throughput: 0: 902.6. Samples: 1356162. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:47:36,504][00035] Avg episode reward: [(0, '-3.743')] [2024-08-05 08:47:41,423][00148] Large shaping reward -2.519 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.27, -90.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-05 08:47:41,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 5447680. Throughput: 0: 907.5. Samples: 1361764. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:47:41,502][00035] Avg episode reward: [(0, '-3.743')] [2024-08-05 08:47:42,121][00147] DAMAGECOUNT value on done: 6506.0 [2024-08-05 08:47:42,121][00147] Sum rewards: -1.793, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.854', 'AMMO2': '0.002', 'AMMO4': '0.008', 'AMMO5': '0.013', 'ARMOR': '0.024', 'weapon5': '0.036', 'AMMO3': '0.150', 'WEAPON5': '0.150', 'WEAPON4': '0.200', 'HITCOUNT': '0.230', 'weapon4': '0.402', 'WEAPON3': '0.900', 'weapon2': '1.004', 'DAMAGECOUNT': '1.005', 'weapon3': '1.688', 'FRAGCOUNT': '4.000'} [2024-08-05 08:47:42,680][00147] DAMAGECOUNT value on done: 5443.0 [2024-08-05 08:47:42,680][00147] Sum rewards: -1.159, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.984', 'AMMO5': '0.005', 'AMMO2': '0.010', 'weapon4': '0.016', 'WEAPON4': '0.050', 'WEAPON5': '0.050', 'AMMO4': '0.052', 'AMMO3': '0.077', 'ARMOR': '0.109', 'HITCOUNT': '0.170', 'DAMAGECOUNT': '0.450', 'WEAPON3': '0.500', 'weapon3': '1.488', 'weapon2': '2.098', 'FRAGCOUNT': '3.000'} [2024-08-05 08:47:43,257][00148] DAMAGECOUNT value on done: 5770.0 [2024-08-05 08:47:43,257][00148] Sum rewards: -2.250, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.190', 'weapon5': '0.002', 'AMMO2': '0.009', 'AMMO5': '0.013', 'AMMO4': '0.043', 'AMMO3': '0.113', 'HITCOUNT': '0.120', 'WEAPON5': '0.150', 'WEAPON3': '0.450', 'DAMAGECOUNT': '0.540', 'FRAGCOUNT': '1.000', 'weapon2': '1.212', 'weapon3': '2.038'} [2024-08-05 08:47:43,298][00147] DAMAGECOUNT value on done: 5148.0 [2024-08-05 08:47:43,298][00147] Sum rewards: -1.602, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.870', 'AMMO5': '0.003', 'AMMO2': '0.013', 'WEAPON1': '0.020', 'weapon5': '0.044', 'AMMO4': '0.066', 'AMMO3': '0.097', 'WEAPON5': '0.100', 'HITCOUNT': '0.200', 'WEAPON4': '0.250', 'weapon4': '0.382', 'WEAPON3': '0.650', 'weapon3': '1.288', 'DAMAGECOUNT': '1.290', 'weapon2': '1.614', 'FRAGCOUNT': '2.500'} [2024-08-05 08:47:43,802][00148] DAMAGECOUNT value on done: 4972.0 [2024-08-05 08:47:43,803][00148] Sum rewards: 1.661, reward structure: {'DEATHCOUNT': '-6.750', 'AMMO2': '0.017', 'AMMO5': '0.018', 'WEAPON4': '0.050', 'weapon5': '0.080', 'AMMO4': '0.086', 'AMMO3': '0.102', 'weapon4': '0.142', 'WEAPON5': '0.200', 'HITCOUNT': '0.250', 'WEAPON3': '0.550', 'HEALTH': '0.647', 'weapon2': '0.726', 'DAMAGECOUNT': '1.017', 'weapon3': '2.026', 'FRAGCOUNT': '2.500'} [2024-08-05 08:47:43,840][00147] DAMAGECOUNT value on done: 5516.0 [2024-08-05 08:47:43,841][00147] Sum rewards: -3.511, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.926', 'AMMO4': '-0.029', 'AMMO2': '-0.006', 'ARMOR': '0.032', 'AMMO3': '0.205', 'HITCOUNT': '0.240', 'DAMAGECOUNT': '0.810', 'WEAPON3': '1.100', 'weapon2': '1.462', 'weapon3': '1.850', 'FRAGCOUNT': '4.000'} [2024-08-05 08:47:44,350][00148] DAMAGECOUNT value on done: 5057.0 [2024-08-05 08:47:44,351][00148] Sum rewards: -5.206, reward structure: {'DEATHCOUNT': '-6.000', 'FRAGCOUNT': '-3.000', 'HEALTH': '-1.032', 'AMMO5': '0.010', 'AMMO2': '0.013', 'WEAPON1': '0.020', 'ARMOR': '0.034', 'AMMO4': '0.062', 'HITCOUNT': '0.090', 'WEAPON4': '0.100', 'AMMO3': '0.104', 'weapon4': '0.134', 'WEAPON5': '0.200', 'weapon5': '0.272', 'DAMAGECOUNT': '0.273', 'WEAPON3': '0.600', 'weapon2': '0.956', 'weapon3': '1.958'} [2024-08-05 08:47:44,935][00148] DAMAGECOUNT value on done: 4948.0 [2024-08-05 08:47:44,936][00148] Sum rewards: -3.809, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-0.570', 'FRAGCOUNT': '-0.500', 'weapon5': '0.006', 'AMMO5': '0.009', 'AMMO2': '0.013', 'WEAPON1': '0.020', 'HITCOUNT': '0.030', 'AMMO4': '0.066', 'DAMAGECOUNT': '0.075', 'WEAPON5': '0.100', 'AMMO3': '0.107', 'WEAPON3': '0.650', 'weapon2': '1.282', 'weapon3': '1.652'} [2024-08-05 08:47:46,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 5464064. Throughput: 0: 911.6. Samples: 1367342. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:47:46,502][00035] Avg episode reward: [(0, '-3.649')] [2024-08-05 08:47:51,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 5480448. Throughput: 0: 910.8. Samples: 1370114. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:47:51,505][00035] Avg episode reward: [(0, '-3.649')] [2024-08-05 08:47:51,845][00146] Updated weights for policy 0, policy_version 670 (0.0027) [2024-08-05 08:47:56,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 5496832. Throughput: 0: 906.6. Samples: 1375340. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:47:56,502][00035] Avg episode reward: [(0, '-3.649')] [2024-08-05 08:48:01,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 5521408. Throughput: 0: 910.1. Samples: 1380962. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:48:01,502][00035] Avg episode reward: [(0, '-3.649')] [2024-08-05 08:48:06,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 5537792. Throughput: 0: 912.7. Samples: 1383828. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:48:06,502][00035] Avg episode reward: [(0, '-3.649')] [2024-08-05 08:48:06,972][00149] DAMAGECOUNT value on done: 5141.0 [2024-08-05 08:48:06,972][00149] Sum rewards: 0.835, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.296', 'AMMO5': '0.010', 'AMMO2': '0.020', 'AMMO3': '0.096', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'AMMO4': '0.102', 'HITCOUNT': '0.200', 'weapon4': '0.414', 'ARMOR': '0.472', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.951', 'weapon2': '1.038', 'weapon3': '1.528', 'FRAGCOUNT': '3.000'} [2024-08-05 08:48:07,511][00149] DAMAGECOUNT value on done: 5102.0 [2024-08-05 08:48:07,511][00149] Sum rewards: -3.357, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.236', 'AMMO2': '0.006', 'AMMO5': '0.008', 'AMMO4': '0.028', 'WEAPON5': '0.100', 'ARMOR': '0.104', 'HITCOUNT': '0.120', 'AMMO3': '0.126', 'weapon5': '0.142', 'weapon4': '0.168', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.417', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '1.268', 'weapon3': '1.792'} [2024-08-05 08:48:08,036][00149] DAMAGECOUNT value on done: 5761.0 [2024-08-05 08:48:08,037][00149] Sum rewards: -5.460, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-0.425', 'AMMO5': '0.005', 'weapon5': '0.016', 'AMMO2': '0.018', 'ARMOR': '0.048', 'weapon4': '0.048', 'AMMO4': '0.090', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'HITCOUNT': '0.130', 'AMMO3': '0.188', 'DAMAGECOUNT': '0.711', 'WEAPON3': '0.900', 'weapon2': '1.436', 'weapon3': '1.924', 'FRAGCOUNT': '2.000'} [2024-08-05 08:48:08,566][00149] DAMAGECOUNT value on done: 5806.0 [2024-08-05 08:48:10,810][00150] DAMAGECOUNT value on done: 5021.0 [2024-08-05 08:48:10,811][00150] Sum rewards: -4.174, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-0.541', 'AMMO5': '0.003', 'WEAPON1': '0.010', 'AMMO2': '0.018', 'WEAPON4': '0.050', 'AMMO4': '0.089', 'AMMO3': '0.137', 'HITCOUNT': '0.190', 'ARMOR': '0.469', 'DAMAGECOUNT': '0.594', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '1.476', 'weapon2': '2.132'} [2024-08-05 08:48:11,368][00150] DAMAGECOUNT value on done: 5958.0 [2024-08-05 08:48:11,368][00150] Sum rewards: -2.800, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-2.572', 'AMMO2': '0.001', 'AMMO4': '0.003', 'AMMO5': '0.012', 'AMMO3': '0.146', 'weapon5': '0.260', 'HITCOUNT': '0.310', 'WEAPON5': '0.400', 'WEAPON3': '1.050', 'weapon2': '1.084', 'DAMAGECOUNT': '1.611', 'weapon3': '1.894', 'FRAGCOUNT': '2.000'} [2024-08-05 08:48:11,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 5554176. Throughput: 0: 921.5. Samples: 1389322. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:48:11,502][00035] Avg episode reward: [(0, '-3.543')] [2024-08-05 08:48:11,509][00137] Saving new best policy, reward=-3.543! [2024-08-05 08:48:11,948][00150] DAMAGECOUNT value on done: 6176.0 [2024-08-05 08:48:11,949][00150] Sum rewards: -0.856, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-1.564', 'AMMO4': '-0.039', 'AMMO2': '-0.008', 'WEAPON4': '0.050', 'weapon4': '0.084', 'AMMO3': '0.109', 'HITCOUNT': '0.110', 'DAMAGECOUNT': '0.288', 'ARMOR': '0.498', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon2': '1.398', 'weapon3': '1.868'} [2024-08-05 08:48:12,515][00150] DAMAGECOUNT value on done: 6439.0 [2024-08-05 08:48:14,461][00146] Updated weights for policy 0, policy_version 680 (0.0027) [2024-08-05 08:48:16,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 5570560. Throughput: 0: 919.4. Samples: 1394810. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:48:16,502][00035] Avg episode reward: [(0, '-3.477')] [2024-08-05 08:48:16,505][00137] Saving new best policy, reward=-3.477! [2024-08-05 08:48:19,500][00147] DAMAGECOUNT value on done: 6945.0 [2024-08-05 08:48:19,500][00147] Sum rewards: -8.816, reward structure: {'DEATHCOUNT': '-15.000', 'HEALTH': '-2.003', 'AMMO5': '0.005', 'AMMO2': '0.022', 'ARMOR': '0.084', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'AMMO4': '0.109', 'AMMO3': '0.170', 'weapon5': '0.188', 'HITCOUNT': '0.240', 'weapon4': '0.418', 'WEAPON3': '1.050', 'DAMAGECOUNT': '1.317', 'weapon2': '1.346', 'FRAGCOUNT': '1.500', 'weapon3': '1.538'} [2024-08-05 08:48:20,044][00147] DAMAGECOUNT value on done: 5699.0 [2024-08-05 08:48:20,045][00147] Sum rewards: -2.229, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.222', 'AMMO4': '-0.044', 'AMMO2': '-0.009', 'AMMO5': '0.005', 'weapon5': '0.016', 'weapon4': '0.042', 'WEAPON4': '0.050', 'WEAPON5': '0.050', 'ARMOR': '0.066', 'AMMO3': '0.137', 'HITCOUNT': '0.220', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.768', 'weapon2': '1.526', 'weapon3': '1.716', 'FRAGCOUNT': '2.000'} [2024-08-05 08:48:20,406][00148] DAMAGECOUNT value on done: 6262.0 [2024-08-05 08:48:20,407][00148] Sum rewards: -3.798, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-2.260', 'AMMO5': '0.020', 'AMMO2': '0.023', 'weapon4': '0.090', 'weapon5': '0.112', 'AMMO4': '0.116', 'AMMO3': '0.125', 'WEAPON4': '0.200', 'HITCOUNT': '0.270', 'WEAPON5': '0.300', 'WEAPON3': '0.750', 'weapon2': '1.328', 'DAMAGECOUNT': '1.476', 'weapon3': '1.902', 'FRAGCOUNT': '3.000'} [2024-08-05 08:48:20,662][00147] DAMAGECOUNT value on done: 5339.0 [2024-08-05 08:48:20,663][00147] Sum rewards: -6.688, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.776', 'AMMO5': '0.003', 'AMMO2': '0.019', 'weapon5': '0.034', 'WEAPON5': '0.050', 'ARMOR': '0.079', 'AMMO4': '0.096', 'WEAPON4': '0.100', 'weapon4': '0.100', 'HITCOUNT': '0.150', 'AMMO3': '0.160', 'DAMAGECOUNT': '0.573', 'WEAPON3': '0.750', 'weapon3': '0.984', 'FRAGCOUNT': '1.000', 'weapon2': '2.240'} [2024-08-05 08:48:20,960][00148] DAMAGECOUNT value on done: 5237.0 [2024-08-05 08:48:20,960][00148] Sum rewards: -6.926, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-2.393', 'weapon5': '0.002', 'AMMO5': '0.007', 'AMMO2': '0.008', 'WEAPON1': '0.010', 'AMMO4': '0.042', 'ARMOR': '0.056', 'weapon4': '0.136', 'WEAPON5': '0.150', 'WEAPON4': '0.150', 'AMMO3': '0.188', 'HITCOUNT': '0.280', 'DAMAGECOUNT': '0.795', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.200', 'weapon2': '1.458', 'weapon3': '1.984'} [2024-08-05 08:48:21,279][00147] DAMAGECOUNT value on done: 5706.0 [2024-08-05 08:48:21,280][00147] Sum rewards: -3.832, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.680', 'AMMO2': '0.008', 'AMMO5': '0.013', 'AMMO4': '0.038', 'ARMOR': '0.040', 'WEAPON4': '0.050', 'weapon4': '0.068', 'weapon5': '0.090', 'HITCOUNT': '0.120', 'AMMO3': '0.131', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.570', 'WEAPON3': '0.850', 'weapon2': '1.498', 'weapon3': '1.922', 'FRAGCOUNT': '2.000'} [2024-08-05 08:48:21,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 5595136. Throughput: 0: 918.1. Samples: 1397476. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:48:21,504][00035] Avg episode reward: [(0, '-3.531')] [2024-08-05 08:48:21,511][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000683_5595136.pth... [2024-08-05 08:48:21,615][00137] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000577_4726784.pth [2024-08-05 08:48:21,628][00148] DAMAGECOUNT value on done: 5192.0 [2024-08-05 08:48:21,629][00148] Sum rewards: -7.739, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-2.390', 'AMMO5': '0.005', 'WEAPON1': '0.010', 'AMMO2': '0.014', 'ARMOR': '0.036', 'AMMO4': '0.071', 'WEAPON5': '0.100', 'weapon5': '0.110', 'HITCOUNT': '0.120', 'weapon4': '0.122', 'AMMO3': '0.172', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.405', 'WEAPON3': '0.900', 'weapon3': '1.516', 'weapon2': '1.620', 'FRAGCOUNT': '2.000'} [2024-08-05 08:48:22,194][00148] DAMAGECOUNT value on done: 5155.0 [2024-08-05 08:48:22,195][00148] Sum rewards: -1.894, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.722', 'AMMO2': '0.003', 'WEAPON1': '0.010', 'AMMO4': '0.013', 'ARMOR': '0.032', 'WEAPON4': '0.100', 'AMMO3': '0.131', 'weapon4': '0.132', 'HITCOUNT': '0.170', 'DAMAGECOUNT': '0.621', 'WEAPON3': '0.800', 'weapon2': '1.436', 'weapon3': '1.630', 'FRAGCOUNT': '2.000'} [2024-08-05 08:48:26,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 5611520. Throughput: 0: 910.2. Samples: 1402724. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:48:26,502][00035] Avg episode reward: [(0, '-3.657')] [2024-08-05 08:48:31,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 5627904. Throughput: 0: 908.7. Samples: 1408234. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:48:31,504][00035] Avg episode reward: [(0, '-3.657')] [2024-08-05 08:48:36,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 5644288. Throughput: 0: 910.0. Samples: 1411062. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:48:36,502][00035] Avg episode reward: [(0, '-3.657')] [2024-08-05 08:48:36,899][00146] Updated weights for policy 0, policy_version 690 (0.0022) [2024-08-05 08:48:41,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 5668864. Throughput: 0: 918.0. Samples: 1416652. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:48:41,502][00035] Avg episode reward: [(0, '-3.657')] [2024-08-05 08:48:43,105][00149] DAMAGECOUNT value on done: 5386.0 [2024-08-05 08:48:43,106][00149] Sum rewards: -0.239, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.442', 'AMMO2': '0.005', 'AMMO5': '0.008', 'WEAPON1': '0.020', 'AMMO4': '0.026', 'weapon5': '0.038', 'ARMOR': '0.056', 'AMMO3': '0.133', 'WEAPON5': '0.150', 'HITCOUNT': '0.190', 'WEAPON4': '0.200', 'weapon4': '0.232', 'DAMAGECOUNT': '0.735', 'WEAPON3': '0.800', 'weapon2': '1.384', 'weapon3': '1.726', 'FRAGCOUNT': '3.000'} [2024-08-05 08:48:43,637][00149] DAMAGECOUNT value on done: 5127.0 [2024-08-05 08:48:44,162][00149] DAMAGECOUNT value on done: 6095.0 [2024-08-05 08:48:44,163][00149] Sum rewards: -4.862, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-1.036', 'AMMO5': '0.003', 'AMMO2': '0.009', 'weapon5': '0.044', 'AMMO4': '0.045', 'WEAPON5': '0.050', 'WEAPON4': '0.050', 'weapon4': '0.060', 'ARMOR': '0.096', 'AMMO3': '0.182', 'HITCOUNT': '0.280', 'weapon2': '0.970', 'DAMAGECOUNT': '1.002', 'WEAPON3': '1.050', 'FRAGCOUNT': '2.000', 'weapon3': '2.334'} [2024-08-05 08:48:44,698][00149] DAMAGECOUNT value on done: 5810.0 [2024-08-05 08:48:46,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 5685248. Throughput: 0: 917.0. Samples: 1422228. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:48:46,502][00035] Avg episode reward: [(0, '-3.704')] [2024-08-05 08:48:46,866][00150] DAMAGECOUNT value on done: 5261.0 [2024-08-05 08:48:46,867][00150] Sum rewards: -4.498, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.490', 'AMMO4': '-0.041', 'AMMO2': '-0.008', 'weapon5': '0.002', 'AMMO5': '0.005', 'WEAPON1': '0.010', 'WEAPON5': '0.100', 'AMMO3': '0.156', 'HITCOUNT': '0.220', 'DAMAGECOUNT': '0.720', 'WEAPON3': '0.750', 'weapon3': '1.694', 'weapon2': '1.884', 'FRAGCOUNT': '2.000'} [2024-08-05 08:48:47,375][00150] DAMAGECOUNT value on done: 6434.0 [2024-08-05 08:48:47,375][00150] Sum rewards: -1.735, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.100', 'AMMO5': '0.017', 'AMMO2': '0.030', 'ARMOR': '0.032', 'AMMO3': '0.145', 'AMMO4': '0.149', 'WEAPON5': '0.150', 'WEAPON4': '0.200', 'HITCOUNT': '0.240', 'weapon5': '0.298', 'weapon4': '0.382', 'WEAPON3': '0.750', 'weapon2': '1.308', 'DAMAGECOUNT': '1.428', 'weapon3': '1.486', 'FRAGCOUNT': '2.500'} [2024-08-05 08:48:47,924][00150] DAMAGECOUNT value on done: 6321.0 [2024-08-05 08:48:47,925][00150] Sum rewards: -6.720, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.180', 'AMMO4': '-0.059', 'AMMO2': '-0.012', 'AMMO5': '0.010', 'ARMOR': '0.016', 'AMMO3': '0.155', 'HITCOUNT': '0.170', 'weapon5': '0.188', 'WEAPON5': '0.250', 'DAMAGECOUNT': '0.435', 'WEAPON3': '0.850', 'FRAGCOUNT': '1.000', 'weapon2': '1.240', 'weapon3': '1.716'} [2024-08-05 08:48:48,487][00150] DAMAGECOUNT value on done: 6627.0 [2024-08-05 08:48:48,488][00150] Sum rewards: -6.645, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.835', 'AMMO5': '0.005', 'AMMO2': '0.007', 'weapon5': '0.024', 'AMMO4': '0.033', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'HITCOUNT': '0.210', 'weapon4': '0.212', 'AMMO3': '0.223', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.564', 'weapon2': '1.068', 'WEAPON3': '1.200', 'weapon3': '2.194'} [2024-08-05 08:48:51,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 5701632. Throughput: 0: 914.9. Samples: 1425000. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:48:51,502][00035] Avg episode reward: [(0, '-3.727')] [2024-08-05 08:48:56,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 5718016. Throughput: 0: 917.6. Samples: 1430612. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:48:56,504][00035] Avg episode reward: [(0, '-3.727')] [2024-08-05 08:48:56,627][00147] DAMAGECOUNT value on done: 7340.0 [2024-08-05 08:48:56,628][00147] Sum rewards: -5.339, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-2.294', 'AMMO5': '0.009', 'AMMO2': '0.009', 'AMMO4': '0.043', 'ARMOR': '0.044', 'WEAPON4': '0.050', 'weapon5': '0.056', 'weapon4': '0.062', 'AMMO3': '0.137', 'WEAPON5': '0.200', 'HITCOUNT': '0.290', 'WEAPON3': '0.850', 'weapon2': '0.922', 'DAMAGECOUNT': '1.185', 'weapon3': '2.098', 'FRAGCOUNT': '3.000'} [2024-08-05 08:48:57,518][00147] DAMAGECOUNT value on done: 5794.0 [2024-08-05 08:48:57,519][00147] Sum rewards: -0.583, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-0.272', 'AMMO5': '0.007', 'AMMO2': '0.012', 'ARMOR': '0.036', 'WEAPON4': '0.050', 'AMMO4': '0.062', 'weapon7': '0.066', 'weapon5': '0.076', 'HITCOUNT': '0.090', 'AMMO3': '0.092', 'AMMO6': '0.100', 'AMMO7': '0.100', 'WEAPON7': '0.100', 'weapon4': '0.126', 'WEAPON5': '0.150', 'DAMAGECOUNT': '0.285', 'WEAPON3': '0.500', 'FRAGCOUNT': '1.000', 'weapon3': '1.014', 'weapon2': '1.072'} [2024-08-05 08:48:58,165][00147] DAMAGECOUNT value on done: 5618.0 [2024-08-05 08:48:58,166][00147] Sum rewards: -1.731, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-1.559', 'AMMO2': '0.003', 'ARMOR': '0.013', 'AMMO4': '0.013', 'AMMO5': '0.013', 'AMMO3': '0.102', 'HITCOUNT': '0.150', 'WEAPON4': '0.200', 'weapon5': '0.240', 'WEAPON5': '0.250', 'weapon4': '0.348', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.837', 'weapon2': '1.150', 'weapon3': '1.408'} [2024-08-05 08:48:58,314][00148] DAMAGECOUNT value on done: 6519.0 [2024-08-05 08:48:58,315][00148] Sum rewards: -2.430, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.355', 'AMMO2': '0.009', 'AMMO4': '0.043', 'weapon4': '0.080', 'WEAPON4': '0.100', 'AMMO3': '0.140', 'HITCOUNT': '0.190', 'ARMOR': '0.502', 'DAMAGECOUNT': '0.771', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '1.682', 'weapon3': '1.858'} [2024-08-05 08:48:58,722][00147] DAMAGECOUNT value on done: 5955.0 [2024-08-05 08:48:58,722][00147] Sum rewards: -3.421, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.426', 'AMMO5': '0.003', 'weapon5': '0.006', 'WEAPON1': '0.010', 'AMMO2': '0.017', 'WEAPON5': '0.050', 'ARMOR': '0.052', 'AMMO4': '0.083', 'WEAPON4': '0.100', 'AMMO3': '0.137', 'HITCOUNT': '0.260', 'weapon4': '0.356', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.747', 'FRAGCOUNT': '1.000', 'weapon2': '1.256', 'weapon3': '1.328'} [2024-08-05 08:48:58,886][00148] DAMAGECOUNT value on done: 5357.0 [2024-08-05 08:48:59,396][00146] Updated weights for policy 0, policy_version 700 (0.0018) [2024-08-05 08:48:59,465][00148] DAMAGECOUNT value on done: 5402.0 [2024-08-05 08:48:59,465][00148] Sum rewards: -4.325, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-2.135', 'AMMO2': '0.007', 'AMMO5': '0.012', 'WEAPON1': '0.020', 'weapon4': '0.030', 'AMMO4': '0.034', 'weapon5': '0.086', 'WEAPON4': '0.100', 'HITCOUNT': '0.120', 'AMMO3': '0.175', 'WEAPON5': '0.300', 'ARMOR': '0.416', 'DAMAGECOUNT': '0.630', 'WEAPON3': '0.750', 'FRAGCOUNT': '1.000', 'weapon3': '1.438', 'weapon2': '1.692'} [2024-08-05 08:49:00,046][00148] DAMAGECOUNT value on done: 5287.0 [2024-08-05 08:49:00,047][00148] Sum rewards: -7.542, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.602', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.012', 'AMMO2': '0.013', 'AMMO4': '0.066', 'ARMOR': '0.089', 'AMMO3': '0.107', 'HITCOUNT': '0.130', 'weapon5': '0.190', 'WEAPON5': '0.250', 'WEAPON4': '0.250', 'weapon4': '0.284', 'DAMAGECOUNT': '0.396', 'WEAPON3': '0.600', 'weapon3': '1.400', 'weapon2': '1.522'} [2024-08-05 08:49:01,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 5734400. Throughput: 0: 908.5. Samples: 1435694. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:49:01,502][00035] Avg episode reward: [(0, '-3.708')] [2024-08-05 08:49:06,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 5758976. Throughput: 0: 911.5. Samples: 1438492. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:49:06,501][00035] Avg episode reward: [(0, '-3.708')] [2024-08-05 08:49:11,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 5775360. Throughput: 0: 918.8. Samples: 1444068. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:49:11,501][00035] Avg episode reward: [(0, '-3.708')] [2024-08-05 08:49:16,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 5791744. Throughput: 0: 920.0. Samples: 1449634. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:49:16,502][00035] Avg episode reward: [(0, '-3.708')] [2024-08-05 08:49:19,530][00149] DAMAGECOUNT value on done: 5750.0 [2024-08-05 08:49:19,531][00149] Sum rewards: -4.698, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-1.906', 'AMMO2': '0.007', 'AMMO5': '0.010', 'weapon4': '0.016', 'AMMO4': '0.032', 'WEAPON1': '0.040', 'ARMOR': '0.064', 'weapon5': '0.106', 'AMMO3': '0.143', 'WEAPON4': '0.150', 'WEAPON5': '0.200', 'HITCOUNT': '0.270', 'WEAPON3': '0.850', 'DAMAGECOUNT': '1.092', 'weapon2': '1.448', 'weapon3': '1.780', 'FRAGCOUNT': '3.000'} [2024-08-05 08:49:20,111][00149] DAMAGECOUNT value on done: 5304.0 [2024-08-05 08:49:20,111][00149] Sum rewards: -6.618, reward structure: {'DEATHCOUNT': '-9.750', 'FRAGCOUNT': '-1.500', 'HEALTH': '-0.650', 'AMMO2': '0.007', 'AMMO5': '0.008', 'AMMO4': '0.034', 'ARMOR': '0.040', 'weapon4': '0.040', 'weapon5': '0.050', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'HITCOUNT': '0.150', 'AMMO3': '0.159', 'DAMAGECOUNT': '0.531', 'WEAPON3': '0.800', 'weapon2': '1.566', 'weapon3': '1.698'} [2024-08-05 08:49:20,664][00149] DAMAGECOUNT value on done: 6180.0 [2024-08-05 08:49:21,235][00149] DAMAGECOUNT value on done: 5999.0 [2024-08-05 08:49:21,236][00149] Sum rewards: -1.300, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.138', 'AMMO5': '0.005', 'AMMO2': '0.019', 'WEAPON1': '0.020', 'weapon4': '0.090', 'AMMO4': '0.093', 'weapon5': '0.110', 'AMMO3': '0.118', 'WEAPON5': '0.150', 'WEAPON4': '0.150', 'HITCOUNT': '0.160', 'DAMAGECOUNT': '0.567', 'WEAPON3': '0.600', 'ARMOR': '0.886', 'weapon2': '1.264', 'weapon3': '1.606', 'FRAGCOUNT': '2.000'} [2024-08-05 08:49:21,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 5808128. Throughput: 0: 918.8. Samples: 1452410. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:49:21,511][00035] Avg episode reward: [(0, '-3.783')] [2024-08-05 08:49:21,617][00146] Updated weights for policy 0, policy_version 710 (0.0026) [2024-08-05 08:49:22,694][00150] DAMAGECOUNT value on done: 5326.0 [2024-08-05 08:49:23,232][00150] DAMAGECOUNT value on done: 6581.0 [2024-08-05 08:49:23,823][00150] DAMAGECOUNT value on done: 6510.0 [2024-08-05 08:49:24,413][00150] DAMAGECOUNT value on done: 6968.0 [2024-08-05 08:49:24,414][00150] Sum rewards: 0.450, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.290', 'AMMO5': '0.012', 'AMMO2': '0.016', 'WEAPON1': '0.020', 'ARMOR': '0.040', 'AMMO4': '0.079', 'AMMO3': '0.114', 'WEAPON4': '0.150', 'HITCOUNT': '0.160', 'WEAPON5': '0.250', 'weapon5': '0.384', 'WEAPON3': '0.750', 'DAMAGECOUNT': '1.023', 'weapon2': '1.426', 'weapon3': '1.566', 'FRAGCOUNT': '4.000'} [2024-08-05 08:49:26,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 5832704. Throughput: 0: 916.8. Samples: 1457906. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:49:26,505][00035] Avg episode reward: [(0, '-3.880')] [2024-08-05 08:49:31,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 5849088. Throughput: 0: 906.9. Samples: 1463040. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:49:31,501][00035] Avg episode reward: [(0, '-3.880')] [2024-08-05 08:49:34,141][00147] DAMAGECOUNT value on done: 7590.0 [2024-08-05 08:49:34,143][00147] Sum rewards: -4.297, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.855', 'AMMO2': '0.009', 'AMMO5': '0.023', 'AMMO4': '0.043', 'AMMO3': '0.076', 'weapon5': '0.118', 'ARMOR': '0.130', 'weapon4': '0.216', 'HITCOUNT': '0.240', 'WEAPON3': '0.250', 'WEAPON4': '0.300', 'WEAPON5': '0.350', 'DAMAGECOUNT': '0.750', 'weapon3': '0.778', 'FRAGCOUNT': '1.000', 'weapon2': '2.276'} [2024-08-05 08:49:34,692][00147] DAMAGECOUNT value on done: 6043.0 [2024-08-05 08:49:34,693][00147] Sum rewards: -6.006, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.230', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.003', 'AMMO2': '0.011', 'weapon5': '0.028', 'WEAPON5': '0.050', 'AMMO4': '0.055', 'ARMOR': '0.104', 'WEAPON4': '0.150', 'AMMO3': '0.161', 'HITCOUNT': '0.190', 'weapon4': '0.234', 'DAMAGECOUNT': '0.747', 'weapon2': '0.840', 'WEAPON3': '0.850', 'weapon3': '2.052'} [2024-08-05 08:49:35,270][00147] DAMAGECOUNT value on done: 5798.0 [2024-08-05 08:49:35,404][00148] DAMAGECOUNT value on done: 6569.0 [2024-08-05 08:49:35,841][00147] DAMAGECOUNT value on done: 6155.0 [2024-08-05 08:49:35,842][00147] Sum rewards: -0.130, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.860', 'AMMO2': '0.006', 'AMMO4': '0.030', 'AMMO3': '0.073', 'WEAPON4': '0.150', 'HITCOUNT': '0.160', 'weapon4': '0.378', 'WEAPON3': '0.550', 'DAMAGECOUNT': '0.600', 'ARMOR': '0.894', 'weapon3': '1.154', 'weapon2': '1.984', 'FRAGCOUNT': '3.000'} [2024-08-05 08:49:35,969][00148] DAMAGECOUNT value on done: 5576.0 [2024-08-05 08:49:35,970][00148] Sum rewards: -0.213, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-1.582', 'AMMO4': '-0.023', 'AMMO2': '-0.005', 'AMMO5': '0.005', 'WEAPON4': '0.100', 'weapon4': '0.116', 'AMMO3': '0.119', 'HITCOUNT': '0.190', 'ARMOR': '0.504', 'DAMAGECOUNT': '0.657', 'WEAPON3': '0.750', 'weapon2': '1.344', 'weapon3': '1.612', 'FRAGCOUNT': '2.000'} [2024-08-05 08:49:36,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3610.1). Total num frames: 5865472. Throughput: 0: 908.7. Samples: 1465890. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:49:36,503][00035] Avg episode reward: [(0, '-3.969')] [2024-08-05 08:49:36,533][00148] DAMAGECOUNT value on done: 5907.0 [2024-08-05 08:49:36,533][00148] Sum rewards: 1.896, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.840', 'AMMO2': '0.001', 'AMMO4': '0.002', 'AMMO5': '0.005', 'WEAPON1': '0.020', 'weapon5': '0.024', 'ARMOR': '0.028', 'WEAPON5': '0.100', 'AMMO3': '0.147', 'WEAPON4': '0.200', 'HITCOUNT': '0.250', 'weapon4': '0.446', 'WEAPON3': '0.700', 'weapon2': '0.820', 'DAMAGECOUNT': '1.515', 'weapon3': '1.978', 'FRAGCOUNT': '4.000'} [2024-08-05 08:49:37,149][00148] DAMAGECOUNT value on done: 5677.0 [2024-08-05 08:49:37,151][00148] Sum rewards: -1.253, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-2.790', 'AMMO4': '-0.042', 'AMMO2': '-0.008', 'AMMO5': '0.003', 'WEAPON1': '0.020', 'ARMOR': '0.044', 'weapon5': '0.090', 'WEAPON5': '0.100', 'AMMO3': '0.164', 'HITCOUNT': '0.270', 'WEAPON3': '1.150', 'DAMAGECOUNT': '1.170', 'weapon2': '1.302', 'weapon3': '2.024', 'FRAGCOUNT': '5.000'} [2024-08-05 08:49:41,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 5881856. Throughput: 0: 906.0. Samples: 1471382. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:49:41,501][00035] Avg episode reward: [(0, '-3.894')] [2024-08-05 08:49:43,992][00146] Updated weights for policy 0, policy_version 720 (0.0019) [2024-08-05 08:49:46,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 5906432. Throughput: 0: 918.4. Samples: 1477024. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:49:46,501][00035] Avg episode reward: [(0, '-3.894')] [2024-08-05 08:49:51,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 5922816. Throughput: 0: 919.1. Samples: 1479852. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:49:51,502][00035] Avg episode reward: [(0, '-3.894')] [2024-08-05 08:49:55,770][00149] DAMAGECOUNT value on done: 5995.0 [2024-08-05 08:49:55,771][00149] Sum rewards: -1.371, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.360', 'AMMO4': '-0.020', 'AMMO2': '-0.004', 'AMMO5': '0.003', 'weapon5': '0.078', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.129', 'weapon4': '0.146', 'HITCOUNT': '0.190', 'ARMOR': '0.444', 'DAMAGECOUNT': '0.735', 'WEAPON3': '0.750', 'FRAGCOUNT': '1.000', 'weapon2': '1.168', 'weapon3': '1.920'} [2024-08-05 08:49:56,316][00149] DAMAGECOUNT value on done: 5443.0 [2024-08-05 08:49:56,317][00149] Sum rewards: -3.792, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.078', 'AMMO5': '0.007', 'ARMOR': '0.036', 'AMMO2': '0.041', 'AMMO3': '0.093', 'HITCOUNT': '0.100', 'weapon5': '0.102', 'WEAPON5': '0.150', 'weapon4': '0.186', 'AMMO4': '0.203', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.417', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon2': '1.502', 'weapon3': '1.548'} [2024-08-05 08:49:56,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 5939200. Throughput: 0: 920.8. Samples: 1485502. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:49:56,502][00035] Avg episode reward: [(0, '-3.938')] [2024-08-05 08:49:56,920][00149] DAMAGECOUNT value on done: 6440.0 [2024-08-05 08:49:56,921][00149] Sum rewards: -3.603, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.117', 'AMMO5': '0.003', 'AMMO2': '0.005', 'weapon5': '0.016', 'AMMO4': '0.026', 'WEAPON4': '0.050', 'WEAPON5': '0.050', 'ARMOR': '0.068', 'weapon4': '0.082', 'AMMO3': '0.132', 'HITCOUNT': '0.230', 'DAMAGECOUNT': '0.780', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '1.538', 'weapon3': '1.734'} [2024-08-05 08:49:57,541][00149] DAMAGECOUNT value on done: 6348.0 [2024-08-05 08:49:57,542][00149] Sum rewards: -5.925, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-3.315', 'AMMO4': '-0.018', 'AMMO2': '-0.004', 'AMMO5': '0.013', 'ARMOR': '0.076', 'weapon5': '0.110', 'WEAPON5': '0.150', 'AMMO3': '0.190', 'HITCOUNT': '0.210', 'WEAPON4': '0.300', 'weapon4': '0.390', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.047', 'weapon3': '1.138', 'weapon2': '1.888', 'FRAGCOUNT': '3.000'} [2024-08-05 08:49:58,546][00150] DAMAGECOUNT value on done: 5564.0 [2024-08-05 08:49:59,138][00150] DAMAGECOUNT value on done: 6666.0 [2024-08-05 08:49:59,139][00150] Sum rewards: -4.096, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.162', 'AMMO5': '0.005', 'AMMO2': '0.010', 'WEAPON1': '0.020', 'ARMOR': '0.040', 'weapon4': '0.046', 'AMMO4': '0.050', 'WEAPON4': '0.050', 'HITCOUNT': '0.080', 'WEAPON5': '0.100', 'AMMO3': '0.146', 'DAMAGECOUNT': '0.255', 'WEAPON3': '0.950', 'weapon2': '1.160', 'weapon3': '1.904', 'FRAGCOUNT': '2.000'} [2024-08-05 08:49:59,724][00150] DAMAGECOUNT value on done: 6571.0 [2024-08-05 08:50:00,346][00150] DAMAGECOUNT value on done: 7071.0 [2024-08-05 08:50:00,347][00150] Sum rewards: -7.133, reward structure: {'DEATHCOUNT': '-10.500', 'FRAGCOUNT': '-1.500', 'HEALTH': '-0.008', 'AMMO5': '0.008', 'weapon5': '0.032', 'AMMO2': '0.035', 'ARMOR': '0.076', 'HITCOUNT': '0.090', 'WEAPON5': '0.100', 'AMMO3': '0.135', 'WEAPON4': '0.150', 'AMMO4': '0.176', 'weapon4': '0.288', 'DAMAGECOUNT': '0.309', 'WEAPON3': '0.650', 'weapon2': '1.386', 'weapon3': '1.440'} [2024-08-05 08:50:01,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 5955584. Throughput: 0: 912.8. Samples: 1490712. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:50:01,504][00035] Avg episode reward: [(0, '-3.977')] [2024-08-05 08:50:06,500][00146] Updated weights for policy 0, policy_version 730 (0.0030) [2024-08-05 08:50:06,506][00035] Fps is (10 sec: 4093.4, 60 sec: 3686.0, 300 sec: 3637.7). Total num frames: 5980160. Throughput: 0: 910.9. Samples: 1493406. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:50:06,510][00035] Avg episode reward: [(0, '-3.977')] [2024-08-05 08:50:11,291][00147] DAMAGECOUNT value on done: 7687.0 [2024-08-05 08:50:11,291][00147] Sum rewards: -3.045, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.700', 'AMMO5': '0.003', 'AMMO2': '0.012', 'WEAPON5': '0.050', 'AMMO4': '0.059', 'AMMO3': '0.079', 'ARMOR': '0.082', 'WEAPON4': '0.100', 'HITCOUNT': '0.110', 'weapon4': '0.186', 'DAMAGECOUNT': '0.291', 'WEAPON3': '0.450', 'FRAGCOUNT': '1.000', 'weapon2': '1.272', 'weapon3': '1.462'} [2024-08-05 08:50:11,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 5996544. Throughput: 0: 914.9. Samples: 1499078. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:50:11,502][00035] Avg episode reward: [(0, '-3.971')] [2024-08-05 08:50:11,853][00147] DAMAGECOUNT value on done: 6163.0 [2024-08-05 08:50:12,255][00148] DAMAGECOUNT value on done: 6781.0 [2024-08-05 08:50:12,256][00148] Sum rewards: -5.084, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.699', 'AMMO4': '-0.044', 'AMMO2': '-0.009', 'AMMO5': '0.003', 'ARMOR': '0.012', 'WEAPON5': '0.050', 'AMMO3': '0.151', 'HITCOUNT': '0.160', 'DAMAGECOUNT': '0.636', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon3': '1.516', 'weapon2': '1.990'} [2024-08-05 08:50:12,419][00147] DAMAGECOUNT value on done: 5932.0 [2024-08-05 08:50:12,420][00147] Sum rewards: -11.261, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-2.025', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.010', 'AMMO2': '0.024', 'weapon4': '0.044', 'weapon5': '0.050', 'ARMOR': '0.060', 'WEAPON5': '0.100', 'AMMO4': '0.119', 'HITCOUNT': '0.120', 'WEAPON4': '0.150', 'AMMO3': '0.197', 'DAMAGECOUNT': '0.402', 'WEAPON3': '1.150', 'weapon2': '1.624', 'weapon3': '1.714'} [2024-08-05 08:50:12,831][00148] DAMAGECOUNT value on done: 5826.0 [2024-08-05 08:50:12,832][00148] Sum rewards: -2.887, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.775', 'AMMO2': '0.012', 'ARMOR': '0.032', 'AMMO4': '0.057', 'AMMO3': '0.083', 'HITCOUNT': '0.210', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.750', 'weapon3': '1.306', 'weapon2': '1.938', 'FRAGCOUNT': '2.000'} [2024-08-05 08:50:12,987][00147] DAMAGECOUNT value on done: 6200.0 [2024-08-05 08:50:12,988][00147] Sum rewards: -3.173, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.288', 'AMMO5': '0.003', 'AMMO2': '0.009', 'AMMO4': '0.046', 'HITCOUNT': '0.050', 'ARMOR': '0.052', 'AMMO3': '0.074', 'DAMAGECOUNT': '0.135', 'WEAPON3': '0.250', 'weapon3': '0.746', 'FRAGCOUNT': '1.000', 'weapon2': '2.250'} [2024-08-05 08:50:13,422][00148] DAMAGECOUNT value on done: 6017.0 [2024-08-05 08:50:13,423][00148] Sum rewards: -6.459, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.595', 'AMMO2': '0.014', 'ARMOR': '0.028', 'AMMO4': '0.070', 'HITCOUNT': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.142', 'weapon4': '0.194', 'DAMAGECOUNT': '0.330', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '1.708', 'weapon3': '1.800'} [2024-08-05 08:50:13,978][00148] DAMAGECOUNT value on done: 6063.0 [2024-08-05 08:50:13,979][00148] Sum rewards: 1.759, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-0.193', 'AMMO4': '-0.015', 'AMMO2': '-0.003', 'AMMO5': '0.005', 'WEAPON5': '0.100', 'weapon5': '0.100', 'AMMO3': '0.117', 'HITCOUNT': '0.240', 'WEAPON3': '0.550', 'DAMAGECOUNT': '1.158', 'weapon2': '1.292', 'weapon3': '2.158', 'FRAGCOUNT': '3.000'} [2024-08-05 08:50:16,500][00035] Fps is (10 sec: 3278.9, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 6012928. Throughput: 0: 922.1. Samples: 1504534. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:50:16,502][00035] Avg episode reward: [(0, '-3.961')] [2024-08-05 08:50:21,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 6029312. Throughput: 0: 920.0. Samples: 1507290. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:50:21,502][00035] Avg episode reward: [(0, '-3.961')] [2024-08-05 08:50:21,509][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000736_6029312.pth... [2024-08-05 08:50:21,609][00137] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000629_5152768.pth [2024-08-05 08:50:26,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 6053888. Throughput: 0: 921.2. Samples: 1512836. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:50:26,502][00035] Avg episode reward: [(0, '-3.961')] [2024-08-05 08:50:28,556][00146] Updated weights for policy 0, policy_version 740 (0.0016) [2024-08-05 08:50:31,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 6070272. Throughput: 0: 917.4. Samples: 1518308. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:50:31,502][00035] Avg episode reward: [(0, '-3.961')] [2024-08-05 08:50:32,090][00149] DAMAGECOUNT value on done: 6195.0 [2024-08-05 08:50:32,091][00149] Sum rewards: -4.330, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.285', 'AMMO5': '0.003', 'AMMO2': '0.004', 'AMMO4': '0.019', 'ARMOR': '0.028', 'WEAPON5': '0.100', 'WEAPON4': '0.150', 'HITCOUNT': '0.150', 'AMMO3': '0.159', 'weapon4': '0.164', 'weapon5': '0.210', 'DAMAGECOUNT': '0.600', 'WEAPON3': '1.000', 'weapon2': '1.356', 'weapon3': '1.762', 'FRAGCOUNT': '3.000'} [2024-08-05 08:50:32,976][00149] DAMAGECOUNT value on done: 5583.0 [2024-08-05 08:50:33,706][00149] DAMAGECOUNT value on done: 6750.0 [2024-08-05 08:50:33,707][00149] Sum rewards: -6.640, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-2.234', 'AMMO4': '-0.010', 'AMMO2': '-0.002', 'ARMOR': '0.068', 'WEAPON4': '0.150', 'AMMO3': '0.200', 'HITCOUNT': '0.290', 'weapon4': '0.366', 'DAMAGECOUNT': '0.930', 'WEAPON3': '1.100', 'weapon2': '1.426', 'weapon3': '1.826', 'FRAGCOUNT': '2.000'} [2024-08-05 08:50:34,215][00149] DAMAGECOUNT value on done: 6468.0 [2024-08-05 08:50:35,327][00150] DAMAGECOUNT value on done: 5843.0 [2024-08-05 08:50:35,328][00150] Sum rewards: -7.678, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.930', 'AMMO4': '-0.064', 'AMMO2': '-0.013', 'AMMO5': '0.005', 'weapon5': '0.044', 'WEAPON5': '0.050', 'ARMOR': '0.052', 'AMMO3': '0.137', 'HITCOUNT': '0.260', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.837', 'weapon2': '1.448', 'weapon3': '1.696'} [2024-08-05 08:50:35,910][00150] DAMAGECOUNT value on done: 7161.0 [2024-08-05 08:50:35,910][00150] Sum rewards: -1.484, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.468', 'AMMO4': '-0.033', 'AMMO2': '-0.007', 'ARMOR': '0.004', 'AMMO5': '0.015', 'weapon5': '0.040', 'AMMO3': '0.162', 'WEAPON5': '0.250', 'HITCOUNT': '0.330', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.485', 'weapon2': '1.640', 'weapon3': '1.698', 'FRAGCOUNT': '4.000'} [2024-08-05 08:50:36,477][00150] DAMAGECOUNT value on done: 7086.0 [2024-08-05 08:50:36,478][00150] Sum rewards: -3.489, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-1.800', 'AMMO5': '0.010', 'AMMO2': '0.019', 'ARMOR': '0.052', 'AMMO4': '0.093', 'weapon4': '0.156', 'weapon5': '0.164', 'AMMO3': '0.182', 'WEAPON5': '0.200', 'WEAPON4': '0.250', 'HITCOUNT': '0.310', 'WEAPON3': '0.850', 'weapon2': '1.224', 'DAMAGECOUNT': '1.545', 'weapon3': '2.006', 'FRAGCOUNT': '4.000'} [2024-08-05 08:50:36,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 6086656. Throughput: 0: 907.2. Samples: 1520676. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:50:36,502][00035] Avg episode reward: [(0, '-3.786')] [2024-08-05 08:50:37,068][00150] DAMAGECOUNT value on done: 7436.0 [2024-08-05 08:50:37,070][00150] Sum rewards: -1.785, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-0.320', 'AMMO5': '0.005', 'AMMO2': '0.011', 'AMMO4': '0.054', 'ARMOR': '0.080', 'weapon5': '0.084', 'WEAPON5': '0.100', 'AMMO3': '0.162', 'HITCOUNT': '0.180', 'WEAPON3': '0.750', 'DAMAGECOUNT': '1.095', 'weapon2': '1.600', 'weapon3': '1.914', 'FRAGCOUNT': '3.000'} [2024-08-05 08:50:41,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 6103040. Throughput: 0: 904.3. Samples: 1526194. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:50:41,502][00035] Avg episode reward: [(0, '-3.749')] [2024-08-05 08:50:46,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 6119424. Throughput: 0: 914.6. Samples: 1531870. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:50:46,501][00035] Avg episode reward: [(0, '-3.749')] [2024-08-05 08:50:48,688][00147] DAMAGECOUNT value on done: 7922.0 [2024-08-05 08:50:49,286][00147] DAMAGECOUNT value on done: 6664.0 [2024-08-05 08:50:49,287][00147] Sum rewards: -2.741, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-0.410', 'AMMO5': '0.003', 'WEAPON1': '0.010', 'AMMO2': '0.012', 'ARMOR': '0.046', 'WEAPON5': '0.050', 'AMMO4': '0.058', 'weapon5': '0.072', 'AMMO3': '0.137', 'WEAPON4': '0.200', 'HITCOUNT': '0.220', 'weapon4': '0.342', 'WEAPON3': '0.550', 'weapon3': '1.198', 'DAMAGECOUNT': '1.503', 'weapon2': '1.768', 'FRAGCOUNT': '2.000'} [2024-08-05 08:50:49,816][00148] DAMAGECOUNT value on done: 7146.0 [2024-08-05 08:50:49,816][00148] Sum rewards: -3.337, reward structure: {'DEATHCOUNT': '-12.750', 'AMMO5': '0.005', 'WEAPON1': '0.010', 'AMMO2': '0.017', 'weapon5': '0.022', 'WEAPON5': '0.050', 'AMMO4': '0.085', 'WEAPON4': '0.100', 'weapon4': '0.134', 'AMMO3': '0.170', 'HEALTH': '0.292', 'HITCOUNT': '0.310', 'WEAPON3': '0.850', 'DAMAGECOUNT': '1.095', 'weapon2': '1.484', 'weapon3': '1.788', 'FRAGCOUNT': '3.000'} [2024-08-05 08:50:49,845][00147] DAMAGECOUNT value on done: 6151.0 [2024-08-05 08:50:49,846][00147] Sum rewards: -1.400, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.272', 'AMMO4': '-0.053', 'AMMO2': '-0.011', 'AMMO5': '0.005', 'weapon5': '0.040', 'WEAPON5': '0.050', 'AMMO3': '0.098', 'HITCOUNT': '0.200', 'ARMOR': '0.460', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.657', 'weapon2': '1.496', 'weapon3': '1.830', 'FRAGCOUNT': '2.000'} [2024-08-05 08:50:50,376][00147] DAMAGECOUNT value on done: 6380.0 [2024-08-05 08:50:50,377][00147] Sum rewards: -5.925, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.096', 'AMMO5': '0.005', 'weapon4': '0.010', 'AMMO2': '0.014', 'WEAPON5': '0.050', 'WEAPON4': '0.050', 'AMMO4': '0.072', 'weapon5': '0.136', 'HITCOUNT': '0.150', 'AMMO3': '0.192', 'DAMAGECOUNT': '0.540', 'WEAPON3': '0.750', 'FRAGCOUNT': '1.000', 'weapon2': '1.716', 'weapon3': '1.736'} [2024-08-05 08:50:50,390][00148] DAMAGECOUNT value on done: 5887.0 [2024-08-05 08:50:50,949][00148] DAMAGECOUNT value on done: 6402.0 [2024-08-05 08:50:50,950][00148] Sum rewards: 1.497, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-0.266', 'AMMO2': '0.021', 'ARMOR': '0.083', 'AMMO3': '0.095', 'AMMO4': '0.103', 'WEAPON4': '0.150', 'HITCOUNT': '0.240', 'weapon4': '0.300', 'WEAPON3': '0.500', 'DAMAGECOUNT': '1.155', 'weapon3': '1.266', 'weapon2': '1.600', 'FRAGCOUNT': '3.000'} [2024-08-05 08:50:51,358][00146] Updated weights for policy 0, policy_version 750 (0.0018) [2024-08-05 08:50:51,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 6144000. Throughput: 0: 914.1. Samples: 1534534. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:50:51,504][00035] Avg episode reward: [(0, '-3.657')] [2024-08-05 08:50:51,563][00148] DAMAGECOUNT value on done: 6434.0 [2024-08-05 08:50:51,564][00148] Sum rewards: -4.421, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-1.678', 'AMMO2': '0.006', 'AMMO5': '0.010', 'AMMO4': '0.030', 'WEAPON5': '0.150', 'AMMO3': '0.185', 'weapon5': '0.208', 'HITCOUNT': '0.250', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.113', 'weapon2': '1.430', 'weapon3': '1.874', 'FRAGCOUNT': '3.000'} [2024-08-05 08:50:56,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 6160384. Throughput: 0: 913.5. Samples: 1540184. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:50:56,504][00035] Avg episode reward: [(0, '-3.703')] [2024-08-05 08:51:01,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 6176768. Throughput: 0: 916.0. Samples: 1545756. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:51:01,502][00035] Avg episode reward: [(0, '-3.703')] [2024-08-05 08:51:06,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3550.2, 300 sec: 3637.8). Total num frames: 6193152. Throughput: 0: 915.0. Samples: 1548464. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:51:06,504][00035] Avg episode reward: [(0, '-3.703')] [2024-08-05 08:51:08,410][00149] DAMAGECOUNT value on done: 6317.0 [2024-08-05 08:51:08,411][00149] Sum rewards: -4.833, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-0.743', 'weapon5': '0.002', 'AMMO2': '0.004', 'AMMO5': '0.013', 'AMMO4': '0.018', 'HITCOUNT': '0.120', 'AMMO3': '0.174', 'WEAPON5': '0.250', 'DAMAGECOUNT': '0.366', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '1.290', 'weapon3': '2.274'} [2024-08-05 08:51:08,951][00149] DAMAGECOUNT value on done: 5628.0 [2024-08-05 08:51:09,533][00149] DAMAGECOUNT value on done: 7074.0 [2024-08-05 08:51:09,534][00149] Sum rewards: -4.493, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.274', 'AMMO5': '0.003', 'AMMO2': '0.010', 'ARMOR': '0.048', 'AMMO4': '0.049', 'WEAPON4': '0.100', 'AMMO3': '0.146', 'weapon4': '0.178', 'HITCOUNT': '0.260', 'DAMAGECOUNT': '0.972', 'WEAPON3': '1.000', 'weapon2': '1.710', 'weapon3': '1.806', 'FRAGCOUNT': '2.000'} [2024-08-05 08:51:10,073][00149] DAMAGECOUNT value on done: 6704.0 [2024-08-05 08:51:10,074][00149] Sum rewards: -0.191, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.050', 'AMMO5': '0.005', 'AMMO2': '0.013', 'ARMOR': '0.058', 'AMMO4': '0.066', 'AMMO3': '0.085', 'weapon4': '0.184', 'WEAPON4': '0.200', 'HITCOUNT': '0.200', 'WEAPON3': '0.550', 'DAMAGECOUNT': '0.708', 'weapon3': '1.676', 'weapon2': '1.864', 'FRAGCOUNT': '2.000'} [2024-08-05 08:51:11,502][00035] Fps is (10 sec: 4095.3, 60 sec: 3686.3, 300 sec: 3665.6). Total num frames: 6217728. Throughput: 0: 909.3. Samples: 1553756. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:51:11,505][00035] Avg episode reward: [(0, '-3.657')] [2024-08-05 08:51:11,690][00150] DAMAGECOUNT value on done: 6252.0 [2024-08-05 08:51:11,691][00150] Sum rewards: -0.644, reward structure: {'DEATHCOUNT': '-8.250', 'AMMO5': '0.009', 'AMMO2': '0.029', 'ARMOR': '0.068', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.110', 'AMMO4': '0.147', 'weapon5': '0.176', 'HITCOUNT': '0.310', 'weapon4': '0.404', 'HEALTH': '0.576', 'WEAPON3': '0.650', 'weapon2': '0.754', 'FRAGCOUNT': '1.000', 'DAMAGECOUNT': '1.227', 'weapon3': '1.946'} [2024-08-05 08:51:12,219][00150] DAMAGECOUNT value on done: 7387.0 [2024-08-05 08:51:12,220][00150] Sum rewards: 1.259, reward structure: {'DEATHCOUNT': '-6.000', 'AMMO2': '0.007', 'AMMO5': '0.010', 'WEAPON1': '0.010', 'AMMO4': '0.036', 'weapon5': '0.038', 'WEAPON5': '0.050', 'WEAPON4': '0.050', 'ARMOR': '0.052', 'HEALTH': '0.092', 'AMMO3': '0.095', 'weapon4': '0.142', 'HITCOUNT': '0.190', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.678', 'weapon2': '1.330', 'weapon3': '1.878', 'FRAGCOUNT': '2.000'} [2024-08-05 08:51:12,798][00150] DAMAGECOUNT value on done: 7331.0 [2024-08-05 08:51:12,799][00150] Sum rewards: -5.341, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-2.270', 'AMMO4': '-0.004', 'AMMO2': '-0.001', 'AMMO5': '0.003', 'WEAPON5': '0.050', 'weapon5': '0.054', 'ARMOR': '0.076', 'AMMO3': '0.166', 'HITCOUNT': '0.180', 'DAMAGECOUNT': '0.735', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon2': '1.554', 'weapon3': '1.866'} [2024-08-05 08:51:13,353][00150] DAMAGECOUNT value on done: 7842.0 [2024-08-05 08:51:13,354][00150] Sum rewards: -0.149, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.461', 'AMMO4': '-0.019', 'AMMO2': '-0.004', 'AMMO5': '0.003', 'weapon5': '0.044', 'WEAPON5': '0.050', 'ARMOR': '0.097', 'WEAPON4': '0.100', 'weapon4': '0.110', 'AMMO3': '0.157', 'HITCOUNT': '0.310', 'WEAPON3': '0.850', 'DAMAGECOUNT': '1.218', 'weapon2': '1.392', 'weapon3': '1.754', 'FRAGCOUNT': '3.500'} [2024-08-05 08:51:13,633][00146] Updated weights for policy 0, policy_version 760 (0.0023) [2024-08-05 08:51:16,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 6234112. Throughput: 0: 911.3. Samples: 1559316. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:51:16,502][00035] Avg episode reward: [(0, '-3.555')] [2024-08-05 08:51:21,500][00035] Fps is (10 sec: 3277.4, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 6250496. Throughput: 0: 920.4. Samples: 1562096. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:51:21,502][00035] Avg episode reward: [(0, '-3.555')] [2024-08-05 08:51:25,738][00147] DAMAGECOUNT value on done: 8057.0 [2024-08-05 08:51:26,286][00147] DAMAGECOUNT value on done: 7049.0 [2024-08-05 08:51:26,287][00147] Sum rewards: -2.779, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.620', 'AMMO2': '0.008', 'AMMO5': '0.010', 'AMMO4': '0.040', 'weapon5': '0.098', 'WEAPON5': '0.100', 'AMMO3': '0.152', 'HITCOUNT': '0.280', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '1.064', 'DAMAGECOUNT': '1.155', 'weapon3': '2.284'} [2024-08-05 08:51:26,500][00035] Fps is (10 sec: 3276.7, 60 sec: 3549.8, 300 sec: 3637.8). Total num frames: 6266880. Throughput: 0: 920.9. Samples: 1567636. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:51:26,502][00035] Avg episode reward: [(0, '-3.521')] [2024-08-05 08:51:26,909][00147] DAMAGECOUNT value on done: 6390.0 [2024-08-05 08:51:26,910][00147] Sum rewards: -0.551, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.656', 'AMMO4': '-0.016', 'AMMO2': '-0.003', 'AMMO5': '0.005', 'ARMOR': '0.048', 'AMMO3': '0.126', 'HITCOUNT': '0.190', 'WEAPON3': '0.650', 'DAMAGECOUNT': '0.717', 'weapon3': '1.710', 'weapon2': '1.928', 'FRAGCOUNT': '3.000'} [2024-08-05 08:51:27,168][00148] DAMAGECOUNT value on done: 7354.0 [2024-08-05 08:51:27,170][00148] Sum rewards: -2.314, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.920', 'AMMO4': '-0.042', 'AMMO2': '-0.008', 'AMMO5': '0.005', 'ARMOR': '0.032', 'AMMO3': '0.125', 'HITCOUNT': '0.170', 'DAMAGECOUNT': '0.624', 'WEAPON3': '0.750', 'weapon3': '1.260', 'weapon2': '1.440', 'FRAGCOUNT': '2.000'} [2024-08-05 08:51:27,468][00147] DAMAGECOUNT value on done: 6490.0 [2024-08-05 08:51:27,739][00148] DAMAGECOUNT value on done: 6086.0 [2024-08-05 08:51:27,741][00148] Sum rewards: -6.499, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-1.232', 'AMMO5': '0.003', 'AMMO2': '0.026', 'WEAPON5': '0.050', 'weapon5': '0.056', 'weapon4': '0.076', 'ARMOR': '0.096', 'AMMO4': '0.127', 'AMMO3': '0.150', 'HITCOUNT': '0.190', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.597', 'WEAPON3': '0.850', 'weapon3': '1.308', 'weapon2': '1.754', 'FRAGCOUNT': '2.000'} [2024-08-05 08:51:28,310][00148] DAMAGECOUNT value on done: 6667.0 [2024-08-05 08:51:28,312][00148] Sum rewards: -6.431, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-2.016', 'AMMO4': '-0.006', 'AMMO2': '-0.001', 'WEAPON1': '0.010', 'AMMO5': '0.012', 'ARMOR': '0.050', 'weapon4': '0.050', 'WEAPON4': '0.100', 'weapon5': '0.112', 'AMMO3': '0.155', 'WEAPON5': '0.200', 'HITCOUNT': '0.220', 'WEAPON3': '0.650', 'DAMAGECOUNT': '0.795', 'FRAGCOUNT': '1.000', 'weapon3': '1.718', 'weapon2': '1.770'} [2024-08-05 08:51:28,849][00148] DAMAGECOUNT value on done: 6709.0 [2024-08-05 08:51:28,850][00148] Sum rewards: -2.245, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.838', 'AMMO2': '0.001', 'AMMO4': '0.004', 'AMMO5': '0.007', 'ARMOR': '0.010', 'weapon5': '0.084', 'AMMO3': '0.131', 'WEAPON5': '0.150', 'HITCOUNT': '0.200', 'WEAPON4': '0.200', 'weapon4': '0.236', 'WEAPON3': '0.650', 'DAMAGECOUNT': '0.825', 'FRAGCOUNT': '1.000', 'weapon2': '1.034', 'weapon3': '1.560'} [2024-08-05 08:51:31,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 6291456. Throughput: 0: 916.7. Samples: 1573122. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:51:31,502][00035] Avg episode reward: [(0, '-3.610')] [2024-08-05 08:51:35,744][00146] Updated weights for policy 0, policy_version 770 (0.0017) [2024-08-05 08:51:36,505][00035] Fps is (10 sec: 4094.3, 60 sec: 3686.1, 300 sec: 3665.5). Total num frames: 6307840. Throughput: 0: 920.9. Samples: 1575978. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:51:36,506][00035] Avg episode reward: [(0, '-3.610')] [2024-08-05 08:51:41,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 6324224. Throughput: 0: 908.5. Samples: 1581068. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:51:41,502][00035] Avg episode reward: [(0, '-3.610')] [2024-08-05 08:51:44,657][00149] DAMAGECOUNT value on done: 6522.0 [2024-08-05 08:51:44,658][00149] Sum rewards: -4.194, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.757', 'AMMO2': '0.002', 'AMMO4': '0.008', 'WEAPON4': '0.050', 'ARMOR': '0.052', 'weapon4': '0.148', 'AMMO3': '0.152', 'HITCOUNT': '0.200', 'DAMAGECOUNT': '0.615', 'WEAPON3': '0.850', 'weapon3': '1.460', 'weapon2': '1.776', 'FRAGCOUNT': '2.000'} [2024-08-05 08:51:45,216][00149] DAMAGECOUNT value on done: 5778.0 [2024-08-05 08:51:45,216][00149] Sum rewards: -2.308, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.032', 'AMMO5': '0.005', 'weapon5': '0.012', 'AMMO2': '0.024', 'WEAPON5': '0.050', 'AMMO3': '0.118', 'AMMO4': '0.119', 'HITCOUNT': '0.140', 'WEAPON4': '0.150', 'weapon4': '0.252', 'DAMAGECOUNT': '0.450', 'WEAPON3': '0.600', 'weapon3': '1.374', 'weapon2': '1.430', 'FRAGCOUNT': '2.000'} [2024-08-05 08:51:45,791][00149] DAMAGECOUNT value on done: 7449.0 [2024-08-05 08:51:45,792][00149] Sum rewards: -1.355, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.215', 'AMMO4': '-0.011', 'AMMO2': '-0.002', 'AMMO5': '0.010', 'WEAPON4': '0.100', 'weapon4': '0.120', 'AMMO3': '0.126', 'WEAPON5': '0.150', 'HITCOUNT': '0.270', 'weapon5': '0.368', 'WEAPON3': '0.700', 'DAMAGECOUNT': '1.125', 'weapon2': '1.196', 'weapon3': '1.708', 'FRAGCOUNT': '3.000'} [2024-08-05 08:51:46,330][00149] DAMAGECOUNT value on done: 7049.0 [2024-08-05 08:51:46,331][00149] Sum rewards: -5.324, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-1.778', 'AMMO4': '-0.018', 'AMMO2': '-0.004', 'weapon5': '0.002', 'AMMO5': '0.005', 'ARMOR': '0.032', 'WEAPON5': '0.100', 'AMMO3': '0.164', 'HITCOUNT': '0.240', 'WEAPON3': '0.750', 'DAMAGECOUNT': '1.035', 'weapon3': '1.288', 'weapon2': '1.860', 'FRAGCOUNT': '3.000'} [2024-08-05 08:51:46,500][00035] Fps is (10 sec: 3278.3, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 6340608. Throughput: 0: 905.5. Samples: 1586504. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:51:46,502][00035] Avg episode reward: [(0, '-3.633')] [2024-08-05 08:51:48,148][00150] DAMAGECOUNT value on done: 6590.0 [2024-08-05 08:51:48,149][00150] Sum rewards: -1.453, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.070', 'AMMO5': '0.007', 'AMMO2': '0.020', 'AMMO4': '0.101', 'weapon5': '0.104', 'AMMO3': '0.106', 'WEAPON5': '0.150', 'HITCOUNT': '0.330', 'WEAPON3': '0.550', 'DAMAGECOUNT': '1.014', 'weapon3': '1.468', 'weapon2': '1.766', 'FRAGCOUNT': '2.000'} [2024-08-05 08:51:48,715][00150] DAMAGECOUNT value on done: 7548.0 [2024-08-05 08:51:48,716][00150] Sum rewards: 0.079, reward structure: {'DEATHCOUNT': '-4.500', 'HEALTH': '-0.405', 'AMMO2': '0.016', 'HITCOUNT': '0.030', 'weapon7': '0.048', 'WEAPON4': '0.050', 'AMMO3': '0.063', 'AMMO4': '0.082', 'ARMOR': '0.096', 'AMMO6': '0.100', 'AMMO7': '0.100', 'WEAPON7': '0.100', 'weapon4': '0.170', 'WEAPON3': '0.400', 'DAMAGECOUNT': '0.483', 'weapon3': '0.992', 'FRAGCOUNT': '1.000', 'weapon2': '1.254'} [2024-08-05 08:51:49,253][00150] DAMAGECOUNT value on done: 7546.0 [2024-08-05 08:51:49,254][00150] Sum rewards: -2.458, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.228', 'AMMO5': '0.003', 'AMMO2': '0.016', 'WEAPON5': '0.050', 'AMMO4': '0.079', 'AMMO3': '0.096', 'HITCOUNT': '0.180', 'WEAPON4': '0.250', 'weapon4': '0.314', 'ARMOR': '0.456', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.645', 'weapon3': '1.492', 'weapon2': '1.590', 'FRAGCOUNT': '2.000'} [2024-08-05 08:51:49,869][00150] DAMAGECOUNT value on done: 8127.0 [2024-08-05 08:51:49,870][00150] Sum rewards: -8.919, reward structure: {'DEATHCOUNT': '-14.250', 'HEALTH': '-1.614', 'AMMO5': '0.005', 'AMMO2': '0.019', 'weapon5': '0.072', 'ARMOR': '0.076', 'AMMO4': '0.095', 'WEAPON5': '0.100', 'weapon4': '0.122', 'WEAPON4': '0.150', 'AMMO3': '0.203', 'HITCOUNT': '0.270', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.855', 'weapon2': '1.190', 'WEAPON3': '1.200', 'weapon3': '2.088'} [2024-08-05 08:51:51,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 6356992. Throughput: 0: 906.0. Samples: 1589232. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:51:51,502][00035] Avg episode reward: [(0, '-3.646')] [2024-08-05 08:51:56,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 6381568. Throughput: 0: 911.5. Samples: 1594774. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:51:56,502][00035] Avg episode reward: [(0, '-3.646')] [2024-08-05 08:51:58,683][00146] Updated weights for policy 0, policy_version 780 (0.0023) [2024-08-05 08:52:01,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 6397952. Throughput: 0: 909.6. Samples: 1600250. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:52:01,502][00035] Avg episode reward: [(0, '-3.646')] [2024-08-05 08:52:03,440][00147] DAMAGECOUNT value on done: 8192.0 [2024-08-05 08:52:03,441][00147] Sum rewards: -4.137, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.578', 'AMMO5': '0.009', 'AMMO2': '0.012', 'ARMOR': '0.016', 'AMMO4': '0.058', 'HITCOUNT': '0.070', 'AMMO3': '0.129', 'weapon5': '0.154', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.405', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.600', 'weapon3': '1.434', 'weapon2': '1.854'} [2024-08-05 08:52:04,052][00147] DAMAGECOUNT value on done: 7524.0 [2024-08-05 08:52:04,053][00147] Sum rewards: -3.556, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-2.370', 'WEAPON1': '0.010', 'AMMO2': '0.012', 'ARMOR': '0.028', 'AMMO4': '0.060', 'WEAPON4': '0.150', 'AMMO3': '0.167', 'weapon4': '0.206', 'HITCOUNT': '0.360', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.425', 'weapon3': '1.464', 'weapon2': '1.882', 'FRAGCOUNT': '5.000'} [2024-08-05 08:52:04,522][00148] DAMAGECOUNT value on done: 7598.0 [2024-08-05 08:52:04,523][00148] Sum rewards: -2.783, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.574', 'AMMO2': '0.003', 'AMMO5': '0.005', 'AMMO4': '0.014', 'weapon5': '0.026', 'ARMOR': '0.070', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.193', 'HITCOUNT': '0.260', 'DAMAGECOUNT': '0.732', 'WEAPON3': '0.950', 'weapon2': '1.528', 'weapon3': '2.060', 'FRAGCOUNT': '4.000'} [2024-08-05 08:52:04,576][00147] DAMAGECOUNT value on done: 6595.0 [2024-08-05 08:52:05,052][00148] DAMAGECOUNT value on done: 6096.0 [2024-08-05 08:52:05,053][00148] Sum rewards: -8.235, reward structure: {'DEATHCOUNT': '-11.250', 'FRAGCOUNT': '-1.500', 'HEALTH': '-0.542', 'AMMO2': '0.001', 'AMMO5': '0.005', 'AMMO4': '0.006', 'HITCOUNT': '0.020', 'DAMAGECOUNT': '0.030', 'weapon5': '0.036', 'weapon7': '0.042', 'WEAPON5': '0.050', 'ARMOR': '0.052', 'AMMO6': '0.100', 'WEAPON7': '0.100', 'AMMO7': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.181', 'weapon4': '0.198', 'weapon2': '1.012', 'WEAPON3': '1.050', 'weapon3': '1.974'} [2024-08-05 08:52:05,147][00147] DAMAGECOUNT value on done: 6629.0 [2024-08-05 08:52:05,621][00148] DAMAGECOUNT value on done: 7019.0 [2024-08-05 08:52:05,623][00148] Sum rewards: -7.939, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-2.680', 'AMMO5': '0.003', 'ARMOR': '0.008', 'AMMO2': '0.016', 'weapon4': '0.054', 'AMMO4': '0.082', 'AMMO3': '0.123', 'WEAPON4': '0.200', 'HITCOUNT': '0.310', 'WEAPON3': '0.850', 'DAMAGECOUNT': '1.056', 'weapon2': '1.606', 'weapon3': '1.932', 'FRAGCOUNT': '2.000'} [2024-08-05 08:52:06,159][00148] DAMAGECOUNT value on done: 6794.0 [2024-08-05 08:52:06,160][00148] Sum rewards: -7.599, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-2.500', 'AMMO5': '0.005', 'AMMO2': '0.018', 'HITCOUNT': '0.090', 'AMMO4': '0.091', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'weapon5': '0.208', 'AMMO3': '0.244', 'DAMAGECOUNT': '0.255', 'weapon4': '0.424', 'ARMOR': '0.487', 'FRAGCOUNT': '1.000', 'weapon2': '1.158', 'WEAPON3': '1.200', 'weapon3': '1.520'} [2024-08-05 08:52:06,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 6414336. Throughput: 0: 909.0. Samples: 1603000. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:52:06,502][00035] Avg episode reward: [(0, '-3.752')] [2024-08-05 08:52:11,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3550.0, 300 sec: 3637.8). Total num frames: 6430720. Throughput: 0: 898.8. Samples: 1608082. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:52:11,502][00035] Avg episode reward: [(0, '-3.752')] [2024-08-05 08:52:16,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 6447104. Throughput: 0: 902.8. Samples: 1613746. Policy #0 lag: (min: 0.0, avg: 0.0, max: 1.0) [2024-08-05 08:52:16,502][00035] Avg episode reward: [(0, '-3.752')] [2024-08-05 08:52:20,942][00149] DAMAGECOUNT value on done: 6874.0 [2024-08-05 08:52:20,943][00149] Sum rewards: -0.823, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.385', 'AMMO5': '0.010', 'AMMO2': '0.016', 'WEAPON1': '0.020', 'ARMOR': '0.048', 'weapon4': '0.050', 'AMMO4': '0.082', 'AMMO3': '0.104', 'WEAPON5': '0.150', 'weapon5': '0.166', 'WEAPON4': '0.200', 'HITCOUNT': '0.310', 'WEAPON3': '0.650', 'DAMAGECOUNT': '1.056', 'weapon2': '1.522', 'weapon3': '1.678', 'FRAGCOUNT': '2.000'} [2024-08-05 08:52:21,241][00146] Updated weights for policy 0, policy_version 790 (0.0023) [2024-08-05 08:52:21,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 6471680. Throughput: 0: 900.8. Samples: 1616508. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:52:21,502][00035] Avg episode reward: [(0, '-3.691')] [2024-08-05 08:52:21,510][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000790_6471680.pth... [2024-08-05 08:52:21,531][00149] DAMAGECOUNT value on done: 5868.0 [2024-08-05 08:52:21,532][00149] Sum rewards: -5.800, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.615', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.005', 'AMMO2': '0.011', 'AMMO4': '0.055', 'weapon5': '0.056', 'HITCOUNT': '0.100', 'WEAPON5': '0.100', 'ARMOR': '0.120', 'AMMO3': '0.128', 'WEAPON4': '0.250', 'DAMAGECOUNT': '0.270', 'weapon4': '0.294', 'WEAPON3': '0.900', 'weapon2': '1.258', 'weapon3': '1.768'} [2024-08-05 08:52:21,612][00137] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000683_5595136.pth [2024-08-05 08:52:22,083][00149] DAMAGECOUNT value on done: 7714.0 [2024-08-05 08:52:22,084][00149] Sum rewards: -2.099, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.210', 'AMMO2': '0.002', 'AMMO5': '0.003', 'AMMO4': '0.009', 'ARMOR': '0.040', 'weapon5': '0.086', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.117', 'HITCOUNT': '0.190', 'DAMAGECOUNT': '0.795', 'WEAPON3': '0.850', 'weapon2': '1.592', 'weapon3': '1.728', 'FRAGCOUNT': '2.000'} [2024-08-05 08:52:22,633][00149] DAMAGECOUNT value on done: 7194.0 [2024-08-05 08:52:24,234][00150] DAMAGECOUNT value on done: 6693.0 [2024-08-05 08:52:24,781][00150] DAMAGECOUNT value on done: 8113.0 [2024-08-05 08:52:24,782][00150] Sum rewards: -2.586, reward structure: {'DEATHCOUNT': '-12.000', 'AMMO5': '0.003', 'AMMO2': '0.014', 'weapon5': '0.022', 'WEAPON5': '0.050', 'HEALTH': '0.050', 'AMMO4': '0.072', 'ARMOR': '0.087', 'WEAPON4': '0.150', 'AMMO3': '0.165', 'weapon4': '0.364', 'HITCOUNT': '0.410', 'WEAPON3': '0.850', 'weapon3': '1.390', 'weapon2': '1.592', 'DAMAGECOUNT': '1.695', 'FRAGCOUNT': '2.500'} [2024-08-05 08:52:25,326][00150] DAMAGECOUNT value on done: 7676.0 [2024-08-05 08:52:25,930][00150] DAMAGECOUNT value on done: 8277.0 [2024-08-05 08:52:25,931][00150] Sum rewards: -6.598, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.640', 'AMMO2': '0.032', 'HITCOUNT': '0.110', 'AMMO3': '0.111', 'AMMO4': '0.158', 'weapon4': '0.218', 'WEAPON4': '0.400', 'DAMAGECOUNT': '0.450', 'ARMOR': '0.457', 'WEAPON3': '0.650', 'FRAGCOUNT': '1.000', 'weapon3': '1.286', 'weapon2': '1.670'} [2024-08-05 08:52:26,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 6488064. Throughput: 0: 910.8. Samples: 1622052. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:52:26,502][00035] Avg episode reward: [(0, '-3.704')] [2024-08-05 08:52:31,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3665.6). Total num frames: 6504448. Throughput: 0: 911.8. Samples: 1627534. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:52:31,502][00035] Avg episode reward: [(0, '-3.704')] [2024-08-05 08:52:36,503][00035] Fps is (10 sec: 3276.0, 60 sec: 3550.0, 300 sec: 3637.8). Total num frames: 6520832. Throughput: 0: 913.8. Samples: 1630354. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:52:36,504][00035] Avg episode reward: [(0, '-3.704')] [2024-08-05 08:52:41,371][00147] DAMAGECOUNT value on done: 8319.0 [2024-08-05 08:52:41,372][00147] Sum rewards: -3.899, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.482', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.003', 'WEAPON1': '0.010', 'AMMO2': '0.017', 'WEAPON5': '0.050', 'AMMO4': '0.087', 'AMMO3': '0.091', 'ARMOR': '0.096', 'HITCOUNT': '0.100', 'weapon5': '0.176', 'WEAPON4': '0.300', 'weapon4': '0.354', 'DAMAGECOUNT': '0.381', 'WEAPON3': '0.650', 'weapon2': '1.258', 'weapon3': '1.260'} [2024-08-05 08:52:41,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 6545408. Throughput: 0: 912.5. Samples: 1635838. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:52:41,501][00035] Avg episode reward: [(0, '-3.698')] [2024-08-05 08:52:41,972][00147] DAMAGECOUNT value on done: 8009.0 [2024-08-05 08:52:41,973][00147] Sum rewards: 0.234, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.175', 'AMMO2': '0.004', 'AMMO4': '0.017', 'ARMOR': '0.028', 'weapon4': '0.088', 'WEAPON4': '0.100', 'AMMO3': '0.191', 'HITCOUNT': '0.320', 'weapon2': '0.924', 'WEAPON3': '0.950', 'DAMAGECOUNT': '1.455', 'weapon3': '2.332', 'FRAGCOUNT': '4.000'} [2024-08-05 08:52:42,311][00148] DAMAGECOUNT value on done: 7754.0 [2024-08-05 08:52:42,312][00148] Sum rewards: -1.875, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.536', 'AMMO2': '0.003', 'AMMO5': '0.010', 'AMMO4': '0.013', 'weapon5': '0.024', 'weapon4': '0.038', 'WEAPON4': '0.050', 'ARMOR': '0.052', 'AMMO3': '0.107', 'HITCOUNT': '0.150', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.468', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '1.760', 'weapon2': '1.836'} [2024-08-05 08:52:42,542][00147] DAMAGECOUNT value on done: 6765.0 [2024-08-05 08:52:42,543][00147] Sum rewards: -4.919, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.763', 'AMMO5': '0.005', 'AMMO2': '0.010', 'AMMO4': '0.049', 'ARMOR': '0.052', 'weapon4': '0.056', 'weapon5': '0.060', 'WEAPON5': '0.100', 'HITCOUNT': '0.150', 'WEAPON4': '0.150', 'AMMO3': '0.154', 'DAMAGECOUNT': '0.510', 'WEAPON3': '0.850', 'FRAGCOUNT': '1.000', 'weapon2': '1.516', 'weapon3': '1.932'} [2024-08-05 08:52:42,886][00148] DAMAGECOUNT value on done: 6385.0 [2024-08-05 08:52:42,887][00148] Sum rewards: -3.516, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.632', 'AMMO5': '0.010', 'AMMO2': '0.011', 'ARMOR': '0.020', 'weapon5': '0.048', 'AMMO4': '0.056', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.120', 'weapon4': '0.220', 'HITCOUNT': '0.270', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.750', 'weapon2': '0.850', 'DAMAGECOUNT': '0.867', 'weapon3': '2.194'} [2024-08-05 08:52:43,101][00147] DAMAGECOUNT value on done: 6809.0 [2024-08-05 08:52:43,102][00147] Sum rewards: -4.542, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.540', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.014', 'AMMO2': '-0.003', 'AMMO5': '0.003', 'WEAPON1': '0.010', 'weapon5': '0.028', 'WEAPON5': '0.050', 'ARMOR': '0.124', 'HITCOUNT': '0.130', 'AMMO3': '0.134', 'WEAPON4': '0.150', 'weapon4': '0.334', 'DAMAGECOUNT': '0.540', 'WEAPON3': '0.750', 'weapon3': '1.254', 'weapon2': '1.508'} [2024-08-05 08:52:43,424][00148] DAMAGECOUNT value on done: 7404.0 [2024-08-05 08:52:43,424][00148] Sum rewards: -2.240, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-2.685', 'AMMO4': '-0.018', 'AMMO2': '-0.004', 'AMMO5': '0.005', 'WEAPON4': '0.100', 'AMMO3': '0.125', 'weapon4': '0.156', 'HITCOUNT': '0.350', 'ARMOR': '0.500', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.155', 'weapon2': '1.216', 'weapon3': '1.960', 'FRAGCOUNT': '3.000'} [2024-08-05 08:52:43,809][00146] Updated weights for policy 0, policy_version 800 (0.0031) [2024-08-05 08:52:43,987][00148] DAMAGECOUNT value on done: 6889.0 [2024-08-05 08:52:46,500][00035] Fps is (10 sec: 4096.9, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 6561792. Throughput: 0: 907.2. Samples: 1641074. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:52:46,502][00035] Avg episode reward: [(0, '-3.667')] [2024-08-05 08:52:51,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 6578176. Throughput: 0: 908.0. Samples: 1643862. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:52:51,502][00035] Avg episode reward: [(0, '-3.667')] [2024-08-05 08:52:56,500][00035] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 6594560. Throughput: 0: 916.9. Samples: 1649342. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:52:56,502][00035] Avg episode reward: [(0, '-3.667')] [2024-08-05 08:52:57,311][00149] DAMAGECOUNT value on done: 6889.0 [2024-08-05 08:52:57,867][00149] DAMAGECOUNT value on done: 6218.0 [2024-08-05 08:52:57,868][00149] Sum rewards: -3.902, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.336', 'AMMO5': '0.005', 'AMMO2': '0.024', 'ARMOR': '0.040', 'WEAPON4': '0.050', 'AMMO4': '0.122', 'weapon4': '0.154', 'AMMO3': '0.161', 'HITCOUNT': '0.270', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'DAMAGECOUNT': '1.050', 'weapon2': '1.606', 'weapon3': '1.802'} [2024-08-05 08:52:58,431][00149] DAMAGECOUNT value on done: 7874.0 [2024-08-05 08:52:58,432][00149] Sum rewards: -2.320, reward structure: {'DEATHCOUNT': '-8.250', 'AMMO5': '0.003', 'AMMO2': '0.022', 'weapon5': '0.022', 'WEAPON4': '0.050', 'WEAPON5': '0.050', 'AMMO3': '0.101', 'AMMO4': '0.108', 'weapon4': '0.128', 'HITCOUNT': '0.150', 'ARMOR': '0.400', 'WEAPON3': '0.450', 'HEALTH': '0.460', 'DAMAGECOUNT': '0.480', 'FRAGCOUNT': '1.000', 'weapon3': '1.188', 'weapon2': '1.318'} [2024-08-05 08:52:58,981][00149] DAMAGECOUNT value on done: 7646.0 [2024-08-05 08:52:58,982][00149] Sum rewards: -1.035, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.791', 'AMMO5': '0.005', 'AMMO2': '0.009', 'ARMOR': '0.028', 'WEAPON1': '0.040', 'AMMO4': '0.045', 'WEAPON5': '0.100', 'AMMO3': '0.146', 'WEAPON4': '0.150', 'weapon4': '0.210', 'HITCOUNT': '0.300', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.356', 'weapon2': '1.490', 'weapon3': '1.726', 'FRAGCOUNT': '4.000'} [2024-08-05 08:53:00,542][00150] DAMAGECOUNT value on done: 7028.0 [2024-08-05 08:53:00,543][00150] Sum rewards: -3.824, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-0.281', 'AMMO5': '0.007', 'WEAPON1': '0.010', 'AMMO2': '0.018', 'ARMOR': '0.036', 'AMMO4': '0.089', 'WEAPON5': '0.100', 'HITCOUNT': '0.170', 'AMMO3': '0.176', 'weapon5': '0.186', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.005', 'weapon2': '1.480', 'weapon3': '1.880', 'FRAGCOUNT': '2.500'} [2024-08-05 08:53:01,075][00150] DAMAGECOUNT value on done: 8233.0 [2024-08-05 08:53:01,076][00150] Sum rewards: -9.495, reward structure: {'DEATHCOUNT': '-11.250', 'FRAGCOUNT': '-2.000', 'HEALTH': '-1.756', 'AMMO5': '0.015', 'AMMO2': '0.020', 'weapon5': '0.080', 'AMMO4': '0.099', 'HITCOUNT': '0.100', 'AMMO3': '0.169', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.360', 'WEAPON3': '1.000', 'weapon2': '1.518', 'weapon3': '1.950'} [2024-08-05 08:53:01,500][00035] Fps is (10 sec: 3276.7, 60 sec: 3549.8, 300 sec: 3637.8). Total num frames: 6610944. Throughput: 0: 913.9. Samples: 1654870. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:53:01,502][00035] Avg episode reward: [(0, '-3.601')] [2024-08-05 08:53:01,743][00150] DAMAGECOUNT value on done: 7978.0 [2024-08-05 08:53:01,743][00150] Sum rewards: -3.935, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-1.574', 'AMMO5': '0.007', 'AMMO2': '0.013', 'weapon5': '0.026', 'ARMOR': '0.036', 'AMMO4': '0.063', 'WEAPON5': '0.150', 'AMMO3': '0.192', 'weapon4': '0.222', 'WEAPON4': '0.250', 'HITCOUNT': '0.250', 'weapon2': '0.810', 'DAMAGECOUNT': '0.906', 'WEAPON3': '1.050', 'weapon3': '2.414', 'FRAGCOUNT': '4.000'} [2024-08-05 08:53:02,302][00150] DAMAGECOUNT value on done: 8302.0 [2024-08-05 08:53:05,985][00146] Updated weights for policy 0, policy_version 810 (0.0020) [2024-08-05 08:53:06,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 6635520. Throughput: 0: 913.2. Samples: 1657602. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:53:06,502][00035] Avg episode reward: [(0, '-3.568')] [2024-08-05 08:53:11,500][00035] Fps is (10 sec: 4096.1, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 6651904. Throughput: 0: 913.8. Samples: 1663174. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:53:11,502][00035] Avg episode reward: [(0, '-3.568')] [2024-08-05 08:53:16,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 6668288. Throughput: 0: 907.3. Samples: 1668364. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:53:16,502][00035] Avg episode reward: [(0, '-3.568')] [2024-08-05 08:53:18,688][00147] DAMAGECOUNT value on done: 8464.0 [2024-08-05 08:53:19,186][00147] DAMAGECOUNT value on done: 8298.0 [2024-08-05 08:53:19,187][00147] Sum rewards: -1.511, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.230', 'AMMO4': '-0.079', 'AMMO2': '-0.016', 'AMMO5': '0.003', 'WEAPON1': '0.020', 'ARMOR': '0.064', 'WEAPON5': '0.100', 'AMMO3': '0.112', 'HITCOUNT': '0.290', 'weapon5': '0.380', 'WEAPON3': '0.750', 'DAMAGECOUNT': '0.867', 'weapon2': '1.326', 'weapon3': '1.652', 'FRAGCOUNT': '2.000'} [2024-08-05 08:53:19,803][00147] DAMAGECOUNT value on done: 6960.0 [2024-08-05 08:53:19,804][00147] Sum rewards: -2.972, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-0.360', 'AMMO5': '0.003', 'weapon5': '0.006', 'AMMO2': '0.017', 'ARMOR': '0.028', 'WEAPON5': '0.050', 'AMMO4': '0.084', 'AMMO3': '0.175', 'weapon4': '0.176', 'WEAPON4': '0.200', 'HITCOUNT': '0.210', 'DAMAGECOUNT': '0.585', 'WEAPON3': '1.000', 'weapon2': '1.340', 'FRAGCOUNT': '2.000', 'weapon3': '2.014'} [2024-08-05 08:53:19,838][00148] DAMAGECOUNT value on done: 7842.0 [2024-08-05 08:53:20,389][00147] DAMAGECOUNT value on done: 7109.0 [2024-08-05 08:53:20,390][00147] Sum rewards: -1.841, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.455', 'AMMO2': '0.007', 'AMMO5': '0.007', 'AMMO4': '0.032', 'weapon5': '0.036', 'WEAPON4': '0.050', 'ARMOR': '0.084', 'WEAPON5': '0.150', 'AMMO3': '0.169', 'weapon4': '0.178', 'HITCOUNT': '0.190', 'WEAPON3': '0.850', 'DAMAGECOUNT': '0.900', 'weapon2': '0.970', 'weapon3': '1.490', 'FRAGCOUNT': '2.000'} [2024-08-05 08:53:20,403][00148] DAMAGECOUNT value on done: 6575.0 [2024-08-05 08:53:20,404][00148] Sum rewards: -4.429, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.214', 'weapon5': '0.002', 'AMMO2': '0.008', 'AMMO5': '0.010', 'AMMO4': '0.040', 'ARMOR': '0.072', 'weapon7': '0.100', 'AMMO6': '0.120', 'AMMO7': '0.120', 'WEAPON4': '0.150', 'AMMO3': '0.182', 'HITCOUNT': '0.190', 'WEAPON7': '0.200', 'WEAPON5': '0.200', 'weapon4': '0.268', 'DAMAGECOUNT': '0.570', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '1.548', 'weapon3': '1.604'} [2024-08-05 08:53:20,953][00148] DAMAGECOUNT value on done: 7459.0 [2024-08-05 08:53:21,500][00035] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 6684672. Throughput: 0: 906.6. Samples: 1671148. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:53:21,502][00035] Avg episode reward: [(0, '-3.432')] [2024-08-05 08:53:21,511][00137] Saving new best policy, reward=-3.432! [2024-08-05 08:53:21,547][00148] DAMAGECOUNT value on done: 7035.0 [2024-08-05 08:53:21,548][00148] Sum rewards: -2.964, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-0.905', 'FRAGCOUNT': '-0.500', 'AMMO2': '0.009', 'WEAPON1': '0.010', 'AMMO5': '0.012', 'ARMOR': '0.024', 'AMMO4': '0.046', 'weapon4': '0.050', 'WEAPON4': '0.100', 'AMMO3': '0.129', 'HITCOUNT': '0.140', 'WEAPON5': '0.200', 'weapon5': '0.206', 'DAMAGECOUNT': '0.438', 'WEAPON3': '0.700', 'weapon3': '1.368', 'weapon2': '1.758'} [2024-08-05 08:53:26,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 6709248. Throughput: 0: 907.2. Samples: 1676662. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:53:26,502][00035] Avg episode reward: [(0, '-3.414')] [2024-08-05 08:53:26,503][00137] Saving new best policy, reward=-3.414! [2024-08-05 08:53:28,628][00146] Updated weights for policy 0, policy_version 820 (0.0019) [2024-08-05 08:53:31,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 6725632. Throughput: 0: 914.0. Samples: 1682206. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:53:31,502][00035] Avg episode reward: [(0, '-3.414')] [2024-08-05 08:53:33,542][00149] DAMAGECOUNT value on done: 7159.0 [2024-08-05 08:53:33,542][00149] Sum rewards: -1.424, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.372', 'AMMO2': '0.008', 'WEAPON1': '0.020', 'AMMO4': '0.039', 'weapon7': '0.080', 'WEAPON4': '0.100', 'ARMOR': '0.108', 'AMMO3': '0.113', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon4': '0.198', 'WEAPON7': '0.200', 'HITCOUNT': '0.240', 'WEAPON3': '0.650', 'DAMAGECOUNT': '0.810', 'weapon2': '1.332', 'weapon3': '1.810', 'FRAGCOUNT': '3.000'} [2024-08-05 08:53:34,052][00149] DAMAGECOUNT value on done: 6374.0 [2024-08-05 08:53:34,053][00149] Sum rewards: -0.820, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-1.650', 'AMMO2': '0.005', 'AMMO5': '0.010', 'AMMO4': '0.025', 'ARMOR': '0.074', 'weapon5': '0.078', 'AMMO3': '0.094', 'HITCOUNT': '0.160', 'WEAPON5': '0.200', 'WEAPON4': '0.300', 'weapon4': '0.302', 'DAMAGECOUNT': '0.468', 'WEAPON3': '0.550', 'FRAGCOUNT': '1.000', 'weapon2': '1.320', 'weapon3': '1.494'} [2024-08-05 08:53:34,577][00149] DAMAGECOUNT value on done: 8023.0 [2024-08-05 08:53:34,577][00149] Sum rewards: -1.041, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-0.550', 'AMMO4': '-0.044', 'AMMO2': '-0.009', 'AMMO5': '0.015', 'ARMOR': '0.032', 'weapon5': '0.042', 'AMMO3': '0.120', 'HITCOUNT': '0.140', 'WEAPON5': '0.150', 'DAMAGECOUNT': '0.447', 'WEAPON3': '0.600', 'weapon2': '1.356', 'weapon3': '1.410', 'FRAGCOUNT': '2.000'} [2024-08-05 08:53:35,119][00149] DAMAGECOUNT value on done: 7793.0 [2024-08-05 08:53:36,501][00035] Fps is (10 sec: 3276.6, 60 sec: 3686.5, 300 sec: 3637.8). Total num frames: 6742016. Throughput: 0: 914.8. Samples: 1685028. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:53:36,505][00035] Avg episode reward: [(0, '-3.487')] [2024-08-05 08:53:36,535][00150] DAMAGECOUNT value on done: 7178.0 [2024-08-05 08:53:36,536][00150] Sum rewards: -2.060, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.682', 'AMMO5': '0.005', 'AMMO2': '0.020', 'AMMO4': '0.100', 'WEAPON5': '0.100', 'ARMOR': '0.125', 'AMMO3': '0.128', 'HITCOUNT': '0.160', 'weapon4': '0.162', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.450', 'WEAPON3': '0.800', 'weapon2': '1.530', 'weapon3': '1.742', 'FRAGCOUNT': '3.000'} [2024-08-05 08:53:37,132][00150] DAMAGECOUNT value on done: 8996.0 [2024-08-05 08:53:37,133][00150] Sum rewards: -3.922, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.802', 'weapon7': '0.002', 'AMMO2': '0.002', 'AMMO5': '0.010', 'AMMO4': '0.011', 'WEAPON4': '0.050', 'ARMOR': '0.052', 'AMMO6': '0.100', 'WEAPON7': '0.100', 'AMMO7': '0.100', 'weapon5': '0.118', 'AMMO3': '0.147', 'WEAPON5': '0.150', 'weapon4': '0.182', 'HITCOUNT': '0.520', 'WEAPON3': '1.000', 'weapon2': '1.112', 'FRAGCOUNT': '1.500', 'weapon3': '1.934', 'DAMAGECOUNT': '2.289'} [2024-08-05 08:53:37,706][00150] DAMAGECOUNT value on done: 8183.0 [2024-08-05 08:53:37,706][00150] Sum rewards: -1.931, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.205', 'AMMO4': '-0.011', 'AMMO2': '-0.002', 'AMMO3': '0.102', 'HITCOUNT': '0.170', 'DAMAGECOUNT': '0.615', 'WEAPON3': '0.750', 'weapon3': '1.342', 'weapon2': '1.808', 'FRAGCOUNT': '3.000'} [2024-08-05 08:53:38,270][00150] DAMAGECOUNT value on done: 8451.0 [2024-08-05 08:53:38,271][00150] Sum rewards: -0.921, reward structure: {'DEATHCOUNT': '-7.500', 'AMMO5': '0.003', 'AMMO2': '0.035', 'WEAPON5': '0.050', 'AMMO3': '0.109', 'weapon5': '0.128', 'ARMOR': '0.131', 'HITCOUNT': '0.140', 'WEAPON4': '0.150', 'AMMO4': '0.172', 'DAMAGECOUNT': '0.447', 'HEALTH': '0.550', 'WEAPON3': '0.550', 'weapon4': '0.568', 'FRAGCOUNT': '1.000', 'weapon3': '1.240', 'weapon2': '1.306'} [2024-08-05 08:53:41,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 6758400. Throughput: 0: 915.6. Samples: 1690542. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:53:41,502][00035] Avg episode reward: [(0, '-3.429')] [2024-08-05 08:53:46,500][00035] Fps is (10 sec: 3277.0, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 6774784. Throughput: 0: 908.7. Samples: 1695762. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:53:46,502][00035] Avg episode reward: [(0, '-3.429')] [2024-08-05 08:53:50,985][00146] Updated weights for policy 0, policy_version 830 (0.0028) [2024-08-05 08:53:51,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 6799360. Throughput: 0: 908.8. Samples: 1698498. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:53:51,502][00035] Avg episode reward: [(0, '-3.429')] [2024-08-05 08:53:55,973][00147] DAMAGECOUNT value on done: 8584.0 [2024-08-05 08:53:55,974][00147] Sum rewards: -5.988, reward structure: {'DEATHCOUNT': '-8.250', 'FRAGCOUNT': '-1.500', 'HEALTH': '-1.396', 'AMMO5': '0.003', 'WEAPON1': '0.010', 'AMMO2': '0.013', 'WEAPON5': '0.050', 'ARMOR': '0.052', 'AMMO4': '0.066', 'HITCOUNT': '0.100', 'weapon5': '0.124', 'AMMO3': '0.138', 'weapon4': '0.146', 'WEAPON4': '0.150', 'DAMAGECOUNT': '0.360', 'WEAPON3': '0.800', 'weapon2': '1.134', 'weapon3': '2.012'} [2024-08-05 08:53:56,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 6815744. Throughput: 0: 909.1. Samples: 1704084. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:53:56,502][00035] Avg episode reward: [(0, '-3.442')] [2024-08-05 08:53:56,530][00147] DAMAGECOUNT value on done: 8485.0 [2024-08-05 08:53:56,531][00147] Sum rewards: -6.361, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-0.630', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.003', 'AMMO2': '0.009', 'AMMO4': '0.044', 'WEAPON5': '0.050', 'weapon5': '0.072', 'AMMO3': '0.121', 'HITCOUNT': '0.160', 'weapon4': '0.182', 'WEAPON4': '0.200', 'ARMOR': '0.452', 'DAMAGECOUNT': '0.561', 'WEAPON3': '0.650', 'weapon2': '1.268', 'weapon3': '1.498'} [2024-08-05 08:53:57,179][00147] DAMAGECOUNT value on done: 7025.0 [2024-08-05 08:53:57,180][00147] Sum rewards: -3.377, reward structure: {'DEATHCOUNT': '-9.750', 'weapon5': '0.006', 'AMMO5': '0.008', 'AMMO2': '0.021', 'weapon4': '0.066', 'HITCOUNT': '0.070', 'ARMOR': '0.076', 'WEAPON5': '0.100', 'AMMO3': '0.103', 'AMMO4': '0.104', 'WEAPON4': '0.150', 'DAMAGECOUNT': '0.195', 'HEALTH': '0.399', 'WEAPON3': '0.650', 'FRAGCOUNT': '1.000', 'weapon2': '1.470', 'weapon3': '1.956'} [2024-08-05 08:53:57,358][00148] DAMAGECOUNT value on done: 8112.0 [2024-08-05 08:53:57,359][00148] Sum rewards: -8.735, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-0.920', 'FRAGCOUNT': '-0.500', 'AMMO2': '0.001', 'AMMO4': '0.004', 'AMMO5': '0.015', 'weapon5': '0.086', 'WEAPON5': '0.150', 'AMMO3': '0.187', 'HITCOUNT': '0.210', 'DAMAGECOUNT': '0.810', 'WEAPON3': '0.850', 'weapon2': '1.114', 'weapon3': '2.008'} [2024-08-05 08:53:57,746][00147] DAMAGECOUNT value on done: 7432.0 [2024-08-05 08:53:57,747][00147] Sum rewards: -2.538, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.195', 'AMMO2': '0.005', 'AMMO5': '0.005', 'AMMO4': '0.024', 'WEAPON5': '0.050', 'AMMO3': '0.144', 'weapon5': '0.180', 'HITCOUNT': '0.200', 'WEAPON3': '0.900', 'DAMAGECOUNT': '0.969', 'weapon3': '1.452', 'weapon2': '1.728', 'FRAGCOUNT': '2.000'} [2024-08-05 08:53:57,946][00148] DAMAGECOUNT value on done: 6765.0 [2024-08-05 08:53:58,501][00148] DAMAGECOUNT value on done: 7503.0 [2024-08-05 08:53:59,024][00148] DAMAGECOUNT value on done: 7291.0 [2024-08-05 08:53:59,025][00148] Sum rewards: -5.533, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-2.372', 'AMMO5': '0.003', 'AMMO2': '0.011', 'ARMOR': '0.044', 'AMMO4': '0.052', 'WEAPON4': '0.100', 'AMMO3': '0.196', 'weapon4': '0.202', 'HITCOUNT': '0.240', 'DAMAGECOUNT': '0.768', 'WEAPON3': '1.050', 'weapon2': '1.322', 'FRAGCOUNT': '2.000', 'weapon3': '2.102'} [2024-08-05 08:54:01,500][00035] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 6832128. Throughput: 0: 913.1. Samples: 1709454. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:54:01,502][00035] Avg episode reward: [(0, '-3.464')] [2024-08-05 08:54:06,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 6848512. Throughput: 0: 913.0. Samples: 1712234. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:54:06,502][00035] Avg episode reward: [(0, '-3.464')] [2024-08-05 08:54:09,979][00149] DAMAGECOUNT value on done: 7319.0 [2024-08-05 08:54:09,980][00149] Sum rewards: -2.240, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.674', 'ARMOR': '0.004', 'AMMO2': '0.012', 'AMMO5': '0.012', 'WEAPON4': '0.050', 'AMMO4': '0.059', 'HITCOUNT': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.126', 'weapon4': '0.248', 'DAMAGECOUNT': '0.480', 'WEAPON3': '0.600', 'weapon2': '1.106', 'weapon3': '1.536', 'FRAGCOUNT': '3.000'} [2024-08-05 08:54:10,562][00149] DAMAGECOUNT value on done: 6649.0 [2024-08-05 08:54:10,564][00149] Sum rewards: -2.746, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.270', 'AMMO2': '0.002', 'AMMO5': '0.003', 'AMMO4': '0.008', 'ARMOR': '0.020', 'AMMO3': '0.136', 'HITCOUNT': '0.190', 'DAMAGECOUNT': '0.825', 'WEAPON3': '0.900', 'weapon2': '1.188', 'weapon3': '2.002', 'FRAGCOUNT': '3.000'} [2024-08-05 08:54:11,123][00149] DAMAGECOUNT value on done: 8263.0 [2024-08-05 08:54:11,124][00149] Sum rewards: -9.448, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-2.436', 'AMMO2': '0.012', 'AMMO5': '0.012', 'ARMOR': '0.044', 'AMMO4': '0.059', 'weapon5': '0.112', 'WEAPON5': '0.150', 'AMMO3': '0.166', 'WEAPON4': '0.200', 'HITCOUNT': '0.230', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.720', 'WEAPON3': '0.850', 'weapon2': '1.610', 'weapon3': '1.822'} [2024-08-05 08:54:11,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 6873088. Throughput: 0: 911.9. Samples: 1717698. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:54:11,501][00035] Avg episode reward: [(0, '-3.483')] [2024-08-05 08:54:11,733][00149] DAMAGECOUNT value on done: 8044.0 [2024-08-05 08:54:11,734][00149] Sum rewards: -7.136, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-1.748', 'weapon4': '0.006', 'AMMO2': '0.021', 'AMMO5': '0.022', 'weapon5': '0.024', 'ARMOR': '0.068', 'WEAPON4': '0.100', 'AMMO4': '0.106', 'AMMO3': '0.159', 'HITCOUNT': '0.270', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.753', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.050', 'weapon2': '1.450', 'weapon3': '2.032'} [2024-08-05 08:54:12,829][00150] DAMAGECOUNT value on done: 7282.0 [2024-08-05 08:54:13,374][00150] DAMAGECOUNT value on done: 9365.0 [2024-08-05 08:54:13,375][00150] Sum rewards: -0.914, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.588', 'AMMO5': '0.003', 'AMMO2': '0.022', 'AMMO4': '0.109', 'ARMOR': '0.128', 'weapon4': '0.128', 'AMMO3': '0.182', 'WEAPON4': '0.200', 'HITCOUNT': '0.270', 'WEAPON3': '1.050', 'DAMAGECOUNT': '1.107', 'weapon2': '1.242', 'weapon3': '1.984', 'FRAGCOUNT': '4.000'} [2024-08-05 08:54:13,747][00146] Updated weights for policy 0, policy_version 840 (0.0019) [2024-08-05 08:54:13,999][00150] DAMAGECOUNT value on done: 8433.0 [2024-08-05 08:54:14,000][00150] Sum rewards: -3.177, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.281', 'AMMO2': '0.020', 'AMMO3': '0.076', 'AMMO4': '0.102', 'ARMOR': '0.112', 'WEAPON4': '0.200', 'HITCOUNT': '0.210', 'weapon4': '0.342', 'WEAPON3': '0.400', 'DAMAGECOUNT': '0.750', 'FRAGCOUNT': '1.000', 'weapon3': '1.384', 'weapon2': '1.508'} [2024-08-05 08:54:14,620][00150] DAMAGECOUNT value on done: 8661.0 [2024-08-05 08:54:14,621][00150] Sum rewards: -2.885, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.026', 'AMMO2': '0.001', 'AMMO5': '0.003', 'AMMO4': '0.005', 'WEAPON4': '0.100', 'AMMO3': '0.146', 'HITCOUNT': '0.170', 'weapon4': '0.180', 'DAMAGECOUNT': '0.630', 'WEAPON3': '0.800', 'weapon2': '1.470', 'weapon3': '1.636', 'FRAGCOUNT': '2.000'} [2024-08-05 08:54:16,504][00035] Fps is (10 sec: 4094.3, 60 sec: 3686.1, 300 sec: 3665.5). Total num frames: 6889472. Throughput: 0: 908.0. Samples: 1723072. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:54:16,508][00035] Avg episode reward: [(0, '-3.537')] [2024-08-05 08:54:21,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 6905856. Throughput: 0: 898.9. Samples: 1725480. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:54:21,502][00035] Avg episode reward: [(0, '-3.537')] [2024-08-05 08:54:21,510][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000843_6905856.pth... [2024-08-05 08:54:21,614][00137] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000736_6029312.pth [2024-08-05 08:54:26,500][00035] Fps is (10 sec: 3278.1, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 6922240. Throughput: 0: 898.1. Samples: 1730958. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:54:26,502][00035] Avg episode reward: [(0, '-3.537')] [2024-08-05 08:54:31,500][00035] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 6938624. Throughput: 0: 905.1. Samples: 1736492. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:54:31,501][00035] Avg episode reward: [(0, '-3.537')] [2024-08-05 08:54:33,797][00147] DAMAGECOUNT value on done: 8709.0 [2024-08-05 08:54:34,452][00147] DAMAGECOUNT value on done: 8904.0 [2024-08-05 08:54:34,453][00147] Sum rewards: 1.053, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.712', 'AMMO2': '0.006', 'AMMO5': '0.007', 'AMMO4': '0.028', 'ARMOR': '0.040', 'WEAPON4': '0.100', 'AMMO3': '0.146', 'WEAPON5': '0.150', 'weapon5': '0.180', 'weapon4': '0.192', 'HITCOUNT': '0.320', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.257', 'weapon2': '1.338', 'weapon3': '1.700', 'FRAGCOUNT': '3.000'} [2024-08-05 08:54:34,788][00148] DAMAGECOUNT value on done: 8270.0 [2024-08-05 08:54:34,789][00148] Sum rewards: -4.169, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-0.896', 'AMMO5': '0.010', 'weapon5': '0.010', 'AMMO2': '0.020', 'AMMO4': '0.100', 'WEAPON5': '0.100', 'HITCOUNT': '0.140', 'AMMO3': '0.162', 'WEAPON4': '0.200', 'weapon4': '0.340', 'DAMAGECOUNT': '0.474', 'ARMOR': '0.487', 'WEAPON3': '0.950', 'weapon2': '1.376', 'weapon3': '1.608', 'FRAGCOUNT': '2.000'} [2024-08-05 08:54:34,983][00147] DAMAGECOUNT value on done: 7134.0 [2024-08-05 08:54:35,366][00148] DAMAGECOUNT value on done: 7070.0 [2024-08-05 08:54:35,367][00148] Sum rewards: 0.359, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-0.300', 'AMMO2': '0.026', 'WEAPON4': '0.050', 'AMMO3': '0.117', 'AMMO4': '0.127', 'weapon4': '0.170', 'HITCOUNT': '0.300', 'ARMOR': '0.440', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.915', 'FRAGCOUNT': '1.000', 'weapon2': '1.172', 'weapon3': '1.742'} [2024-08-05 08:54:35,557][00147] DAMAGECOUNT value on done: 7727.0 [2024-08-05 08:54:35,558][00147] Sum rewards: -2.070, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.910', 'AMMO5': '0.003', 'weapon5': '0.030', 'AMMO2': '0.033', 'WEAPON5': '0.050', 'ARMOR': '0.075', 'AMMO3': '0.122', 'WEAPON4': '0.150', 'AMMO4': '0.162', 'weapon4': '0.198', 'HITCOUNT': '0.250', 'WEAPON3': '0.550', 'DAMAGECOUNT': '0.885', 'weapon3': '1.514', 'weapon2': '1.568', 'FRAGCOUNT': '3.000'} [2024-08-05 08:54:35,895][00148] DAMAGECOUNT value on done: 7605.0 [2024-08-05 08:54:35,896][00148] Sum rewards: -4.963, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-0.726', 'AMMO5': '0.003', 'AMMO2': '0.020', 'WEAPON5': '0.050', 'weapon5': '0.052', 'AMMO4': '0.101', 'HITCOUNT': '0.120', 'weapon4': '0.138', 'ARMOR': '0.148', 'WEAPON4': '0.150', 'AMMO3': '0.155', 'DAMAGECOUNT': '0.306', 'WEAPON3': '0.950', 'FRAGCOUNT': '1.000', 'weapon2': '1.100', 'weapon3': '1.970'} [2024-08-05 08:54:36,289][00146] Updated weights for policy 0, policy_version 850 (0.0025) [2024-08-05 08:54:36,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 6963200. Throughput: 0: 906.4. Samples: 1739286. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:54:36,501][00035] Avg episode reward: [(0, '-3.510')] [2024-08-05 08:54:36,536][00148] DAMAGECOUNT value on done: 7496.0 [2024-08-05 08:54:41,500][00035] Fps is (10 sec: 4095.9, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 6979584. Throughput: 0: 905.1. Samples: 1744814. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:54:41,502][00035] Avg episode reward: [(0, '-3.560')] [2024-08-05 08:54:46,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 6995968. Throughput: 0: 909.6. Samples: 1750384. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:54:46,503][00035] Avg episode reward: [(0, '-3.560')] [2024-08-05 08:54:46,642][00149] DAMAGECOUNT value on done: 7506.0 [2024-08-05 08:54:46,643][00149] Sum rewards: -4.510, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.620', 'AMMO2': '0.013', 'ARMOR': '0.048', 'AMMO4': '0.066', 'WEAPON4': '0.100', 'AMMO3': '0.128', 'HITCOUNT': '0.140', 'weapon4': '0.280', 'DAMAGECOUNT': '0.561', 'WEAPON3': '0.650', 'FRAGCOUNT': '1.000', 'weapon2': '1.372', 'weapon3': '1.502'} [2024-08-05 08:54:47,211][00149] DAMAGECOUNT value on done: 6955.0 [2024-08-05 08:54:47,212][00149] Sum rewards: -3.961, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.018', 'ARMOR': '0.008', 'AMMO2': '0.010', 'weapon4': '0.020', 'AMMO4': '0.050', 'WEAPON4': '0.050', 'AMMO3': '0.139', 'HITCOUNT': '0.270', 'WEAPON3': '0.850', 'DAMAGECOUNT': '0.918', 'FRAGCOUNT': '1.000', 'weapon2': '1.042', 'weapon3': '1.700'} [2024-08-05 08:54:47,799][00149] DAMAGECOUNT value on done: 8343.0 [2024-08-05 08:54:47,800][00149] Sum rewards: 0.173, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-0.300', 'WEAPON1': '0.010', 'AMMO2': '0.020', 'AMMO3': '0.093', 'HITCOUNT': '0.100', 'WEAPON4': '0.100', 'AMMO4': '0.102', 'DAMAGECOUNT': '0.240', 'weapon4': '0.270', 'ARMOR': '0.440', 'WEAPON3': '0.550', 'weapon2': '0.966', 'FRAGCOUNT': '1.000', 'weapon3': '1.832'} [2024-08-05 08:54:48,459][00149] DAMAGECOUNT value on done: 8464.0 [2024-08-05 08:54:48,460][00149] Sum rewards: -5.062, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-2.351', 'AMMO4': '-0.071', 'AMMO2': '-0.014', 'ARMOR': '0.051', 'AMMO3': '0.175', 'HITCOUNT': '0.340', 'WEAPON3': '0.950', 'DAMAGECOUNT': '1.260', 'weapon3': '1.624', 'weapon2': '1.974', 'FRAGCOUNT': '3.000'} [2024-08-05 08:54:49,905][00150] DAMAGECOUNT value on done: 7522.0 [2024-08-05 08:54:49,906][00150] Sum rewards: -3.572, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.866', 'AMMO2': '0.005', 'AMMO5': '0.007', 'WEAPON1': '0.010', 'AMMO4': '0.022', 'ARMOR': '0.056', 'weapon5': '0.060', 'HITCOUNT': '0.110', 'AMMO3': '0.129', 'WEAPON5': '0.150', 'WEAPON4': '0.200', 'weapon4': '0.290', 'DAMAGECOUNT': '0.720', 'WEAPON3': '0.750', 'weapon3': '1.222', 'weapon2': '1.312', 'FRAGCOUNT': '2.000'} [2024-08-05 08:54:50,478][00150] DAMAGECOUNT value on done: 9520.0 [2024-08-05 08:54:50,479][00150] Sum rewards: -4.816, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-0.134', 'AMMO2': '0.016', 'WEAPON4': '0.050', 'ARMOR': '0.068', 'AMMO4': '0.082', 'HITCOUNT': '0.140', 'AMMO3': '0.149', 'weapon4': '0.156', 'DAMAGECOUNT': '0.465', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon3': '1.050', 'weapon2': '2.042'} [2024-08-05 08:54:50,998][00150] DAMAGECOUNT value on done: 8508.0 [2024-08-05 08:54:51,500][00035] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 7012352. Throughput: 0: 900.5. Samples: 1752758. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:54:51,504][00035] Avg episode reward: [(0, '-3.613')] [2024-08-05 08:54:51,522][00150] DAMAGECOUNT value on done: 8915.0 [2024-08-05 08:54:51,522][00150] Sum rewards: -1.061, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.772', 'AMMO4': '-0.025', 'AMMO2': '-0.005', 'ARMOR': '0.012', 'WEAPON4': '0.100', 'AMMO3': '0.119', 'weapon4': '0.124', 'HITCOUNT': '0.230', 'WEAPON3': '0.450', 'DAMAGECOUNT': '0.762', 'weapon3': '1.330', 'weapon2': '1.364', 'FRAGCOUNT': '3.000'} [2024-08-05 08:54:56,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 7028736. Throughput: 0: 902.1. Samples: 1758294. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:54:56,502][00035] Avg episode reward: [(0, '-3.622')] [2024-08-05 08:54:58,996][00146] Updated weights for policy 0, policy_version 860 (0.0018) [2024-08-05 08:55:01,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.9). Total num frames: 7053312. Throughput: 0: 905.3. Samples: 1763808. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:55:01,502][00035] Avg episode reward: [(0, '-3.622')] [2024-08-05 08:55:06,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 7069696. Throughput: 0: 915.1. Samples: 1766658. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:55:06,502][00035] Avg episode reward: [(0, '-3.622')] [2024-08-05 08:55:11,270][00147] DAMAGECOUNT value on done: 8774.0 [2024-08-05 08:55:11,271][00147] Sum rewards: -8.562, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.922', 'FRAGCOUNT': '-0.500', 'AMMO2': '0.007', 'AMMO5': '0.009', 'AMMO4': '0.033', 'HITCOUNT': '0.060', 'ARMOR': '0.064', 'weapon5': '0.066', 'weapon4': '0.130', 'WEAPON4': '0.150', 'AMMO3': '0.163', 'DAMAGECOUNT': '0.195', 'WEAPON5': '0.200', 'WEAPON3': '0.950', 'weapon2': '1.334', 'weapon3': '1.748'} [2024-08-05 08:55:11,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 7086080. Throughput: 0: 915.2. Samples: 1772144. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:55:11,501][00035] Avg episode reward: [(0, '-3.701')] [2024-08-05 08:55:11,855][00147] DAMAGECOUNT value on done: 9229.0 [2024-08-05 08:55:11,855][00147] Sum rewards: -1.387, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.176', 'AMMO4': '-0.044', 'AMMO2': '-0.009', 'ARMOR': '0.090', 'AMMO3': '0.104', 'WEAPON4': '0.150', 'weapon4': '0.252', 'HITCOUNT': '0.310', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.975', 'weapon3': '1.166', 'weapon2': '1.794', 'FRAGCOUNT': '2.000'} [2024-08-05 08:55:12,488][00148] DAMAGECOUNT value on done: 8375.0 [2024-08-05 08:55:12,489][00148] Sum rewards: -2.796, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.732', 'AMMO2': '0.001', 'AMMO4': '0.006', 'ARMOR': '0.033', 'HITCOUNT': '0.090', 'WEAPON4': '0.100', 'AMMO3': '0.132', 'weapon4': '0.184', 'DAMAGECOUNT': '0.315', 'WEAPON3': '0.800', 'weapon2': '1.304', 'weapon3': '1.970', 'FRAGCOUNT': '2.000'} [2024-08-05 08:55:12,498][00147] DAMAGECOUNT value on done: 7255.0 [2024-08-05 08:55:12,499][00147] Sum rewards: -4.776, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-2.010', 'AMMO4': '-0.002', 'AMMO2': '-0.000', 'AMMO5': '0.005', 'WEAPON1': '0.030', 'ARMOR': '0.040', 'HITCOUNT': '0.070', 'weapon5': '0.080', 'WEAPON5': '0.100', 'AMMO3': '0.130', 'DAMAGECOUNT': '0.363', 'WEAPON3': '0.650', 'FRAGCOUNT': '1.000', 'weapon3': '1.150', 'weapon2': '1.868'} [2024-08-05 08:55:13,056][00147] DAMAGECOUNT value on done: 7902.0 [2024-08-05 08:55:13,057][00147] Sum rewards: -1.780, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.648', 'AMMO5': '0.003', 'AMMO2': '0.009', 'AMMO4': '0.045', 'ARMOR': '0.052', 'HITCOUNT': '0.150', 'AMMO3': '0.152', 'DAMAGECOUNT': '0.525', 'WEAPON3': '0.700', 'weapon3': '1.094', 'weapon2': '1.638', 'FRAGCOUNT': '2.000'} [2024-08-05 08:55:13,067][00148] DAMAGECOUNT value on done: 7453.0 [2024-08-05 08:55:13,068][00148] Sum rewards: -2.181, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.270', 'weapon5': '0.006', 'AMMO2': '0.009', 'AMMO5': '0.013', 'AMMO4': '0.044', 'AMMO3': '0.122', 'WEAPON4': '0.150', 'WEAPON5': '0.150', 'weapon4': '0.176', 'HITCOUNT': '0.340', 'WEAPON3': '0.800', 'weapon2': '1.002', 'DAMAGECOUNT': '1.149', 'FRAGCOUNT': '2.000', 'weapon3': '2.128'} [2024-08-05 08:55:13,621][00148] DAMAGECOUNT value on done: 7825.0 [2024-08-05 08:55:13,622][00148] Sum rewards: -4.362, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-0.248', 'AMMO2': '0.021', 'ARMOR': '0.046', 'WEAPON4': '0.050', 'AMMO4': '0.103', 'AMMO3': '0.114', 'weapon4': '0.120', 'HITCOUNT': '0.220', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.660', 'FRAGCOUNT': '1.000', 'weapon3': '1.498', 'weapon2': '1.954'} [2024-08-05 08:55:14,162][00148] DAMAGECOUNT value on done: 7553.0 [2024-08-05 08:55:14,164][00148] Sum rewards: -1.735, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-1.300', 'AMMO5': '0.003', 'AMMO2': '0.005', 'AMMO4': '0.026', 'HITCOUNT': '0.050', 'WEAPON5': '0.050', 'weapon5': '0.078', 'AMMO3': '0.080', 'ARMOR': '0.088', 'DAMAGECOUNT': '0.171', 'WEAPON4': '0.200', 'weapon4': '0.322', 'WEAPON3': '0.550', 'FRAGCOUNT': '1.000', 'weapon2': '1.448', 'weapon3': '1.494'} [2024-08-05 08:55:16,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3550.1, 300 sec: 3637.8). Total num frames: 7102464. Throughput: 0: 914.3. Samples: 1777636. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:55:16,502][00035] Avg episode reward: [(0, '-3.774')] [2024-08-05 08:55:21,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 7118848. Throughput: 0: 913.4. Samples: 1780388. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:55:21,504][00035] Avg episode reward: [(0, '-3.774')] [2024-08-05 08:55:21,672][00146] Updated weights for policy 0, policy_version 870 (0.0017) [2024-08-05 08:55:23,100][00149] DAMAGECOUNT value on done: 7713.0 [2024-08-05 08:55:23,101][00149] Sum rewards: -4.631, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-0.994', 'AMMO2': '0.012', 'WEAPON4': '0.050', 'AMMO4': '0.059', 'ARMOR': '0.088', 'weapon4': '0.090', 'HITCOUNT': '0.160', 'AMMO3': '0.175', 'DAMAGECOUNT': '0.621', 'WEAPON3': '1.000', 'weapon2': '1.238', 'FRAGCOUNT': '2.000', 'weapon3': '2.120'} [2024-08-05 08:55:23,657][00149] DAMAGECOUNT value on done: 7193.0 [2024-08-05 08:55:23,658][00149] Sum rewards: 1.036, reward structure: {'DEATHCOUNT': '-6.750', 'AMMO5': '0.005', 'weapon4': '0.020', 'AMMO2': '0.030', 'AMMO3': '0.076', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO4': '0.152', 'weapon5': '0.156', 'HITCOUNT': '0.190', 'HEALTH': '0.414', 'ARMOR': '0.444', 'WEAPON3': '0.450', 'DAMAGECOUNT': '0.714', 'weapon3': '1.334', 'FRAGCOUNT': '1.500', 'weapon2': '2.100'} [2024-08-05 08:55:24,228][00149] DAMAGECOUNT value on done: 8463.0 [2024-08-05 08:55:24,777][00149] DAMAGECOUNT value on done: 8539.0 [2024-08-05 08:55:24,778][00149] Sum rewards: -2.011, reward structure: {'DEATHCOUNT': '-5.250', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.005', 'weapon5': '0.018', 'AMMO2': '0.019', 'HEALTH': '0.022', 'WEAPON5': '0.050', 'weapon7': '0.064', 'AMMO3': '0.067', 'HITCOUNT': '0.070', 'AMMO4': '0.095', 'AMMO6': '0.100', 'WEAPON7': '0.100', 'AMMO7': '0.100', 'ARMOR': '0.168', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.225', 'WEAPON3': '0.450', 'weapon4': '0.490', 'weapon2': '1.012', 'weapon3': '1.484'} [2024-08-05 08:55:25,968][00150] DAMAGECOUNT value on done: 7579.0 [2024-08-05 08:55:26,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 7143424. Throughput: 0: 905.0. Samples: 1785540. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:55:26,501][00035] Avg episode reward: [(0, '-3.658')] [2024-08-05 08:55:26,608][00150] DAMAGECOUNT value on done: 9697.0 [2024-08-05 08:55:26,609][00150] Sum rewards: -7.980, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-2.839', 'AMMO4': '-0.015', 'AMMO2': '-0.003', 'weapon5': '0.004', 'AMMO5': '0.005', 'ARMOR': '0.016', 'WEAPON1': '0.020', 'weapon4': '0.042', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'HITCOUNT': '0.160', 'AMMO3': '0.180', 'DAMAGECOUNT': '0.531', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.150', 'weapon2': '1.542', 'weapon3': '2.026'} [2024-08-05 08:55:27,191][00150] DAMAGECOUNT value on done: 8783.0 [2024-08-05 08:55:27,191][00150] Sum rewards: -4.985, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.538', 'AMMO2': '0.013', 'AMMO4': '0.066', 'ARMOR': '0.104', 'weapon4': '0.144', 'WEAPON4': '0.150', 'AMMO3': '0.155', 'HITCOUNT': '0.210', 'DAMAGECOUNT': '0.825', 'WEAPON3': '1.150', 'weapon2': '1.152', 'FRAGCOUNT': '2.000', 'weapon3': '2.084'} [2024-08-05 08:55:27,741][00150] DAMAGECOUNT value on done: 9039.0 [2024-08-05 08:55:27,741][00150] Sum rewards: -4.932, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-0.173', 'AMMO4': '-0.013', 'AMMO2': '-0.002', 'WEAPON1': '0.020', 'ARMOR': '0.036', 'weapon4': '0.048', 'WEAPON4': '0.050', 'HITCOUNT': '0.110', 'AMMO3': '0.118', 'DAMAGECOUNT': '0.372', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon2': '1.468', 'weapon3': '1.834'} [2024-08-05 08:55:31,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 7159808. Throughput: 0: 901.4. Samples: 1790948. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:55:31,502][00035] Avg episode reward: [(0, '-3.747')] [2024-08-05 08:55:36,503][00035] Fps is (10 sec: 3275.9, 60 sec: 3549.7, 300 sec: 3637.8). Total num frames: 7176192. Throughput: 0: 912.2. Samples: 1793808. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:55:36,505][00035] Avg episode reward: [(0, '-3.747')] [2024-08-05 08:55:41,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 7192576. Throughput: 0: 911.4. Samples: 1799306. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:55:41,502][00035] Avg episode reward: [(0, '-3.747')] [2024-08-05 08:55:43,796][00146] Updated weights for policy 0, policy_version 880 (0.0022) [2024-08-05 08:55:46,500][00035] Fps is (10 sec: 4097.2, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 7217152. Throughput: 0: 913.3. Samples: 1804906. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:55:46,502][00035] Avg episode reward: [(0, '-3.747')] [2024-08-05 08:55:48,549][00147] DAMAGECOUNT value on done: 8919.0 [2024-08-05 08:55:49,153][00147] DAMAGECOUNT value on done: 9618.0 [2024-08-05 08:55:49,154][00147] Sum rewards: -0.804, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-0.718', 'AMMO2': '0.016', 'AMMO4': '0.078', 'ARMOR': '0.090', 'AMMO3': '0.151', 'WEAPON4': '0.250', 'HITCOUNT': '0.300', 'weapon4': '0.396', 'WEAPON3': '0.900', 'weapon2': '1.002', 'DAMAGECOUNT': '1.167', 'weapon3': '2.064', 'FRAGCOUNT': '4.000'} [2024-08-05 08:55:49,714][00147] DAMAGECOUNT value on done: 7470.0 [2024-08-05 08:55:50,163][00148] DAMAGECOUNT value on done: 8487.0 [2024-08-05 08:55:50,312][00147] DAMAGECOUNT value on done: 7993.0 [2024-08-05 08:55:50,769][00148] DAMAGECOUNT value on done: 7566.0 [2024-08-05 08:55:50,770][00148] Sum rewards: -3.765, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.890', 'AMMO5': '0.005', 'weapon5': '0.006', 'AMMO2': '0.012', 'AMMO4': '0.060', 'AMMO3': '0.091', 'WEAPON5': '0.100', 'HITCOUNT': '0.120', 'weapon4': '0.128', 'WEAPON4': '0.150', 'DAMAGECOUNT': '0.339', 'WEAPON3': '0.650', 'FRAGCOUNT': '1.000', 'weapon3': '1.322', 'weapon2': '1.642'} [2024-08-05 08:55:51,295][00148] DAMAGECOUNT value on done: 8032.0 [2024-08-05 08:55:51,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 7233536. Throughput: 0: 911.6. Samples: 1807682. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:55:51,502][00035] Avg episode reward: [(0, '-3.870')] [2024-08-05 08:55:51,860][00148] DAMAGECOUNT value on done: 7592.0 [2024-08-05 08:55:56,501][00035] Fps is (10 sec: 3276.6, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 7249920. Throughput: 0: 904.2. Samples: 1812832. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:55:56,502][00035] Avg episode reward: [(0, '-3.871')] [2024-08-05 08:55:59,466][00149] DAMAGECOUNT value on done: 7988.0 [2024-08-05 08:55:59,467][00149] Sum rewards: 0.541, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-1.268', 'AMMO5': '0.005', 'AMMO2': '0.005', 'WEAPON1': '0.020', 'weapon5': '0.020', 'AMMO4': '0.027', 'AMMO3': '0.088', 'WEAPON5': '0.100', 'ARMOR': '0.113', 'WEAPON4': '0.150', 'HITCOUNT': '0.190', 'weapon4': '0.272', 'WEAPON3': '0.550', 'DAMAGECOUNT': '0.825', 'weapon2': '1.204', 'weapon3': '1.490', 'FRAGCOUNT': '2.000'} [2024-08-05 08:56:00,082][00149] DAMAGECOUNT value on done: 7513.0 [2024-08-05 08:56:00,083][00149] Sum rewards: -3.805, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.970', 'AMMO4': '-0.021', 'AMMO2': '-0.004', 'AMMO5': '0.003', 'ARMOR': '0.063', 'weapon5': '0.088', 'WEAPON5': '0.100', 'AMMO3': '0.149', 'HITCOUNT': '0.150', 'WEAPON3': '0.900', 'DAMAGECOUNT': '0.960', 'weapon2': '1.398', 'weapon3': '1.880', 'FRAGCOUNT': '3.000'} [2024-08-05 08:56:00,641][00149] DAMAGECOUNT value on done: 8740.0 [2024-08-05 08:56:00,642][00149] Sum rewards: -4.138, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.894', 'AMMO2': '0.010', 'ARMOR': '0.028', 'AMMO4': '0.049', 'WEAPON4': '0.050', 'weapon4': '0.056', 'AMMO3': '0.128', 'HITCOUNT': '0.210', 'DAMAGECOUNT': '0.831', 'WEAPON3': '0.850', 'FRAGCOUNT': '1.000', 'weapon2': '1.324', 'weapon3': '1.970'} [2024-08-05 08:56:01,180][00149] DAMAGECOUNT value on done: 8629.0 [2024-08-05 08:56:01,254][00147] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-05 08:56:01,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 7266304. Throughput: 0: 904.3. Samples: 1818328. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:56:01,502][00035] Avg episode reward: [(0, '-3.673')] [2024-08-05 08:56:02,366][00150] DAMAGECOUNT value on done: 7934.0 [2024-08-05 08:56:02,367][00150] Sum rewards: -2.127, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.520', 'AMMO4': '-0.061', 'AMMO2': '-0.012', 'AMMO5': '0.010', 'ARMOR': '0.024', 'weapon5': '0.032', 'AMMO3': '0.121', 'WEAPON5': '0.150', 'HITCOUNT': '0.270', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.065', 'weapon2': '1.404', 'weapon3': '1.840', 'FRAGCOUNT': '2.000'} [2024-08-05 08:56:02,943][00150] DAMAGECOUNT value on done: 9807.0 [2024-08-05 08:56:02,944][00150] Sum rewards: -3.649, reward structure: {'DEATHCOUNT': '-9.750', 'AMMO2': '0.006', 'AMMO4': '0.029', 'HITCOUNT': '0.080', 'HEALTH': '0.098', 'ARMOR': '0.140', 'WEAPON4': '0.150', 'AMMO3': '0.152', 'weapon4': '0.196', 'DAMAGECOUNT': '0.330', 'WEAPON3': '0.850', 'FRAGCOUNT': '1.000', 'weapon2': '1.280', 'weapon3': '1.790'} [2024-08-05 08:56:03,495][00150] DAMAGECOUNT value on done: 8893.0 [2024-08-05 08:56:04,014][00150] DAMAGECOUNT value on done: 9104.0 [2024-08-05 08:56:06,443][00146] Updated weights for policy 0, policy_version 890 (0.0019) [2024-08-05 08:56:06,500][00035] Fps is (10 sec: 4096.3, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 7290880. Throughput: 0: 904.6. Samples: 1821096. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:56:06,501][00035] Avg episode reward: [(0, '-3.724')] [2024-08-05 08:56:11,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 7307264. Throughput: 0: 914.9. Samples: 1826710. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:56:11,502][00035] Avg episode reward: [(0, '-3.724')] [2024-08-05 08:56:16,500][00035] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 7323648. Throughput: 0: 917.5. Samples: 1832234. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:56:16,502][00035] Avg episode reward: [(0, '-3.724')] [2024-08-05 08:56:21,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 7340032. Throughput: 0: 915.7. Samples: 1835010. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:56:21,502][00035] Avg episode reward: [(0, '-3.724')] [2024-08-05 08:56:21,509][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000896_7340032.pth... [2024-08-05 08:56:21,615][00137] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000790_6471680.pth [2024-08-05 08:56:26,487][00147] DAMAGECOUNT value on done: 9060.0 [2024-08-05 08:56:26,488][00147] Sum rewards: -1.810, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-0.630', 'AMMO4': '-0.011', 'AMMO2': '-0.002', 'ARMOR': '0.040', 'AMMO3': '0.070', 'HITCOUNT': '0.130', 'WEAPON3': '0.400', 'DAMAGECOUNT': '0.423', 'FRAGCOUNT': '1.000', 'weapon3': '1.320', 'weapon2': '1.450'} [2024-08-05 08:56:26,500][00035] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 7356416. Throughput: 0: 904.8. Samples: 1840024. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:56:26,501][00035] Avg episode reward: [(0, '-3.724')] [2024-08-05 08:56:27,147][00147] DAMAGECOUNT value on done: 10290.0 [2024-08-05 08:56:27,148][00147] Sum rewards: -3.388, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.158', 'AMMO4': '-0.024', 'AMMO2': '-0.005', 'ARMOR': '0.040', 'HITCOUNT': '0.080', 'WEAPON4': '0.100', 'AMMO6': '0.120', 'AMMO7': '0.120', 'AMMO3': '0.139', 'weapon7': '0.162', 'WEAPON7': '0.200', 'weapon4': '0.250', 'WEAPON3': '0.850', 'weapon2': '1.338', 'DAMAGECOUNT': '1.416', 'weapon3': '1.484', 'FRAGCOUNT': '3.000'} [2024-08-05 08:56:27,704][00147] DAMAGECOUNT value on done: 7540.0 [2024-08-05 08:56:27,704][00147] Sum rewards: -4.343, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-0.870', 'FRAGCOUNT': '-0.500', 'AMMO2': '0.003', 'AMMO5': '0.009', 'AMMO4': '0.016', 'ARMOR': '0.032', 'weapon5': '0.032', 'AMMO3': '0.045', 'WEAPON4': '0.050', 'HITCOUNT': '0.060', 'WEAPON5': '0.100', 'weapon4': '0.108', 'DAMAGECOUNT': '0.210', 'WEAPON3': '0.350', 'weapon3': '0.904', 'weapon2': '1.858'} [2024-08-05 08:56:28,252][00147] DAMAGECOUNT value on done: 8133.0 [2024-08-05 08:56:28,253][00147] Sum rewards: -0.460, reward structure: {'DEATHCOUNT': '-4.500', 'HEALTH': '-1.052', 'AMMO4': '-0.034', 'AMMO2': '-0.007', 'AMMO5': '0.005', 'ARMOR': '0.045', 'WEAPON4': '0.050', 'AMMO3': '0.086', 'HITCOUNT': '0.120', 'weapon4': '0.210', 'DAMAGECOUNT': '0.420', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon3': '1.282', 'weapon2': '1.314'} [2024-08-05 08:56:28,387][00148] DAMAGECOUNT value on done: 8672.0 [2024-08-05 08:56:28,388][00148] Sum rewards: -2.724, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.371', 'AMMO2': '0.002', 'AMMO4': '0.009', 'weapon4': '0.046', 'ARMOR': '0.052', 'AMMO3': '0.121', 'HITCOUNT': '0.130', 'WEAPON4': '0.150', 'DAMAGECOUNT': '0.555', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon2': '1.502', 'weapon3': '1.880'} [2024-08-05 08:56:28,976][00148] DAMAGECOUNT value on done: 7618.0 [2024-08-05 08:56:29,241][00146] Updated weights for policy 0, policy_version 900 (0.0028) [2024-08-05 08:56:29,615][00148] DAMAGECOUNT value on done: 8186.0 [2024-08-05 08:56:29,616][00148] Sum rewards: -5.149, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-2.586', 'AMMO2': '0.016', 'AMMO4': '0.077', 'weapon4': '0.112', 'ARMOR': '0.122', 'AMMO3': '0.132', 'HITCOUNT': '0.150', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.462', 'WEAPON3': '0.950', 'FRAGCOUNT': '1.000', 'weapon2': '1.084', 'weapon3': '2.132'} [2024-08-05 08:56:30,210][00148] DAMAGECOUNT value on done: 7847.0 [2024-08-05 08:56:31,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.1). Total num frames: 7372800. Throughput: 0: 900.4. Samples: 1845424. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:56:31,504][00035] Avg episode reward: [(0, '-3.694')] [2024-08-05 08:56:35,809][00149] DAMAGECOUNT value on done: 8153.0 [2024-08-05 08:56:35,810][00149] Sum rewards: -5.787, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-1.741', 'AMMO4': '-0.004', 'AMMO2': '-0.001', 'AMMO5': '0.010', 'ARMOR': '0.016', 'WEAPON5': '0.100', 'weapon5': '0.102', 'HITCOUNT': '0.150', 'AMMO3': '0.168', 'DAMAGECOUNT': '0.495', 'WEAPON3': '0.850', 'weapon3': '1.530', 'weapon2': '1.538', 'FRAGCOUNT': '3.000'} [2024-08-05 08:56:36,426][00149] DAMAGECOUNT value on done: 7753.0 [2024-08-05 08:56:36,427][00149] Sum rewards: 0.784, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-0.514', 'AMMO5': '0.010', 'AMMO2': '0.012', 'WEAPON1': '0.020', 'AMMO4': '0.057', 'AMMO3': '0.079', 'ARMOR': '0.088', 'HITCOUNT': '0.110', 'weapon4': '0.120', 'WEAPON4': '0.150', 'WEAPON5': '0.250', 'weapon5': '0.398', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.720', 'weapon2': '1.352', 'weapon3': '1.432', 'FRAGCOUNT': '2.000'} [2024-08-05 08:56:36,501][00035] Fps is (10 sec: 4095.7, 60 sec: 3686.5, 300 sec: 3637.8). Total num frames: 7397376. Throughput: 0: 899.9. Samples: 1848178. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:56:36,503][00035] Avg episode reward: [(0, '-3.663')] [2024-08-05 08:56:37,084][00149] DAMAGECOUNT value on done: 8985.0 [2024-08-05 08:56:37,085][00149] Sum rewards: -7.621, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-2.880', 'AMMO2': '0.002', 'AMMO4': '0.011', 'ARMOR': '0.045', 'HITCOUNT': '0.190', 'AMMO3': '0.197', 'DAMAGECOUNT': '0.735', 'WEAPON3': '1.150', 'weapon2': '1.362', 'FRAGCOUNT': '2.000', 'weapon3': '2.316'} [2024-08-05 08:56:37,654][00149] DAMAGECOUNT value on done: 8846.0 [2024-08-05 08:56:38,864][00150] DAMAGECOUNT value on done: 8325.0 [2024-08-05 08:56:38,865][00150] Sum rewards: -5.078, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-2.369', 'AMMO4': '-0.032', 'AMMO2': '-0.006', 'AMMO5': '0.003', 'weapon5': '0.020', 'WEAPON5': '0.050', 'WEAPON4': '0.100', 'AMMO3': '0.138', 'weapon4': '0.178', 'HITCOUNT': '0.270', 'ARMOR': '0.432', 'WEAPON3': '0.850', 'DAMAGECOUNT': '1.173', 'weapon2': '1.258', 'FRAGCOUNT': '2.000', 'weapon3': '2.108'} [2024-08-05 08:56:39,375][00150] DAMAGECOUNT value on done: 9965.0 [2024-08-05 08:56:39,881][00150] DAMAGECOUNT value on done: 9136.0 [2024-08-05 08:56:39,882][00150] Sum rewards: -3.131, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.722', 'AMMO2': '0.001', 'AMMO4': '0.003', 'WEAPON1': '0.010', 'ARMOR': '0.036', 'WEAPON4': '0.050', 'AMMO3': '0.136', 'HITCOUNT': '0.210', 'DAMAGECOUNT': '0.729', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '1.378', 'weapon3': '2.138'} [2024-08-05 08:56:40,449][00150] DAMAGECOUNT value on done: 9289.0 [2024-08-05 08:56:40,450][00150] Sum rewards: 0.047, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-0.440', 'AMMO2': '0.019', 'WEAPON4': '0.050', 'AMMO3': '0.070', 'AMMO4': '0.096', 'weapon4': '0.110', 'ARMOR': '0.120', 'HITCOUNT': '0.150', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.555', 'FRAGCOUNT': '1.000', 'weapon3': '1.448', 'weapon2': '1.618'} [2024-08-05 08:56:41,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 7413760. Throughput: 0: 906.9. Samples: 1853644. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:56:41,502][00035] Avg episode reward: [(0, '-3.702')] [2024-08-05 08:56:46,500][00035] Fps is (10 sec: 3277.0, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 7430144. Throughput: 0: 908.1. Samples: 1859194. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:56:46,504][00035] Avg episode reward: [(0, '-3.702')] [2024-08-05 08:56:51,449][00146] Updated weights for policy 0, policy_version 910 (0.0025) [2024-08-05 08:56:51,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 7454720. Throughput: 0: 907.6. Samples: 1861938. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:56:51,502][00035] Avg episode reward: [(0, '-3.702')] [2024-08-05 08:56:56,501][00035] Fps is (10 sec: 4095.6, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 7471104. Throughput: 0: 908.6. Samples: 1867598. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:56:56,503][00035] Avg episode reward: [(0, '-3.702')] [2024-08-05 08:57:01,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 7487488. Throughput: 0: 895.2. Samples: 1872516. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:57:01,501][00035] Avg episode reward: [(0, '-3.702')] [2024-08-05 08:57:04,153][00147] DAMAGECOUNT value on done: 9300.0 [2024-08-05 08:57:04,154][00147] Sum rewards: -7.162, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-2.256', 'weapon5': '0.006', 'AMMO2': '0.009', 'AMMO5': '0.010', 'weapon4': '0.014', 'ARMOR': '0.016', 'WEAPON1': '0.020', 'AMMO4': '0.043', 'WEAPON5': '0.050', 'WEAPON4': '0.100', 'HITCOUNT': '0.170', 'AMMO3': '0.194', 'DAMAGECOUNT': '0.720', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.150', 'weapon2': '1.392', 'weapon3': '2.200'} [2024-08-05 08:57:04,704][00147] DAMAGECOUNT value on done: 10450.0 [2024-08-05 08:57:04,705][00147] Sum rewards: -5.236, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-1.178', 'AMMO2': '0.004', 'AMMO5': '0.010', 'AMMO4': '0.020', 'ARMOR': '0.050', 'WEAPON5': '0.050', 'weapon5': '0.124', 'AMMO3': '0.148', 'HITCOUNT': '0.160', 'DAMAGECOUNT': '0.480', 'WEAPON3': '0.750', 'weapon3': '1.558', 'weapon2': '2.088', 'FRAGCOUNT': '4.000'} [2024-08-05 08:57:05,281][00147] DAMAGECOUNT value on done: 7616.0 [2024-08-05 08:57:05,282][00147] Sum rewards: -5.557, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.330', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.003', 'AMMO2': '0.003', 'AMMO4': '0.014', 'WEAPON5': '0.050', 'weapon5': '0.072', 'HITCOUNT': '0.090', 'AMMO3': '0.137', 'DAMAGECOUNT': '0.228', 'ARMOR': '0.500', 'WEAPON3': '0.850', 'weapon2': '1.546', 'weapon3': '1.780'} [2024-08-05 08:57:05,922][00147] DAMAGECOUNT value on done: 8376.0 [2024-08-05 08:57:05,923][00147] Sum rewards: -5.534, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-0.444', 'weapon5': '0.004', 'AMMO5': '0.005', 'AMMO2': '0.024', 'ARMOR': '0.036', 'WEAPON5': '0.100', 'AMMO4': '0.121', 'WEAPON4': '0.150', 'AMMO3': '0.152', 'weapon4': '0.164', 'HITCOUNT': '0.250', 'DAMAGECOUNT': '0.729', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '1.672', 'weapon3': '1.702'} [2024-08-05 08:57:06,336][00148] DAMAGECOUNT value on done: 8927.0 [2024-08-05 08:57:06,337][00148] Sum rewards: -1.346, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.714', 'AMMO4': '-0.011', 'AMMO2': '-0.002', 'AMMO5': '0.005', 'ARMOR': '0.024', 'WEAPON5': '0.100', 'AMMO3': '0.127', 'HITCOUNT': '0.240', 'DAMAGECOUNT': '0.765', 'WEAPON3': '0.800', 'weapon2': '1.424', 'FRAGCOUNT': '2.000', 'weapon3': '2.146'} [2024-08-05 08:57:06,500][00035] Fps is (10 sec: 3277.2, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 7503872. Throughput: 0: 893.9. Samples: 1875234. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:57:06,502][00035] Avg episode reward: [(0, '-3.725')] [2024-08-05 08:57:06,933][00148] DAMAGECOUNT value on done: 8073.0 [2024-08-05 08:57:06,934][00148] Sum rewards: -4.167, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.420', 'AMMO4': '-0.034', 'AMMO2': '-0.007', 'AMMO5': '0.007', 'WEAPON5': '0.100', 'weapon5': '0.128', 'AMMO3': '0.141', 'HITCOUNT': '0.280', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.365', 'weapon2': '1.418', 'weapon3': '1.804', 'FRAGCOUNT': '2.500'} [2024-08-05 08:57:07,534][00148] DAMAGECOUNT value on done: 8295.0 [2024-08-05 08:57:07,535][00148] Sum rewards: -2.133, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.946', 'weapon5': '0.004', 'AMMO2': '0.005', 'AMMO5': '0.012', 'AMMO4': '0.026', 'ARMOR': '0.028', 'HITCOUNT': '0.110', 'AMMO3': '0.132', 'WEAPON5': '0.150', 'WEAPON4': '0.200', 'weapon4': '0.324', 'DAMAGECOUNT': '0.327', 'WEAPON3': '0.750', 'weapon2': '1.428', 'weapon3': '1.566', 'FRAGCOUNT': '2.000'} [2024-08-05 08:57:08,155][00148] DAMAGECOUNT value on done: 8012.0 [2024-08-05 08:57:08,156][00148] Sum rewards: -4.073, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.175', 'AMMO2': '0.012', 'AMMO4': '0.062', 'HITCOUNT': '0.110', 'AMMO3': '0.165', 'ARMOR': '0.460', 'DAMAGECOUNT': '0.495', 'WEAPON3': '0.900', 'weapon2': '1.574', 'weapon3': '1.824', 'FRAGCOUNT': '2.000'} [2024-08-05 08:57:11,500][00035] Fps is (10 sec: 3276.7, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 7520256. Throughput: 0: 901.3. Samples: 1880582. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:57:11,502][00035] Avg episode reward: [(0, '-3.741')] [2024-08-05 08:57:12,608][00149] DAMAGECOUNT value on done: 8248.0 [2024-08-05 08:57:13,125][00149] DAMAGECOUNT value on done: 7933.0 [2024-08-05 08:57:13,126][00149] Sum rewards: 1.630, reward structure: {'DEATHCOUNT': '-3.750', 'AMMO5': '0.003', 'weapon5': '0.006', 'AMMO2': '0.010', 'ARMOR': '0.045', 'AMMO3': '0.050', 'WEAPON4': '0.050', 'WEAPON5': '0.050', 'AMMO4': '0.052', 'weapon7': '0.076', 'AMMO6': '0.100', 'AMMO7': '0.100', 'WEAPON7': '0.100', 'HEALTH': '0.160', 'HITCOUNT': '0.170', 'weapon4': '0.188', 'WEAPON3': '0.300', 'DAMAGECOUNT': '0.540', 'FRAGCOUNT': '1.000', 'weapon2': '1.144', 'weapon3': '1.236'} [2024-08-05 08:57:13,664][00149] DAMAGECOUNT value on done: 9090.0 [2024-08-05 08:57:14,252][00149] DAMAGECOUNT value on done: 9026.0 [2024-08-05 08:57:14,600][00146] Updated weights for policy 0, policy_version 920 (0.0019) [2024-08-05 08:57:15,541][00150] DAMAGECOUNT value on done: 8620.0 [2024-08-05 08:57:15,542][00150] Sum rewards: 0.615, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-1.440', 'AMMO4': '-0.028', 'AMMO2': '-0.006', 'weapon7': '0.036', 'ARMOR': '0.040', 'WEAPON4': '0.050', 'AMMO3': '0.095', 'AMMO6': '0.100', 'WEAPON7': '0.100', 'AMMO7': '0.100', 'weapon4': '0.196', 'HITCOUNT': '0.240', 'WEAPON3': '0.450', 'DAMAGECOUNT': '0.885', 'weapon3': '1.054', 'weapon2': '1.742', 'FRAGCOUNT': '3.000'} [2024-08-05 08:57:16,073][00150] DAMAGECOUNT value on done: 10075.0 [2024-08-05 08:57:16,074][00150] Sum rewards: -3.377, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.286', 'AMMO2': '0.010', 'AMMO4': '0.050', 'WEAPON4': '0.050', 'ARMOR': '0.088', 'HITCOUNT': '0.110', 'AMMO3': '0.117', 'DAMAGECOUNT': '0.330', 'WEAPON3': '0.700', 'weapon3': '1.452', 'weapon2': '1.752', 'FRAGCOUNT': '2.000'} [2024-08-05 08:57:16,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 7536640. Throughput: 0: 904.0. Samples: 1886104. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:57:16,502][00035] Avg episode reward: [(0, '-3.722')] [2024-08-05 08:57:16,621][00150] DAMAGECOUNT value on done: 9446.0 [2024-08-05 08:57:16,622][00150] Sum rewards: -3.716, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-2.430', 'AMMO4': '-0.005', 'AMMO2': '-0.001', 'ARMOR': '0.064', 'weapon4': '0.080', 'WEAPON4': '0.150', 'AMMO3': '0.156', 'HITCOUNT': '0.260', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.930', 'weapon2': '1.422', 'weapon3': '2.108', 'FRAGCOUNT': '4.000'} [2024-08-05 08:57:17,208][00150] DAMAGECOUNT value on done: 9544.0 [2024-08-05 08:57:17,209][00150] Sum rewards: -3.127, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-2.620', 'AMMO5': '0.005', 'WEAPON1': '0.010', 'AMMO2': '0.018', 'ARMOR': '0.036', 'weapon5': '0.048', 'AMMO4': '0.089', 'WEAPON5': '0.100', 'AMMO3': '0.122', 'HITCOUNT': '0.130', 'DAMAGECOUNT': '0.765', 'WEAPON3': '0.800', 'weapon2': '1.506', 'weapon3': '1.864', 'FRAGCOUNT': '3.000'} [2024-08-05 08:57:21,500][00035] Fps is (10 sec: 4096.1, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 7561216. Throughput: 0: 903.4. Samples: 1888832. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:57:21,502][00035] Avg episode reward: [(0, '-3.742')] [2024-08-05 08:57:26,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 7577600. Throughput: 0: 906.8. Samples: 1894450. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:57:26,502][00035] Avg episode reward: [(0, '-3.742')] [2024-08-05 08:57:31,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 7593984. Throughput: 0: 895.7. Samples: 1899500. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:57:31,502][00035] Avg episode reward: [(0, '-3.742')] [2024-08-05 08:57:36,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 7610368. Throughput: 0: 896.3. Samples: 1902270. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:57:36,502][00035] Avg episode reward: [(0, '-3.742')] [2024-08-05 08:57:37,274][00146] Updated weights for policy 0, policy_version 930 (0.0017) [2024-08-05 08:57:41,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 7626752. Throughput: 0: 889.8. Samples: 1907640. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:57:41,502][00035] Avg episode reward: [(0, '-3.742')] [2024-08-05 08:57:41,813][00147] DAMAGECOUNT value on done: 9425.0 [2024-08-05 08:57:41,814][00147] Sum rewards: -5.366, reward structure: {'DEATHCOUNT': '-8.250', 'FRAGCOUNT': '-1.500', 'HEALTH': '-0.760', 'AMMO2': '0.002', 'ARMOR': '0.008', 'AMMO4': '0.010', 'AMMO5': '0.013', 'weapon5': '0.060', 'AMMO3': '0.110', 'HITCOUNT': '0.120', 'WEAPON5': '0.150', 'DAMAGECOUNT': '0.375', 'WEAPON3': '0.750', 'weapon2': '1.412', 'weapon3': '2.134'} [2024-08-05 08:57:42,416][00147] DAMAGECOUNT value on done: 10495.0 [2024-08-05 08:57:42,961][00147] DAMAGECOUNT value on done: 7740.0 [2024-08-05 08:57:42,962][00147] Sum rewards: -2.911, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.724', 'AMMO2': '0.002', 'AMMO4': '0.012', 'weapon7': '0.048', 'ARMOR': '0.090', 'HITCOUNT': '0.100', 'AMMO3': '0.103', 'AMMO6': '0.120', 'AMMO7': '0.120', 'WEAPON4': '0.200', 'WEAPON7': '0.200', 'weapon4': '0.226', 'DAMAGECOUNT': '0.372', 'WEAPON3': '0.750', 'weapon2': '0.798', 'FRAGCOUNT': '1.000', 'weapon3': '1.422'} [2024-08-05 08:57:43,572][00147] DAMAGECOUNT value on done: 8723.0 [2024-08-05 08:57:43,572][00147] Sum rewards: -3.311, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-2.010', 'AMMO2': '0.003', 'AMMO5': '0.005', 'AMMO4': '0.014', 'weapon5': '0.014', 'ARMOR': '0.028', 'AMMO3': '0.086', 'WEAPON5': '0.100', 'WEAPON4': '0.200', 'weapon4': '0.244', 'HITCOUNT': '0.320', 'WEAPON3': '0.600', 'DAMAGECOUNT': '1.041', 'weapon3': '1.576', 'weapon2': '1.718', 'FRAGCOUNT': '4.000'} [2024-08-05 08:57:44,565][00148] DAMAGECOUNT value on done: 9137.0 [2024-08-05 08:57:44,566][00148] Sum rewards: -1.163, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.596', 'AMMO4': '-0.010', 'AMMO2': '-0.002', 'AMMO5': '0.010', 'AMMO3': '0.126', 'HITCOUNT': '0.180', 'WEAPON5': '0.200', 'weapon5': '0.248', 'DAMAGECOUNT': '0.630', 'WEAPON3': '0.800', 'weapon2': '1.024', 'weapon3': '1.976', 'FRAGCOUNT': '2.000'} [2024-08-05 08:57:45,143][00148] DAMAGECOUNT value on done: 8120.0 [2024-08-05 08:57:45,144][00148] Sum rewards: -3.916, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.530', 'AMMO2': '0.010', 'ARMOR': '0.035', 'HITCOUNT': '0.040', 'AMMO4': '0.049', 'AMMO3': '0.107', 'DAMAGECOUNT': '0.141', 'WEAPON3': '0.600', 'weapon3': '1.322', 'FRAGCOUNT': '2.000', 'weapon2': '2.060'} [2024-08-05 08:57:45,704][00148] DAMAGECOUNT value on done: 8324.0 [2024-08-05 08:57:46,296][00148] DAMAGECOUNT value on done: 8272.0 [2024-08-05 08:57:46,297][00148] Sum rewards: -4.171, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.338', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.005', 'AMMO2': '0.017', 'weapon5': '0.028', 'AMMO4': '0.084', 'WEAPON5': '0.100', 'AMMO3': '0.104', 'ARMOR': '0.104', 'WEAPON4': '0.150', 'weapon4': '0.188', 'HITCOUNT': '0.250', 'WEAPON3': '0.750', 'DAMAGECOUNT': '0.780', 'weapon2': '1.364', 'weapon3': '1.994'} [2024-08-05 08:57:46,501][00035] Fps is (10 sec: 4095.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 7651328. Throughput: 0: 901.5. Samples: 1913086. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:57:46,502][00035] Avg episode reward: [(0, '-3.747')] [2024-08-05 08:57:49,232][00149] DAMAGECOUNT value on done: 8303.0 [2024-08-05 08:57:49,794][00149] DAMAGECOUNT value on done: 7985.0 [2024-08-05 08:57:50,333][00149] DAMAGECOUNT value on done: 9235.0 [2024-08-05 08:57:50,334][00149] Sum rewards: -1.692, reward structure: {'DEATHCOUNT': '-7.500', 'AMMO5': '0.003', 'WEAPON1': '0.010', 'AMMO2': '0.020', 'weapon4': '0.034', 'ARMOR': '0.040', 'WEAPON4': '0.050', 'WEAPON5': '0.050', 'AMMO3': '0.088', 'AMMO4': '0.099', 'HITCOUNT': '0.140', 'HEALTH': '0.177', 'weapon5': '0.260', 'DAMAGECOUNT': '0.435', 'WEAPON3': '0.500', 'FRAGCOUNT': '0.500', 'weapon3': '1.070', 'weapon2': '2.332'} [2024-08-05 08:57:50,890][00149] DAMAGECOUNT value on done: 9081.0 [2024-08-05 08:57:51,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 7667712. Throughput: 0: 901.3. Samples: 1915792. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:57:51,502][00035] Avg episode reward: [(0, '-3.757')] [2024-08-05 08:57:52,278][00150] DAMAGECOUNT value on done: 8820.0 [2024-08-05 08:57:52,279][00150] Sum rewards: -3.608, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.178', 'AMMO2': '0.005', 'WEAPON1': '0.020', 'AMMO4': '0.024', 'ARMOR': '0.056', 'AMMO3': '0.119', 'HITCOUNT': '0.180', 'DAMAGECOUNT': '0.600', 'WEAPON3': '0.750', 'weapon3': '1.506', 'FRAGCOUNT': '2.000', 'weapon2': '2.060'} [2024-08-05 08:57:52,843][00150] DAMAGECOUNT value on done: 10525.0 [2024-08-05 08:57:52,844][00150] Sum rewards: 1.598, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.402', 'AMMO4': '-0.019', 'AMMO2': '-0.004', 'WEAPON1': '0.020', 'WEAPON4': '0.100', 'AMMO3': '0.121', 'weapon4': '0.146', 'HITCOUNT': '0.290', 'WEAPON3': '0.750', 'DAMAGECOUNT': '1.350', 'weapon2': '1.370', 'weapon3': '2.126', 'FRAGCOUNT': '5.000'} [2024-08-05 08:57:53,432][00150] DAMAGECOUNT value on done: 9793.0 [2024-08-05 08:57:53,433][00150] Sum rewards: -5.263, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.648', 'AMMO2': '0.012', 'AMMO5': '0.014', 'AMMO4': '0.058', 'ARMOR': '0.068', 'weapon5': '0.086', 'AMMO3': '0.133', 'WEAPON5': '0.250', 'HITCOUNT': '0.320', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.750', 'DAMAGECOUNT': '1.041', 'weapon3': '1.794', 'weapon2': '1.858'} [2024-08-05 08:57:54,002][00150] DAMAGECOUNT value on done: 9714.0 [2024-08-05 08:57:54,003][00150] Sum rewards: -4.613, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-0.680', 'AMMO5': '0.005', 'AMMO2': '0.006', 'AMMO4': '0.032', 'ARMOR': '0.036', 'weapon5': '0.056', 'WEAPON5': '0.100', 'AMMO3': '0.105', 'HITCOUNT': '0.220', 'DAMAGECOUNT': '0.510', 'WEAPON3': '0.700', 'weapon3': '1.424', 'FRAGCOUNT': '2.000', 'weapon2': '2.122'} [2024-08-05 08:57:56,500][00035] Fps is (10 sec: 3277.0, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 7684096. Throughput: 0: 904.1. Samples: 1921268. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:57:56,504][00035] Avg episode reward: [(0, '-3.661')] [2024-08-05 08:58:00,133][00146] Updated weights for policy 0, policy_version 940 (0.0026) [2024-08-05 08:58:01,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 7700480. Throughput: 0: 894.1. Samples: 1926338. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:58:01,502][00035] Avg episode reward: [(0, '-3.661')] [2024-08-05 08:58:06,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 7716864. Throughput: 0: 894.0. Samples: 1929060. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:58:06,505][00035] Avg episode reward: [(0, '-3.661')] [2024-08-05 08:58:11,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 7733248. Throughput: 0: 888.5. Samples: 1934434. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:58:11,502][00035] Avg episode reward: [(0, '-3.661')] [2024-08-05 08:58:16,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 7757824. Throughput: 0: 896.9. Samples: 1939862. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:58:16,504][00035] Avg episode reward: [(0, '-3.661')] [2024-08-05 08:58:19,956][00147] DAMAGECOUNT value on done: 9500.0 [2024-08-05 08:58:19,957][00147] Sum rewards: -5.480, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.562', 'AMMO2': '0.006', 'AMMO4': '0.032', 'HITCOUNT': '0.070', 'AMMO3': '0.083', 'ARMOR': '0.100', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.225', 'weapon4': '0.326', 'WEAPON3': '0.550', 'FRAGCOUNT': '1.000', 'weapon3': '1.460', 'weapon2': '1.780'} [2024-08-05 08:58:20,519][00147] DAMAGECOUNT value on done: 10760.0 [2024-08-05 08:58:20,519][00147] Sum rewards: -2.894, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.881', 'ARMOR': '0.008', 'AMMO5': '0.010', 'AMMO2': '0.014', 'AMMO4': '0.067', 'WEAPON5': '0.100', 'AMMO3': '0.121', 'weapon5': '0.160', 'HITCOUNT': '0.250', 'WEAPON3': '0.750', 'DAMAGECOUNT': '0.795', 'weapon3': '1.638', 'weapon2': '1.824', 'FRAGCOUNT': '2.000'} [2024-08-05 08:58:21,154][00147] DAMAGECOUNT value on done: 8035.0 [2024-08-05 08:58:21,155][00147] Sum rewards: -1.948, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-0.694', 'weapon5': '0.012', 'AMMO5': '0.015', 'AMMO2': '0.017', 'AMMO4': '0.087', 'ARMOR': '0.088', 'WEAPON4': '0.100', 'AMMO3': '0.176', 'WEAPON5': '0.200', 'HITCOUNT': '0.210', 'weapon4': '0.214', 'DAMAGECOUNT': '0.885', 'WEAPON3': '0.900', 'weapon2': '1.512', 'weapon3': '1.830', 'FRAGCOUNT': '3.000'} [2024-08-05 08:58:21,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 7774208. Throughput: 0: 895.9. Samples: 1942586. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:58:21,503][00035] Avg episode reward: [(0, '-3.694')] [2024-08-05 08:58:21,511][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000949_7774208.pth... [2024-08-05 08:58:21,621][00137] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000843_6905856.pth [2024-08-05 08:58:21,758][00147] DAMAGECOUNT value on done: 9057.0 [2024-08-05 08:58:21,759][00147] Sum rewards: -1.168, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.050', 'AMMO4': '-0.030', 'AMMO2': '-0.006', 'AMMO5': '0.003', 'ARMOR': '0.036', 'WEAPON5': '0.050', 'weapon5': '0.070', 'AMMO3': '0.103', 'HITCOUNT': '0.140', 'WEAPON3': '0.550', 'DAMAGECOUNT': '1.002', 'weapon3': '1.438', 'weapon2': '1.776', 'FRAGCOUNT': '3.000'} [2024-08-05 08:58:22,608][00148] DAMAGECOUNT value on done: 9227.0 [2024-08-05 08:58:22,608][00148] Sum rewards: -3.286, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.799', 'AMMO2': '0.001', 'AMMO5': '0.003', 'AMMO4': '0.007', 'WEAPON1': '0.010', 'weapon5': '0.028', 'WEAPON5': '0.050', 'HITCOUNT': '0.090', 'WEAPON4': '0.100', 'AMMO3': '0.110', 'ARMOR': '0.116', 'weapon4': '0.138', 'DAMAGECOUNT': '0.270', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon3': '1.452', 'weapon2': '1.788'} [2024-08-05 08:58:22,969][00146] Updated weights for policy 0, policy_version 950 (0.0024) [2024-08-05 08:58:23,226][00148] DAMAGECOUNT value on done: 8315.0 [2024-08-05 08:58:23,845][00148] DAMAGECOUNT value on done: 8641.0 [2024-08-05 08:58:23,846][00148] Sum rewards: -2.897, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.318', 'AMMO5': '0.003', 'AMMO2': '0.010', 'AMMO4': '0.050', 'ARMOR': '0.076', 'WEAPON5': '0.100', 'weapon5': '0.130', 'AMMO3': '0.133', 'WEAPON4': '0.150', 'HITCOUNT': '0.250', 'weapon4': '0.380', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.951', 'weapon2': '1.322', 'weapon3': '1.566', 'FRAGCOUNT': '3.000'} [2024-08-05 08:58:24,452][00148] DAMAGECOUNT value on done: 8404.0 [2024-08-05 08:58:24,453][00148] Sum rewards: -1.787, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.257', 'AMMO2': '0.001', 'AMMO4': '0.003', 'AMMO5': '0.005', 'WEAPON1': '0.010', 'weapon5': '0.020', 'weapon4': '0.034', 'ARMOR': '0.040', 'WEAPON4': '0.050', 'WEAPON5': '0.100', 'AMMO3': '0.119', 'HITCOUNT': '0.160', 'DAMAGECOUNT': '0.396', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '1.638', 'weapon2': '1.944'} [2024-08-05 08:58:26,181][00149] DAMAGECOUNT value on done: 8503.0 [2024-08-05 08:58:26,182][00149] Sum rewards: -7.571, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-1.145', 'AMMO2': '0.008', 'AMMO4': '0.042', 'ARMOR': '0.044', 'WEAPON4': '0.050', 'AMMO3': '0.142', 'HITCOUNT': '0.150', 'weapon4': '0.178', 'DAMAGECOUNT': '0.600', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '1.452', 'weapon3': '1.758'} [2024-08-05 08:58:26,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 7790592. Throughput: 0: 895.7. Samples: 1947948. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:58:26,502][00035] Avg episode reward: [(0, '-3.718')] [2024-08-05 08:58:26,795][00149] DAMAGECOUNT value on done: 8104.0 [2024-08-05 08:58:27,361][00149] DAMAGECOUNT value on done: 9470.0 [2024-08-05 08:58:27,362][00149] Sum rewards: -0.962, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.060', 'AMMO4': '-0.009', 'AMMO2': '-0.002', 'ARMOR': '0.064', 'AMMO3': '0.156', 'HITCOUNT': '0.220', 'DAMAGECOUNT': '0.705', 'WEAPON3': '0.900', 'weapon2': '1.490', 'weapon3': '2.324', 'FRAGCOUNT': '3.000'} [2024-08-05 08:58:27,996][00149] DAMAGECOUNT value on done: 9406.0 [2024-08-05 08:58:27,997][00149] Sum rewards: 1.690, reward structure: {'DEATHCOUNT': '-6.750', 'AMMO2': '0.029', 'AMMO3': '0.088', 'WEAPON4': '0.100', 'ARMOR': '0.124', 'AMMO4': '0.145', 'HITCOUNT': '0.230', 'HEALTH': '0.294', 'weapon4': '0.386', 'WEAPON3': '0.550', 'DAMAGECOUNT': '0.975', 'weapon2': '1.000', 'weapon3': '1.518', 'FRAGCOUNT': '3.000'} [2024-08-05 08:58:29,275][00150] DAMAGECOUNT value on done: 8875.0 [2024-08-05 08:58:29,850][00150] DAMAGECOUNT value on done: 10760.0 [2024-08-05 08:58:29,851][00150] Sum rewards: -3.252, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.190', 'AMMO2': '0.018', 'WEAPON4': '0.050', 'AMMO4': '0.091', 'ARMOR': '0.108', 'AMMO3': '0.146', 'weapon4': '0.186', 'HITCOUNT': '0.210', 'DAMAGECOUNT': '0.705', 'WEAPON3': '0.900', 'weapon2': '1.252', 'FRAGCOUNT': '2.000', 'weapon3': '2.022'} [2024-08-05 08:58:30,463][00150] DAMAGECOUNT value on done: 10168.0 [2024-08-05 08:58:30,465][00150] Sum rewards: -1.119, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.355', 'AMMO4': '-0.010', 'AMMO2': '-0.002', 'WEAPON1': '0.010', 'AMMO5': '0.015', 'ARMOR': '0.040', 'weapon5': '0.072', 'WEAPON4': '0.100', 'weapon4': '0.104', 'AMMO3': '0.112', 'WEAPON5': '0.200', 'HITCOUNT': '0.310', 'WEAPON3': '0.600', 'DAMAGECOUNT': '1.125', 'weapon3': '1.528', 'weapon2': '1.532', 'FRAGCOUNT': '2.000'} [2024-08-05 08:58:31,021][00150] DAMAGECOUNT value on done: 10109.0 [2024-08-05 08:58:31,023][00150] Sum rewards: -0.190, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-0.910', 'AMMO2': '0.003', 'AMMO4': '0.013', 'ARMOR': '0.016', 'weapon4': '0.020', 'WEAPON4': '0.050', 'AMMO3': '0.105', 'HITCOUNT': '0.260', 'WEAPON3': '0.650', 'DAMAGECOUNT': '1.185', 'weapon2': '1.388', 'weapon3': '1.780', 'FRAGCOUNT': '2.000'} [2024-08-05 08:58:31,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 7806976. Throughput: 0: 894.5. Samples: 1953340. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:58:31,504][00035] Avg episode reward: [(0, '-3.534')] [2024-08-05 08:58:36,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 7823360. Throughput: 0: 886.1. Samples: 1955666. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:58:36,502][00035] Avg episode reward: [(0, '-3.534')] [2024-08-05 08:58:41,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 7839744. Throughput: 0: 882.4. Samples: 1960978. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:58:41,502][00035] Avg episode reward: [(0, '-3.534')] [2024-08-05 08:58:45,390][00147] Large shaping reward -2.534 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.28500000000000003, -95.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-05 08:58:46,329][00146] Updated weights for policy 0, policy_version 960 (0.0019) [2024-08-05 08:58:46,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 7864320. Throughput: 0: 888.8. Samples: 1966332. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:58:46,504][00035] Avg episode reward: [(0, '-3.534')] [2024-08-05 08:58:51,501][00035] Fps is (10 sec: 4095.8, 60 sec: 3549.8, 300 sec: 3610.0). Total num frames: 7880704. Throughput: 0: 887.3. Samples: 1968988. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:58:51,502][00035] Avg episode reward: [(0, '-3.534')] [2024-08-05 08:58:56,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 7897088. Throughput: 0: 890.0. Samples: 1974486. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:58:56,502][00035] Avg episode reward: [(0, '-3.534')] [2024-08-05 08:58:58,928][00147] DAMAGECOUNT value on done: 9590.0 [2024-08-05 08:58:58,929][00147] Sum rewards: -5.902, reward structure: {'DEATHCOUNT': '-8.250', 'FRAGCOUNT': '-1.500', 'HEALTH': '-0.814', 'AMMO5': '0.003', 'AMMO2': '0.016', 'weapon5': '0.022', 'WEAPON5': '0.050', 'weapon4': '0.050', 'AMMO4': '0.077', 'HITCOUNT': '0.080', 'AMMO3': '0.100', 'ARMOR': '0.116', 'WEAPON4': '0.150', 'DAMAGECOUNT': '0.270', 'WEAPON3': '0.600', 'weapon3': '1.182', 'weapon2': '1.946'} [2024-08-05 08:58:59,540][00147] DAMAGECOUNT value on done: 10985.0 [2024-08-05 08:58:59,541][00147] Sum rewards: -1.875, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.090', 'AMMO5': '0.008', 'AMMO2': '0.012', 'WEAPON1': '0.020', 'ARMOR': '0.032', 'AMMO4': '0.061', 'weapon4': '0.078', 'weapon5': '0.090', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.130', 'HITCOUNT': '0.240', 'DAMAGECOUNT': '0.675', 'WEAPON3': '0.850', 'weapon2': '1.560', 'weapon3': '1.758', 'FRAGCOUNT': '5.000'} [2024-08-05 08:59:00,213][00147] DAMAGECOUNT value on done: 8189.0 [2024-08-05 08:59:00,213][00147] Sum rewards: -4.085, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.700', 'AMMO2': '0.026', 'ARMOR': '0.088', 'AMMO3': '0.099', 'HITCOUNT': '0.110', 'AMMO4': '0.131', 'WEAPON4': '0.200', 'weapon4': '0.240', 'DAMAGECOUNT': '0.462', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon2': '1.312', 'weapon3': '1.496'} [2024-08-05 08:59:00,800][00147] DAMAGECOUNT value on done: 9140.0 [2024-08-05 08:59:00,801][00147] Sum rewards: -5.183, reward structure: {'DEATHCOUNT': '-7.500', 'FRAGCOUNT': '-1.500', 'HEALTH': '-0.775', 'AMMO4': '-0.006', 'AMMO2': '-0.001', 'AMMO5': '0.007', 'ARMOR': '0.072', 'HITCOUNT': '0.080', 'AMMO3': '0.111', 'WEAPON5': '0.150', 'DAMAGECOUNT': '0.249', 'weapon5': '0.458', 'WEAPON3': '0.650', 'weapon3': '1.394', 'weapon2': '1.428'} [2024-08-05 08:59:01,270][00148] DAMAGECOUNT value on done: 9420.0 [2024-08-05 08:59:01,500][00035] Fps is (10 sec: 3277.0, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 7913472. Throughput: 0: 887.3. Samples: 1979790. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:59:01,504][00035] Avg episode reward: [(0, '-3.532')] [2024-08-05 08:59:01,819][00148] DAMAGECOUNT value on done: 8493.0 [2024-08-05 08:59:02,403][00148] DAMAGECOUNT value on done: 8701.0 [2024-08-05 08:59:02,957][00148] DAMAGECOUNT value on done: 8515.0 [2024-08-05 08:59:03,546][00149] DAMAGECOUNT value on done: 8944.0 [2024-08-05 08:59:03,547][00149] Sum rewards: -1.754, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.460', 'AMMO2': '0.004', 'AMMO5': '0.012', 'AMMO4': '0.017', 'ARMOR': '0.020', 'AMMO3': '0.123', 'weapon5': '0.220', 'HITCOUNT': '0.250', 'WEAPON5': '0.250', 'WEAPON3': '0.850', 'DAMAGECOUNT': '1.323', 'weapon3': '1.546', 'weapon2': '1.840', 'FRAGCOUNT': '3.000'} [2024-08-05 08:59:04,262][00149] DAMAGECOUNT value on done: 8463.0 [2024-08-05 08:59:04,263][00149] Sum rewards: -6.170, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-1.094', 'weapon4': '0.002', 'AMMO2': '0.011', 'ARMOR': '0.056', 'AMMO4': '0.056', 'WEAPON4': '0.100', 'AMMO3': '0.175', 'HITCOUNT': '0.330', 'WEAPON3': '0.950', 'DAMAGECOUNT': '1.077', 'weapon2': '1.516', 'FRAGCOUNT': '2.000', 'weapon3': '2.150'} [2024-08-05 08:59:04,946][00149] DAMAGECOUNT value on done: 9713.0 [2024-08-05 08:59:04,948][00149] Sum rewards: -1.996, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.932', 'AMMO2': '0.014', 'ARMOR': '0.064', 'AMMO4': '0.072', 'AMMO3': '0.133', 'WEAPON4': '0.150', 'HITCOUNT': '0.220', 'weapon4': '0.366', 'WEAPON3': '0.650', 'DAMAGECOUNT': '0.729', 'weapon3': '1.274', 'weapon2': '1.514', 'FRAGCOUNT': '2.000'} [2024-08-05 08:59:05,673][00149] DAMAGECOUNT value on done: 9566.0 [2024-08-05 08:59:05,674][00149] Sum rewards: -4.081, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.286', 'AMMO5': '0.003', 'AMMO2': '0.010', 'WEAPON1': '0.020', 'ARMOR': '0.028', 'AMMO4': '0.051', 'weapon5': '0.072', 'WEAPON5': '0.100', 'HITCOUNT': '0.140', 'AMMO3': '0.141', 'DAMAGECOUNT': '0.480', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '1.476', 'weapon3': '1.784'} [2024-08-05 08:59:06,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 7929856. Throughput: 0: 883.9. Samples: 1982362. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:59:06,502][00035] Avg episode reward: [(0, '-3.625')] [2024-08-05 08:59:06,954][00150] DAMAGECOUNT value on done: 8940.0 [2024-08-05 08:59:06,956][00150] Sum rewards: -5.520, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.080', 'AMMO2': '0.011', 'WEAPON4': '0.050', 'AMMO4': '0.053', 'weapon4': '0.054', 'HITCOUNT': '0.060', 'AMMO3': '0.172', 'DAMAGECOUNT': '0.195', 'ARMOR': '0.505', 'WEAPON3': '0.650', 'FRAGCOUNT': '1.000', 'weapon3': '1.234', 'weapon2': '2.076'} [2024-08-05 08:59:07,533][00150] DAMAGECOUNT value on done: 10910.0 [2024-08-05 08:59:07,534][00150] Sum rewards: 1.400, reward structure: {'DEATHCOUNT': '-6.000', 'AMMO2': '0.010', 'AMMO4': '0.048', 'AMMO3': '0.073', 'HEALTH': '0.101', 'HITCOUNT': '0.170', 'DAMAGECOUNT': '0.450', 'WEAPON3': '0.450', 'ARMOR': '0.552', 'weapon3': '1.058', 'weapon2': '1.488', 'FRAGCOUNT': '3.000'} [2024-08-05 08:59:08,082][00150] DAMAGECOUNT value on done: 10530.0 [2024-08-05 08:59:08,084][00150] Sum rewards: -1.939, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.340', 'AMMO5': '0.005', 'AMMO2': '0.008', 'AMMO4': '0.040', 'WEAPON5': '0.100', 'AMMO3': '0.112', 'ARMOR': '0.132', 'WEAPON4': '0.150', 'HITCOUNT': '0.200', 'weapon5': '0.222', 'weapon4': '0.262', 'WEAPON3': '0.650', 'DAMAGECOUNT': '1.086', 'weapon3': '1.420', 'FRAGCOUNT': '1.500', 'weapon2': '1.514'} [2024-08-05 08:59:08,643][00150] DAMAGECOUNT value on done: 10365.0 [2024-08-05 08:59:08,644][00150] Sum rewards: -2.921, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.648', 'AMMO4': '-0.044', 'AMMO2': '-0.009', 'AMMO5': '0.007', 'ARMOR': '0.060', 'weapon5': '0.112', 'AMMO3': '0.148', 'WEAPON5': '0.150', 'HITCOUNT': '0.220', 'DAMAGECOUNT': '0.768', 'WEAPON3': '0.950', 'weapon2': '1.466', 'weapon3': '1.898', 'FRAGCOUNT': '2.000'} [2024-08-05 08:59:09,794][00146] Updated weights for policy 0, policy_version 970 (0.0019) [2024-08-05 08:59:11,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 7946240. Throughput: 0: 877.5. Samples: 1987436. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:59:11,502][00035] Avg episode reward: [(0, '-3.613')] [2024-08-05 08:59:16,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3582.3). Total num frames: 7962624. Throughput: 0: 878.4. Samples: 1992870. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 08:59:16,502][00035] Avg episode reward: [(0, '-3.613')] [2024-08-05 08:59:21,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 7987200. Throughput: 0: 884.8. Samples: 1995484. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:59:21,502][00035] Avg episode reward: [(0, '-3.613')] [2024-08-05 08:59:26,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 8003584. Throughput: 0: 889.3. Samples: 2000998. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:59:26,502][00035] Avg episode reward: [(0, '-3.613')] [2024-08-05 08:59:31,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8019968. Throughput: 0: 891.8. Samples: 2006464. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:59:31,501][00035] Avg episode reward: [(0, '-3.613')] [2024-08-05 08:59:32,367][00146] Updated weights for policy 0, policy_version 980 (0.0022) [2024-08-05 08:59:36,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8036352. Throughput: 0: 894.9. Samples: 2009260. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:59:36,502][00035] Avg episode reward: [(0, '-3.613')] [2024-08-05 08:59:37,932][00147] DAMAGECOUNT value on done: 9785.0 [2024-08-05 08:59:37,933][00147] Sum rewards: -6.679, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.861', 'AMMO2': '0.008', 'ARMOR': '0.040', 'AMMO4': '0.041', 'WEAPON4': '0.050', 'weapon4': '0.080', 'HITCOUNT': '0.140', 'AMMO3': '0.204', 'DAMAGECOUNT': '0.585', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.200', 'weapon2': '1.406', 'weapon3': '1.678'} [2024-08-05 08:59:38,516][00147] DAMAGECOUNT value on done: 11201.0 [2024-08-05 08:59:38,518][00147] Sum rewards: 0.108, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.790', 'AMMO5': '0.003', 'weapon5': '0.008', 'AMMO2': '0.016', 'WEAPON5': '0.050', 'AMMO4': '0.078', 'ARMOR': '0.084', 'AMMO3': '0.133', 'HITCOUNT': '0.190', 'DAMAGECOUNT': '0.648', 'WEAPON3': '0.800', 'weapon2': '1.396', 'weapon3': '1.992', 'FRAGCOUNT': '3.000'} [2024-08-05 08:59:39,096][00147] DAMAGECOUNT value on done: 8314.0 [2024-08-05 08:59:39,097][00147] Sum rewards: -0.805, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.284', 'AMMO4': '-0.020', 'AMMO2': '-0.004', 'AMMO5': '0.007', 'weapon5': '0.016', 'WEAPON5': '0.050', 'ARMOR': '0.056', 'AMMO3': '0.128', 'HITCOUNT': '0.130', 'DAMAGECOUNT': '0.375', 'WEAPON3': '0.750', 'weapon2': '1.312', 'weapon3': '2.178', 'FRAGCOUNT': '3.000'} [2024-08-05 08:59:39,685][00147] DAMAGECOUNT value on done: 9385.0 [2024-08-05 08:59:39,685][00147] Sum rewards: -2.769, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.886', 'AMMO5': '0.005', 'AMMO2': '0.020', 'WEAPON4': '0.050', 'ARMOR': '0.072', 'WEAPON5': '0.100', 'AMMO4': '0.102', 'AMMO3': '0.151', 'weapon4': '0.194', 'HITCOUNT': '0.230', 'DAMAGECOUNT': '0.735', 'WEAPON3': '0.750', 'weapon2': '1.434', 'FRAGCOUNT': '2.000', 'weapon3': '2.024'} [2024-08-05 08:59:40,029][00148] DAMAGECOUNT value on done: 9740.0 [2024-08-05 08:59:40,030][00148] Sum rewards: -5.685, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.748', 'AMMO2': '0.001', 'AMMO4': '0.005', 'AMMO5': '0.014', 'WEAPON1': '0.020', 'weapon5': '0.030', 'ARMOR': '0.040', 'AMMO3': '0.159', 'WEAPON5': '0.200', 'HITCOUNT': '0.300', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.915', 'WEAPON3': '1.000', 'weapon2': '1.190', 'weapon3': '2.188'} [2024-08-05 08:59:40,577][00148] DAMAGECOUNT value on done: 8756.0 [2024-08-05 08:59:40,827][00149] DAMAGECOUNT value on done: 9182.0 [2024-08-05 08:59:40,827][00149] Sum rewards: -0.366, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.086', 'AMMO2': '0.002', 'AMMO4': '0.012', 'AMMO5': '0.013', 'WEAPON1': '0.020', 'ARMOR': '0.040', 'weapon5': '0.070', 'AMMO3': '0.105', 'HITCOUNT': '0.160', 'WEAPON5': '0.200', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.714', 'weapon3': '1.578', 'weapon2': '1.856', 'FRAGCOUNT': '2.000'} [2024-08-05 08:59:41,185][00148] DAMAGECOUNT value on done: 9059.0 [2024-08-05 08:59:41,186][00148] Sum rewards: -1.865, reward structure: {'DEATHCOUNT': '-9.000', 'AMMO5': '0.005', 'WEAPON1': '0.010', 'AMMO2': '0.017', 'weapon5': '0.034', 'weapon4': '0.034', 'WEAPON5': '0.050', 'AMMO3': '0.083', 'AMMO4': '0.085', 'WEAPON4': '0.100', 'HITCOUNT': '0.210', 'HEALTH': '0.418', 'ARMOR': '0.420', 'WEAPON3': '0.450', 'DAMAGECOUNT': '1.074', 'weapon3': '1.244', 'weapon2': '1.400', 'FRAGCOUNT': '1.500'} [2024-08-05 08:59:41,372][00149] DAMAGECOUNT value on done: 8820.0 [2024-08-05 08:59:41,372][00149] Sum rewards: -4.726, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.300', 'AMMO4': '-0.020', 'AMMO2': '-0.004', 'AMMO5': '0.005', 'ARMOR': '0.038', 'WEAPON5': '0.050', 'weapon5': '0.136', 'AMMO3': '0.157', 'HITCOUNT': '0.260', 'WEAPON3': '1.050', 'DAMAGECOUNT': '1.071', 'weapon2': '1.094', 'FRAGCOUNT': '2.000', 'weapon3': '2.236'} [2024-08-05 08:59:41,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8052736. Throughput: 0: 882.2. Samples: 2014184. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:59:41,502][00035] Avg episode reward: [(0, '-3.454')] [2024-08-05 08:59:41,750][00148] DAMAGECOUNT value on done: 8690.0 [2024-08-05 08:59:41,751][00148] Sum rewards: -1.619, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.302', 'AMMO4': '-0.026', 'AMMO2': '-0.005', 'WEAPON4': '0.100', 'AMMO3': '0.107', 'HITCOUNT': '0.110', 'ARMOR': '0.144', 'weapon4': '0.212', 'DAMAGECOUNT': '0.525', 'WEAPON3': '0.800', 'weapon2': '1.110', 'FRAGCOUNT': '2.000', 'weapon3': '2.106'} [2024-08-05 08:59:41,979][00149] DAMAGECOUNT value on done: 10023.0 [2024-08-05 08:59:41,979][00149] Sum rewards: 0.754, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.260', 'AMMO2': '0.004', 'AMMO4': '0.021', 'ARMOR': '0.080', 'WEAPON4': '0.100', 'AMMO3': '0.130', 'weapon4': '0.158', 'HITCOUNT': '0.250', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.930', 'weapon2': '1.538', 'weapon3': '1.752', 'FRAGCOUNT': '6.000'} [2024-08-05 08:59:42,530][00149] DAMAGECOUNT value on done: 9823.0 [2024-08-05 08:59:42,531][00149] Sum rewards: -5.351, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-1.106', 'AMMO5': '0.007', 'AMMO2': '0.010', 'AMMO4': '0.048', 'WEAPON5': '0.050', 'ARMOR': '0.068', 'AMMO3': '0.185', 'WEAPON4': '0.200', 'HITCOUNT': '0.270', 'weapon4': '0.272', 'DAMAGECOUNT': '0.771', 'weapon2': '0.894', 'WEAPON3': '1.000', 'weapon3': '1.980', 'FRAGCOUNT': '2.000'} [2024-08-05 08:59:43,943][00150] DAMAGECOUNT value on done: 9155.0 [2024-08-05 08:59:44,543][00150] DAMAGECOUNT value on done: 11105.0 [2024-08-05 08:59:45,075][00150] DAMAGECOUNT value on done: 10676.0 [2024-08-05 08:59:45,599][00150] DAMAGECOUNT value on done: 10782.0 [2024-08-05 08:59:45,600][00150] Sum rewards: -3.415, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-2.964', 'AMMO2': '0.002', 'AMMO5': '0.005', 'AMMO4': '0.009', 'weapon4': '0.020', 'WEAPON4': '0.050', 'WEAPON5': '0.100', 'AMMO3': '0.142', 'HITCOUNT': '0.360', 'WEAPON3': '0.950', 'DAMAGECOUNT': '1.251', 'weapon3': '1.826', 'weapon2': '1.834', 'FRAGCOUNT': '5.000'} [2024-08-05 08:59:46,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 8077312. Throughput: 0: 885.4. Samples: 2019632. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:59:46,502][00035] Avg episode reward: [(0, '-3.483')] [2024-08-05 08:59:51,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 8093696. Throughput: 0: 889.2. Samples: 2022374. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:59:51,505][00035] Avg episode reward: [(0, '-3.483')] [2024-08-05 08:59:55,119][00146] Updated weights for policy 0, policy_version 990 (0.0019) [2024-08-05 08:59:56,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8110080. Throughput: 0: 899.1. Samples: 2027896. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 08:59:56,502][00035] Avg episode reward: [(0, '-3.483')] [2024-08-05 09:00:01,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8126464. Throughput: 0: 902.0. Samples: 2033462. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:00:01,502][00035] Avg episode reward: [(0, '-3.483')] [2024-08-05 09:00:06,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 8151040. Throughput: 0: 905.4. Samples: 2036226. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:00:06,502][00035] Avg episode reward: [(0, '-3.483')] [2024-08-05 09:00:11,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 8167424. Throughput: 0: 896.8. Samples: 2041352. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:00:11,503][00035] Avg episode reward: [(0, '-3.483')] [2024-08-05 09:00:15,376][00147] DAMAGECOUNT value on done: 9984.0 [2024-08-05 09:00:15,377][00147] Sum rewards: -5.925, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-2.196', 'AMMO4': '-0.016', 'AMMO2': '-0.003', 'AMMO5': '0.003', 'WEAPON1': '0.010', 'WEAPON5': '0.050', 'weapon5': '0.092', 'ARMOR': '0.108', 'AMMO3': '0.131', 'HITCOUNT': '0.180', 'WEAPON4': '0.200', 'weapon4': '0.374', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.597', 'WEAPON3': '0.800', 'weapon2': '1.416', 'weapon3': '1.580'} [2024-08-05 09:00:15,986][00147] DAMAGECOUNT value on done: 11561.0 [2024-08-05 09:00:15,987][00147] Sum rewards: -0.690, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.304', 'AMMO5': '0.003', 'weapon5': '0.008', 'AMMO2': '0.016', 'WEAPON5': '0.050', 'AMMO4': '0.078', 'ARMOR': '0.104', 'AMMO3': '0.123', 'WEAPON4': '0.150', 'HITCOUNT': '0.290', 'weapon4': '0.364', 'WEAPON3': '0.700', 'weapon2': '1.056', 'DAMAGECOUNT': '1.080', 'weapon3': '1.592', 'FRAGCOUNT': '3.000'} [2024-08-05 09:00:16,501][00035] Fps is (10 sec: 3276.6, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 8183808. Throughput: 0: 898.0. Samples: 2046876. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:00:16,502][00035] Avg episode reward: [(0, '-3.492')] [2024-08-05 09:00:16,578][00147] DAMAGECOUNT value on done: 8809.0 [2024-08-05 09:00:16,579][00147] Sum rewards: 1.791, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.070', 'AMMO5': '0.003', 'weapon5': '0.006', 'AMMO2': '0.007', 'AMMO4': '0.035', 'ARMOR': '0.036', 'WEAPON5': '0.050', 'WEAPON4': '0.050', 'weapon4': '0.122', 'AMMO3': '0.123', 'HITCOUNT': '0.400', 'WEAPON3': '0.750', 'weapon2': '1.038', 'DAMAGECOUNT': '1.485', 'weapon3': '2.006', 'FRAGCOUNT': '4.000'} [2024-08-05 09:00:17,201][00147] DAMAGECOUNT value on done: 9575.0 [2024-08-05 09:00:17,202][00147] Sum rewards: -2.268, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.138', 'AMMO5': '0.010', 'AMMO2': '0.012', 'weapon5': '0.024', 'WEAPON1': '0.030', 'WEAPON4': '0.050', 'AMMO4': '0.058', 'ARMOR': '0.076', 'weapon4': '0.086', 'AMMO3': '0.142', 'HITCOUNT': '0.160', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.570', 'WEAPON3': '0.900', 'weapon2': '1.578', 'weapon3': '1.724', 'FRAGCOUNT': '3.000'} [2024-08-05 09:00:17,238][00149] DAMAGECOUNT value on done: 9292.0 [2024-08-05 09:00:17,239][00149] Sum rewards: -2.696, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.441', 'AMMO4': '-0.038', 'AMMO2': '-0.007', 'AMMO5': '0.005', 'weapon5': '0.020', 'AMMO3': '0.091', 'HITCOUNT': '0.100', 'WEAPON5': '0.100', 'ARMOR': '0.108', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.330', 'weapon4': '0.536', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon2': '1.108', 'weapon3': '1.392'} [2024-08-05 09:00:17,772][00149] DAMAGECOUNT value on done: 9123.0 [2024-08-05 09:00:17,773][00149] Sum rewards: -3.776, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.522', 'AMMO5': '0.003', 'AMMO2': '0.008', 'weapon5': '0.026', 'ARMOR': '0.037', 'AMMO4': '0.039', 'WEAPON5': '0.050', 'AMMO3': '0.110', 'WEAPON4': '0.150', 'HITCOUNT': '0.190', 'weapon4': '0.214', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.909', 'weapon2': '1.328', 'weapon3': '1.632'} [2024-08-05 09:00:17,804][00148] DAMAGECOUNT value on done: 10005.0 [2024-08-05 09:00:17,804][00148] Sum rewards: -2.445, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.681', 'AMMO4': '-0.003', 'AMMO2': '-0.000', 'weapon5': '0.002', 'AMMO5': '0.010', 'WEAPON5': '0.100', 'ARMOR': '0.116', 'AMMO3': '0.146', 'HITCOUNT': '0.180', 'DAMAGECOUNT': '0.795', 'WEAPON3': '0.850', 'weapon2': '1.408', 'weapon3': '1.632', 'FRAGCOUNT': '3.000'} [2024-08-05 09:00:18,035][00146] Updated weights for policy 0, policy_version 1000 (0.0025) [2024-08-05 09:00:18,384][00148] DAMAGECOUNT value on done: 8981.0 [2024-08-05 09:00:18,386][00148] Sum rewards: -2.013, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.345', 'AMMO5': '0.005', 'AMMO2': '0.006', 'ARMOR': '0.028', 'AMMO4': '0.029', 'WEAPON5': '0.050', 'AMMO3': '0.145', 'HITCOUNT': '0.180', 'WEAPON3': '0.650', 'DAMAGECOUNT': '0.675', 'weapon2': '1.344', 'weapon3': '1.970', 'FRAGCOUNT': '3.000'} [2024-08-05 09:00:18,387][00149] DAMAGECOUNT value on done: 10245.0 [2024-08-05 09:00:18,914][00148] DAMAGECOUNT value on done: 9134.0 [2024-08-05 09:00:18,937][00149] DAMAGECOUNT value on done: 10007.0 [2024-08-05 09:00:18,938][00149] Sum rewards: -4.412, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-2.070', 'AMMO2': '0.001', 'AMMO5': '0.003', 'AMMO4': '0.004', 'ARMOR': '0.005', 'WEAPON1': '0.010', 'WEAPON5': '0.050', 'weapon5': '0.096', 'AMMO3': '0.146', 'HITCOUNT': '0.200', 'DAMAGECOUNT': '0.552', 'WEAPON3': '0.950', 'weapon2': '1.460', 'weapon3': '1.932', 'FRAGCOUNT': '2.000'} [2024-08-05 09:00:19,500][00148] DAMAGECOUNT value on done: 8767.0 [2024-08-05 09:00:19,501][00148] Sum rewards: -0.649, reward structure: {'DEATHCOUNT': '-6.000', 'AMMO2': '0.008', 'WEAPON1': '0.010', 'HEALTH': '0.019', 'ARMOR': '0.040', 'AMMO4': '0.041', 'HITCOUNT': '0.090', 'AMMO3': '0.095', 'DAMAGECOUNT': '0.231', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon2': '1.166', 'weapon3': '2.050'} [2024-08-05 09:00:20,405][00150] DAMAGECOUNT value on done: 9293.0 [2024-08-05 09:00:20,406][00150] Sum rewards: -7.801, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-2.470', 'AMMO5': '0.010', 'AMMO2': '0.013', 'AMMO4': '0.064', 'weapon5': '0.142', 'HITCOUNT': '0.160', 'AMMO3': '0.196', 'WEAPON5': '0.250', 'DAMAGECOUNT': '0.414', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.150', 'weapon2': '1.276', 'weapon3': '1.994'} [2024-08-05 09:00:20,976][00150] DAMAGECOUNT value on done: 11322.0 [2024-08-05 09:00:20,977][00150] Sum rewards: 1.297, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-0.444', 'AMMO5': '0.007', 'AMMO2': '0.031', 'AMMO3': '0.076', 'weapon4': '0.086', 'WEAPON5': '0.100', 'ARMOR': '0.109', 'AMMO4': '0.156', 'HITCOUNT': '0.180', 'WEAPON4': '0.300', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.651', 'weapon3': '1.466', 'weapon2': '1.828', 'FRAGCOUNT': '3.000'} [2024-08-05 09:00:21,486][00150] DAMAGECOUNT value on done: 11008.0 [2024-08-05 09:00:21,487][00150] Sum rewards: -6.864, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-1.366', 'ARMOR': '0.012', 'AMMO5': '0.015', 'AMMO2': '0.016', 'weapon5': '0.032', 'AMMO4': '0.081', 'WEAPON5': '0.150', 'AMMO3': '0.200', 'HITCOUNT': '0.230', 'DAMAGECOUNT': '0.996', 'WEAPON3': '1.100', 'FRAGCOUNT': '1.500', 'weapon2': '1.686', 'weapon3': '1.984'} [2024-08-05 09:00:21,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8200192. Throughput: 0: 895.6. Samples: 2049560. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 09:00:21,502][00035] Avg episode reward: [(0, '-3.398')] [2024-08-05 09:00:21,510][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001001_8200192.pth... [2024-08-05 09:00:21,610][00137] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000896_7340032.pth [2024-08-05 09:00:21,620][00137] Saving new best policy, reward=-3.398! [2024-08-05 09:00:22,110][00150] DAMAGECOUNT value on done: 10815.0 [2024-08-05 09:00:22,111][00150] Sum rewards: -2.997, reward structure: {'DEATHCOUNT': '-3.750', 'FRAGCOUNT': '-1.500', 'HEALTH': '-0.944', 'AMMO4': '-0.021', 'AMMO2': '-0.004', 'AMMO5': '0.005', 'WEAPON1': '0.020', 'AMMO3': '0.040', 'HITCOUNT': '0.040', 'ARMOR': '0.048', 'WEAPON4': '0.050', 'weapon5': '0.070', 'DAMAGECOUNT': '0.099', 'WEAPON5': '0.150', 'weapon4': '0.164', 'WEAPON3': '0.350', 'weapon3': '0.864', 'weapon2': '1.322'} [2024-08-05 09:00:26,500][00035] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8216576. Throughput: 0: 907.6. Samples: 2055024. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:00:26,502][00035] Avg episode reward: [(0, '-3.371')] [2024-08-05 09:00:26,504][00137] Saving new best policy, reward=-3.371! [2024-08-05 09:00:31,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.1). Total num frames: 8241152. Throughput: 0: 909.0. Samples: 2060536. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:00:31,502][00035] Avg episode reward: [(0, '-3.371')] [2024-08-05 09:00:36,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 8257536. Throughput: 0: 910.0. Samples: 2063326. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 09:00:36,502][00035] Avg episode reward: [(0, '-3.371')] [2024-08-05 09:00:40,621][00146] Updated weights for policy 0, policy_version 1010 (0.0030) [2024-08-05 09:00:41,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 8273920. Throughput: 0: 907.7. Samples: 2068744. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 09:00:41,504][00035] Avg episode reward: [(0, '-3.371')] [2024-08-05 09:00:46,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8290304. Throughput: 0: 898.6. Samples: 2073900. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 09:00:46,502][00035] Avg episode reward: [(0, '-3.371')] [2024-08-05 09:00:51,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8306688. Throughput: 0: 898.4. Samples: 2076654. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 09:00:51,501][00035] Avg episode reward: [(0, '-3.371')] [2024-08-05 09:00:52,690][00147] DAMAGECOUNT value on done: 10318.0 [2024-08-05 09:00:52,691][00147] Sum rewards: -4.365, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-0.680', 'AMMO2': '0.004', 'AMMO5': '0.005', 'weapon5': '0.012', 'AMMO4': '0.021', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.105', 'ARMOR': '0.124', 'weapon4': '0.126', 'HITCOUNT': '0.260', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'DAMAGECOUNT': '1.002', 'weapon3': '1.438', 'weapon2': '1.918'} [2024-08-05 09:00:53,230][00147] DAMAGECOUNT value on done: 11751.0 [2024-08-05 09:00:53,231][00147] Sum rewards: -2.755, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.033', 'AMMO2': '0.013', 'AMMO4': '0.066', 'AMMO3': '0.073', 'ARMOR': '0.075', 'WEAPON4': '0.100', 'HITCOUNT': '0.160', 'WEAPON3': '0.550', 'DAMAGECOUNT': '0.570', 'FRAGCOUNT': '1.000', 'weapon3': '1.516', 'weapon2': '1.654'} [2024-08-05 09:00:53,811][00149] DAMAGECOUNT value on done: 9489.0 [2024-08-05 09:00:53,812][00149] Sum rewards: -5.640, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-2.172', 'AMMO4': '-0.024', 'AMMO2': '-0.005', 'ARMOR': '0.060', 'AMMO3': '0.185', 'HITCOUNT': '0.220', 'DAMAGECOUNT': '0.591', 'weapon2': '1.186', 'WEAPON3': '1.200', 'FRAGCOUNT': '2.000', 'weapon3': '2.368'} [2024-08-05 09:00:53,823][00147] DAMAGECOUNT value on done: 8869.0 [2024-08-05 09:00:54,414][00147] DAMAGECOUNT value on done: 9905.0 [2024-08-05 09:00:54,415][00147] Sum rewards: -3.598, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-2.220', 'AMMO2': '0.013', 'ARMOR': '0.048', 'AMMO4': '0.067', 'WEAPON4': '0.150', 'weapon4': '0.204', 'AMMO3': '0.214', 'HITCOUNT': '0.260', 'DAMAGECOUNT': '0.990', 'WEAPON3': '1.250', 'weapon2': '1.464', 'weapon3': '1.712', 'FRAGCOUNT': '5.000'} [2024-08-05 09:00:54,437][00149] DAMAGECOUNT value on done: 9426.0 [2024-08-05 09:00:54,438][00149] Sum rewards: 0.710, reward structure: {'DEATHCOUNT': '-6.750', 'AMMO5': '0.010', 'AMMO2': '0.011', 'weapon5': '0.030', 'WEAPON4': '0.050', 'AMMO4': '0.056', 'AMMO3': '0.074', 'ARMOR': '0.096', 'weapon4': '0.114', 'WEAPON5': '0.200', 'HITCOUNT': '0.230', 'WEAPON3': '0.350', 'HEALTH': '0.369', 'DAMAGECOUNT': '0.909', 'weapon3': '1.328', 'weapon2': '1.632', 'FRAGCOUNT': '2.000'} [2024-08-05 09:00:54,947][00149] DAMAGECOUNT value on done: 10410.0 [2024-08-05 09:00:55,478][00149] DAMAGECOUNT value on done: 10194.0 [2024-08-05 09:00:55,479][00149] Sum rewards: -4.553, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.712', 'AMMO2': '0.002', 'AMMO5': '0.005', 'AMMO4': '0.008', 'ARMOR': '0.056', 'WEAPON4': '0.100', 'weapon4': '0.110', 'AMMO3': '0.145', 'HITCOUNT': '0.160', 'DAMAGECOUNT': '0.561', 'WEAPON3': '0.800', 'weapon3': '1.262', 'weapon2': '1.700', 'FRAGCOUNT': '2.000'} [2024-08-05 09:00:55,813][00148] DAMAGECOUNT value on done: 10104.0 [2024-08-05 09:00:56,393][00148] DAMAGECOUNT value on done: 9181.0 [2024-08-05 09:00:56,393][00148] Sum rewards: -5.594, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-2.807', 'AMMO4': '-0.062', 'AMMO2': '-0.012', 'AMMO5': '0.003', 'WEAPON5': '0.050', 'ARMOR': '0.094', 'HITCOUNT': '0.140', 'AMMO3': '0.175', 'DAMAGECOUNT': '0.600', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.050', 'weapon3': '1.348', 'weapon2': '1.828'} [2024-08-05 09:00:56,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 8331264. Throughput: 0: 906.2. Samples: 2082132. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:00:56,502][00035] Avg episode reward: [(0, '-3.369')] [2024-08-05 09:00:56,504][00137] Saving new best policy, reward=-3.369! [2024-08-05 09:00:57,034][00148] DAMAGECOUNT value on done: 9314.0 [2024-08-05 09:00:57,035][00148] Sum rewards: -2.784, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.739', 'AMMO2': '0.008', 'ARMOR': '0.028', 'AMMO4': '0.041', 'weapon7': '0.080', 'AMMO6': '0.100', 'AMMO7': '0.100', 'WEAPON7': '0.100', 'AMMO3': '0.105', 'HITCOUNT': '0.110', 'DAMAGECOUNT': '0.540', 'WEAPON3': '0.700', 'weapon3': '1.632', 'weapon2': '1.660', 'FRAGCOUNT': '2.000'} [2024-08-05 09:00:57,209][00150] DAMAGECOUNT value on done: 9553.0 [2024-08-05 09:00:57,209][00150] Sum rewards: 1.080, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.620', 'AMMO4': '-0.036', 'AMMO2': '-0.007', 'AMMO3': '0.143', 'HITCOUNT': '0.240', 'DAMAGECOUNT': '0.780', 'WEAPON3': '0.900', 'weapon2': '1.464', 'weapon3': '1.716', 'FRAGCOUNT': '5.000'} [2024-08-05 09:00:57,607][00148] DAMAGECOUNT value on done: 8917.0 [2024-08-05 09:00:57,769][00150] DAMAGECOUNT value on done: 11473.0 [2024-08-05 09:00:57,769][00150] Sum rewards: -7.206, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-1.382', 'AMMO2': '0.007', 'AMMO5': '0.010', 'AMMO4': '0.033', 'HITCOUNT': '0.110', 'AMMO3': '0.139', 'DAMAGECOUNT': '0.453', 'WEAPON3': '0.850', 'weapon3': '1.468', 'weapon2': '1.856', 'FRAGCOUNT': '2.000'} [2024-08-05 09:00:58,350][00150] DAMAGECOUNT value on done: 11133.0 [2024-08-05 09:00:58,350][00150] Sum rewards: -5.695, reward structure: {'DEATHCOUNT': '-12.750', 'AMMO2': '0.009', 'HEALTH': '0.024', 'ARMOR': '0.040', 'AMMO4': '0.045', 'HITCOUNT': '0.100', 'AMMO3': '0.143', 'DAMAGECOUNT': '0.375', 'WEAPON3': '0.750', 'weapon2': '1.744', 'weapon3': '1.824', 'FRAGCOUNT': '2.000'} [2024-08-05 09:00:58,979][00150] DAMAGECOUNT value on done: 10921.0 [2024-08-05 09:01:01,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 8347648. Throughput: 0: 902.1. Samples: 2087468. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:01:01,501][00035] Avg episode reward: [(0, '-3.488')] [2024-08-05 09:01:03,304][00146] Updated weights for policy 0, policy_version 1020 (0.0022) [2024-08-05 09:01:06,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8364032. Throughput: 0: 903.4. Samples: 2090212. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:01:06,502][00035] Avg episode reward: [(0, '-3.488')] [2024-08-05 09:01:11,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8380416. Throughput: 0: 905.3. Samples: 2095764. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:01:11,503][00035] Avg episode reward: [(0, '-3.488')] [2024-08-05 09:01:16,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8396800. Throughput: 0: 895.9. Samples: 2100852. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:01:16,502][00035] Avg episode reward: [(0, '-3.488')] [2024-08-05 09:01:21,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8413184. Throughput: 0: 894.0. Samples: 2103554. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:01:21,502][00035] Avg episode reward: [(0, '-3.488')] [2024-08-05 09:01:25,867][00146] Updated weights for policy 0, policy_version 1030 (0.0018) [2024-08-05 09:01:26,500][00035] Fps is (10 sec: 4095.9, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 8437760. Throughput: 0: 898.7. Samples: 2109186. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:01:26,505][00035] Avg episode reward: [(0, '-3.488')] [2024-08-05 09:01:30,122][00149] DAMAGECOUNT value on done: 9673.0 [2024-08-05 09:01:30,124][00149] Sum rewards: -4.567, reward structure: {'DEATHCOUNT': '-8.250', 'FRAGCOUNT': '-0.500', 'HEALTH': '-0.490', 'AMMO5': '0.005', 'AMMO2': '0.011', 'AMMO4': '0.052', 'ARMOR': '0.082', 'HITCOUNT': '0.090', 'AMMO3': '0.097', 'WEAPON5': '0.100', 'weapon5': '0.204', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.552', 'weapon3': '1.424', 'weapon2': '1.556'} [2024-08-05 09:01:30,162][00147] DAMAGECOUNT value on done: 10438.0 [2024-08-05 09:01:30,715][00149] DAMAGECOUNT value on done: 9616.0 [2024-08-05 09:01:30,716][00149] Sum rewards: -2.657, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.161', 'AMMO2': '0.015', 'weapon4': '0.056', 'AMMO4': '0.073', 'WEAPON4': '0.100', 'ARMOR': '0.108', 'AMMO3': '0.140', 'HITCOUNT': '0.170', 'DAMAGECOUNT': '0.570', 'WEAPON3': '0.750', 'weapon2': '1.482', 'weapon3': '1.790', 'FRAGCOUNT': '3.000'} [2024-08-05 09:01:30,783][00147] DAMAGECOUNT value on done: 12016.0 [2024-08-05 09:01:30,784][00147] Sum rewards: -2.044, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.718', 'AMMO5': '0.007', 'AMMO2': '0.037', 'ARMOR': '0.048', 'weapon5': '0.062', 'AMMO3': '0.099', 'HITCOUNT': '0.110', 'WEAPON5': '0.150', 'AMMO4': '0.183', 'weapon4': '0.236', 'WEAPON4': '0.250', 'WEAPON3': '0.550', 'DAMAGECOUNT': '0.795', 'weapon3': '0.986', 'FRAGCOUNT': '2.000', 'weapon2': '2.160'} [2024-08-05 09:01:31,254][00149] DAMAGECOUNT value on done: 10695.0 [2024-08-05 09:01:31,255][00149] Sum rewards: -3.226, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.896', 'AMMO4': '-0.031', 'AMMO2': '-0.006', 'ARMOR': '0.116', 'AMMO3': '0.154', 'HITCOUNT': '0.240', 'DAMAGECOUNT': '0.855', 'WEAPON3': '0.950', 'FRAGCOUNT': '1.000', 'weapon2': '1.530', 'weapon3': '2.112'} [2024-08-05 09:01:31,327][00147] DAMAGECOUNT value on done: 9147.0 [2024-08-05 09:01:31,328][00147] Sum rewards: -4.501, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.910', 'weapon5': '0.002', 'AMMO2': '0.002', 'AMMO5': '0.003', 'AMMO4': '0.011', 'ARMOR': '0.034', 'WEAPON5': '0.050', 'AMMO3': '0.111', 'HITCOUNT': '0.260', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.834', 'weapon3': '1.868', 'weapon2': '1.934', 'FRAGCOUNT': '2.000'} [2024-08-05 09:01:31,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8454144. Throughput: 0: 905.6. Samples: 2114654. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:01:31,502][00035] Avg episode reward: [(0, '-3.530')] [2024-08-05 09:01:31,792][00149] DAMAGECOUNT value on done: 10326.0 [2024-08-05 09:01:31,872][00147] DAMAGECOUNT value on done: 10095.0 [2024-08-05 09:01:31,873][00147] Sum rewards: -3.652, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.822', 'AMMO4': '-0.012', 'AMMO2': '-0.002', 'AMMO5': '0.003', 'ARMOR': '0.040', 'WEAPON5': '0.050', 'WEAPON4': '0.100', 'AMMO3': '0.111', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.148', 'weapon5': '0.158', 'weapon4': '0.188', 'HITCOUNT': '0.190', 'WEAPON7': '0.200', 'DAMAGECOUNT': '0.570', 'WEAPON3': '0.750', 'weapon3': '1.076', 'weapon2': '1.360', 'FRAGCOUNT': '2.000'} [2024-08-05 09:01:33,877][00148] DAMAGECOUNT value on done: 10197.0 [2024-08-05 09:01:33,878][00148] Sum rewards: -4.720, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.242', 'AMMO2': '0.008', 'weapon4': '0.022', 'AMMO4': '0.040', 'AMMO3': '0.070', 'HITCOUNT': '0.090', 'WEAPON4': '0.100', 'ARMOR': '0.112', 'DAMAGECOUNT': '0.279', 'WEAPON3': '0.450', 'FRAGCOUNT': '1.000', 'weapon3': '1.026', 'weapon2': '1.574'} [2024-08-05 09:01:34,001][00150] DAMAGECOUNT value on done: 9613.0 [2024-08-05 09:01:34,475][00148] DAMAGECOUNT value on done: 9392.0 [2024-08-05 09:01:34,475][00148] Sum rewards: -4.549, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.995', 'AMMO2': '0.002', 'AMMO4': '0.009', 'AMMO5': '0.010', 'ARMOR': '0.064', 'AMMO3': '0.136', 'HITCOUNT': '0.150', 'DAMAGECOUNT': '0.633', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '1.598', 'weapon3': '1.794'} [2024-08-05 09:01:34,566][00150] DAMAGECOUNT value on done: 11645.0 [2024-08-05 09:01:34,567][00150] Sum rewards: -1.538, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.480', 'AMMO2': '0.015', 'WEAPON4': '0.050', 'AMMO4': '0.076', 'AMMO3': '0.100', 'ARMOR': '0.108', 'HITCOUNT': '0.150', 'weapon4': '0.194', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.516', 'weapon2': '1.396', 'weapon3': '1.836', 'FRAGCOUNT': '3.000'} [2024-08-05 09:01:35,070][00148] DAMAGECOUNT value on done: 9451.0 [2024-08-05 09:01:35,150][00150] DAMAGECOUNT value on done: 11766.0 [2024-08-05 09:01:35,150][00150] Sum rewards: -2.585, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-1.557', 'AMMO5': '0.010', 'AMMO2': '0.016', 'ARMOR': '0.040', 'weapon4': '0.046', 'AMMO4': '0.081', 'WEAPON4': '0.100', 'weapon5': '0.136', 'WEAPON5': '0.150', 'AMMO3': '0.186', 'HITCOUNT': '0.450', 'WEAPON3': '1.000', 'weapon2': '1.666', 'DAMAGECOUNT': '1.899', 'weapon3': '1.942', 'FRAGCOUNT': '4.000'} [2024-08-05 09:01:35,613][00148] DAMAGECOUNT value on done: 9167.0 [2024-08-05 09:01:35,613][00148] Sum rewards: 0.881, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.439', 'AMMO5': '0.005', 'WEAPON1': '0.010', 'AMMO2': '0.022', 'ARMOR': '0.048', 'WEAPON5': '0.050', 'AMMO3': '0.090', 'AMMO4': '0.107', 'weapon5': '0.110', 'HITCOUNT': '0.170', 'WEAPON3': '0.650', 'DAMAGECOUNT': '0.750', 'weapon2': '1.520', 'weapon3': '2.038', 'FRAGCOUNT': '4.000'} [2024-08-05 09:01:35,687][00150] DAMAGECOUNT value on done: 11106.0 [2024-08-05 09:01:36,500][00035] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8470528. Throughput: 0: 905.7. Samples: 2117412. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:01:36,502][00035] Avg episode reward: [(0, '-3.463')] [2024-08-05 09:01:41,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8486912. Throughput: 0: 905.4. Samples: 2122876. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:01:41,502][00035] Avg episode reward: [(0, '-3.463')] [2024-08-05 09:01:46,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3554.5). Total num frames: 8503296. Throughput: 0: 899.4. Samples: 2127940. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:01:46,502][00035] Avg episode reward: [(0, '-3.463')] [2024-08-05 09:01:49,055][00146] Updated weights for policy 0, policy_version 1040 (0.0023) [2024-08-05 09:01:51,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 8527872. Throughput: 0: 897.1. Samples: 2130580. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 09:01:51,502][00035] Avg episode reward: [(0, '-3.463')] [2024-08-05 09:01:56,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8544256. Throughput: 0: 895.8. Samples: 2136076. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:01:56,502][00035] Avg episode reward: [(0, '-3.463')] [2024-08-05 09:02:01,500][00035] Fps is (10 sec: 3276.7, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8560640. Throughput: 0: 904.4. Samples: 2141550. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:02:01,502][00035] Avg episode reward: [(0, '-3.463')] [2024-08-05 09:02:06,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8577024. Throughput: 0: 906.4. Samples: 2144340. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:02:06,501][00035] Avg episode reward: [(0, '-3.463')] [2024-08-05 09:02:06,983][00149] DAMAGECOUNT value on done: 10236.0 [2024-08-05 09:02:06,984][00149] Sum rewards: 0.339, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-2.142', 'AMMO4': '-0.017', 'AMMO2': '-0.003', 'AMMO5': '0.015', 'weapon5': '0.024', 'ARMOR': '0.028', 'WEAPON5': '0.150', 'AMMO3': '0.165', 'HITCOUNT': '0.410', 'WEAPON3': '1.050', 'weapon2': '1.500', 'DAMAGECOUNT': '1.689', 'weapon3': '2.220', 'FRAGCOUNT': '5.000'} [2024-08-05 09:02:07,491][00149] DAMAGECOUNT value on done: 9941.0 [2024-08-05 09:02:07,492][00149] Sum rewards: -3.280, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.131', 'AMMO2': '0.010', 'AMMO4': '0.048', 'WEAPON4': '0.050', 'AMMO3': '0.134', 'weapon4': '0.180', 'HITCOUNT': '0.260', 'WEAPON3': '0.950', 'DAMAGECOUNT': '0.975', 'weapon2': '0.998', 'FRAGCOUNT': '1.000', 'weapon3': '2.246'} [2024-08-05 09:02:07,993][00149] DAMAGECOUNT value on done: 11142.0 [2024-08-05 09:02:07,994][00149] Sum rewards: -0.702, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-2.024', 'AMMO2': '0.001', 'AMMO4': '0.005', 'AMMO5': '0.013', 'ARMOR': '0.064', 'AMMO3': '0.118', 'WEAPON5': '0.250', 'HITCOUNT': '0.280', 'weapon5': '0.294', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.341', 'weapon2': '1.388', 'weapon3': '1.768', 'FRAGCOUNT': '4.000'} [2024-08-05 09:02:08,029][00147] DAMAGECOUNT value on done: 10843.0 [2024-08-05 09:02:08,030][00147] Sum rewards: -6.373, reward structure: {'DEATHCOUNT': '-14.250', 'HEALTH': '-2.502', 'AMMO4': '-0.027', 'AMMO2': '-0.005', 'ARMOR': '0.089', 'AMMO3': '0.141', 'HITCOUNT': '0.280', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.215', 'weapon3': '1.652', 'weapon2': '2.134', 'FRAGCOUNT': '4.000'} [2024-08-05 09:02:08,615][00149] DAMAGECOUNT value on done: 10641.0 [2024-08-05 09:02:08,616][00149] Sum rewards: -0.250, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.060', 'AMMO2': '0.008', 'AMMO4': '0.042', 'ARMOR': '0.076', 'AMMO3': '0.095', 'HITCOUNT': '0.270', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.945', 'weapon2': '1.534', 'weapon3': '1.890', 'FRAGCOUNT': '2.000'} [2024-08-05 09:02:08,624][00147] DAMAGECOUNT value on done: 12376.0 [2024-08-05 09:02:08,625][00147] Sum rewards: -3.235, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-1.686', 'AMMO4': '-0.001', 'AMMO2': '-0.000', 'weapon5': '0.012', 'AMMO5': '0.012', 'ARMOR': '0.040', 'weapon4': '0.042', 'WEAPON4': '0.050', 'WEAPON5': '0.150', 'AMMO3': '0.167', 'HITCOUNT': '0.330', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.080', 'weapon2': '1.410', 'weapon3': '2.158', 'FRAGCOUNT': '4.000'} [2024-08-05 09:02:09,249][00147] DAMAGECOUNT value on done: 9377.0 [2024-08-05 09:02:09,249][00147] Sum rewards: -5.236, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-1.194', 'AMMO2': '0.006', 'AMMO4': '0.031', 'WEAPON4': '0.050', 'weapon4': '0.126', 'HITCOUNT': '0.130', 'ARMOR': '0.142', 'AMMO3': '0.178', 'DAMAGECOUNT': '0.690', 'WEAPON3': '0.950', 'weapon3': '1.560', 'FRAGCOUNT': '2.000', 'weapon2': '2.094'} [2024-08-05 09:02:09,843][00147] DAMAGECOUNT value on done: 10245.0 [2024-08-05 09:02:09,844][00147] Sum rewards: -3.538, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.674', 'weapon4': '0.002', 'AMMO2': '0.032', 'HITCOUNT': '0.110', 'AMMO3': '0.133', 'WEAPON4': '0.150', 'AMMO4': '0.161', 'DAMAGECOUNT': '0.450', 'ARMOR': '0.464', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '1.518', 'weapon2': '2.166'} [2024-08-05 09:02:10,932][00150] DAMAGECOUNT value on done: 9760.0 [2024-08-05 09:02:10,934][00150] Sum rewards: -7.212, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-2.190', 'AMMO4': '-0.069', 'AMMO2': '-0.014', 'AMMO5': '0.007', 'weapon5': '0.008', 'AMMO3': '0.116', 'ARMOR': '0.128', 'HITCOUNT': '0.140', 'WEAPON5': '0.150', 'DAMAGECOUNT': '0.441', 'WEAPON3': '0.750', 'FRAGCOUNT': '1.000', 'weapon3': '1.756', 'weapon2': '1.814'} [2024-08-05 09:02:11,498][00146] Updated weights for policy 0, policy_version 1050 (0.0017) [2024-08-05 09:02:11,500][00035] Fps is (10 sec: 4096.2, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 8601600. Throughput: 0: 900.8. Samples: 2149722. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:02:11,501][00035] Avg episode reward: [(0, '-3.491')] [2024-08-05 09:02:11,593][00150] DAMAGECOUNT value on done: 11780.0 [2024-08-05 09:02:11,594][00150] Sum rewards: -2.920, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.552', 'AMMO4': '-0.019', 'AMMO2': '-0.004', 'WEAPON4': '0.050', 'AMMO3': '0.101', 'HITCOUNT': '0.110', 'ARMOR': '0.136', 'weapon4': '0.176', 'DAMAGECOUNT': '0.405', 'WEAPON3': '0.650', 'FRAGCOUNT': '1.000', 'weapon3': '1.452', 'weapon2': '2.074'} [2024-08-05 09:02:11,736][00148] DAMAGECOUNT value on done: 10442.0 [2024-08-05 09:02:11,736][00148] Sum rewards: -3.869, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.242', 'AMMO5': '0.005', 'AMMO2': '0.019', 'WEAPON4': '0.050', 'WEAPON5': '0.050', 'ARMOR': '0.068', 'AMMO4': '0.093', 'weapon5': '0.104', 'AMMO3': '0.129', 'weapon4': '0.144', 'HITCOUNT': '0.220', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.735', 'WEAPON3': '0.800', 'weapon2': '1.366', 'weapon3': '1.840'} [2024-08-05 09:02:12,142][00150] DAMAGECOUNT value on done: 12176.0 [2024-08-05 09:02:12,143][00150] Sum rewards: -2.293, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.547', 'AMMO4': '-0.046', 'AMMO2': '-0.009', 'AMMO5': '0.007', 'ARMOR': '0.062', 'WEAPON5': '0.150', 'AMMO3': '0.155', 'weapon5': '0.266', 'HITCOUNT': '0.310', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.230', 'weapon2': '1.532', 'weapon3': '1.946', 'FRAGCOUNT': '4.000'} [2024-08-05 09:02:12,383][00148] DAMAGECOUNT value on done: 9765.0 [2024-08-05 09:02:12,384][00148] Sum rewards: -3.943, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-0.880', 'AMMO4': '-0.020', 'AMMO2': '-0.004', 'AMMO5': '0.005', 'ARMOR': '0.032', 'WEAPON5': '0.050', 'AMMO3': '0.136', 'HITCOUNT': '0.240', 'weapon5': '0.434', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.119', 'weapon2': '1.160', 'FRAGCOUNT': '1.500', 'weapon3': '1.984'} [2024-08-05 09:02:12,690][00150] DAMAGECOUNT value on done: 11196.0 [2024-08-05 09:02:12,983][00148] DAMAGECOUNT value on done: 9641.0 [2024-08-05 09:02:13,546][00148] DAMAGECOUNT value on done: 9307.0 [2024-08-05 09:02:16,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 8617984. Throughput: 0: 898.1. Samples: 2155070. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:02:16,502][00035] Avg episode reward: [(0, '-3.709')] [2024-08-05 09:02:21,500][00035] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 8634368. Throughput: 0: 887.7. Samples: 2157360. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:02:21,502][00035] Avg episode reward: [(0, '-3.709')] [2024-08-05 09:02:21,512][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001054_8634368.pth... [2024-08-05 09:02:21,610][00137] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000949_7774208.pth [2024-08-05 09:02:26,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8650752. Throughput: 0: 888.4. Samples: 2162854. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:02:26,502][00035] Avg episode reward: [(0, '-3.709')] [2024-08-05 09:02:31,501][00035] Fps is (10 sec: 3276.5, 60 sec: 3549.8, 300 sec: 3582.3). Total num frames: 8667136. Throughput: 0: 897.7. Samples: 2168336. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:02:31,504][00035] Avg episode reward: [(0, '-3.709')] [2024-08-05 09:02:34,473][00146] Updated weights for policy 0, policy_version 1060 (0.0026) [2024-08-05 09:02:36,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8683520. Throughput: 0: 901.4. Samples: 2171144. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:02:36,502][00035] Avg episode reward: [(0, '-3.709')] [2024-08-05 09:02:41,500][00035] Fps is (10 sec: 4096.4, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 8708096. Throughput: 0: 901.5. Samples: 2176644. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:02:41,502][00035] Avg episode reward: [(0, '-3.709')] [2024-08-05 09:02:43,474][00149] DAMAGECOUNT value on done: 10436.0 [2024-08-05 09:02:43,475][00149] Sum rewards: -4.120, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-2.310', 'AMMO2': '0.000', 'AMMO4': '0.000', 'AMMO3': '0.120', 'ARMOR': '0.125', 'HITCOUNT': '0.140', 'weapon4': '0.198', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.600', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '1.124', 'weapon3': '2.032'} [2024-08-05 09:02:44,038][00149] DAMAGECOUNT value on done: 10194.0 [2024-08-05 09:02:44,038][00149] Sum rewards: -1.101, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.930', 'AMMO2': '0.001', 'AMMO4': '0.004', 'ARMOR': '0.024', 'AMMO3': '0.129', 'HITCOUNT': '0.230', 'DAMAGECOUNT': '0.759', 'WEAPON3': '0.800', 'weapon3': '1.590', 'weapon2': '1.792', 'FRAGCOUNT': '2.000'} [2024-08-05 09:02:44,579][00149] DAMAGECOUNT value on done: 11477.0 [2024-08-05 09:02:44,580][00149] Sum rewards: -4.106, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.864', 'AMMO4': '-0.067', 'AMMO2': '-0.013', 'AMMO5': '0.004', 'WEAPON4': '0.050', 'ARMOR': '0.052', 'weapon5': '0.052', 'weapon4': '0.070', 'WEAPON5': '0.100', 'AMMO3': '0.120', 'HITCOUNT': '0.150', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.005', 'weapon3': '1.588', 'weapon2': '1.598', 'FRAGCOUNT': '2.000'} [2024-08-05 09:02:45,129][00149] DAMAGECOUNT value on done: 10831.0 [2024-08-05 09:02:45,130][00149] Sum rewards: -6.698, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-1.539', 'AMMO5': '0.005', 'AMMO2': '0.012', 'weapon5': '0.024', 'weapon4': '0.046', 'WEAPON4': '0.050', 'WEAPON5': '0.050', 'AMMO4': '0.061', 'ARMOR': '0.068', 'AMMO3': '0.157', 'HITCOUNT': '0.220', 'DAMAGECOUNT': '0.570', 'WEAPON3': '0.950', 'FRAGCOUNT': '1.000', 'weapon2': '1.688', 'weapon3': '1.940'} [2024-08-05 09:02:46,130][00147] DAMAGECOUNT value on done: 10882.0 [2024-08-05 09:02:46,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 8724480. Throughput: 0: 900.1. Samples: 2182056. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:02:46,502][00035] Avg episode reward: [(0, '-3.801')] [2024-08-05 09:02:46,758][00147] DAMAGECOUNT value on done: 12521.0 [2024-08-05 09:02:46,759][00147] Sum rewards: -6.947, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-2.072', 'AMMO4': '-0.026', 'AMMO2': '-0.005', 'ARMOR': '0.068', 'WEAPON4': '0.100', 'weapon4': '0.142', 'HITCOUNT': '0.150', 'AMMO3': '0.151', 'DAMAGECOUNT': '0.435', 'WEAPON3': '0.850', 'FRAGCOUNT': '1.000', 'weapon3': '1.404', 'weapon2': '2.106'} [2024-08-05 09:02:47,303][00147] DAMAGECOUNT value on done: 9702.0 [2024-08-05 09:02:47,304][00147] Sum rewards: -3.097, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.706', 'AMMO5': '0.005', 'AMMO2': '0.013', 'WEAPON1': '0.030', 'weapon5': '0.062', 'AMMO4': '0.065', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'ARMOR': '0.112', 'AMMO3': '0.128', 'weapon4': '0.152', 'HITCOUNT': '0.210', 'WEAPON3': '0.900', 'DAMAGECOUNT': '0.975', 'weapon2': '1.512', 'weapon3': '1.744', 'FRAGCOUNT': '3.000'} [2024-08-05 09:02:47,899][00147] DAMAGECOUNT value on done: 10485.0 [2024-08-05 09:02:47,900][00147] Sum rewards: -5.880, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-1.480', 'weapon5': '0.002', 'AMMO5': '0.007', 'weapon4': '0.012', 'AMMO2': '0.016', 'ARMOR': '0.040', 'AMMO4': '0.078', 'WEAPON4': '0.100', 'WEAPON5': '0.150', 'AMMO3': '0.220', 'HITCOUNT': '0.220', 'DAMAGECOUNT': '0.720', 'weapon2': '1.118', 'WEAPON3': '1.300', 'FRAGCOUNT': '2.000', 'weapon3': '2.366'} [2024-08-05 09:02:47,990][00150] DAMAGECOUNT value on done: 10109.0 [2024-08-05 09:02:47,990][00150] Sum rewards: -1.613, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.158', 'AMMO4': '-0.034', 'AMMO2': '-0.007', 'AMMO5': '0.015', 'ARMOR': '0.016', 'weapon5': '0.118', 'AMMO3': '0.180', 'WEAPON5': '0.200', 'HITCOUNT': '0.280', 'WEAPON3': '0.950', 'weapon2': '1.016', 'DAMAGECOUNT': '1.047', 'FRAGCOUNT': '1.500', 'weapon3': '2.514'} [2024-08-05 09:02:48,682][00150] DAMAGECOUNT value on done: 11835.0 [2024-08-05 09:02:49,460][00150] DAMAGECOUNT value on done: 12481.0 [2024-08-05 09:02:49,461][00150] Sum rewards: -4.899, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.614', 'AMMO2': '0.012', 'AMMO4': '0.058', 'ARMOR': '0.064', 'WEAPON4': '0.100', 'weapon4': '0.140', 'AMMO3': '0.152', 'HITCOUNT': '0.270', 'WEAPON3': '0.900', 'DAMAGECOUNT': '0.915', 'weapon3': '1.580', 'weapon2': '1.774', 'FRAGCOUNT': '2.000'} [2024-08-05 09:02:50,102][00150] DAMAGECOUNT value on done: 11507.0 [2024-08-05 09:02:50,521][00148] DAMAGECOUNT value on done: 10697.0 [2024-08-05 09:02:50,521][00148] Sum rewards: -4.169, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-2.878', 'AMMO4': '-0.038', 'AMMO2': '-0.008', 'ARMOR': '0.068', 'AMMO3': '0.137', 'HITCOUNT': '0.200', 'DAMAGECOUNT': '0.765', 'WEAPON3': '1.000', 'weapon2': '1.678', 'weapon3': '1.906', 'FRAGCOUNT': '2.000'} [2024-08-05 09:02:51,163][00148] DAMAGECOUNT value on done: 9935.0 [2024-08-05 09:02:51,164][00148] Sum rewards: -1.808, reward structure: {'DEATHCOUNT': '-6.750', 'FRAGCOUNT': '-0.500', 'HEALTH': '0.000', 'AMMO2': '0.017', 'AMMO5': '0.027', 'WEAPON4': '0.050', 'ARMOR': '0.064', 'AMMO4': '0.083', 'AMMO3': '0.105', 'weapon4': '0.116', 'HITCOUNT': '0.150', 'WEAPON5': '0.400', 'weapon5': '0.400', 'DAMAGECOUNT': '0.510', 'WEAPON3': '0.650', 'weapon2': '0.666', 'weapon3': '2.204'} [2024-08-05 09:02:51,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8740864. Throughput: 0: 890.3. Samples: 2184404. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:02:51,502][00035] Avg episode reward: [(0, '-3.761')] [2024-08-05 09:02:51,715][00148] DAMAGECOUNT value on done: 9898.0 [2024-08-05 09:02:51,715][00148] Sum rewards: -0.940, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.444', 'AMMO2': '0.006', 'AMMO4': '0.028', 'WEAPON4': '0.050', 'weapon4': '0.056', 'AMMO3': '0.077', 'ARMOR': '0.108', 'HITCOUNT': '0.180', 'WEAPON3': '0.550', 'DAMAGECOUNT': '0.771', 'weapon3': '1.220', 'weapon2': '1.958', 'FRAGCOUNT': '2.000'} [2024-08-05 09:02:52,273][00148] DAMAGECOUNT value on done: 9497.0 [2024-08-05 09:02:52,273][00148] Sum rewards: -2.417, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.250', 'AMMO2': '0.015', 'AMMO5': '0.022', 'ARMOR': '0.048', 'AMMO4': '0.076', 'weapon4': '0.114', 'AMMO3': '0.121', 'HITCOUNT': '0.190', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'weapon5': '0.212', 'DAMAGECOUNT': '0.570', 'WEAPON3': '0.750', 'FRAGCOUNT': '1.000', 'weapon2': '1.550', 'weapon3': '1.764'} [2024-08-05 09:02:56,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8757248. Throughput: 0: 888.6. Samples: 2189708. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:02:56,501][00035] Avg episode reward: [(0, '-3.734')] [2024-08-05 09:02:57,621][00146] Updated weights for policy 0, policy_version 1070 (0.0022) [2024-08-05 09:03:01,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8773632. Throughput: 0: 891.1. Samples: 2195168. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 09:03:01,502][00035] Avg episode reward: [(0, '-3.734')] [2024-08-05 09:03:06,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8790016. Throughput: 0: 901.0. Samples: 2197904. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 09:03:06,502][00035] Avg episode reward: [(0, '-3.734')] [2024-08-05 09:03:08,089][00150] Large shaping reward 2.632 for [('FRAGCOUNT', 2.0, 2.0), ('HITCOUNT', 0.03, 3.0), ('DAMAGECOUNT', 0.6, 200), ('weapon7', 0.002)] [2024-08-05 09:03:11,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8814592. Throughput: 0: 900.8. Samples: 2203392. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 09:03:11,502][00035] Avg episode reward: [(0, '-3.734')] [2024-08-05 09:03:16,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8830976. Throughput: 0: 901.0. Samples: 2208880. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:03:16,501][00035] Avg episode reward: [(0, '-3.734')] [2024-08-05 09:03:19,938][00146] Updated weights for policy 0, policy_version 1080 (0.0019) [2024-08-05 09:03:20,412][00149] DAMAGECOUNT value on done: 10677.0 [2024-08-05 09:03:20,412][00149] Sum rewards: 0.294, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-0.497', 'AMMO2': '0.005', 'ARMOR': '0.008', 'AMMO4': '0.023', 'WEAPON4': '0.050', 'AMMO3': '0.060', 'weapon4': '0.106', 'HITCOUNT': '0.170', 'WEAPON3': '0.400', 'DAMAGECOUNT': '0.723', 'weapon3': '1.304', 'weapon2': '1.692', 'FRAGCOUNT': '3.000'} [2024-08-05 09:03:21,224][00149] DAMAGECOUNT value on done: 10327.0 [2024-08-05 09:03:21,224][00149] Sum rewards: -1.031, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.086', 'AMMO2': '0.005', 'AMMO5': '0.007', 'AMMO4': '0.023', 'WEAPON4': '0.050', 'weapon5': '0.096', 'ARMOR': '0.100', 'AMMO3': '0.111', 'HITCOUNT': '0.150', 'WEAPON5': '0.150', 'weapon4': '0.182', 'DAMAGECOUNT': '0.399', 'WEAPON3': '0.700', 'weapon2': '1.432', 'FRAGCOUNT': '1.500', 'weapon3': '1.900'} [2024-08-05 09:03:21,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8847360. Throughput: 0: 899.2. Samples: 2211606. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:03:21,504][00035] Avg episode reward: [(0, '-3.700')] [2024-08-05 09:03:21,986][00149] DAMAGECOUNT value on done: 11669.0 [2024-08-05 09:03:21,987][00149] Sum rewards: -5.560, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.260', 'AMMO2': '0.001', 'AMMO4': '0.006', 'ARMOR': '0.048', 'AMMO3': '0.121', 'HITCOUNT': '0.150', 'DAMAGECOUNT': '0.576', 'WEAPON3': '0.850', 'FRAGCOUNT': '1.000', 'weapon3': '1.590', 'weapon2': '1.858'} [2024-08-05 09:03:22,537][00149] DAMAGECOUNT value on done: 11024.0 [2024-08-05 09:03:22,539][00149] Sum rewards: -3.243, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.918', 'AMMO2': '0.000', 'AMMO4': '0.002', 'AMMO5': '0.003', 'ARMOR': '0.020', 'weapon5': '0.054', 'WEAPON5': '0.100', 'AMMO3': '0.125', 'HITCOUNT': '0.150', 'WEAPON4': '0.200', 'weapon4': '0.356', 'DAMAGECOUNT': '0.579', 'WEAPON3': '0.750', 'weapon2': '1.448', 'weapon3': '1.638', 'FRAGCOUNT': '2.000'} [2024-08-05 09:03:24,770][00147] DAMAGECOUNT value on done: 11148.0 [2024-08-05 09:03:24,772][00147] Sum rewards: -0.603, reward structure: {'DEATHCOUNT': '-8.250', 'AMMO5': '0.007', 'HEALTH': '0.015', 'AMMO2': '0.026', 'ARMOR': '0.028', 'weapon5': '0.048', 'WEAPON4': '0.050', 'WEAPON5': '0.100', 'AMMO3': '0.115', 'weapon4': '0.116', 'AMMO4': '0.131', 'HITCOUNT': '0.240', 'WEAPON3': '0.650', 'DAMAGECOUNT': '0.798', 'weapon2': '1.412', 'weapon3': '1.910', 'FRAGCOUNT': '2.000'} [2024-08-05 09:03:25,186][00150] DAMAGECOUNT value on done: 10476.0 [2024-08-05 09:03:25,187][00150] Sum rewards: 2.914, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-0.188', 'AMMO5': '0.007', 'WEAPON1': '0.010', 'weapon5': '0.014', 'AMMO2': '0.015', 'WEAPON4': '0.050', 'AMMO4': '0.072', 'ARMOR': '0.076', 'AMMO3': '0.078', 'weapon7': '0.080', 'AMMO6': '0.100', 'AMMO7': '0.100', 'WEAPON5': '0.100', 'WEAPON7': '0.100', 'weapon4': '0.104', 'HITCOUNT': '0.150', 'WEAPON3': '0.450', 'DAMAGECOUNT': '1.035', 'weapon2': '1.088', 'weapon3': '1.472', 'FRAGCOUNT': '4.000'} [2024-08-05 09:03:25,391][00147] DAMAGECOUNT value on done: 12716.0 [2024-08-05 09:03:25,392][00147] Sum rewards: -5.754, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.830', 'AMMO4': '-0.061', 'AMMO2': '-0.012', 'AMMO5': '0.005', 'ARMOR': '0.040', 'WEAPON4': '0.100', 'HITCOUNT': '0.140', 'AMMO3': '0.175', 'weapon4': '0.178', 'DAMAGECOUNT': '0.585', 'WEAPON3': '0.900', 'weapon3': '1.160', 'FRAGCOUNT': '2.000', 'weapon2': '2.116'} [2024-08-05 09:03:25,738][00150] DAMAGECOUNT value on done: 12015.0 [2024-08-05 09:03:25,739][00150] Sum rewards: -6.155, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.298', 'AMMO4': '-0.044', 'AMMO2': '-0.009', 'AMMO5': '0.009', 'ARMOR': '0.079', 'weapon5': '0.082', 'AMMO3': '0.146', 'HITCOUNT': '0.180', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.540', 'WEAPON3': '0.850', 'FRAGCOUNT': '1.000', 'weapon3': '1.756', 'weapon2': '1.854'} [2024-08-05 09:03:25,924][00147] DAMAGECOUNT value on done: 9858.0 [2024-08-05 09:03:25,925][00147] Sum rewards: -6.107, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.860', 'AMMO4': '-0.026', 'AMMO2': '-0.005', 'ARMOR': '0.004', 'WEAPON4': '0.100', 'weapon4': '0.110', 'HITCOUNT': '0.130', 'AMMO3': '0.162', 'DAMAGECOUNT': '0.468', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.050', 'weapon2': '1.408', 'weapon3': '1.852'} [2024-08-05 09:03:26,313][00150] DAMAGECOUNT value on done: 12571.0 [2024-08-05 09:03:26,314][00150] Sum rewards: -1.326, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-0.370', 'AMMO5': '0.003', 'AMMO2': '0.008', 'weapon5': '0.016', 'AMMO4': '0.038', 'WEAPON5': '0.050', 'AMMO3': '0.071', 'HITCOUNT': '0.100', 'ARMOR': '0.108', 'DAMAGECOUNT': '0.270', 'WEAPON3': '0.350', 'FRAGCOUNT': '1.000', 'weapon3': '1.740', 'weapon2': '2.040'} [2024-08-05 09:03:26,493][00147] DAMAGECOUNT value on done: 10590.0 [2024-08-05 09:03:26,493][00147] Sum rewards: -3.052, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.182', 'AMMO2': '0.023', 'ARMOR': '0.040', 'HITCOUNT': '0.110', 'AMMO3': '0.114', 'AMMO4': '0.116', 'DAMAGECOUNT': '0.315', 'WEAPON3': '0.750', 'FRAGCOUNT': '1.000', 'weapon2': '1.630', 'weapon3': '2.032'} [2024-08-05 09:03:26,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8863744. Throughput: 0: 886.9. Samples: 2216556. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:03:26,501][00035] Avg episode reward: [(0, '-3.692')] [2024-08-05 09:03:26,899][00150] DAMAGECOUNT value on done: 11637.0 [2024-08-05 09:03:26,900][00150] Sum rewards: -4.123, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.208', 'AMMO5': '0.003', 'AMMO2': '0.008', 'weapon4': '0.026', 'ARMOR': '0.040', 'AMMO4': '0.040', 'WEAPON5': '0.050', 'WEAPON4': '0.050', 'HITCOUNT': '0.110', 'AMMO3': '0.126', 'DAMAGECOUNT': '0.390', 'WEAPON3': '0.750', 'FRAGCOUNT': '1.000', 'weapon2': '1.408', 'weapon3': '1.834'} [2024-08-05 09:03:28,527][00148] DAMAGECOUNT value on done: 10961.0 [2024-08-05 09:03:28,528][00148] Sum rewards: -5.510, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.060', 'AMMO2': '0.008', 'AMMO4': '0.042', 'ARMOR': '0.072', 'AMMO3': '0.160', 'HITCOUNT': '0.180', 'DAMAGECOUNT': '0.792', 'WEAPON3': '0.950', 'FRAGCOUNT': '1.000', 'weapon2': '1.736', 'weapon3': '1.860'} [2024-08-05 09:03:29,077][00148] DAMAGECOUNT value on done: 10248.0 [2024-08-05 09:03:29,078][00148] Sum rewards: -3.697, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.410', 'AMMO2': '0.002', 'AMMO5': '0.007', 'AMMO4': '0.011', 'ARMOR': '0.060', 'weapon5': '0.080', 'WEAPON4': '0.100', 'AMMO3': '0.125', 'WEAPON5': '0.150', 'weapon4': '0.178', 'HITCOUNT': '0.300', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.850', 'DAMAGECOUNT': '0.939', 'weapon2': '1.144', 'weapon3': '2.266'} [2024-08-05 09:03:29,696][00148] DAMAGECOUNT value on done: 10003.0 [2024-08-05 09:03:30,274][00148] DAMAGECOUNT value on done: 9559.0 [2024-08-05 09:03:31,500][00035] Fps is (10 sec: 3276.7, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8880128. Throughput: 0: 887.0. Samples: 2221972. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:03:31,502][00035] Avg episode reward: [(0, '-3.876')] [2024-08-05 09:03:36,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 8904704. Throughput: 0: 896.3. Samples: 2224736. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:03:36,502][00035] Avg episode reward: [(0, '-3.876')] [2024-08-05 09:03:41,500][00035] Fps is (10 sec: 4096.1, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8921088. Throughput: 0: 902.6. Samples: 2230324. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:03:41,502][00035] Avg episode reward: [(0, '-3.876')] [2024-08-05 09:03:42,939][00146] Updated weights for policy 0, policy_version 1090 (0.0034) [2024-08-05 09:03:46,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8937472. Throughput: 0: 904.4. Samples: 2235868. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:03:46,503][00035] Avg episode reward: [(0, '-3.876')] [2024-08-05 09:03:51,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 8953856. Throughput: 0: 905.3. Samples: 2238644. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:03:51,501][00035] Avg episode reward: [(0, '-3.876')] [2024-08-05 09:03:56,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 8978432. Throughput: 0: 898.0. Samples: 2243804. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:03:56,502][00035] Avg episode reward: [(0, '-3.876')] [2024-08-05 09:03:57,307][00149] DAMAGECOUNT value on done: 11162.0 [2024-08-05 09:03:57,308][00149] Sum rewards: -0.640, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-2.632', 'AMMO2': '0.007', 'AMMO5': '0.007', 'AMMO4': '0.032', 'weapon5': '0.038', 'ARMOR': '0.040', 'WEAPON5': '0.100', 'AMMO3': '0.140', 'HITCOUNT': '0.300', 'WEAPON3': '0.950', 'DAMAGECOUNT': '1.455', 'weapon3': '1.648', 'weapon2': '2.024', 'FRAGCOUNT': '5.000'} [2024-08-05 09:03:57,858][00149] DAMAGECOUNT value on done: 10502.0 [2024-08-05 09:03:57,859][00149] Sum rewards: -3.781, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.776', 'AMMO2': '0.013', 'WEAPON1': '0.020', 'AMMO4': '0.062', 'AMMO3': '0.183', 'HITCOUNT': '0.190', 'DAMAGECOUNT': '0.525', 'WEAPON3': '0.950', 'weapon2': '1.490', 'weapon3': '2.062', 'FRAGCOUNT': '3.000'} [2024-08-05 09:03:58,370][00149] DAMAGECOUNT value on done: 11991.0 [2024-08-05 09:03:58,371][00149] Sum rewards: -3.544, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.982', 'AMMO5': '0.003', 'AMMO2': '0.010', 'AMMO4': '0.049', 'ARMOR': '0.070', 'WEAPON4': '0.100', 'AMMO3': '0.132', 'weapon4': '0.158', 'HITCOUNT': '0.220', 'WEAPON3': '0.650', 'DAMAGECOUNT': '0.966', 'FRAGCOUNT': '1.000', 'weapon3': '1.602', 'weapon2': '1.728'} [2024-08-05 09:03:58,954][00149] DAMAGECOUNT value on done: 11529.0 [2024-08-05 09:03:58,955][00149] Sum rewards: 1.779, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.556', 'AMMO4': '-0.040', 'AMMO2': '-0.008', 'AMMO5': '0.005', 'weapon5': '0.068', 'WEAPON5': '0.100', 'ARMOR': '0.100', 'AMMO3': '0.139', 'HITCOUNT': '0.390', 'WEAPON3': '0.950', 'DAMAGECOUNT': '1.515', 'weapon2': '1.570', 'weapon3': '2.046', 'FRAGCOUNT': '7.000'} [2024-08-05 09:04:01,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 8994816. Throughput: 0: 898.5. Samples: 2249312. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:04:01,501][00035] Avg episode reward: [(0, '-3.710')] [2024-08-05 09:04:01,687][00150] DAMAGECOUNT value on done: 10788.0 [2024-08-05 09:04:01,688][00150] Sum rewards: 0.833, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-1.740', 'AMMO4': '-0.012', 'AMMO2': '-0.002', 'ARMOR': '0.084', 'WEAPON4': '0.100', 'AMMO3': '0.117', 'weapon4': '0.156', 'HITCOUNT': '0.220', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.936', 'weapon2': '1.254', 'weapon3': '2.020', 'FRAGCOUNT': '3.000'} [2024-08-05 09:04:02,215][00150] DAMAGECOUNT value on done: 12490.0 [2024-08-05 09:04:02,216][00150] Sum rewards: 0.396, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.133', 'AMMO2': '0.000', 'AMMO4': '0.001', 'AMMO5': '0.003', 'WEAPON1': '0.010', 'WEAPON5': '0.050', 'weapon5': '0.066', 'ARMOR': '0.092', 'AMMO3': '0.130', 'HITCOUNT': '0.310', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.425', 'weapon2': '1.526', 'weapon3': '2.016', 'FRAGCOUNT': '4.000'} [2024-08-05 09:04:02,401][00147] DAMAGECOUNT value on done: 11239.0 [2024-08-05 09:04:02,402][00147] Sum rewards: -5.106, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.482', 'AMMO5': '0.005', 'AMMO2': '0.010', 'AMMO4': '0.049', 'HITCOUNT': '0.080', 'AMMO3': '0.097', 'ARMOR': '0.100', 'DAMAGECOUNT': '0.273', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '1.758', 'weapon2': '2.054'} [2024-08-05 09:04:02,749][00150] DAMAGECOUNT value on done: 12665.0 [2024-08-05 09:04:02,750][00150] Sum rewards: -3.064, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.775', 'AMMO4': '-0.012', 'AMMO2': '-0.002', 'weapon5': '0.002', 'AMMO5': '0.010', 'ARMOR': '0.048', 'WEAPON5': '0.100', 'HITCOUNT': '0.110', 'AMMO3': '0.159', 'DAMAGECOUNT': '0.282', 'weapon2': '0.778', 'WEAPON3': '1.000', 'weapon3': '2.236', 'FRAGCOUNT': '3.000'} [2024-08-05 09:04:02,956][00147] DAMAGECOUNT value on done: 13005.0 [2024-08-05 09:04:02,957][00147] Sum rewards: 0.685, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.592', 'AMMO5': '0.003', 'AMMO2': '0.007', 'AMMO4': '0.036', 'WEAPON5': '0.050', 'WEAPON4': '0.100', 'AMMO3': '0.104', 'ARMOR': '0.112', 'weapon5': '0.122', 'weapon4': '0.202', 'HITCOUNT': '0.240', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.867', 'weapon2': '1.536', 'weapon3': '1.798', 'FRAGCOUNT': '3.000'} [2024-08-05 09:04:03,335][00150] DAMAGECOUNT value on done: 12017.0 [2024-08-05 09:04:03,337][00150] Sum rewards: -2.614, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.816', 'AMMO5': '0.011', 'ARMOR': '0.012', 'AMMO2': '0.013', 'WEAPON4': '0.050', 'AMMO4': '0.064', 'weapon5': '0.078', 'AMMO3': '0.093', 'weapon4': '0.134', 'WEAPON5': '0.150', 'HITCOUNT': '0.170', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.750', 'DAMAGECOUNT': '1.140', 'weapon2': '1.152', 'weapon3': '2.134'} [2024-08-05 09:04:03,559][00147] DAMAGECOUNT value on done: 10171.0 [2024-08-05 09:04:03,560][00147] Sum rewards: -1.661, reward structure: {'DEATHCOUNT': '-9.750', 'AMMO5': '0.003', 'AMMO2': '0.017', 'weapon5': '0.042', 'ARMOR': '0.044', 'WEAPON5': '0.050', 'AMMO4': '0.082', 'WEAPON4': '0.100', 'AMMO3': '0.138', 'HEALTH': '0.200', 'HITCOUNT': '0.290', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.939', 'weapon2': '1.578', 'weapon3': '1.906', 'FRAGCOUNT': '2.000'} [2024-08-05 09:04:04,101][00147] DAMAGECOUNT value on done: 10824.0 [2024-08-05 09:04:04,102][00147] Sum rewards: -0.883, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.439', 'AMMO5': '0.003', 'AMMO2': '0.007', 'weapon5': '0.020', 'AMMO4': '0.035', 'WEAPON5': '0.050', 'AMMO3': '0.084', 'ARMOR': '0.091', 'WEAPON4': '0.100', 'HITCOUNT': '0.160', 'weapon4': '0.234', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.702', 'weapon3': '1.258', 'weapon2': '1.812', 'FRAGCOUNT': '2.000'} [2024-08-05 09:04:05,389][00146] Updated weights for policy 0, policy_version 1100 (0.0018) [2024-08-05 09:04:05,716][00148] DAMAGECOUNT value on done: 11276.0 [2024-08-05 09:04:05,717][00148] Sum rewards: -1.669, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.372', 'AMMO5': '0.012', 'weapon5': '0.016', 'AMMO2': '0.023', 'WEAPON4': '0.100', 'AMMO4': '0.114', 'weapon4': '0.158', 'AMMO3': '0.162', 'HITCOUNT': '0.230', 'WEAPON5': '0.250', 'ARMOR': '0.468', 'DAMAGECOUNT': '0.945', 'WEAPON3': '0.950', 'weapon2': '1.184', 'FRAGCOUNT': '2.000', 'weapon3': '2.090'} [2024-08-05 09:04:06,296][00148] DAMAGECOUNT value on done: 10548.0 [2024-08-05 09:04:06,297][00148] Sum rewards: -3.839, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.210', 'AMMO2': '0.001', 'AMMO5': '0.005', 'AMMO4': '0.005', 'weapon5': '0.040', 'WEAPON5': '0.100', 'AMMO3': '0.110', 'HITCOUNT': '0.240', 'WEAPON3': '0.750', 'DAMAGECOUNT': '0.900', 'weapon2': '1.702', 'FRAGCOUNT': '2.000', 'weapon3': '2.018'} [2024-08-05 09:04:06,501][00035] Fps is (10 sec: 3276.5, 60 sec: 3686.3, 300 sec: 3610.0). Total num frames: 9011200. Throughput: 0: 899.3. Samples: 2252076. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:04:06,503][00035] Avg episode reward: [(0, '-3.614')] [2024-08-05 09:04:06,907][00148] DAMAGECOUNT value on done: 10013.0 [2024-08-05 09:04:07,465][00148] DAMAGECOUNT value on done: 9696.0 [2024-08-05 09:04:07,466][00148] Sum rewards: -5.691, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-2.220', 'AMMO2': '0.004', 'AMMO5': '0.005', 'AMMO4': '0.020', 'WEAPON4': '0.050', 'weapon5': '0.082', 'WEAPON5': '0.100', 'ARMOR': '0.105', 'AMMO3': '0.154', 'HITCOUNT': '0.160', 'weapon4': '0.166', 'DAMAGECOUNT': '0.411', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon2': '1.600', 'weapon3': '1.722'} [2024-08-05 09:04:11,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 9027584. Throughput: 0: 911.9. Samples: 2257592. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:04:11,501][00035] Avg episode reward: [(0, '-3.644')] [2024-08-05 09:04:16,500][00035] Fps is (10 sec: 4096.4, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 9052160. Throughput: 0: 916.5. Samples: 2263216. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:04:16,502][00035] Avg episode reward: [(0, '-3.644')] [2024-08-05 09:04:21,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 9068544. Throughput: 0: 915.3. Samples: 2265926. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:04:21,504][00035] Avg episode reward: [(0, '-3.644')] [2024-08-05 09:04:21,513][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001107_9068544.pth... [2024-08-05 09:04:21,622][00137] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001001_8200192.pth [2024-08-05 09:04:26,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 9084928. Throughput: 0: 906.8. Samples: 2271132. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 09:04:26,502][00035] Avg episode reward: [(0, '-3.644')] [2024-08-05 09:04:28,264][00146] Updated weights for policy 0, policy_version 1110 (0.0026) [2024-08-05 09:04:31,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 9101312. Throughput: 0: 903.7. Samples: 2276534. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 09:04:31,502][00035] Avg episode reward: [(0, '-3.644')] [2024-08-05 09:04:33,667][00149] DAMAGECOUNT value on done: 11361.0 [2024-08-05 09:04:33,669][00149] Sum rewards: -0.772, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-0.760', 'AMMO5': '0.012', 'AMMO2': '0.013', 'ARMOR': '0.044', 'weapon7': '0.046', 'WEAPON4': '0.050', 'weapon5': '0.060', 'AMMO4': '0.065', 'AMMO3': '0.081', 'AMMO6': '0.100', 'AMMO7': '0.100', 'WEAPON7': '0.100', 'weapon4': '0.118', 'HITCOUNT': '0.130', 'WEAPON5': '0.200', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.597', 'weapon2': '0.974', 'FRAGCOUNT': '1.000', 'weapon3': '1.048'} [2024-08-05 09:04:34,193][00149] DAMAGECOUNT value on done: 10842.0 [2024-08-05 09:04:34,194][00149] Sum rewards: -3.849, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.070', 'AMMO2': '0.002', 'AMMO5': '0.007', 'AMMO4': '0.012', 'ARMOR': '0.032', 'weapon5': '0.078', 'AMMO3': '0.107', 'WEAPON5': '0.150', 'HITCOUNT': '0.280', 'WEAPON3': '0.500', 'DAMAGECOUNT': '1.020', 'weapon2': '1.424', 'weapon3': '1.858', 'FRAGCOUNT': '3.000'} [2024-08-05 09:04:34,785][00149] DAMAGECOUNT value on done: 12230.0 [2024-08-05 09:04:34,786][00149] Sum rewards: -3.069, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.166', 'AMMO2': '0.009', 'AMMO4': '0.046', 'AMMO3': '0.063', 'ARMOR': '0.088', 'WEAPON4': '0.100', 'HITCOUNT': '0.150', 'weapon4': '0.278', 'WEAPON3': '0.400', 'DAMAGECOUNT': '0.717', 'weapon3': '1.208', 'FRAGCOUNT': '2.000', 'weapon2': '2.038'} [2024-08-05 09:04:35,314][00149] DAMAGECOUNT value on done: 11634.0 [2024-08-05 09:04:36,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 9117696. Throughput: 0: 904.1. Samples: 2279330. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:04:36,504][00035] Avg episode reward: [(0, '-3.652')] [2024-08-05 09:04:37,794][00150] DAMAGECOUNT value on done: 10904.0 [2024-08-05 09:04:37,795][00150] Sum rewards: 0.278, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-0.072', 'AMMO4': '-0.017', 'AMMO2': '-0.003', 'AMMO5': '0.003', 'weapon5': '0.036', 'WEAPON5': '0.050', 'HITCOUNT': '0.080', 'AMMO3': '0.102', 'DAMAGECOUNT': '0.348', 'ARMOR': '0.507', 'WEAPON3': '0.550', 'FRAGCOUNT': '1.000', 'weapon2': '1.238', 'weapon3': '1.706'} [2024-08-05 09:04:38,296][00150] DAMAGECOUNT value on done: 12660.0 [2024-08-05 09:04:38,297][00150] Sum rewards: -3.174, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.518', 'AMMO5': '0.003', 'AMMO2': '0.003', 'AMMO4': '0.015', 'weapon5': '0.026', 'ARMOR': '0.048', 'WEAPON5': '0.050', 'HITCOUNT': '0.110', 'AMMO3': '0.143', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.510', 'WEAPON3': '0.850', 'weapon2': '1.380', 'weapon3': '1.956'} [2024-08-05 09:04:38,830][00150] DAMAGECOUNT value on done: 12905.0 [2024-08-05 09:04:38,831][00150] Sum rewards: 0.106, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-0.540', 'AMMO2': '0.005', 'AMMO5': '0.010', 'AMMO4': '0.023', 'weapon7': '0.064', 'AMMO3': '0.092', 'AMMO6': '0.100', 'AMMO7': '0.100', 'WEAPON7': '0.100', 'WEAPON5': '0.100', 'weapon5': '0.168', 'HITCOUNT': '0.170', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.720', 'weapon2': '1.086', 'FRAGCOUNT': '1.500', 'weapon3': '1.808'} [2024-08-05 09:04:39,415][00150] DAMAGECOUNT value on done: 12078.0 [2024-08-05 09:04:39,780][00147] DAMAGECOUNT value on done: 11389.0 [2024-08-05 09:04:39,781][00147] Sum rewards: -6.756, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.880', 'AMMO4': '-0.053', 'AMMO2': '-0.011', 'weapon5': '0.002', 'AMMO5': '0.005', 'WEAPON5': '0.050', 'weapon4': '0.050', 'ARMOR': '0.076', 'WEAPON4': '0.100', 'HITCOUNT': '0.120', 'AMMO3': '0.169', 'DAMAGECOUNT': '0.450', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon3': '1.658', 'weapon2': '1.908'} [2024-08-05 09:04:40,303][00147] DAMAGECOUNT value on done: 13253.0 [2024-08-05 09:04:40,304][00147] Sum rewards: -4.348, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-1.255', 'AMMO2': '0.000', 'AMMO4': '0.000', 'ARMOR': '0.112', 'AMMO3': '0.144', 'HITCOUNT': '0.250', 'DAMAGECOUNT': '0.744', 'WEAPON3': '0.850', 'weapon3': '1.886', 'weapon2': '1.920', 'FRAGCOUNT': '3.000'} [2024-08-05 09:04:40,827][00147] DAMAGECOUNT value on done: 10481.0 [2024-08-05 09:04:40,828][00147] Sum rewards: -2.081, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.216', 'AMMO4': '-0.008', 'AMMO2': '-0.002', 'ARMOR': '0.096', 'AMMO3': '0.125', 'HITCOUNT': '0.230', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.930', 'FRAGCOUNT': '1.000', 'weapon2': '1.538', 'weapon3': '1.926'} [2024-08-05 09:04:41,393][00147] DAMAGECOUNT value on done: 11251.0 [2024-08-05 09:04:41,394][00147] Sum rewards: 1.774, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.510', 'AMMO2': '0.009', 'AMMO5': '0.010', 'weapon5': '0.024', 'AMMO4': '0.043', 'AMMO3': '0.081', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'HITCOUNT': '0.380', 'WEAPON3': '0.500', 'DAMAGECOUNT': '1.281', 'weapon2': '1.344', 'weapon3': '1.912', 'FRAGCOUNT': '4.000'} [2024-08-05 09:04:41,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 9142272. Throughput: 0: 915.8. Samples: 2285014. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:04:41,502][00035] Avg episode reward: [(0, '-3.577')] [2024-08-05 09:04:43,119][00148] DAMAGECOUNT value on done: 11536.0 [2024-08-05 09:04:43,120][00148] Sum rewards: -3.102, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.036', 'AMMO5': '0.005', 'AMMO2': '0.005', 'ARMOR': '0.020', 'AMMO4': '0.027', 'AMMO3': '0.167', 'HITCOUNT': '0.220', 'DAMAGECOUNT': '0.780', 'weapon2': '0.948', 'WEAPON3': '1.050', 'FRAGCOUNT': '2.000', 'weapon3': '2.462'} [2024-08-05 09:04:43,719][00148] DAMAGECOUNT value on done: 10788.0 [2024-08-05 09:04:43,720][00148] Sum rewards: -5.762, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-0.653', 'AMMO2': '0.001', 'AMMO4': '0.003', 'AMMO5': '0.006', 'WEAPON1': '0.020', 'ARMOR': '0.028', 'WEAPON5': '0.100', 'AMMO3': '0.132', 'weapon5': '0.150', 'HITCOUNT': '0.220', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.720', 'WEAPON3': '0.800', 'weapon2': '1.334', 'weapon3': '2.126'} [2024-08-05 09:04:44,261][00148] DAMAGECOUNT value on done: 10193.0 [2024-08-05 09:04:44,840][00148] DAMAGECOUNT value on done: 9815.0 [2024-08-05 09:04:46,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 9158656. Throughput: 0: 922.2. Samples: 2290812. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:04:46,502][00035] Avg episode reward: [(0, '-3.620')] [2024-08-05 09:04:49,822][00146] Updated weights for policy 0, policy_version 1120 (0.0029) [2024-08-05 09:04:51,500][00035] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 9175040. Throughput: 0: 925.5. Samples: 2293722. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:04:51,502][00035] Avg episode reward: [(0, '-3.620')] [2024-08-05 09:04:56,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 9199616. Throughput: 0: 931.8. Samples: 2299522. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:04:56,504][00035] Avg episode reward: [(0, '-3.620')] [2024-08-05 09:05:01,500][00035] Fps is (10 sec: 4096.1, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 9216000. Throughput: 0: 924.2. Samples: 2304806. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:05:01,502][00035] Avg episode reward: [(0, '-3.620')] [2024-08-05 09:05:06,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.5, 300 sec: 3610.0). Total num frames: 9232384. Throughput: 0: 929.1. Samples: 2307734. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:05:06,502][00035] Avg episode reward: [(0, '-3.620')] [2024-08-05 09:05:08,359][00149] DAMAGECOUNT value on done: 11496.0 [2024-08-05 09:05:08,360][00149] Sum rewards: -6.580, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.500', 'AMMO5': '0.007', 'AMMO2': '0.009', 'ARMOR': '0.024', 'weapon5': '0.032', 'AMMO4': '0.044', 'HITCOUNT': '0.130', 'WEAPON5': '0.150', 'AMMO3': '0.166', 'DAMAGECOUNT': '0.405', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon2': '1.554', 'weapon3': '1.798'} [2024-08-05 09:05:08,933][00149] DAMAGECOUNT value on done: 11467.0 [2024-08-05 09:05:08,935][00149] Sum rewards: -3.738, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-1.848', 'AMMO2': '0.006', 'AMMO4': '0.031', 'WEAPON4': '0.050', 'ARMOR': '0.108', 'AMMO3': '0.199', 'HITCOUNT': '0.400', 'WEAPON3': '1.200', 'weapon2': '1.816', 'DAMAGECOUNT': '1.875', 'weapon3': '1.924', 'FRAGCOUNT': '4.000'} [2024-08-05 09:05:09,500][00149] DAMAGECOUNT value on done: 12452.0 [2024-08-05 09:05:09,501][00149] Sum rewards: -1.509, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.320', 'AMMO4': '-0.016', 'AMMO2': '-0.003', 'AMMO5': '0.003', 'WEAPON5': '0.100', 'AMMO3': '0.105', 'HITCOUNT': '0.120', 'weapon5': '0.174', 'ARMOR': '0.464', 'DAMAGECOUNT': '0.666', 'WEAPON3': '0.750', 'FRAGCOUNT': '1.000', 'weapon2': '1.414', 'weapon3': '1.784'} [2024-08-05 09:05:10,001][00149] DAMAGECOUNT value on done: 11924.0 [2024-08-05 09:05:10,002][00149] Sum rewards: -4.447, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.832', 'AMMO2': '0.015', 'weapon4': '0.042', 'AMMO4': '0.074', 'ARMOR': '0.084', 'WEAPON4': '0.100', 'AMMO3': '0.168', 'HITCOUNT': '0.230', 'DAMAGECOUNT': '0.870', 'WEAPON3': '1.050', 'weapon2': '1.574', 'weapon3': '1.678', 'FRAGCOUNT': '2.000'} [2024-08-05 09:05:11,490][00146] Updated weights for policy 0, policy_version 1130 (0.0019) [2024-08-05 09:05:11,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3637.8). Total num frames: 9256960. Throughput: 0: 940.2. Samples: 2313442. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:05:11,501][00035] Avg episode reward: [(0, '-3.526')] [2024-08-05 09:05:12,842][00150] DAMAGECOUNT value on done: 11456.0 [2024-08-05 09:05:12,843][00150] Sum rewards: -1.769, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-1.940', 'AMMO4': '-0.002', 'AMMO2': '-0.000', 'AMMO5': '0.005', 'weapon5': '0.064', 'WEAPON5': '0.100', 'AMMO3': '0.200', 'HITCOUNT': '0.450', 'weapon2': '1.086', 'WEAPON3': '1.300', 'DAMAGECOUNT': '1.656', 'weapon3': '2.562', 'FRAGCOUNT': '4.000'} [2024-08-05 09:05:13,363][00150] DAMAGECOUNT value on done: 12973.0 [2024-08-05 09:05:13,363][00150] Sum rewards: -2.745, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.226', 'AMMO4': '-0.057', 'AMMO2': '-0.011', 'AMMO5': '0.012', 'weapon5': '0.014', 'ARMOR': '0.080', 'AMMO3': '0.131', 'WEAPON5': '0.150', 'HITCOUNT': '0.250', 'DAMAGECOUNT': '0.939', 'WEAPON3': '0.950', 'weapon2': '1.494', 'weapon3': '2.028', 'FRAGCOUNT': '4.000'} [2024-08-05 09:05:13,908][00150] DAMAGECOUNT value on done: 13287.0 [2024-08-05 09:05:13,909][00150] Sum rewards: -2.869, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-0.012', 'AMMO4': '-0.000', 'AMMO2': '-0.000', 'weapon5': '0.016', 'AMMO5': '0.018', 'WEAPON4': '0.050', 'ARMOR': '0.068', 'weapon4': '0.090', 'AMMO3': '0.139', 'WEAPON5': '0.200', 'HITCOUNT': '0.310', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.146', 'weapon3': '1.546', 'weapon2': '1.760', 'FRAGCOUNT': '3.000'} [2024-08-05 09:05:14,437][00150] DAMAGECOUNT value on done: 12480.0 [2024-08-05 09:05:14,438][00150] Sum rewards: -0.140, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-1.167', 'AMMO4': '-0.022', 'AMMO2': '-0.004', 'AMMO5': '0.009', 'AMMO3': '0.060', 'ARMOR': '0.082', 'weapon5': '0.128', 'HITCOUNT': '0.180', 'WEAPON5': '0.200', 'WEAPON3': '0.500', 'DAMAGECOUNT': '1.206', 'weapon3': '1.320', 'weapon2': '1.368', 'FRAGCOUNT': '2.000'} [2024-08-05 09:05:15,456][00147] DAMAGECOUNT value on done: 11669.0 [2024-08-05 09:05:16,039][00147] DAMAGECOUNT value on done: 13517.0 [2024-08-05 09:05:16,040][00147] Sum rewards: -3.842, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.875', 'AMMO2': '0.000', 'AMMO4': '0.000', 'AMMO5': '0.005', 'WEAPON5': '0.050', 'ARMOR': '0.072', 'AMMO3': '0.135', 'HITCOUNT': '0.220', 'DAMAGECOUNT': '0.792', 'WEAPON3': '0.850', 'FRAGCOUNT': '1.000', 'weapon2': '1.794', 'weapon3': '1.864'} [2024-08-05 09:05:16,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 9273344. Throughput: 0: 947.6. Samples: 2319174. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:05:16,502][00035] Avg episode reward: [(0, '-3.469')] [2024-08-05 09:05:16,572][00147] DAMAGECOUNT value on done: 10556.0 [2024-08-05 09:05:17,182][00147] DAMAGECOUNT value on done: 11375.0 [2024-08-05 09:05:17,183][00147] Sum rewards: 0.265, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-0.944', 'AMMO4': '-0.011', 'AMMO2': '-0.002', 'WEAPON1': '0.010', 'AMMO3': '0.076', 'HITCOUNT': '0.100', 'ARMOR': '0.148', 'DAMAGECOUNT': '0.372', 'WEAPON3': '0.550', 'weapon3': '1.356', 'weapon2': '1.610', 'FRAGCOUNT': '3.000'} [2024-08-05 09:05:19,344][00148] DAMAGECOUNT value on done: 11756.0 [2024-08-05 09:05:19,345][00148] Sum rewards: -2.227, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.493', 'weapon4': '0.014', 'AMMO2': '0.016', 'ARMOR': '0.040', 'AMMO4': '0.080', 'WEAPON4': '0.100', 'AMMO3': '0.122', 'HITCOUNT': '0.150', 'DAMAGECOUNT': '0.660', 'WEAPON3': '0.850', 'weapon2': '1.220', 'weapon3': '2.014', 'FRAGCOUNT': '3.000'} [2024-08-05 09:05:19,871][00148] DAMAGECOUNT value on done: 10813.0 [2024-08-05 09:05:19,872][00148] Sum rewards: 0.541, reward structure: {'DEATHCOUNT': '-3.750', 'AMMO5': '0.005', 'AMMO2': '0.007', 'HEALTH': '0.031', 'AMMO4': '0.036', 'weapon5': '0.038', 'HITCOUNT': '0.040', 'AMMO3': '0.050', 'DAMAGECOUNT': '0.075', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'weapon4': '0.102', 'ARMOR': '0.223', 'WEAPON3': '0.300', 'FRAGCOUNT': '1.000', 'weapon2': '1.088', 'weapon3': '1.096'} [2024-08-05 09:05:20,434][00148] DAMAGECOUNT value on done: 10397.0 [2024-08-05 09:05:20,435][00148] Sum rewards: -1.769, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-1.520', 'AMMO4': '-0.033', 'AMMO2': '-0.007', 'WEAPON1': '0.020', 'ARMOR': '0.068', 'AMMO3': '0.102', 'HITCOUNT': '0.180', 'DAMAGECOUNT': '0.612', 'WEAPON3': '0.650', 'FRAGCOUNT': '1.000', 'weapon3': '1.568', 'weapon2': '1.590'} [2024-08-05 09:05:20,973][00148] DAMAGECOUNT value on done: 9965.0 [2024-08-05 09:05:20,974][00148] Sum rewards: -4.614, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-1.059', 'AMMO5': '0.003', 'weapon5': '0.006', 'AMMO2': '0.011', 'weapon4': '0.014', 'ARMOR': '0.036', 'WEAPON4': '0.050', 'WEAPON5': '0.050', 'AMMO4': '0.055', 'AMMO3': '0.124', 'HITCOUNT': '0.130', 'DAMAGECOUNT': '0.450', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '1.596', 'weapon2': '1.970'} [2024-08-05 09:05:21,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 9289728. Throughput: 0: 949.1. Samples: 2322038. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:05:21,504][00035] Avg episode reward: [(0, '-3.349')] [2024-08-05 09:05:21,513][00137] Saving new best policy, reward=-3.349! [2024-08-05 09:05:26,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3637.8). Total num frames: 9314304. Throughput: 0: 951.0. Samples: 2327808. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:05:26,502][00035] Avg episode reward: [(0, '-3.349')] [2024-08-05 09:05:31,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3637.8). Total num frames: 9330688. Throughput: 0: 940.9. Samples: 2333154. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:05:31,502][00035] Avg episode reward: [(0, '-3.349')] [2024-08-05 09:05:33,248][00146] Updated weights for policy 0, policy_version 1140 (0.0030) [2024-08-05 09:05:36,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3637.8). Total num frames: 9347072. Throughput: 0: 942.4. Samples: 2336128. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:05:36,502][00035] Avg episode reward: [(0, '-3.349')] [2024-08-05 09:05:41,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 9363456. Throughput: 0: 939.8. Samples: 2341814. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:05:41,504][00035] Avg episode reward: [(0, '-3.349')] [2024-08-05 09:05:43,335][00149] DAMAGECOUNT value on done: 11796.0 [2024-08-05 09:05:43,336][00149] Sum rewards: -2.051, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.566', 'AMMO2': '0.014', 'AMMO4': '0.067', 'ARMOR': '0.085', 'AMMO3': '0.093', 'WEAPON4': '0.100', 'HITCOUNT': '0.260', 'WEAPON3': '0.550', 'DAMAGECOUNT': '0.900', 'weapon3': '1.446', 'FRAGCOUNT': '2.000', 'weapon2': '2.000'} [2024-08-05 09:05:43,905][00149] DAMAGECOUNT value on done: 11792.0 [2024-08-05 09:05:43,906][00149] Sum rewards: -0.809, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '0.002', 'AMMO5': '0.003', 'AMMO2': '0.017', 'WEAPON5': '0.050', 'weapon5': '0.056', 'AMMO4': '0.086', 'AMMO3': '0.092', 'ARMOR': '0.124', 'HITCOUNT': '0.210', 'WEAPON3': '0.550', 'DAMAGECOUNT': '0.975', 'weapon3': '1.544', 'weapon2': '1.732', 'FRAGCOUNT': '2.000'} [2024-08-05 09:05:44,415][00149] DAMAGECOUNT value on done: 12761.0 [2024-08-05 09:05:44,416][00149] Sum rewards: -4.931, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.566', 'AMMO4': '-0.024', 'AMMO2': '-0.005', 'AMMO5': '0.005', 'weapon5': '0.044', 'ARMOR': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.159', 'HITCOUNT': '0.240', 'DAMAGECOUNT': '0.927', 'WEAPON3': '1.100', 'weapon2': '1.200', 'FRAGCOUNT': '2.000', 'weapon3': '2.288'} [2024-08-05 09:05:44,947][00149] DAMAGECOUNT value on done: 12109.0 [2024-08-05 09:05:46,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3665.6). Total num frames: 9388032. Throughput: 0: 950.1. Samples: 2347560. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:05:46,502][00035] Avg episode reward: [(0, '-3.295')] [2024-08-05 09:05:46,504][00137] Saving new best policy, reward=-3.295! [2024-08-05 09:05:47,667][00150] DAMAGECOUNT value on done: 11563.0 [2024-08-05 09:05:48,183][00150] DAMAGECOUNT value on done: 13138.0 [2024-08-05 09:05:48,772][00150] DAMAGECOUNT value on done: 13754.0 [2024-08-05 09:05:48,773][00150] Sum rewards: -6.990, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-2.716', 'AMMO4': '-0.043', 'AMMO2': '-0.009', 'ARMOR': '0.086', 'AMMO3': '0.168', 'HITCOUNT': '0.400', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.150', 'DAMAGECOUNT': '1.401', 'weapon2': '1.616', 'weapon3': '1.956'} [2024-08-05 09:05:49,281][00150] DAMAGECOUNT value on done: 12731.0 [2024-08-05 09:05:51,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3637.8). Total num frames: 9404416. Throughput: 0: 947.1. Samples: 2350354. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:05:51,502][00035] Avg episode reward: [(0, '-3.454')] [2024-08-05 09:05:51,691][00147] DAMAGECOUNT value on done: 12011.0 [2024-08-05 09:05:51,692][00147] Sum rewards: -4.578, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.176', 'AMMO2': '0.004', 'AMMO5': '0.005', 'weapon5': '0.008', 'AMMO4': '0.021', 'ARMOR': '0.040', 'WEAPON5': '0.100', 'AMMO3': '0.144', 'HITCOUNT': '0.260', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'DAMAGECOUNT': '1.026', 'weapon2': '1.512', 'weapon3': '2.078'} [2024-08-05 09:05:52,221][00147] DAMAGECOUNT value on done: 13847.0 [2024-08-05 09:05:52,222][00147] Sum rewards: -3.478, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-2.220', 'AMMO4': '-0.035', 'AMMO2': '-0.007', 'AMMO3': '0.112', 'ARMOR': '0.180', 'HITCOUNT': '0.260', 'WEAPON3': '0.850', 'DAMAGECOUNT': '0.990', 'weapon2': '1.530', 'weapon3': '1.862', 'FRAGCOUNT': '2.000'} [2024-08-05 09:05:52,823][00147] DAMAGECOUNT value on done: 10692.0 [2024-08-05 09:05:52,824][00147] Sum rewards: 1.805, reward structure: {'DEATHCOUNT': '-4.500', 'HEALTH': '-0.188', 'AMMO5': '0.007', 'AMMO2': '0.008', 'WEAPON1': '0.020', 'AMMO4': '0.038', 'AMMO3': '0.073', 'ARMOR': '0.080', 'HITCOUNT': '0.140', 'WEAPON5': '0.150', 'weapon5': '0.258', 'DAMAGECOUNT': '0.408', 'WEAPON3': '0.500', 'weapon2': '1.376', 'weapon3': '1.434', 'FRAGCOUNT': '2.000'} [2024-08-05 09:05:53,368][00147] DAMAGECOUNT value on done: 11410.0 [2024-08-05 09:05:54,817][00146] Updated weights for policy 0, policy_version 1150 (0.0027) [2024-08-05 09:05:55,498][00148] DAMAGECOUNT value on done: 11901.0 [2024-08-05 09:05:56,074][00148] DAMAGECOUNT value on done: 11033.0 [2024-08-05 09:05:56,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 9420800. Throughput: 0: 947.6. Samples: 2356082. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 09:05:56,502][00035] Avg episode reward: [(0, '-3.402')] [2024-08-05 09:05:56,668][00148] DAMAGECOUNT value on done: 10587.0 [2024-08-05 09:05:56,669][00148] Sum rewards: -5.158, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-2.190', 'AMMO4': '-0.060', 'AMMO2': '-0.012', 'AMMO5': '0.005', 'AMMO3': '0.094', 'ARMOR': '0.120', 'HITCOUNT': '0.140', 'DAMAGECOUNT': '0.570', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '1.478', 'weapon2': '1.996'} [2024-08-05 09:05:57,241][00148] DAMAGECOUNT value on done: 10334.0 [2024-08-05 09:05:57,242][00148] Sum rewards: 1.434, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-0.338', 'AMMO5': '0.005', 'AMMO2': '0.006', 'AMMO4': '0.030', 'AMMO3': '0.093', 'ARMOR': '0.120', 'HITCOUNT': '0.290', 'WEAPON3': '0.550', 'DAMAGECOUNT': '1.107', 'weapon2': '1.398', 'weapon3': '1.422', 'FRAGCOUNT': '2.000'} [2024-08-05 09:06:01,500][00035] Fps is (10 sec: 4095.9, 60 sec: 3822.9, 300 sec: 3665.6). Total num frames: 9445376. Throughput: 0: 938.8. Samples: 2361422. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:06:01,502][00035] Avg episode reward: [(0, '-3.377')] [2024-08-05 09:06:06,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3665.6). Total num frames: 9461760. Throughput: 0: 938.3. Samples: 2364260. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:06:06,502][00035] Avg episode reward: [(0, '-3.377')] [2024-08-05 09:06:11,500][00035] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 9478144. Throughput: 0: 936.9. Samples: 2369970. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:06:11,502][00035] Avg episode reward: [(0, '-3.377')] [2024-08-05 09:06:16,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 9494528. Throughput: 0: 947.6. Samples: 2375796. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:06:16,502][00035] Avg episode reward: [(0, '-3.377')] [2024-08-05 09:06:16,596][00146] Updated weights for policy 0, policy_version 1160 (0.0022) [2024-08-05 09:06:18,307][00149] DAMAGECOUNT value on done: 12001.0 [2024-08-05 09:06:18,902][00149] DAMAGECOUNT value on done: 11886.0 [2024-08-05 09:06:18,903][00149] Sum rewards: -4.091, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.416', 'AMMO5': '0.003', 'AMMO2': '0.016', 'WEAPON1': '0.020', 'ARMOR': '0.052', 'AMMO4': '0.081', 'HITCOUNT': '0.100', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'weapon5': '0.104', 'AMMO3': '0.107', 'weapon4': '0.138', 'DAMAGECOUNT': '0.282', 'WEAPON3': '0.750', 'FRAGCOUNT': '1.000', 'weapon2': '1.666', 'weapon3': '1.806'} [2024-08-05 09:06:19,413][00149] DAMAGECOUNT value on done: 12961.0 [2024-08-05 09:06:19,923][00149] DAMAGECOUNT value on done: 12359.0 [2024-08-05 09:06:19,924][00149] Sum rewards: -2.048, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.214', 'AMMO2': '0.013', 'ARMOR': '0.036', 'WEAPON4': '0.050', 'AMMO4': '0.066', 'AMMO3': '0.111', 'weapon4': '0.184', 'HITCOUNT': '0.220', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.750', 'weapon2': '1.260', 'weapon3': '1.776', 'FRAGCOUNT': '2.000'} [2024-08-05 09:06:21,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3665.6). Total num frames: 9519104. Throughput: 0: 943.9. Samples: 2378602. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:06:21,502][00035] Avg episode reward: [(0, '-3.229')] [2024-08-05 09:06:21,509][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001162_9519104.pth... [2024-08-05 09:06:21,609][00137] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001054_8634368.pth [2024-08-05 09:06:21,620][00137] Saving new best policy, reward=-3.229! [2024-08-05 09:06:22,855][00150] DAMAGECOUNT value on done: 11753.0 [2024-08-05 09:06:22,855][00150] Sum rewards: -4.364, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.400', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.036', 'AMMO2': '-0.007', 'AMMO5': '0.005', 'WEAPON4': '0.050', 'WEAPON5': '0.050', 'ARMOR': '0.069', 'AMMO3': '0.093', 'weapon5': '0.098', 'HITCOUNT': '0.110', 'weapon4': '0.202', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.570', 'weapon3': '1.662', 'weapon2': '1.670'} [2024-08-05 09:06:23,449][00150] DAMAGECOUNT value on done: 13432.0 [2024-08-05 09:06:23,450][00150] Sum rewards: -3.819, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.640', 'AMMO4': '-0.073', 'AMMO2': '-0.014', 'AMMO5': '0.005', 'weapon5': '0.028', 'WEAPON5': '0.050', 'ARMOR': '0.104', 'AMMO3': '0.115', 'HITCOUNT': '0.260', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.882', 'FRAGCOUNT': '1.000', 'weapon3': '1.338', 'weapon2': '1.826'} [2024-08-05 09:06:23,972][00150] DAMAGECOUNT value on done: 13937.0 [2024-08-05 09:06:24,516][00150] DAMAGECOUNT value on done: 12836.0 [2024-08-05 09:06:24,517][00150] Sum rewards: -1.537, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-0.721', 'AMMO2': '0.000', 'AMMO4': '0.002', 'WEAPON1': '0.010', 'ARMOR': '0.040', 'HITCOUNT': '0.060', 'AMMO3': '0.081', 'DAMAGECOUNT': '0.315', 'WEAPON3': '0.500', 'FRAGCOUNT': '1.000', 'weapon3': '1.166', 'weapon2': '1.260'} [2024-08-05 09:06:26,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 9535488. Throughput: 0: 942.5. Samples: 2384226. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:06:26,501][00035] Avg episode reward: [(0, '-3.192')] [2024-08-05 09:06:26,503][00137] Saving new best policy, reward=-3.192! [2024-08-05 09:06:27,977][00147] DAMAGECOUNT value on done: 12245.0 [2024-08-05 09:06:27,978][00147] Sum rewards: -2.481, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.678', 'AMMO4': '-0.076', 'AMMO2': '-0.015', 'AMMO5': '0.005', 'ARMOR': '0.052', 'AMMO3': '0.135', 'HITCOUNT': '0.170', 'DAMAGECOUNT': '0.702', 'WEAPON3': '0.850', 'weapon2': '1.618', 'FRAGCOUNT': '2.000', 'weapon3': '2.006'} [2024-08-05 09:06:28,527][00147] DAMAGECOUNT value on done: 13937.0 [2024-08-05 09:06:29,074][00147] DAMAGECOUNT value on done: 10939.0 [2024-08-05 09:06:29,075][00147] Sum rewards: -2.824, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.641', 'AMMO4': '-0.006', 'AMMO2': '-0.001', 'AMMO5': '0.005', 'ARMOR': '0.076', 'AMMO3': '0.142', 'HITCOUNT': '0.230', 'DAMAGECOUNT': '0.741', 'WEAPON3': '0.900', 'weapon2': '1.712', 'weapon3': '1.768', 'FRAGCOUNT': '2.000'} [2024-08-05 09:06:29,579][00147] DAMAGECOUNT value on done: 11788.0 [2024-08-05 09:06:29,580][00147] Sum rewards: 0.728, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.674', 'AMMO4': '-0.006', 'AMMO2': '-0.001', 'AMMO5': '0.012', 'ARMOR': '0.076', 'weapon5': '0.094', 'AMMO3': '0.103', 'WEAPON5': '0.200', 'HITCOUNT': '0.270', 'WEAPON3': '0.600', 'DAMAGECOUNT': '1.134', 'weapon3': '1.602', 'weapon2': '1.818', 'FRAGCOUNT': '3.000'} [2024-08-05 09:06:31,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 9551872. Throughput: 0: 941.2. Samples: 2389914. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:06:31,502][00035] Avg episode reward: [(0, '-3.066')] [2024-08-05 09:06:31,509][00137] Saving new best policy, reward=-3.066! [2024-08-05 09:06:31,939][00148] DAMAGECOUNT value on done: 12391.0 [2024-08-05 09:06:31,940][00148] Sum rewards: -5.951, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-2.398', 'AMMO5': '0.003', 'AMMO2': '0.004', 'ARMOR': '0.008', 'weapon5': '0.014', 'AMMO4': '0.020', 'WEAPON5': '0.050', 'AMMO3': '0.190', 'HITCOUNT': '0.410', 'WEAPON3': '1.250', 'DAMAGECOUNT': '1.470', 'weapon2': '1.492', 'FRAGCOUNT': '2.000', 'weapon3': '2.286'} [2024-08-05 09:06:32,661][00148] DAMAGECOUNT value on done: 11057.0 [2024-08-05 09:06:33,416][00148] DAMAGECOUNT value on done: 10899.0 [2024-08-05 09:06:33,417][00148] Sum rewards: -5.682, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.415', 'AMMO4': '-0.018', 'AMMO2': '-0.004', 'ARMOR': '0.036', 'AMMO3': '0.153', 'HITCOUNT': '0.310', 'DAMAGECOUNT': '0.936', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.050', 'weapon3': '1.804', 'weapon2': '1.966'} [2024-08-05 09:06:34,040][00148] DAMAGECOUNT value on done: 10619.0 [2024-08-05 09:06:34,041][00148] Sum rewards: 2.072, reward structure: {'DEATHCOUNT': '-3.750', 'AMMO5': '0.003', 'AMMO2': '0.022', 'WEAPON5': '0.050', 'AMMO3': '0.067', 'AMMO4': '0.109', 'ARMOR': '0.120', 'weapon5': '0.126', 'HITCOUNT': '0.170', 'WEAPON3': '0.300', 'FRAGCOUNT': '0.500', 'HEALTH': '0.690', 'DAMAGECOUNT': '0.855', 'weapon3': '1.002', 'weapon2': '1.808'} [2024-08-05 09:06:36,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 9568256. Throughput: 0: 931.9. Samples: 2392290. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 09:06:36,504][00035] Avg episode reward: [(0, '-3.054')] [2024-08-05 09:06:36,506][00137] Saving new best policy, reward=-3.054! [2024-08-05 09:06:38,805][00146] Updated weights for policy 0, policy_version 1170 (0.0022) [2024-08-05 09:06:41,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3693.3). Total num frames: 9592832. Throughput: 0: 929.7. Samples: 2397920. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:06:41,502][00035] Avg episode reward: [(0, '-3.054')] [2024-08-05 09:06:46,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 9609216. Throughput: 0: 939.4. Samples: 2403694. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:06:46,502][00035] Avg episode reward: [(0, '-3.054')] [2024-08-05 09:06:51,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 9625600. Throughput: 0: 940.4. Samples: 2406578. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:06:51,502][00035] Avg episode reward: [(0, '-3.054')] [2024-08-05 09:06:53,731][00149] DAMAGECOUNT value on done: 12392.0 [2024-08-05 09:06:53,732][00149] Sum rewards: -0.220, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-0.142', 'AMMO2': '0.018', 'AMMO4': '0.087', 'AMMO3': '0.118', 'ARMOR': '0.136', 'HITCOUNT': '0.280', 'WEAPON3': '0.650', 'DAMAGECOUNT': '1.173', 'weapon3': '1.710', 'weapon2': '1.750', 'FRAGCOUNT': '3.000'} [2024-08-05 09:06:54,330][00149] DAMAGECOUNT value on done: 12148.0 [2024-08-05 09:06:54,331][00149] Sum rewards: -7.156, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-2.800', 'AMMO5': '0.003', 'AMMO2': '0.003', 'AMMO4': '0.016', 'WEAPON5': '0.050', 'ARMOR': '0.072', 'AMMO3': '0.154', 'HITCOUNT': '0.200', 'DAMAGECOUNT': '0.786', 'WEAPON3': '1.000', 'weapon2': '1.618', 'weapon3': '1.742', 'FRAGCOUNT': '2.000'} [2024-08-05 09:06:54,849][00149] DAMAGECOUNT value on done: 13216.0 [2024-08-05 09:06:54,850][00149] Sum rewards: -1.048, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.575', 'AMMO4': '-0.017', 'AMMO2': '-0.003', 'AMMO3': '0.118', 'HITCOUNT': '0.200', 'WEAPON3': '0.750', 'DAMAGECOUNT': '0.765', 'weapon2': '1.264', 'weapon3': '1.700', 'FRAGCOUNT': '4.000'} [2024-08-05 09:06:55,351][00149] DAMAGECOUNT value on done: 12766.0 [2024-08-05 09:06:55,352][00149] Sum rewards: -5.752, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-0.644', 'AMMO5': '0.007', 'AMMO2': '0.009', 'weapon4': '0.014', 'weapon5': '0.036', 'AMMO4': '0.043', 'WEAPON4': '0.050', 'WEAPON5': '0.150', 'AMMO3': '0.180', 'HITCOUNT': '0.300', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'DAMAGECOUNT': '1.221', 'weapon2': '1.634', 'weapon3': '2.098'} [2024-08-05 09:06:56,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3693.3). Total num frames: 9650176. Throughput: 0: 939.6. Samples: 2412250. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:06:56,502][00035] Avg episode reward: [(0, '-3.102')] [2024-08-05 09:06:58,631][00150] DAMAGECOUNT value on done: 12078.0 [2024-08-05 09:06:58,632][00150] Sum rewards: 0.927, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-0.625', 'AMMO4': '-0.042', 'AMMO2': '-0.008', 'AMMO5': '0.005', 'weapon5': '0.012', 'ARMOR': '0.032', 'AMMO3': '0.070', 'WEAPON5': '0.100', 'HITCOUNT': '0.290', 'WEAPON3': '0.550', 'DAMAGECOUNT': '0.975', 'weapon3': '1.520', 'FRAGCOUNT': '2.000', 'weapon2': '2.048'} [2024-08-05 09:06:59,191][00150] DAMAGECOUNT value on done: 13472.0 [2024-08-05 09:06:59,192][00150] Sum rewards: -3.900, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.143', 'AMMO4': '-0.015', 'AMMO2': '-0.003', 'AMMO5': '0.005', 'HITCOUNT': '0.060', 'ARMOR': '0.090', 'WEAPON4': '0.100', 'DAMAGECOUNT': '0.120', 'AMMO3': '0.128', 'weapon4': '0.160', 'WEAPON3': '0.850', 'FRAGCOUNT': '1.000', 'weapon3': '1.192', 'weapon2': '2.056'} [2024-08-05 09:06:59,735][00150] DAMAGECOUNT value on done: 14067.0 [2024-08-05 09:06:59,736][00150] Sum rewards: -3.503, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.365', 'AMMO5': '0.005', 'AMMO2': '0.007', 'WEAPON1': '0.010', 'AMMO4': '0.037', 'ARMOR': '0.080', 'HITCOUNT': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.135', 'DAMAGECOUNT': '0.390', 'WEAPON3': '0.850', 'FRAGCOUNT': '1.000', 'weapon2': '1.528', 'weapon3': '1.870'} [2024-08-05 09:07:00,310][00150] DAMAGECOUNT value on done: 13028.0 [2024-08-05 09:07:00,311][00150] Sum rewards: -5.545, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.756', 'AMMO5': '0.003', 'AMMO2': '0.008', 'weapon5': '0.020', 'AMMO4': '0.037', 'WEAPON5': '0.050', 'WEAPON4': '0.050', 'ARMOR': '0.072', 'AMMO3': '0.123', 'weapon4': '0.188', 'HITCOUNT': '0.220', 'DAMAGECOUNT': '0.576', 'WEAPON3': '0.750', 'FRAGCOUNT': '1.000', 'weapon3': '1.736', 'weapon2': '1.878'} [2024-08-05 09:07:00,626][00146] Updated weights for policy 0, policy_version 1180 (0.0025) [2024-08-05 09:07:01,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 9666560. Throughput: 0: 929.3. Samples: 2417616. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:07:01,502][00035] Avg episode reward: [(0, '-3.127')] [2024-08-05 09:07:04,875][00147] DAMAGECOUNT value on done: 12550.0 [2024-08-05 09:07:04,876][00147] Sum rewards: -0.173, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-1.204', 'AMMO4': '-0.029', 'AMMO2': '-0.006', 'AMMO5': '0.007', 'ARMOR': '0.032', 'AMMO3': '0.091', 'WEAPON4': '0.100', 'WEAPON5': '0.150', 'HITCOUNT': '0.160', 'weapon5': '0.166', 'weapon4': '0.190', 'WEAPON3': '0.650', 'DAMAGECOUNT': '0.915', 'weapon2': '1.058', 'weapon3': '1.546', 'FRAGCOUNT': '2.000'} [2024-08-05 09:07:05,774][00147] DAMAGECOUNT value on done: 14132.0 [2024-08-05 09:07:05,776][00147] Sum rewards: -2.889, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-1.640', 'AMMO4': '-0.073', 'AMMO2': '-0.015', 'AMMO5': '0.005', 'WEAPON5': '0.050', 'ARMOR': '0.068', 'AMMO3': '0.097', 'HITCOUNT': '0.190', 'weapon5': '0.202', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.585', 'FRAGCOUNT': '1.000', 'weapon3': '1.436', 'weapon2': '1.456'} [2024-08-05 09:07:06,342][00147] DAMAGECOUNT value on done: 11194.0 [2024-08-05 09:07:06,343][00147] Sum rewards: -1.857, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-0.568', 'AMMO5': '0.005', 'AMMO2': '0.016', 'AMMO4': '0.079', 'AMMO3': '0.142', 'HITCOUNT': '0.160', 'ARMOR': '0.172', 'DAMAGECOUNT': '0.765', 'WEAPON3': '0.850', 'weapon3': '1.488', 'weapon2': '2.284', 'FRAGCOUNT': '4.000'} [2024-08-05 09:07:06,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 9682944. Throughput: 0: 927.9. Samples: 2420356. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:07:06,501][00035] Avg episode reward: [(0, '-3.142')] [2024-08-05 09:07:06,996][00147] DAMAGECOUNT value on done: 12113.0 [2024-08-05 09:07:06,997][00147] Sum rewards: -6.730, reward structure: {'DEATHCOUNT': '-11.250', 'FRAGCOUNT': '-1.000', 'HEALTH': '-0.430', 'AMMO4': '-0.029', 'AMMO2': '-0.006', 'AMMO5': '0.010', 'ARMOR': '0.040', 'AMMO3': '0.126', 'weapon5': '0.182', 'WEAPON5': '0.200', 'HITCOUNT': '0.310', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.975', 'weapon2': '1.368', 'weapon3': '1.974'} [2024-08-05 09:07:09,124][00148] DAMAGECOUNT value on done: 12731.0 [2024-08-05 09:07:09,125][00148] Sum rewards: -1.960, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-1.324', 'AMMO5': '0.007', 'AMMO2': '0.022', 'WEAPON4': '0.050', 'weapon4': '0.050', 'ARMOR': '0.068', 'WEAPON5': '0.100', 'AMMO4': '0.110', 'AMMO3': '0.117', 'weapon5': '0.118', 'HITCOUNT': '0.230', 'WEAPON3': '0.750', 'DAMAGECOUNT': '1.020', 'weapon3': '1.664', 'FRAGCOUNT': '2.000', 'weapon2': '2.058'} [2024-08-05 09:07:09,691][00148] DAMAGECOUNT value on done: 11329.0 [2024-08-05 09:07:09,693][00148] Sum rewards: -6.749, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.212', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.062', 'AMMO2': '-0.012', 'AMMO5': '0.008', 'weapon5': '0.040', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'ARMOR': '0.140', 'AMMO3': '0.162', 'HITCOUNT': '0.180', 'DAMAGECOUNT': '0.816', 'WEAPON3': '1.050', 'weapon2': '1.690', 'weapon3': '1.750'} [2024-08-05 09:07:10,304][00148] DAMAGECOUNT value on done: 11151.0 [2024-08-05 09:07:10,305][00148] Sum rewards: -2.970, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.765', 'AMMO4': '-0.072', 'AMMO2': '-0.014', 'AMMO5': '0.005', 'ARMOR': '0.040', 'WEAPON5': '0.100', 'weapon5': '0.128', 'AMMO3': '0.138', 'HITCOUNT': '0.240', 'WEAPON3': '0.650', 'DAMAGECOUNT': '0.756', 'weapon3': '1.232', 'weapon2': '1.842', 'FRAGCOUNT': '2.000'} [2024-08-05 09:07:10,870][00148] DAMAGECOUNT value on done: 10948.0 [2024-08-05 09:07:10,871][00148] Sum rewards: -7.351, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-2.612', 'AMMO2': '0.008', 'AMMO5': '0.013', 'AMMO4': '0.042', 'ARMOR': '0.060', 'weapon4': '0.084', 'WEAPON4': '0.100', 'WEAPON5': '0.150', 'AMMO3': '0.193', 'HITCOUNT': '0.210', 'weapon5': '0.334', 'DAMAGECOUNT': '0.987', 'WEAPON3': '1.200', 'weapon2': '1.460', 'weapon3': '1.920', 'FRAGCOUNT': '2.000'} [2024-08-05 09:07:11,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 9699328. Throughput: 0: 916.1. Samples: 2425450. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:07:11,504][00035] Avg episode reward: [(0, '-3.192')] [2024-08-05 09:07:16,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 9715712. Throughput: 0: 914.1. Samples: 2431048. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:07:16,501][00035] Avg episode reward: [(0, '-3.192')] [2024-08-05 09:07:21,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 9740288. Throughput: 0: 922.0. Samples: 2433782. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:07:21,502][00035] Avg episode reward: [(0, '-3.192')] [2024-08-05 09:07:23,276][00146] Updated weights for policy 0, policy_version 1190 (0.0025) [2024-08-05 09:07:26,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3693.4). Total num frames: 9756672. Throughput: 0: 920.9. Samples: 2439360. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:07:26,502][00035] Avg episode reward: [(0, '-3.192')] [2024-08-05 09:07:30,314][00149] DAMAGECOUNT value on done: 12772.0 [2024-08-05 09:07:30,315][00149] Sum rewards: -6.803, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-3.810', 'AMMO4': '-0.056', 'AMMO2': '-0.011', 'AMMO5': '0.010', 'weapon5': '0.034', 'ARMOR': '0.086', 'WEAPON5': '0.100', 'AMMO3': '0.154', 'HITCOUNT': '0.270', 'DAMAGECOUNT': '1.140', 'WEAPON3': '1.150', 'weapon2': '1.388', 'weapon3': '1.992', 'FRAGCOUNT': '2.000'} [2024-08-05 09:07:30,853][00149] DAMAGECOUNT value on done: 12228.0 [2024-08-05 09:07:31,411][00149] DAMAGECOUNT value on done: 13446.0 [2024-08-05 09:07:31,413][00149] Sum rewards: -6.746, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-1.239', 'AMMO2': '0.021', 'AMMO4': '0.105', 'AMMO3': '0.142', 'WEAPON4': '0.200', 'HITCOUNT': '0.230', 'weapon4': '0.258', 'ARMOR': '0.477', 'DAMAGECOUNT': '0.690', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon3': '1.460', 'weapon2': '1.860'} [2024-08-05 09:07:31,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 9773056. Throughput: 0: 913.9. Samples: 2444820. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:07:31,502][00035] Avg episode reward: [(0, '-3.191')] [2024-08-05 09:07:31,942][00149] DAMAGECOUNT value on done: 12881.0 [2024-08-05 09:07:31,943][00149] Sum rewards: 1.227, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-0.503', 'AMMO2': '0.004', 'AMMO5': '0.005', 'AMMO4': '0.020', 'WEAPON1': '0.020', 'ARMOR': '0.072', 'WEAPON5': '0.100', 'weapon5': '0.114', 'AMMO3': '0.116', 'HITCOUNT': '0.120', 'DAMAGECOUNT': '0.345', 'WEAPON3': '0.600', 'weapon2': '1.568', 'weapon3': '1.896', 'FRAGCOUNT': '2.000'} [2024-08-05 09:07:35,030][00150] DAMAGECOUNT value on done: 12407.0 [2024-08-05 09:07:35,032][00150] Sum rewards: -2.281, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-2.450', 'AMMO4': '-0.052', 'AMMO2': '-0.010', 'weapon5': '0.002', 'AMMO5': '0.010', 'WEAPON5': '0.100', 'AMMO3': '0.125', 'HITCOUNT': '0.260', 'ARMOR': '0.595', 'WEAPON3': '0.900', 'DAMAGECOUNT': '0.987', 'weapon3': '1.712', 'weapon2': '1.790', 'FRAGCOUNT': '2.000'} [2024-08-05 09:07:35,574][00150] DAMAGECOUNT value on done: 13647.0 [2024-08-05 09:07:35,575][00150] Sum rewards: -7.200, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-2.611', 'AMMO4': '-0.030', 'AMMO2': '-0.006', 'AMMO5': '0.005', 'WEAPON5': '0.050', 'weapon5': '0.076', 'HITCOUNT': '0.170', 'AMMO3': '0.199', 'DAMAGECOUNT': '0.525', 'WEAPON3': '1.250', 'FRAGCOUNT': '1.500', 'weapon2': '1.592', 'weapon3': '2.080'} [2024-08-05 09:07:36,075][00150] DAMAGECOUNT value on done: 14266.0 [2024-08-05 09:07:36,076][00150] Sum rewards: -4.274, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.776', 'AMMO2': '0.007', 'AMMO5': '0.012', 'weapon5': '0.030', 'AMMO4': '0.034', 'ARMOR': '0.064', 'AMMO3': '0.131', 'WEAPON5': '0.150', 'HITCOUNT': '0.190', 'DAMAGECOUNT': '0.597', 'WEAPON3': '0.750', 'FRAGCOUNT': '1.000', 'weapon3': '1.556', 'weapon2': '1.730'} [2024-08-05 09:07:36,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 9789440. Throughput: 0: 912.4. Samples: 2447638. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:07:36,504][00035] Avg episode reward: [(0, '-3.153')] [2024-08-05 09:07:36,922][00150] DAMAGECOUNT value on done: 13103.0 [2024-08-05 09:07:41,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3665.6). Total num frames: 9805824. Throughput: 0: 899.0. Samples: 2452706. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:07:41,502][00035] Avg episode reward: [(0, '-3.212')] [2024-08-05 09:07:42,934][00147] DAMAGECOUNT value on done: 12752.0 [2024-08-05 09:07:42,935][00147] Sum rewards: -6.059, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-2.641', 'AMMO4': '-0.010', 'AMMO2': '-0.002', 'AMMO5': '0.010', 'ARMOR': '0.044', 'WEAPON4': '0.100', 'AMMO3': '0.133', 'HITCOUNT': '0.140', 'WEAPON5': '0.150', 'weapon5': '0.164', 'DAMAGECOUNT': '0.606', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon2': '1.728', 'weapon3': '2.018'} [2024-08-05 09:07:43,467][00147] DAMAGECOUNT value on done: 14247.0 [2024-08-05 09:07:44,054][00147] DAMAGECOUNT value on done: 11375.0 [2024-08-05 09:07:44,055][00147] Sum rewards: -5.415, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.570', 'AMMO4': '-0.027', 'AMMO2': '-0.005', 'AMMO5': '0.004', 'weapon5': '0.078', 'WEAPON5': '0.100', 'AMMO3': '0.143', 'HITCOUNT': '0.190', 'DAMAGECOUNT': '0.543', 'WEAPON3': '0.950', 'FRAGCOUNT': '1.000', 'weapon2': '1.320', 'weapon3': '2.360'} [2024-08-05 09:07:44,597][00147] DAMAGECOUNT value on done: 12588.0 [2024-08-05 09:07:44,598][00147] Sum rewards: -3.667, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-0.892', 'AMMO5': '0.003', 'AMMO2': '0.006', 'weapon5': '0.018', 'AMMO4': '0.032', 'weapon4': '0.042', 'WEAPON5': '0.050', 'WEAPON4': '0.050', 'ARMOR': '0.080', 'AMMO3': '0.141', 'HITCOUNT': '0.280', 'WEAPON3': '0.850', 'DAMAGECOUNT': '1.425', 'weapon3': '1.730', 'weapon2': '2.018', 'FRAGCOUNT': '2.500'} [2024-08-05 09:07:45,981][00146] Updated weights for policy 0, policy_version 1200 (0.0021) [2024-08-05 09:07:46,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 9830400. Throughput: 0: 903.3. Samples: 2458266. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:07:46,502][00035] Avg episode reward: [(0, '-3.322')] [2024-08-05 09:07:46,506][00148] DAMAGECOUNT value on done: 12791.0 [2024-08-05 09:07:46,507][00148] Sum rewards: -1.840, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-0.595', 'weapon5': '0.006', 'AMMO2': '0.007', 'AMMO5': '0.015', 'AMMO4': '0.036', 'HITCOUNT': '0.070', 'WEAPON5': '0.100', 'AMMO3': '0.109', 'DAMAGECOUNT': '0.180', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '1.426', 'weapon2': '1.856'} [2024-08-05 09:07:47,104][00148] DAMAGECOUNT value on done: 11488.0 [2024-08-05 09:07:47,104][00148] Sum rewards: -2.970, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.210', 'AMMO2': '0.003', 'AMMO5': '0.010', 'AMMO4': '0.015', 'ARMOR': '0.082', 'WEAPON5': '0.100', 'AMMO3': '0.131', 'HITCOUNT': '0.170', 'DAMAGECOUNT': '0.477', 'WEAPON3': '0.850', 'FRAGCOUNT': '1.000', 'weapon2': '1.548', 'weapon3': '2.104'} [2024-08-05 09:07:47,669][00148] DAMAGECOUNT value on done: 11241.0 [2024-08-05 09:07:47,669][00148] Sum rewards: -1.879, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-0.730', 'AMMO5': '0.005', 'AMMO2': '0.010', 'AMMO4': '0.049', 'HITCOUNT': '0.080', 'AMMO3': '0.083', 'WEAPON5': '0.100', 'weapon5': '0.128', 'DAMAGECOUNT': '0.270', 'WEAPON3': '0.450', 'FRAGCOUNT': '0.500', 'weapon3': '0.846', 'weapon2': '1.580'} [2024-08-05 09:07:48,268][00148] DAMAGECOUNT value on done: 11183.0 [2024-08-05 09:07:48,269][00148] Sum rewards: -3.498, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-1.270', 'AMMO4': '-0.040', 'AMMO2': '-0.008', 'AMMO5': '0.003', 'WEAPON1': '0.020', 'ARMOR': '0.044', 'WEAPON5': '0.050', 'WEAPON4': '0.100', 'AMMO3': '0.102', 'HITCOUNT': '0.170', 'weapon4': '0.174', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.705', 'weapon3': '1.350', 'weapon2': '2.002', 'FRAGCOUNT': '3.000'} [2024-08-05 09:07:51,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 9846784. Throughput: 0: 903.6. Samples: 2461020. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:07:51,502][00035] Avg episode reward: [(0, '-3.380')] [2024-08-05 09:07:56,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3693.3). Total num frames: 9863168. Throughput: 0: 915.6. Samples: 2466650. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:07:56,502][00035] Avg episode reward: [(0, '-3.380')] [2024-08-05 09:08:01,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 9887744. Throughput: 0: 913.6. Samples: 2472160. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:08:01,501][00035] Avg episode reward: [(0, '-3.380')] [2024-08-05 09:08:06,500][00035] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 9904128. Throughput: 0: 914.4. Samples: 2474930. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:08:06,502][00035] Avg episode reward: [(0, '-3.380')] [2024-08-05 09:08:06,724][00149] DAMAGECOUNT value on done: 13103.0 [2024-08-05 09:08:06,725][00149] Sum rewards: 2.632, reward structure: {'DEATHCOUNT': '-3.750', 'HEALTH': '-0.288', 'AMMO4': '-0.010', 'AMMO2': '-0.002', 'AMMO5': '0.010', 'AMMO3': '0.060', 'weapon5': '0.088', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'weapon4': '0.120', 'HITCOUNT': '0.210', 'WEAPON3': '0.350', 'ARMOR': '0.488', 'DAMAGECOUNT': '0.993', 'weapon3': '1.014', 'weapon2': '1.148', 'FRAGCOUNT': '2.000'} [2024-08-05 09:08:07,271][00149] DAMAGECOUNT value on done: 12308.0 [2024-08-05 09:08:07,823][00149] DAMAGECOUNT value on done: 13571.0 [2024-08-05 09:08:07,823][00149] Sum rewards: -2.543, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.639', 'AMMO2': '0.006', 'AMMO5': '0.007', 'AMMO4': '0.031', 'ARMOR': '0.036', 'AMMO3': '0.084', 'HITCOUNT': '0.120', 'WEAPON5': '0.150', 'weapon5': '0.342', 'DAMAGECOUNT': '0.375', 'WEAPON3': '0.500', 'FRAGCOUNT': '1.000', 'weapon3': '1.298', 'weapon2': '1.646'} [2024-08-05 09:08:08,221][00146] Updated weights for policy 0, policy_version 1210 (0.0029) [2024-08-05 09:08:08,468][00149] DAMAGECOUNT value on done: 13135.0 [2024-08-05 09:08:08,469][00149] Sum rewards: -0.449, reward structure: {'DEATHCOUNT': '-4.500', 'HEALTH': '-0.812', 'AMMO4': '-0.046', 'AMMO2': '-0.009', 'weapon5': '0.002', 'AMMO5': '0.003', 'WEAPON1': '0.020', 'WEAPON5': '0.050', 'AMMO3': '0.058', 'HITCOUNT': '0.220', 'WEAPON3': '0.400', 'ARMOR': '0.499', 'DAMAGECOUNT': '0.762', 'weapon3': '0.796', 'FRAGCOUNT': '1.000', 'weapon2': '1.108'} [2024-08-05 09:08:11,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 9920512. Throughput: 0: 903.0. Samples: 2479996. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:08:11,501][00035] Avg episode reward: [(0, '-3.282')] [2024-08-05 09:08:11,541][00150] DAMAGECOUNT value on done: 12590.0 [2024-08-05 09:08:11,542][00150] Sum rewards: -3.003, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.084', 'AMMO5': '0.003', 'AMMO2': '0.005', 'AMMO4': '0.027', 'WEAPON5': '0.050', 'weapon4': '0.052', 'ARMOR': '0.068', 'AMMO3': '0.097', 'WEAPON4': '0.100', 'HITCOUNT': '0.140', 'weapon5': '0.156', 'DAMAGECOUNT': '0.549', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon2': '1.384', 'weapon3': '1.500'} [2024-08-05 09:08:12,096][00150] DAMAGECOUNT value on done: 13936.0 [2024-08-05 09:08:12,097][00150] Sum rewards: -1.195, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.818', 'AMMO5': '0.010', 'ARMOR': '0.016', 'AMMO2': '0.025', 'weapon4': '0.030', 'WEAPON4': '0.050', 'AMMO3': '0.110', 'AMMO4': '0.123', 'weapon5': '0.186', 'WEAPON5': '0.200', 'HITCOUNT': '0.240', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.867', 'weapon2': '1.388', 'weapon3': '1.928', 'FRAGCOUNT': '2.000'} [2024-08-05 09:08:12,648][00150] DAMAGECOUNT value on done: 14422.0 [2024-08-05 09:08:12,649][00150] Sum rewards: -2.527, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-0.174', 'AMMO5': '0.009', 'ARMOR': '0.012', 'AMMO2': '0.013', 'weapon5': '0.026', 'AMMO4': '0.062', 'WEAPON5': '0.100', 'AMMO3': '0.118', 'HITCOUNT': '0.150', 'DAMAGECOUNT': '0.468', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon2': '1.338', 'weapon3': '2.000'} [2024-08-05 09:08:13,222][00150] DAMAGECOUNT value on done: 13529.0 [2024-08-05 09:08:13,224][00150] Sum rewards: -5.526, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-2.686', 'AMMO5': '0.003', 'AMMO2': '0.005', 'AMMO4': '0.023', 'ARMOR': '0.032', 'WEAPON5': '0.050', 'weapon5': '0.062', 'AMMO3': '0.176', 'HITCOUNT': '0.320', 'WEAPON3': '1.100', 'DAMAGECOUNT': '1.278', 'weapon3': '1.606', 'weapon2': '1.756', 'FRAGCOUNT': '2.000'} [2024-08-05 09:08:16,500][00035] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 9936896. Throughput: 0: 904.4. Samples: 2485520. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 09:08:16,502][00035] Avg episode reward: [(0, '-3.234')] [2024-08-05 09:08:20,291][00147] DAMAGECOUNT value on done: 13332.0 [2024-08-05 09:08:20,293][00147] Sum rewards: 4.154, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-0.139', 'AMMO5': '0.010', 'AMMO2': '0.012', 'WEAPON1': '0.020', 'WEAPON4': '0.050', 'AMMO4': '0.058', 'AMMO3': '0.115', 'weapon4': '0.164', 'WEAPON5': '0.250', 'HITCOUNT': '0.400', 'WEAPON3': '0.500', 'weapon5': '0.514', 'weapon2': '1.274', 'weapon3': '1.686', 'DAMAGECOUNT': '1.740', 'FRAGCOUNT': '5.000'} [2024-08-05 09:08:20,842][00147] DAMAGECOUNT value on done: 14526.0 [2024-08-05 09:08:20,843][00147] Sum rewards: -1.930, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-0.686', 'AMMO2': '0.003', 'AMMO5': '0.005', 'AMMO4': '0.014', 'weapon5': '0.024', 'ARMOR': '0.068', 'WEAPON5': '0.100', 'AMMO3': '0.143', 'HITCOUNT': '0.240', 'DAMAGECOUNT': '0.837', 'WEAPON3': '0.850', 'weapon2': '1.606', 'weapon3': '1.616', 'FRAGCOUNT': '3.000'} [2024-08-05 09:08:21,429][00147] DAMAGECOUNT value on done: 11645.0 [2024-08-05 09:08:21,431][00147] Sum rewards: -1.896, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-1.420', 'AMMO2': '0.004', 'AMMO4': '0.019', 'AMMO5': '0.025', 'ARMOR': '0.090', 'AMMO3': '0.105', 'weapon5': '0.232', 'HITCOUNT': '0.280', 'WEAPON5': '0.350', 'WEAPON3': '0.550', 'DAMAGECOUNT': '0.810', 'weapon3': '1.616', 'weapon2': '1.694', 'FRAGCOUNT': '2.000'} [2024-08-05 09:08:21,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3693.3). Total num frames: 9953280. Throughput: 0: 903.4. Samples: 2488292. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 09:08:21,501][00035] Avg episode reward: [(0, '-3.203')] [2024-08-05 09:08:21,512][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001215_9953280.pth... [2024-08-05 09:08:21,621][00137] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001107_9068544.pth [2024-08-05 09:08:22,039][00147] DAMAGECOUNT value on done: 12731.0 [2024-08-05 09:08:22,040][00147] Sum rewards: -1.926, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-1.703', 'AMMO4': '-0.060', 'AMMO2': '-0.012', 'AMMO5': '0.005', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'weapon5': '0.106', 'AMMO3': '0.111', 'ARMOR': '0.120', 'weapon4': '0.138', 'HITCOUNT': '0.150', 'DAMAGECOUNT': '0.429', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '1.418', 'weapon2': '1.472'} [2024-08-05 09:08:24,380][00148] DAMAGECOUNT value on done: 12878.0 [2024-08-05 09:08:24,381][00148] Sum rewards: -3.215, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-1.110', 'AMMO2': '0.001', 'AMMO4': '0.004', 'HITCOUNT': '0.080', 'AMMO3': '0.101', 'DAMAGECOUNT': '0.261', 'WEAPON3': '0.650', 'FRAGCOUNT': '1.000', 'weapon3': '1.568', 'weapon2': '1.730'} [2024-08-05 09:08:25,101][00148] DAMAGECOUNT value on done: 11538.0 [2024-08-05 09:08:25,760][00148] DAMAGECOUNT value on done: 11532.0 [2024-08-05 09:08:25,761][00148] Sum rewards: -4.813, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-1.080', 'AMMO5': '0.007', 'ARMOR': '0.016', 'AMMO2': '0.017', 'AMMO4': '0.084', 'weapon5': '0.098', 'WEAPON5': '0.150', 'HITCOUNT': '0.180', 'AMMO3': '0.196', 'DAMAGECOUNT': '0.873', 'WEAPON3': '1.050', 'weapon2': '1.512', 'FRAGCOUNT': '2.000', 'weapon3': '2.084'} [2024-08-05 09:08:26,500][00035] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3693.3). Total num frames: 9969664. Throughput: 0: 907.9. Samples: 2493560. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-08-05 09:08:26,502][00035] Avg episode reward: [(0, '-3.135')] [2024-08-05 09:08:26,549][00148] DAMAGECOUNT value on done: 11570.0 [2024-08-05 09:08:26,551][00148] Sum rewards: -5.370, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-2.040', 'AMMO4': '-0.018', 'AMMO2': '-0.004', 'ARMOR': '0.040', 'AMMO3': '0.184', 'HITCOUNT': '0.280', 'WEAPON3': '1.050', 'DAMAGECOUNT': '1.161', 'weapon2': '1.368', 'weapon3': '2.358', 'FRAGCOUNT': '3.000'} [2024-08-05 09:08:31,500][00035] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3665.6). Total num frames: 9986048. Throughput: 0: 893.4. Samples: 2498470. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) [2024-08-05 09:08:31,504][00035] Avg episode reward: [(0, '-3.207')] [2024-08-05 09:08:31,814][00146] Updated weights for policy 0, policy_version 1220 (0.0017) [2024-08-05 09:08:36,153][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001222_10010624.pth... [2024-08-05 09:08:36,152][00035] Component Batcher_0 stopped! [2024-08-05 09:08:36,154][00137] Stopping Batcher_0... [2024-08-05 09:08:36,160][00137] Loop batcher_evt_loop terminating... [2024-08-05 09:08:36,180][00150] Stopping RolloutWorker_w3... [2024-08-05 09:08:36,179][00035] Component RolloutWorker_w2 stopped! [2024-08-05 09:08:36,180][00150] Loop rollout_proc3_evt_loop terminating... [2024-08-05 09:08:36,181][00035] Component RolloutWorker_w3 stopped! [2024-08-05 09:08:36,179][00149] Stopping RolloutWorker_w2... [2024-08-05 09:08:36,185][00149] Loop rollout_proc2_evt_loop terminating... [2024-08-05 09:08:36,209][00147] Stopping RolloutWorker_w0... [2024-08-05 09:08:36,210][00147] Loop rollout_proc0_evt_loop terminating... [2024-08-05 09:08:36,202][00146] Weights refcount: 2 0 [2024-08-05 09:08:36,209][00035] Component RolloutWorker_w0 stopped! [2024-08-05 09:08:36,214][00146] Stopping InferenceWorker_p0-w0... [2024-08-05 09:08:36,215][00146] Loop inference_proc0-0_evt_loop terminating... [2024-08-05 09:08:36,214][00035] Component InferenceWorker_p0-w0 stopped! [2024-08-05 09:08:36,217][00035] Component RolloutWorker_w1 stopped! [2024-08-05 09:08:36,219][00148] Stopping RolloutWorker_w1... [2024-08-05 09:08:36,220][00148] Loop rollout_proc1_evt_loop terminating... [2024-08-05 09:08:36,271][00137] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001162_9519104.pth [2024-08-05 09:08:36,283][00137] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001222_10010624.pth... [2024-08-05 09:08:36,429][00137] Stopping LearnerWorker_p0... [2024-08-05 09:08:36,428][00035] Component LearnerWorker_p0 stopped! [2024-08-05 09:08:36,430][00035] Waiting for process learner_proc0 to stop... [2024-08-05 09:08:36,429][00137] Loop learner_proc0_evt_loop terminating... [2024-08-05 09:08:37,499][00035] Waiting for process inference_proc0-0 to join... [2024-08-05 09:08:37,500][00035] Waiting for process rollout_proc0 to join... [2024-08-05 09:08:37,501][00035] Waiting for process rollout_proc1 to join... [2024-08-05 09:08:37,502][00035] Waiting for process rollout_proc2 to join... [2024-08-05 09:08:37,503][00035] Waiting for process rollout_proc3 to join... [2024-08-05 09:08:37,504][00035] Batcher 0 profile tree view: batching: 39.6981, releasing_batches: 0.0385 [2024-08-05 09:08:37,505][00035] InferenceWorker_p0-w0 profile tree view: wait_policy: 0.0000 wait_policy_total: 53.7229 update_model: 23.9539 weight_update: 0.0017 one_step: 0.0061 handle_policy_step: 2566.8665 deserialize: 56.1935, stack: 12.7403, obs_to_device_normalize: 515.2413, forward: 1678.7558, send_messages: 64.3603 prepare_outputs: 149.0987 to_cpu: 80.9960 [2024-08-05 09:08:37,506][00035] Learner 0 profile tree view: misc: 0.0085, prepare_batch: 13.9620 train: 73.7660 epoch_init: 0.0085, minibatch_init: 0.0078, losses_postprocess: 0.3910, kl_divergence: 1.3680, after_optimizer: 34.7322 calculate_losses: 19.9922 losses_init: 0.0054, forward_head: 1.3334, bptt_initial: 11.3362, tail: 1.8940, advantages_returns: 0.1832, losses: 3.2245 bptt: 1.7626 bptt_forward_core: 1.6912 update: 16.6283 clip: 1.1831 [2024-08-05 09:08:37,507][00035] RolloutWorker_w0 profile tree view: wait_for_trajectories: 1.0737, enqueue_policy_requests: 48.3867, env_step: 1525.1729, overhead: 34.8718, complete_rollouts: 4.4346 save_policy_outputs: 66.4143 split_output_tensors: 24.4566 [2024-08-05 09:08:37,508][00035] RolloutWorker_w3 profile tree view: wait_for_trajectories: 1.0830, enqueue_policy_requests: 49.5244, env_step: 1565.8592, overhead: 35.9288, complete_rollouts: 4.5319 save_policy_outputs: 67.4730 split_output_tensors: 24.7632 [2024-08-05 09:08:37,510][00035] Loop Runner_EvtLoop terminating... [2024-08-05 09:08:37,511][00035] Runner profile tree view: main_loop: 2770.4399 [2024-08-05 09:08:37,511][00035] Collected {0: 10010624}, FPS: 3613.4 [2024-08-05 09:15:48,731][00035] Loading existing experiment configuration from /kaggle/working/train_dir/default_experiment/config.json [2024-08-05 09:15:48,732][00035] Overriding arg 'num_workers' with value 1 passed from command line [2024-08-05 09:15:48,733][00035] Adding new argument 'no_render'=True that is not in the saved config file! [2024-08-05 09:15:48,734][00035] Adding new argument 'save_video'=True that is not in the saved config file! [2024-08-05 09:15:48,734][00035] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! [2024-08-05 09:15:48,735][00035] Adding new argument 'video_name'=None that is not in the saved config file! [2024-08-05 09:15:48,736][00035] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! [2024-08-05 09:15:48,736][00035] Adding new argument 'max_num_episodes'=4 that is not in the saved config file! [2024-08-05 09:15:48,737][00035] Adding new argument 'push_to_hub'=False that is not in the saved config file! [2024-08-05 09:15:48,739][00035] Adding new argument 'hf_repository'=None that is not in the saved config file! [2024-08-05 09:15:48,740][00035] Adding new argument 'policy_index'=0 that is not in the saved config file! [2024-08-05 09:15:48,740][00035] Adding new argument 'eval_deterministic'=False that is not in the saved config file! [2024-08-05 09:15:48,741][00035] Adding new argument 'train_script'=None that is not in the saved config file! [2024-08-05 09:15:48,742][00035] Adding new argument 'enjoy_script'=None that is not in the saved config file! [2024-08-05 09:15:48,743][00035] Using frameskip 1 and render_action_repeat=4 for evaluation [2024-08-05 09:15:48,775][00035] Doom resolution: 160x120, resize resolution: (128, 72) [2024-08-05 09:15:48,778][00035] Port 40300 is available [2024-08-05 09:15:48,779][00035] Using port 40300 [2024-08-05 09:15:48,782][00035] RunningMeanStd input shape: (23,) [2024-08-05 09:15:48,783][00035] RunningMeanStd input shape: (3, 72, 128) [2024-08-05 09:15:48,784][00035] RunningMeanStd input shape: (1,) [2024-08-05 09:15:48,802][00035] ConvEncoder: input_channels=3 [2024-08-05 09:15:48,926][00035] Conv encoder output size: 512 [2024-08-05 09:15:48,928][00035] Policy head output size: 640 [2024-08-05 09:15:49,119][00035] Loading state from checkpoint /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001222_10010624.pth... [2024-08-05 09:15:49,157][00035] Using port 40300 on host... [2024-08-05 09:15:49,477][00035] Initialized w:0 v:0 player:0 [2024-08-05 09:15:49,990][00035] Num frames 100... [2024-08-05 09:15:50,208][00035] Num frames 200... [2024-08-05 09:15:50,426][00035] Num frames 300... [2024-08-05 09:15:50,642][00035] Num frames 400... [2024-08-05 09:15:50,860][00035] Num frames 500... [2024-08-05 09:15:51,072][00035] Num frames 600... [2024-08-05 09:15:51,286][00035] Num frames 700... [2024-08-05 09:15:51,502][00035] Num frames 800... [2024-08-05 09:15:51,718][00035] Num frames 900... [2024-08-05 09:15:51,931][00035] Num frames 1000... [2024-08-05 09:15:52,143][00035] Num frames 1100... [2024-08-05 09:15:52,367][00035] Num frames 1200... [2024-08-05 09:15:52,598][00035] Num frames 1300... [2024-08-05 09:15:52,819][00035] Num frames 1400... [2024-08-05 09:15:53,041][00035] Num frames 1500... [2024-08-05 09:15:53,265][00035] Num frames 1600... [2024-08-05 09:15:53,482][00035] Num frames 1700... [2024-08-05 09:15:53,700][00035] Num frames 1800... [2024-08-05 09:15:53,911][00035] Num frames 1900... [2024-08-05 09:15:54,128][00035] Num frames 2000... [2024-08-05 09:15:54,355][00035] Num frames 2100... [2024-08-05 09:15:54,567][00035] Num frames 2200... [2024-08-05 09:15:54,781][00035] Num frames 2300... [2024-08-05 09:15:54,995][00035] Num frames 2400... [2024-08-05 09:15:55,220][00035] Num frames 2500... [2024-08-05 09:15:55,438][00035] Num frames 2600... [2024-08-05 09:15:55,665][00035] Num frames 2700... [2024-08-05 09:15:55,885][00035] Num frames 2800... [2024-08-05 09:15:56,110][00035] Num frames 2900... [2024-08-05 09:15:56,337][00035] Num frames 3000... [2024-08-05 09:15:56,577][00035] Num frames 3100... [2024-08-05 09:15:56,806][00035] Num frames 3200... [2024-08-05 09:15:57,026][00035] Num frames 3300... [2024-08-05 09:15:57,237][00035] Num frames 3400... [2024-08-05 09:15:57,461][00035] Num frames 3500... [2024-08-05 09:15:57,680][00035] Num frames 3600... [2024-08-05 09:15:57,897][00035] Num frames 3700... [2024-08-05 09:15:58,113][00035] Num frames 3800... [2024-08-05 09:15:58,340][00035] Num frames 3900... [2024-08-05 09:15:58,553][00035] Num frames 4000... [2024-08-05 09:15:58,772][00035] Num frames 4100... [2024-08-05 09:15:58,985][00035] Num frames 4200... [2024-08-05 09:15:59,200][00035] Num frames 4300... [2024-08-05 09:15:59,441][00035] Num frames 4400... [2024-08-05 09:15:59,692][00035] Num frames 4500... [2024-08-05 09:15:59,927][00035] Num frames 4600... [2024-08-05 09:16:00,155][00035] Num frames 4700... [2024-08-05 09:16:00,404][00035] Num frames 4800... [2024-08-05 09:16:00,629][00035] Num frames 4900... [2024-08-05 09:16:00,845][00035] Num frames 5000... [2024-08-05 09:16:01,058][00035] Num frames 5100... [2024-08-05 09:16:01,272][00035] Num frames 5200... [2024-08-05 09:16:01,489][00035] Num frames 5300... [2024-08-05 09:16:01,703][00035] Num frames 5400... [2024-08-05 09:16:01,948][00035] Num frames 5500... [2024-08-05 09:16:02,172][00035] Num frames 5600... [2024-08-05 09:16:02,399][00035] Num frames 5700... [2024-08-05 09:16:02,628][00035] Num frames 5800... [2024-08-05 09:16:02,853][00035] Num frames 5900... [2024-08-05 09:16:03,081][00035] Num frames 6000... [2024-08-05 09:16:03,298][00035] Num frames 6100... [2024-08-05 09:16:03,516][00035] Num frames 6200... [2024-08-05 09:16:03,738][00035] Num frames 6300... [2024-08-05 09:16:03,963][00035] Num frames 6400... [2024-08-05 09:16:04,180][00035] Num frames 6500... [2024-08-05 09:16:04,402][00035] Num frames 6600... [2024-08-05 09:16:04,615][00035] Num frames 6700... [2024-08-05 09:16:04,833][00035] Num frames 6800... [2024-08-05 09:16:05,051][00035] Num frames 6900... [2024-08-05 09:16:05,270][00035] Num frames 7000... [2024-08-05 09:16:05,489][00035] Num frames 7100... [2024-08-05 09:16:05,710][00035] Num frames 7200... [2024-08-05 09:16:05,937][00035] Num frames 7300... [2024-08-05 09:16:06,149][00035] Num frames 7400... [2024-08-05 09:16:06,370][00035] Num frames 7500... [2024-08-05 09:16:06,612][00035] Num frames 7600... [2024-08-05 09:16:06,837][00035] Num frames 7700... [2024-08-05 09:16:07,057][00035] Num frames 7800... [2024-08-05 09:16:07,274][00035] Num frames 7900... [2024-08-05 09:16:07,496][00035] Num frames 8000... [2024-08-05 09:16:07,721][00035] Num frames 8100... [2024-08-05 09:16:07,937][00035] Num frames 8200... [2024-08-05 09:16:08,154][00035] Num frames 8300... [2024-08-05 09:16:08,373][00035] DAMAGECOUNT value on done: 278.0 [2024-08-05 09:16:08,375][00035] Sum rewards: 4.431, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.160', 'AMMO4': '-0.107', 'AMMO2': '-0.021', 'AMMO5': '0.005', 'ARMOR': '0.096', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.132', 'HITCOUNT': '0.230', 'weapon5': '0.264', 'weapon4': '0.314', 'DAMAGECOUNT': '0.834', 'WEAPON3': '0.900', 'FRAGCOUNT': '2.000', 'weapon3': '5.018', 'weapon2': '9.226'} [2024-08-05 09:16:08,437][00035] Avg episode rewards: #0: 4.431, true rewards: #0: 2.000 [2024-08-05 09:16:08,438][00035] Avg episode reward: 4.431, avg true_objective: 2.000 [2024-08-05 09:16:08,443][00035] Num frames 8400... [2024-08-05 09:16:08,696][00035] Num frames 8500... [2024-08-05 09:16:08,912][00035] Num frames 8600... [2024-08-05 09:16:09,128][00035] Num frames 8700... [2024-08-05 09:16:09,352][00035] Num frames 8800... [2024-08-05 09:16:09,574][00035] Num frames 8900... [2024-08-05 09:16:09,786][00035] Num frames 9000... [2024-08-05 09:16:09,999][00035] Num frames 9100... [2024-08-05 09:16:10,218][00035] Num frames 9200... [2024-08-05 09:16:10,456][00035] Num frames 9300... [2024-08-05 09:16:10,686][00035] Num frames 9400... [2024-08-05 09:16:10,904][00035] Num frames 9500... [2024-08-05 09:16:11,127][00035] Num frames 9600... [2024-08-05 09:16:11,350][00035] Num frames 9700... [2024-08-05 09:16:11,564][00035] Num frames 9800... [2024-08-05 09:16:11,774][00035] Num frames 9900... [2024-08-05 09:16:11,990][00035] Num frames 10000... [2024-08-05 09:16:12,203][00035] Num frames 10100... [2024-08-05 09:16:12,421][00035] Num frames 10200... [2024-08-05 09:16:12,637][00035] Num frames 10300... [2024-08-05 09:16:12,853][00035] Num frames 10400... [2024-08-05 09:16:13,071][00035] Num frames 10500... [2024-08-05 09:16:13,304][00035] Num frames 10600... [2024-08-05 09:16:13,534][00035] Num frames 10700... [2024-08-05 09:16:13,755][00035] Num frames 10800... [2024-08-05 09:16:13,972][00035] Num frames 10900... [2024-08-05 09:16:14,183][00035] Num frames 11000... [2024-08-05 09:16:14,415][00035] Num frames 11100... [2024-08-05 09:16:14,637][00035] Num frames 11200... [2024-08-05 09:16:14,861][00035] Num frames 11300... [2024-08-05 09:16:15,071][00035] Num frames 11400... [2024-08-05 09:16:15,286][00035] Num frames 11500... [2024-08-05 09:16:15,501][00035] Num frames 11600... [2024-08-05 09:16:15,710][00035] Num frames 11700... [2024-08-05 09:16:15,921][00035] Num frames 11800... [2024-08-05 09:16:16,148][00035] Num frames 11900... [2024-08-05 09:16:16,372][00035] Num frames 12000... [2024-08-05 09:16:16,619][00035] Num frames 12100... [2024-08-05 09:16:16,838][00035] Num frames 12200... [2024-08-05 09:16:17,056][00035] Num frames 12300... [2024-08-05 09:16:17,271][00035] Num frames 12400... [2024-08-05 09:16:17,486][00035] Num frames 12500... [2024-08-05 09:16:17,703][00035] Num frames 12600... [2024-08-05 09:16:17,919][00035] Num frames 12700... [2024-08-05 09:16:18,128][00035] Num frames 12800... [2024-08-05 09:16:18,341][00035] Num frames 12900... [2024-08-05 09:16:18,554][00035] Num frames 13000... [2024-08-05 09:16:18,763][00035] Num frames 13100... [2024-08-05 09:16:18,973][00035] Num frames 13200... [2024-08-05 09:16:19,182][00035] Num frames 13300... [2024-08-05 09:16:19,400][00035] Num frames 13400... [2024-08-05 09:16:19,613][00035] Num frames 13500... [2024-08-05 09:16:19,827][00035] Num frames 13600... [2024-08-05 09:16:20,038][00035] Num frames 13700... [2024-08-05 09:16:20,253][00035] Num frames 13800... [2024-08-05 09:16:20,472][00035] Num frames 13900... [2024-08-05 09:16:20,683][00035] Num frames 14000... [2024-08-05 09:16:20,898][00035] Num frames 14100... [2024-08-05 09:16:21,120][00035] Num frames 14200... [2024-08-05 09:16:21,332][00035] Num frames 14300... [2024-08-05 09:16:21,547][00035] Num frames 14400... [2024-08-05 09:16:21,756][00035] Num frames 14500... [2024-08-05 09:16:21,975][00035] Num frames 14600... [2024-08-05 09:16:22,195][00035] Num frames 14700... [2024-08-05 09:16:22,420][00035] Num frames 14800... [2024-08-05 09:16:22,636][00035] Num frames 14900... [2024-08-05 09:16:22,854][00035] Num frames 15000... [2024-08-05 09:16:23,073][00035] Num frames 15100... [2024-08-05 09:16:23,292][00035] Num frames 15200... [2024-08-05 09:16:23,510][00035] Num frames 15300... [2024-08-05 09:16:23,726][00035] Num frames 15400... [2024-08-05 09:16:23,936][00035] Num frames 15500... [2024-08-05 09:16:24,146][00035] Num frames 15600... [2024-08-05 09:16:24,361][00035] Num frames 15700... [2024-08-05 09:16:24,575][00035] Num frames 15800... [2024-08-05 09:16:24,793][00035] Num frames 15900... [2024-08-05 09:16:25,010][00035] Num frames 16000... [2024-08-05 09:16:25,231][00035] Num frames 16100... [2024-08-05 09:16:25,455][00035] Num frames 16200... [2024-08-05 09:16:25,667][00035] Num frames 16300... [2024-08-05 09:16:25,878][00035] Num frames 16400... [2024-08-05 09:16:26,093][00035] Num frames 16500... [2024-08-05 09:16:26,312][00035] Num frames 16600... [2024-08-05 09:16:26,538][00035] Num frames 16700... [2024-08-05 09:16:26,772][00035] DAMAGECOUNT value on done: 293.0 [2024-08-05 09:16:26,835][00035] Avg episode rewards: #0: 2.920, true rewards: #0: 1.000 [2024-08-05 09:16:26,836][00035] Avg episode reward: 2.920, avg true_objective: 1.000 [2024-08-05 09:16:26,843][00035] Num frames 16800... [2024-08-05 09:16:27,071][00035] Num frames 16900... [2024-08-05 09:16:27,282][00035] Num frames 17000... [2024-08-05 09:16:27,502][00035] Num frames 17100... [2024-08-05 09:16:27,732][00035] Num frames 17200... [2024-08-05 09:16:27,964][00035] Num frames 17300... [2024-08-05 09:16:28,180][00035] Num frames 17400... [2024-08-05 09:16:28,399][00035] Num frames 17500... [2024-08-05 09:16:28,612][00035] Num frames 17600... [2024-08-05 09:16:28,828][00035] Num frames 17700... [2024-08-05 09:16:29,041][00035] Num frames 17800... [2024-08-05 09:16:29,255][00035] Num frames 17900... [2024-08-05 09:16:29,471][00035] Num frames 18000... [2024-08-05 09:16:29,687][00035] Num frames 18100... [2024-08-05 09:16:29,908][00035] Num frames 18200... [2024-08-05 09:16:30,121][00035] Num frames 18300... [2024-08-05 09:16:30,337][00035] Num frames 18400... [2024-08-05 09:16:30,560][00035] Num frames 18500... [2024-08-05 09:16:30,777][00035] Num frames 18600... [2024-08-05 09:16:31,030][00035] Num frames 18700... [2024-08-05 09:16:31,290][00035] Num frames 18800... [2024-08-05 09:16:31,540][00035] Num frames 18900... [2024-08-05 09:16:31,773][00035] Num frames 19000... [2024-08-05 09:16:32,002][00035] Num frames 19100... [2024-08-05 09:16:32,224][00035] Num frames 19200... [2024-08-05 09:16:32,448][00035] Num frames 19300... [2024-08-05 09:16:32,667][00035] Num frames 19400... [2024-08-05 09:16:32,888][00035] Num frames 19500... [2024-08-05 09:16:33,113][00035] Num frames 19600... [2024-08-05 09:16:33,341][00035] Num frames 19700... [2024-08-05 09:16:33,565][00035] Num frames 19800... [2024-08-05 09:16:33,786][00035] Num frames 19900... [2024-08-05 09:16:34,007][00035] Num frames 20000... [2024-08-05 09:16:34,228][00035] Num frames 20100... [2024-08-05 09:16:34,449][00035] Num frames 20200... [2024-08-05 09:16:34,682][00035] Num frames 20300... [2024-08-05 09:16:34,906][00035] Num frames 20400... [2024-08-05 09:16:35,126][00035] Num frames 20500... [2024-08-05 09:16:35,350][00035] Num frames 20600... [2024-08-05 09:16:35,574][00035] Num frames 20700... [2024-08-05 09:16:35,793][00035] Num frames 20800... [2024-08-05 09:16:36,009][00035] Num frames 20900... [2024-08-05 09:16:36,226][00035] Num frames 21000... [2024-08-05 09:16:36,448][00035] Num frames 21100... [2024-08-05 09:16:36,694][00035] Num frames 21200... [2024-08-05 09:16:36,927][00035] Num frames 21300... [2024-08-05 09:16:37,152][00035] Num frames 21400... [2024-08-05 09:16:37,376][00035] Num frames 21500... [2024-08-05 09:16:37,598][00035] Num frames 21600... [2024-08-05 09:16:37,813][00035] Num frames 21700... [2024-08-05 09:16:38,027][00035] Num frames 21800... [2024-08-05 09:16:38,246][00035] Num frames 21900... [2024-08-05 09:16:38,460][00035] Num frames 22000... [2024-08-05 09:16:38,706][00035] Num frames 22100... [2024-08-05 09:16:38,936][00035] Num frames 22200... [2024-08-05 09:16:39,156][00035] Num frames 22300... [2024-08-05 09:16:39,373][00035] Num frames 22400... [2024-08-05 09:16:39,591][00035] Num frames 22500... [2024-08-05 09:16:39,805][00035] Num frames 22600... [2024-08-05 09:16:40,019][00035] Num frames 22700... [2024-08-05 09:16:40,233][00035] Num frames 22800... [2024-08-05 09:16:40,450][00035] Num frames 22900... [2024-08-05 09:16:40,665][00035] Num frames 23000... [2024-08-05 09:16:40,878][00035] Num frames 23100... [2024-08-05 09:16:41,095][00035] Num frames 23200... [2024-08-05 09:16:41,312][00035] Num frames 23300... [2024-08-05 09:16:41,523][00035] Num frames 23400... [2024-08-05 09:16:41,739][00035] Num frames 23500... [2024-08-05 09:16:41,955][00035] Num frames 23600... [2024-08-05 09:16:42,175][00035] Num frames 23700... [2024-08-05 09:16:42,396][00035] Num frames 23800... [2024-08-05 09:16:42,619][00035] Num frames 23900... [2024-08-05 09:16:42,837][00035] Num frames 24000... [2024-08-05 09:16:43,056][00035] Num frames 24100... [2024-08-05 09:16:43,275][00035] Num frames 24200... [2024-08-05 09:16:43,503][00035] Num frames 24300... [2024-08-05 09:16:43,723][00035] Num frames 24400... [2024-08-05 09:16:43,947][00035] Num frames 24500... [2024-08-05 09:16:44,175][00035] Num frames 24600... [2024-08-05 09:16:44,421][00035] Num frames 24700... [2024-08-05 09:16:44,654][00035] Num frames 24800... [2024-08-05 09:16:44,866][00035] Num frames 24900... [2024-08-05 09:16:45,077][00035] Num frames 25000... [2024-08-05 09:16:45,288][00035] Num frames 25100... [2024-08-05 09:16:45,499][00035] DAMAGECOUNT value on done: 633.0 [2024-08-05 09:16:45,500][00035] Sum rewards: 10.039, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.587', 'AMMO4': '-0.108', 'AMMO2': '-0.021', 'AMMO5': '0.005', 'WEAPON1': '0.020', 'ARMOR': '0.050', 'WEAPON5': '0.100', 'weapon5': '0.118', 'AMMO3': '0.198', 'HITCOUNT': '0.220', 'DAMAGECOUNT': '1.020', 'WEAPON3': '1.300', 'FRAGCOUNT': '4.000', 'weapon2': '7.140', 'weapon3': '8.584'} [2024-08-05 09:16:45,562][00035] Avg episode rewards: #0: 5.293, true rewards: #0: 2.000 [2024-08-05 09:16:45,563][00035] Avg episode reward: 5.293, avg true_objective: 2.000 [2024-08-05 09:16:45,572][00035] Num frames 25200... [2024-08-05 09:16:45,789][00035] Num frames 25300... [2024-08-05 09:16:46,007][00035] Num frames 25400... [2024-08-05 09:16:46,222][00035] Num frames 25500... [2024-08-05 09:16:46,436][00035] Num frames 25600... [2024-08-05 09:16:46,686][00035] Num frames 25700... [2024-08-05 09:16:46,901][00035] Num frames 25800... [2024-08-05 09:16:47,115][00035] Num frames 25900... [2024-08-05 09:16:47,328][00035] Num frames 26000... [2024-08-05 09:16:47,545][00035] Num frames 26100... [2024-08-05 09:16:47,758][00035] Num frames 26200... [2024-08-05 09:16:47,970][00035] Num frames 26300... [2024-08-05 09:16:48,190][00035] Num frames 26400... [2024-08-05 09:16:48,412][00035] Num frames 26500... [2024-08-05 09:16:48,637][00035] Num frames 26600... [2024-08-05 09:16:48,854][00035] Num frames 26700... [2024-08-05 09:16:49,068][00035] Num frames 26800... [2024-08-05 09:16:49,289][00035] Num frames 26900... [2024-08-05 09:16:49,513][00035] Num frames 27000... [2024-08-05 09:16:49,726][00035] Num frames 27100... [2024-08-05 09:16:49,955][00035] Num frames 27200... [2024-08-05 09:16:50,181][00035] Num frames 27300... [2024-08-05 09:16:50,406][00035] Num frames 27400... [2024-08-05 09:16:50,634][00035] Num frames 27500... [2024-08-05 09:16:50,862][00035] Num frames 27600... [2024-08-05 09:16:51,083][00035] Num frames 27700... [2024-08-05 09:16:51,303][00035] Num frames 27800... [2024-08-05 09:16:51,523][00035] Num frames 27900... [2024-08-05 09:16:51,737][00035] Num frames 28000... [2024-08-05 09:16:51,947][00035] Num frames 28100... [2024-08-05 09:16:52,162][00035] Num frames 28200... [2024-08-05 09:16:52,386][00035] Num frames 28300... [2024-08-05 09:16:52,616][00035] Num frames 28400... [2024-08-05 09:16:52,837][00035] Num frames 28500... [2024-08-05 09:16:53,050][00035] Num frames 28600... [2024-08-05 09:16:53,262][00035] Num frames 28700... [2024-08-05 09:16:53,477][00035] Num frames 28800... [2024-08-05 09:16:53,691][00035] Num frames 28900... [2024-08-05 09:16:53,908][00035] Num frames 29000... [2024-08-05 09:16:54,120][00035] Num frames 29100... [2024-08-05 09:16:54,333][00035] Num frames 29200... [2024-08-05 09:16:54,549][00035] Num frames 29300... [2024-08-05 09:16:54,761][00035] Num frames 29400... [2024-08-05 09:16:54,976][00035] Num frames 29500... [2024-08-05 09:16:55,191][00035] Num frames 29600... [2024-08-05 09:16:55,407][00035] Num frames 29700... [2024-08-05 09:16:55,625][00035] Num frames 29800... [2024-08-05 09:16:55,839][00035] Num frames 29900... [2024-08-05 09:16:56,053][00035] Num frames 30000... [2024-08-05 09:16:56,272][00035] Num frames 30100... [2024-08-05 09:16:56,496][00035] Num frames 30200... [2024-08-05 09:16:56,734][00035] Num frames 30300... [2024-08-05 09:16:56,954][00035] Num frames 30400... [2024-08-05 09:16:57,173][00035] Num frames 30500... [2024-08-05 09:16:57,401][00035] Num frames 30600... [2024-08-05 09:16:57,635][00035] Num frames 30700... [2024-08-05 09:16:57,861][00035] Num frames 30800... [2024-08-05 09:16:58,080][00035] Num frames 30900... [2024-08-05 09:16:58,305][00035] Num frames 31000... [2024-08-05 09:16:58,523][00035] Num frames 31100... [2024-08-05 09:16:58,741][00035] Num frames 31200... [2024-08-05 09:16:58,954][00035] Num frames 31300... [2024-08-05 09:16:59,169][00035] Num frames 31400... [2024-08-05 09:16:59,385][00035] Num frames 31500... [2024-08-05 09:16:59,600][00035] Num frames 31600... [2024-08-05 09:16:59,817][00035] Num frames 31700... [2024-08-05 09:17:00,030][00035] Num frames 31800... [2024-08-05 09:17:00,249][00035] Num frames 31900... [2024-08-05 09:17:00,480][00035] Num frames 32000... [2024-08-05 09:17:00,696][00035] Num frames 32100... [2024-08-05 09:17:00,910][00035] Num frames 32200... [2024-08-05 09:17:01,122][00035] Num frames 32300... [2024-08-05 09:17:01,345][00035] Num frames 32400... [2024-08-05 09:17:01,565][00035] Num frames 32500... [2024-08-05 09:17:01,785][00035] Num frames 32600... [2024-08-05 09:17:02,022][00035] Num frames 32700... [2024-08-05 09:17:02,242][00035] Num frames 32800... [2024-08-05 09:17:02,502][00035] Num frames 32900... [2024-08-05 09:17:02,755][00035] Num frames 33000... [2024-08-05 09:17:02,999][00035] Num frames 33100... [2024-08-05 09:17:03,229][00035] Num frames 33200... [2024-08-05 09:17:03,458][00035] Num frames 33300... [2024-08-05 09:17:03,681][00035] Num frames 33400... [2024-08-05 09:17:03,903][00035] Num frames 33500... [2024-08-05 09:17:04,115][00035] DAMAGECOUNT value on done: 1117.0 [2024-08-05 09:17:04,116][00035] Sum rewards: 7.877, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.560', 'AMMO4': '-0.087', 'AMMO2': '-0.017', 'AMMO5': '0.003', 'ARMOR': '0.036', 'WEAPON5': '0.100', 'AMMO3': '0.144', 'weapon5': '0.226', 'HITCOUNT': '0.250', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.452', 'FRAGCOUNT': '4.000', 'weapon2': '5.770', 'weapon3': '7.560'} [2024-08-05 09:17:04,178][00035] Avg episode rewards: #0: 5.939, true rewards: #0: 2.500 [2024-08-05 09:17:04,179][00035] Avg episode reward: 5.939, avg true_objective: 2.500 [2024-08-05 09:18:46,991][00035] Replay video saved to /kaggle/working/train_dir/default_experiment/replay.mp4! [2024-08-05 09:19:25,883][00035] Loading existing experiment configuration from /kaggle/working/train_dir/default_experiment/config.json [2024-08-05 09:19:25,884][00035] Overriding arg 'num_workers' with value 1 passed from command line [2024-08-05 09:19:25,885][00035] Adding new argument 'no_render'=True that is not in the saved config file! [2024-08-05 09:19:25,886][00035] Adding new argument 'save_video'=True that is not in the saved config file! [2024-08-05 09:19:25,887][00035] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! [2024-08-05 09:19:25,888][00035] Adding new argument 'video_name'=None that is not in the saved config file! [2024-08-05 09:19:25,889][00035] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! [2024-08-05 09:19:25,890][00035] Adding new argument 'max_num_episodes'=4 that is not in the saved config file! [2024-08-05 09:19:25,890][00035] Adding new argument 'push_to_hub'=True that is not in the saved config file! [2024-08-05 09:19:25,891][00035] Adding new argument 'hf_repository'='Mojitrk/deathmatch-4-4' that is not in the saved config file! [2024-08-05 09:19:25,892][00035] Adding new argument 'policy_index'=0 that is not in the saved config file! [2024-08-05 09:19:25,893][00035] Adding new argument 'eval_deterministic'=False that is not in the saved config file! [2024-08-05 09:19:25,894][00035] Adding new argument 'train_script'=None that is not in the saved config file! [2024-08-05 09:19:25,895][00035] Adding new argument 'enjoy_script'=None that is not in the saved config file! [2024-08-05 09:19:25,896][00035] Using frameskip 1 and render_action_repeat=4 for evaluation [2024-08-05 09:19:25,927][00035] Port 40300 is available [2024-08-05 09:19:25,928][00035] Using port 40300 [2024-08-05 09:19:25,930][00035] RunningMeanStd input shape: (23,) [2024-08-05 09:19:25,932][00035] RunningMeanStd input shape: (3, 72, 128) [2024-08-05 09:19:25,933][00035] RunningMeanStd input shape: (1,) [2024-08-05 09:19:25,948][00035] ConvEncoder: input_channels=3 [2024-08-05 09:19:26,000][00035] Conv encoder output size: 512 [2024-08-05 09:19:26,002][00035] Policy head output size: 640 [2024-08-05 09:19:26,032][00035] Loading state from checkpoint /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001222_10010624.pth... [2024-08-05 09:19:26,071][00035] Using port 40300 on host... [2024-08-05 09:19:26,438][00035] Initialized w:0 v:0 player:0 [2024-08-05 09:19:26,718][00035] Num frames 100... [2024-08-05 09:19:26,951][00035] Num frames 200... [2024-08-05 09:19:27,176][00035] Num frames 300... [2024-08-05 09:19:27,395][00035] Num frames 400... [2024-08-05 09:19:27,636][00035] Num frames 500... [2024-08-05 09:19:27,884][00035] Num frames 600... [2024-08-05 09:19:28,117][00035] Num frames 700... [2024-08-05 09:19:28,334][00035] Num frames 800... [2024-08-05 09:19:28,555][00035] Num frames 900... [2024-08-05 09:19:28,776][00035] Num frames 1000... [2024-08-05 09:19:29,005][00035] Num frames 1100... [2024-08-05 09:19:29,227][00035] Num frames 1200... [2024-08-05 09:19:29,444][00035] Num frames 1300... [2024-08-05 09:19:29,662][00035] Num frames 1400... [2024-08-05 09:19:29,876][00035] Num frames 1500... [2024-08-05 09:19:30,090][00035] Num frames 1600... [2024-08-05 09:19:30,316][00035] Num frames 1700... [2024-08-05 09:19:30,545][00035] Num frames 1800... [2024-08-05 09:19:30,766][00035] Num frames 1900... [2024-08-05 09:19:30,985][00035] Num frames 2000... [2024-08-05 09:19:31,210][00035] Num frames 2100... [2024-08-05 09:19:31,428][00035] Num frames 2200... [2024-08-05 09:19:31,649][00035] Num frames 2300... [2024-08-05 09:19:31,871][00035] Num frames 2400... [2024-08-05 09:19:32,090][00035] Num frames 2500... [2024-08-05 09:19:32,312][00035] Num frames 2600... [2024-08-05 09:19:32,533][00035] Num frames 2700... [2024-08-05 09:19:32,755][00035] Num frames 2800... [2024-08-05 09:19:32,986][00035] Num frames 2900... [2024-08-05 09:19:33,208][00035] Num frames 3000... [2024-08-05 09:19:33,427][00035] Num frames 3100... [2024-08-05 09:19:33,644][00035] Num frames 3200... [2024-08-05 09:19:33,863][00035] Num frames 3300... [2024-08-05 09:19:34,079][00035] Num frames 3400... [2024-08-05 09:19:34,299][00035] Num frames 3500... [2024-08-05 09:19:34,514][00035] Num frames 3600... [2024-08-05 09:19:34,732][00035] Num frames 3700... [2024-08-05 09:19:34,949][00035] Num frames 3800... [2024-08-05 09:19:35,170][00035] Num frames 3900... [2024-08-05 09:19:35,393][00035] Num frames 4000... [2024-08-05 09:19:35,611][00035] Num frames 4100... [2024-08-05 09:19:35,831][00035] Num frames 4200... [2024-08-05 09:19:36,048][00035] Num frames 4300... [2024-08-05 09:19:36,268][00035] Num frames 4400... [2024-08-05 09:19:36,507][00035] Num frames 4500... [2024-08-05 09:19:36,750][00035] Num frames 4600... [2024-08-05 09:19:36,981][00035] Num frames 4700... [2024-08-05 09:19:37,202][00035] Num frames 4800... [2024-08-05 09:19:37,420][00035] Num frames 4900... [2024-08-05 09:19:37,643][00035] Num frames 5000... [2024-08-05 09:19:37,870][00035] Num frames 5100... [2024-08-05 09:19:38,087][00035] Num frames 5200... [2024-08-05 09:19:38,309][00035] Num frames 5300... [2024-08-05 09:19:38,545][00035] Num frames 5400... [2024-08-05 09:19:38,789][00035] Num frames 5500... [2024-08-05 09:19:39,011][00035] Num frames 5600... [2024-08-05 09:19:39,237][00035] Num frames 5700... [2024-08-05 09:19:39,463][00035] Num frames 5800... [2024-08-05 09:19:39,693][00035] Num frames 5900... [2024-08-05 09:19:39,927][00035] Num frames 6000... [2024-08-05 09:19:40,161][00035] Num frames 6100... [2024-08-05 09:19:40,380][00035] Num frames 6200... [2024-08-05 09:19:40,607][00035] Num frames 6300... [2024-08-05 09:19:40,828][00035] Num frames 6400... [2024-08-05 09:19:41,044][00035] Num frames 6500... [2024-08-05 09:19:41,276][00035] Num frames 6600... [2024-08-05 09:19:41,498][00035] Num frames 6700... [2024-08-05 09:19:41,718][00035] Num frames 6800... [2024-08-05 09:19:41,978][00035] Num frames 6900... [2024-08-05 09:19:42,251][00035] Num frames 7000... [2024-08-05 09:19:42,495][00035] Num frames 7100... [2024-08-05 09:19:42,749][00035] Num frames 7200... [2024-08-05 09:19:42,980][00035] Num frames 7300... [2024-08-05 09:19:43,202][00035] Num frames 7400... [2024-08-05 09:19:43,432][00035] Num frames 7500... [2024-08-05 09:19:43,666][00035] Num frames 7600... [2024-08-05 09:19:43,905][00035] Num frames 7700... [2024-08-05 09:19:44,141][00035] Num frames 7800... [2024-08-05 09:19:44,367][00035] Num frames 7900... [2024-08-05 09:19:44,597][00035] Num frames 8000... [2024-08-05 09:19:44,820][00035] Num frames 8100... [2024-08-05 09:19:45,041][00035] Num frames 8200... [2024-08-05 09:19:45,277][00035] Num frames 8300... [2024-08-05 09:19:45,502][00035] DAMAGECOUNT value on done: 188.0 [2024-08-05 09:19:45,504][00035] Sum rewards: 4.563, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.900', 'AMMO4': '-0.085', 'AMMO2': '-0.017', 'AMMO5': '0.005', 'ARMOR': '0.092', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.168', 'HITCOUNT': '0.170', 'DAMAGECOUNT': '0.564', 'weapon4': '0.674', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon2': '6.568', 'weapon3': '7.774'} [2024-08-05 09:19:45,567][00035] Avg episode rewards: #0: 4.563, true rewards: #0: 1.000 [2024-08-05 09:19:45,568][00035] Avg episode reward: 4.563, avg true_objective: 1.000 [2024-08-05 09:19:45,574][00035] Num frames 8400... [2024-08-05 09:19:45,796][00035] Num frames 8500... [2024-08-05 09:19:46,023][00035] Num frames 8600... [2024-08-05 09:19:46,246][00035] Num frames 8700... [2024-08-05 09:19:46,473][00035] Num frames 8800... [2024-08-05 09:19:46,731][00035] Num frames 8900... [2024-08-05 09:19:46,947][00035] Num frames 9000... [2024-08-05 09:19:47,166][00035] Num frames 9100... [2024-08-05 09:19:47,387][00035] Num frames 9200... [2024-08-05 09:19:47,627][00035] Num frames 9300... [2024-08-05 09:19:47,856][00035] Num frames 9400... [2024-08-05 09:19:48,088][00035] Num frames 9500... [2024-08-05 09:19:48,321][00035] Num frames 9600... [2024-08-05 09:19:48,564][00035] Num frames 9700... [2024-08-05 09:19:48,803][00035] Num frames 9800... [2024-08-05 09:19:49,031][00035] Num frames 9900... [2024-08-05 09:19:49,257][00035] Num frames 10000... [2024-08-05 09:19:49,480][00035] Num frames 10100... [2024-08-05 09:19:49,714][00035] Num frames 10200... [2024-08-05 09:19:49,950][00035] Num frames 10300... [2024-08-05 09:19:50,181][00035] Num frames 10400... [2024-08-05 09:19:50,406][00035] Num frames 10500... [2024-08-05 09:19:50,642][00035] Num frames 10600... [2024-08-05 09:19:50,870][00035] Num frames 10700... [2024-08-05 09:19:51,104][00035] Num frames 10800... [2024-08-05 09:19:51,337][00035] Num frames 10900... [2024-08-05 09:19:51,573][00035] Num frames 11000... [2024-08-05 09:19:51,805][00035] Num frames 11100... [2024-08-05 09:19:52,034][00035] Num frames 11200... [2024-08-05 09:19:52,262][00035] Num frames 11300... [2024-08-05 09:19:52,496][00035] Num frames 11400... [2024-08-05 09:19:52,741][00035] Num frames 11500... [2024-08-05 09:19:52,976][00035] Num frames 11600... [2024-08-05 09:19:53,202][00035] Num frames 11700... [2024-08-05 09:19:53,420][00035] Num frames 11800... [2024-08-05 09:19:53,641][00035] Num frames 11900... [2024-08-05 09:19:53,868][00035] Num frames 12000... [2024-08-05 09:19:54,102][00035] Num frames 12100... [2024-08-05 09:19:54,327][00035] Num frames 12200... [2024-08-05 09:19:54,542][00035] Num frames 12300... [2024-08-05 09:19:54,758][00035] Num frames 12400... [2024-08-05 09:19:54,975][00035] Num frames 12500... [2024-08-05 09:19:55,193][00035] Num frames 12600... [2024-08-05 09:19:55,412][00035] Num frames 12700... [2024-08-05 09:19:55,637][00035] Num frames 12800... [2024-08-05 09:19:55,865][00035] Num frames 12900... [2024-08-05 09:19:56,081][00035] Num frames 13000... [2024-08-05 09:19:56,305][00035] Num frames 13100... [2024-08-05 09:19:56,537][00035] Num frames 13200... [2024-08-05 09:19:56,794][00035] Num frames 13300... [2024-08-05 09:19:57,023][00035] Num frames 13400... [2024-08-05 09:19:57,257][00035] Num frames 13500... [2024-08-05 09:19:57,498][00035] Num frames 13600... [2024-08-05 09:19:57,738][00035] Num frames 13700... [2024-08-05 09:19:57,968][00035] Num frames 13800... [2024-08-05 09:19:58,193][00035] Num frames 13900... [2024-08-05 09:19:58,416][00035] Num frames 14000... [2024-08-05 09:19:58,636][00035] Num frames 14100... [2024-08-05 09:19:58,856][00035] Num frames 14200... [2024-08-05 09:19:59,073][00035] Num frames 14300... [2024-08-05 09:19:59,286][00035] Num frames 14400... [2024-08-05 09:19:59,505][00035] Num frames 14500... [2024-08-05 09:19:59,735][00035] Num frames 14600... [2024-08-05 09:19:59,969][00035] Num frames 14700... [2024-08-05 09:20:00,201][00035] Num frames 14800... [2024-08-05 09:20:00,448][00035] Num frames 14900... [2024-08-05 09:20:00,678][00035] Num frames 15000... [2024-08-05 09:20:00,902][00035] Num frames 15100... [2024-08-05 09:20:01,125][00035] Num frames 15200... [2024-08-05 09:20:01,352][00035] Num frames 15300... [2024-08-05 09:20:01,573][00035] Num frames 15400... [2024-08-05 09:20:01,801][00035] Num frames 15500... [2024-08-05 09:20:02,035][00035] Num frames 15600... [2024-08-05 09:20:02,269][00035] Num frames 15700... [2024-08-05 09:20:02,517][00035] Num frames 15800... [2024-08-05 09:20:02,745][00035] Num frames 15900... [2024-08-05 09:20:02,972][00035] Num frames 16000... [2024-08-05 09:20:03,202][00035] Num frames 16100... [2024-08-05 09:20:03,430][00035] Num frames 16200... [2024-08-05 09:20:03,650][00035] Num frames 16300... [2024-08-05 09:20:03,881][00035] Num frames 16400... [2024-08-05 09:20:04,106][00035] Num frames 16500... [2024-08-05 09:20:04,326][00035] Num frames 16600... [2024-08-05 09:20:04,540][00035] Num frames 16700... [2024-08-05 09:20:04,758][00035] DAMAGECOUNT value on done: 418.0 [2024-08-05 09:20:04,759][00035] Sum rewards: 6.370, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.540', 'AMMO4': '-0.130', 'AMMO2': '-0.026', 'AMMO5': '0.005', 'ARMOR': '0.040', 'weapon5': '0.082', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.119', 'HITCOUNT': '0.200', 'weapon4': '0.626', 'DAMAGECOUNT': '0.690', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon3': '6.282', 'weapon2': '9.022'} [2024-08-05 09:20:04,821][00035] Avg episode rewards: #0: 5.466, true rewards: #0: 1.000 [2024-08-05 09:20:04,823][00035] Avg episode reward: 5.466, avg true_objective: 1.000 [2024-08-05 09:20:04,831][00035] Num frames 16800... [2024-08-05 09:20:05,054][00035] Num frames 16900... [2024-08-05 09:20:05,274][00035] Num frames 17000... [2024-08-05 09:20:05,505][00035] Num frames 17100... [2024-08-05 09:20:05,726][00035] Num frames 17200... [2024-08-05 09:20:05,952][00035] Num frames 17300... [2024-08-05 09:20:06,192][00035] Num frames 17400... [2024-08-05 09:20:06,427][00035] Num frames 17500... [2024-08-05 09:20:06,671][00035] Num frames 17600... [2024-08-05 09:20:06,896][00035] Num frames 17700... [2024-08-05 09:20:07,118][00035] Num frames 17800... [2024-08-05 09:20:07,341][00035] Num frames 17900... [2024-08-05 09:20:07,556][00035] Num frames 18000... [2024-08-05 09:20:07,778][00035] Num frames 18100... [2024-08-05 09:20:08,004][00035] Num frames 18200... [2024-08-05 09:20:08,240][00035] Num frames 18300... [2024-08-05 09:20:08,477][00035] Num frames 18400... [2024-08-05 09:20:08,711][00035] Num frames 18500... [2024-08-05 09:20:08,938][00035] Num frames 18600... [2024-08-05 09:20:09,165][00035] Num frames 18700... [2024-08-05 09:20:09,389][00035] Num frames 18800... [2024-08-05 09:20:09,604][00035] Num frames 18900... [2024-08-05 09:20:09,824][00035] Num frames 19000... [2024-08-05 09:20:10,045][00035] Num frames 19100... [2024-08-05 09:20:10,276][00035] Num frames 19200... [2024-08-05 09:20:10,509][00035] Num frames 19300... [2024-08-05 09:20:10,730][00035] Num frames 19400... [2024-08-05 09:20:10,957][00035] Num frames 19500... [2024-08-05 09:20:11,184][00035] Num frames 19600... [2024-08-05 09:20:11,414][00035] Num frames 19700... [2024-08-05 09:20:11,638][00035] Num frames 19800... [2024-08-05 09:20:11,872][00035] Num frames 19900... [2024-08-05 09:20:12,111][00035] Num frames 20000... [2024-08-05 09:20:12,340][00035] Num frames 20100... [2024-08-05 09:20:12,567][00035] Num frames 20200... [2024-08-05 09:20:12,808][00035] Num frames 20300... [2024-08-05 09:20:13,037][00035] Num frames 20400... [2024-08-05 09:20:13,275][00035] Num frames 20500... [2024-08-05 09:20:13,540][00035] Num frames 20600... [2024-08-05 09:20:13,793][00035] Num frames 20700... [2024-08-05 09:20:14,029][00035] Num frames 20800... [2024-08-05 09:20:14,269][00035] Num frames 20900... [2024-08-05 09:20:14,518][00035] Num frames 21000... [2024-08-05 09:20:14,752][00035] Num frames 21100... [2024-08-05 09:20:14,977][00035] Num frames 21200... [2024-08-05 09:20:15,199][00035] Num frames 21300... [2024-08-05 09:20:15,427][00035] Num frames 21400... [2024-08-05 09:20:15,648][00035] Num frames 21500... [2024-08-05 09:20:15,876][00035] Num frames 21600... [2024-08-05 09:20:16,103][00035] Num frames 21700... [2024-08-05 09:20:16,325][00035] Num frames 21800... [2024-08-05 09:20:16,553][00035] Num frames 21900... [2024-08-05 09:20:16,798][00035] Num frames 22000... [2024-08-05 09:20:17,020][00035] Num frames 22100... [2024-08-05 09:20:17,239][00035] Num frames 22200... [2024-08-05 09:20:17,465][00035] Num frames 22300... [2024-08-05 09:20:17,697][00035] Num frames 22400... [2024-08-05 09:20:17,922][00035] Num frames 22500... [2024-08-05 09:20:18,144][00035] Num frames 22600... [2024-08-05 09:20:18,368][00035] Num frames 22700... [2024-08-05 09:20:18,595][00035] Num frames 22800... [2024-08-05 09:20:18,825][00035] Num frames 22900... [2024-08-05 09:20:19,050][00035] Num frames 23000... [2024-08-05 09:20:19,278][00035] Num frames 23100... [2024-08-05 09:20:19,506][00035] Num frames 23200... [2024-08-05 09:20:19,733][00035] Num frames 23300... [2024-08-05 09:20:19,962][00035] Num frames 23400... [2024-08-05 09:20:20,180][00035] Num frames 23500... [2024-08-05 09:20:20,399][00035] Num frames 23600... [2024-08-05 09:20:20,617][00035] Num frames 23700... [2024-08-05 09:20:20,839][00035] Num frames 23800... [2024-08-05 09:20:21,055][00035] Num frames 23900... [2024-08-05 09:20:21,280][00035] Num frames 24000... [2024-08-05 09:20:21,499][00035] Num frames 24100... [2024-08-05 09:20:21,714][00035] Num frames 24200... [2024-08-05 09:20:21,924][00035] Num frames 24300... [2024-08-05 09:20:22,136][00035] Num frames 24400... [2024-08-05 09:20:22,362][00035] Num frames 24500... [2024-08-05 09:20:22,583][00035] Num frames 24600... [2024-08-05 09:20:22,798][00035] Num frames 24700... [2024-08-05 09:20:23,016][00035] Num frames 24800... [2024-08-05 09:20:23,236][00035] Num frames 24900... [2024-08-05 09:20:23,461][00035] Num frames 25000... [2024-08-05 09:20:23,683][00035] Num frames 25100... [2024-08-05 09:20:23,897][00035] DAMAGECOUNT value on done: 913.0 [2024-08-05 09:20:23,898][00035] Sum rewards: 4.071, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.460', 'AMMO4': '-0.102', 'AMMO2': '-0.020', 'AMMO5': '0.005', 'WEAPON1': '0.020', 'ARMOR': '0.096', 'WEAPON5': '0.100', 'AMMO3': '0.185', 'HITCOUNT': '0.340', 'weapon5': '0.594', 'WEAPON3': '1.200', 'DAMAGECOUNT': '1.485', 'FRAGCOUNT': '4.000', 'weapon3': '5.262', 'weapon2': '6.616'} [2024-08-05 09:20:23,960][00035] Avg episode rewards: #0: 5.001, true rewards: #0: 2.000 [2024-08-05 09:20:23,961][00035] Avg episode reward: 5.001, avg true_objective: 2.000 [2024-08-05 09:20:23,970][00035] Num frames 25200... [2024-08-05 09:20:24,194][00035] Num frames 25300... [2024-08-05 09:20:24,415][00035] Num frames 25400... [2024-08-05 09:20:24,632][00035] Num frames 25500... [2024-08-05 09:20:24,848][00035] Num frames 25600... [2024-08-05 09:20:25,066][00035] Num frames 25700... [2024-08-05 09:20:25,282][00035] Num frames 25800... [2024-08-05 09:20:25,500][00035] Num frames 25900... [2024-08-05 09:20:25,722][00035] Num frames 26000... [2024-08-05 09:20:25,942][00035] Num frames 26100... [2024-08-05 09:20:26,160][00035] Num frames 26200... [2024-08-05 09:20:26,383][00035] Num frames 26300... [2024-08-05 09:20:26,622][00035] Num frames 26400... [2024-08-05 09:20:26,866][00035] Num frames 26500... [2024-08-05 09:20:27,086][00035] Num frames 26600... [2024-08-05 09:20:27,303][00035] Num frames 26700... [2024-08-05 09:20:27,526][00035] Num frames 26800... [2024-08-05 09:20:27,752][00035] Num frames 26900... [2024-08-05 09:20:27,967][00035] Num frames 27000... [2024-08-05 09:20:28,186][00035] Num frames 27100... [2024-08-05 09:20:28,421][00035] Num frames 27200... [2024-08-05 09:20:28,655][00035] Num frames 27300... [2024-08-05 09:20:28,883][00035] Num frames 27400... [2024-08-05 09:20:29,104][00035] Num frames 27500... [2024-08-05 09:20:29,325][00035] Num frames 27600... [2024-08-05 09:20:29,552][00035] Num frames 27700... [2024-08-05 09:20:29,780][00035] Num frames 27800... [2024-08-05 09:20:30,009][00035] Num frames 27900... [2024-08-05 09:20:30,242][00035] Num frames 28000... [2024-08-05 09:20:30,489][00035] Num frames 28100... [2024-08-05 09:20:30,712][00035] Num frames 28200... [2024-08-05 09:20:30,943][00035] Num frames 28300... [2024-08-05 09:20:31,175][00035] Num frames 28400... [2024-08-05 09:20:31,409][00035] Num frames 28500... [2024-08-05 09:20:31,646][00035] Num frames 28600... [2024-08-05 09:20:31,873][00035] Num frames 28700... [2024-08-05 09:20:32,104][00035] Num frames 28800... [2024-08-05 09:20:32,333][00035] Num frames 28900... [2024-08-05 09:20:32,556][00035] Num frames 29000... [2024-08-05 09:20:32,778][00035] Num frames 29100... [2024-08-05 09:20:33,001][00035] Num frames 29200... [2024-08-05 09:20:33,227][00035] Num frames 29300... [2024-08-05 09:20:33,454][00035] Num frames 29400... [2024-08-05 09:20:33,678][00035] Num frames 29500... [2024-08-05 09:20:33,903][00035] Num frames 29600... [2024-08-05 09:20:34,131][00035] Num frames 29700... [2024-08-05 09:20:34,357][00035] Num frames 29800... [2024-08-05 09:20:34,586][00035] Num frames 29900... [2024-08-05 09:20:34,810][00035] Num frames 30000... [2024-08-05 09:20:35,036][00035] Num frames 30100... [2024-08-05 09:20:35,268][00035] Num frames 30200... [2024-08-05 09:20:35,496][00035] Num frames 30300... [2024-08-05 09:20:35,724][00035] Num frames 30400... [2024-08-05 09:20:35,954][00035] Num frames 30500... [2024-08-05 09:20:36,179][00035] Num frames 30600... [2024-08-05 09:20:36,412][00035] Num frames 30700... [2024-08-05 09:20:36,672][00035] Num frames 30800... [2024-08-05 09:20:36,894][00035] Num frames 30900... [2024-08-05 09:20:37,113][00035] Num frames 31000... [2024-08-05 09:20:37,328][00035] Num frames 31100... [2024-08-05 09:20:37,553][00035] Num frames 31200... [2024-08-05 09:20:37,784][00035] Num frames 31300... [2024-08-05 09:20:38,014][00035] Num frames 31400... [2024-08-05 09:20:38,241][00035] Num frames 31500... [2024-08-05 09:20:38,476][00035] Num frames 31600... [2024-08-05 09:20:38,731][00035] Num frames 31700... [2024-08-05 09:20:38,982][00035] Num frames 31800... [2024-08-05 09:20:39,219][00035] Num frames 31900... [2024-08-05 09:20:39,468][00035] Num frames 32000... [2024-08-05 09:20:39,700][00035] Num frames 32100... [2024-08-05 09:20:39,933][00035] Num frames 32200... [2024-08-05 09:20:40,159][00035] Num frames 32300... [2024-08-05 09:20:40,387][00035] Num frames 32400... [2024-08-05 09:20:40,609][00035] Num frames 32500... [2024-08-05 09:20:40,834][00035] Num frames 32600... [2024-08-05 09:20:41,054][00035] Num frames 32700... [2024-08-05 09:20:41,282][00035] Num frames 32800... [2024-08-05 09:20:41,508][00035] Num frames 32900... [2024-08-05 09:20:41,730][00035] Num frames 33000... [2024-08-05 09:20:41,952][00035] Num frames 33100... [2024-08-05 09:20:42,175][00035] Num frames 33200... [2024-08-05 09:20:42,402][00035] Num frames 33300... [2024-08-05 09:20:42,626][00035] Num frames 33400... [2024-08-05 09:20:42,849][00035] Num frames 33500... [2024-08-05 09:20:43,057][00035] DAMAGECOUNT value on done: 1080.0 [2024-08-05 09:20:43,058][00035] Sum rewards: 2.276, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.460', 'AMMO4': '-0.093', 'AMMO2': '-0.019', 'AMMO5': '0.005', 'ARMOR': '0.058', 'HITCOUNT': '0.170', 'AMMO3': '0.192', 'DAMAGECOUNT': '0.501', 'WEAPON3': '1.200', 'FRAGCOUNT': '2.000', 'weapon2': '6.490', 'weapon3': '7.482'} [2024-08-05 09:20:43,120][00035] Avg episode rewards: #0: 4.320, true rewards: #0: 2.000 [2024-08-05 09:20:43,121][00035] Avg episode reward: 4.320, avg true_objective: 2.000 [2024-08-05 09:22:26,125][00035] Replay video saved to /kaggle/working/train_dir/default_experiment/replay.mp4!