| [2024-11-06 21:37:23,671][00300] Saving configuration to /content/train_dir/default_experiment/config.json... | |
| [2024-11-06 21:37:23,674][00300] Rollout worker 0 uses device cpu | |
| [2024-11-06 21:37:23,676][00300] Rollout worker 1 uses device cpu | |
| [2024-11-06 21:37:23,680][00300] Rollout worker 2 uses device cpu | |
| [2024-11-06 21:37:23,682][00300] Rollout worker 3 uses device cpu | |
| [2024-11-06 21:37:23,683][00300] Rollout worker 4 uses device cpu | |
| [2024-11-06 21:37:23,684][00300] Rollout worker 5 uses device cpu | |
| [2024-11-06 21:37:23,685][00300] Rollout worker 6 uses device cpu | |
| [2024-11-06 21:37:23,686][00300] Rollout worker 7 uses device cpu | |
| [2024-11-06 21:37:23,839][00300] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-11-06 21:37:23,841][00300] InferenceWorker_p0-w0: min num requests: 2 | |
| [2024-11-06 21:37:23,876][00300] Starting all processes... | |
| [2024-11-06 21:37:23,878][00300] Starting process learner_proc0 | |
| [2024-11-06 21:37:23,926][00300] Starting all processes... | |
| [2024-11-06 21:37:23,934][00300] Starting process inference_proc0-0 | |
| [2024-11-06 21:37:23,936][00300] Starting process rollout_proc1 | |
| [2024-11-06 21:37:23,935][00300] Starting process rollout_proc0 | |
| [2024-11-06 21:37:23,937][00300] Starting process rollout_proc2 | |
| [2024-11-06 21:37:23,937][00300] Starting process rollout_proc3 | |
| [2024-11-06 21:37:23,937][00300] Starting process rollout_proc4 | |
| [2024-11-06 21:37:23,937][00300] Starting process rollout_proc5 | |
| [2024-11-06 21:37:23,937][00300] Starting process rollout_proc6 | |
| [2024-11-06 21:37:23,937][00300] Starting process rollout_proc7 | |
| [2024-11-06 21:37:34,765][03124] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-11-06 21:37:34,771][03124] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 | |
| [2024-11-06 21:37:34,864][03124] Num visible devices: 1 | |
| [2024-11-06 21:37:34,942][03126] Worker 0 uses CPU cores [0] | |
| [2024-11-06 21:37:35,001][03136] Worker 7 uses CPU cores [1] | |
| [2024-11-06 21:37:35,089][03111] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-11-06 21:37:35,089][03111] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 | |
| [2024-11-06 21:37:35,130][03133] Worker 3 uses CPU cores [1] | |
| [2024-11-06 21:37:35,139][03111] Num visible devices: 1 | |
| [2024-11-06 21:37:35,162][03111] Starting seed is not provided | |
| [2024-11-06 21:37:35,163][03111] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-11-06 21:37:35,163][03111] Initializing actor-critic model on device cuda:0 | |
| [2024-11-06 21:37:35,163][03111] RunningMeanStd input shape: (3, 72, 128) | |
| [2024-11-06 21:37:35,164][03111] RunningMeanStd input shape: (1,) | |
| [2024-11-06 21:37:35,162][03125] Worker 1 uses CPU cores [1] | |
| [2024-11-06 21:37:35,217][03135] Worker 6 uses CPU cores [0] | |
| [2024-11-06 21:37:35,214][03111] ConvEncoder: input_channels=3 | |
| [2024-11-06 21:37:35,281][03132] Worker 5 uses CPU cores [1] | |
| [2024-11-06 21:37:35,323][03134] Worker 4 uses CPU cores [0] | |
| [2024-11-06 21:37:35,352][03129] Worker 2 uses CPU cores [0] | |
| [2024-11-06 21:37:35,473][03111] Conv encoder output size: 512 | |
| [2024-11-06 21:37:35,473][03111] Policy head output size: 512 | |
| [2024-11-06 21:37:35,492][03111] Created Actor Critic model with architecture: | |
| [2024-11-06 21:37:35,492][03111] ActorCriticSharedWeights( | |
| (obs_normalizer): ObservationNormalizer( | |
| (running_mean_std): RunningMeanStdDictInPlace( | |
| (running_mean_std): ModuleDict( | |
| (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=ELU) | |
| (2): RecursiveScriptModule(original_name=Conv2d) | |
| (3): RecursiveScriptModule(original_name=ELU) | |
| (4): RecursiveScriptModule(original_name=Conv2d) | |
| (5): RecursiveScriptModule(original_name=ELU) | |
| ) | |
| (mlp_layers): RecursiveScriptModule( | |
| original_name=Sequential | |
| (0): RecursiveScriptModule(original_name=Linear) | |
| (1): RecursiveScriptModule(original_name=ELU) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (core): ModelCoreRNN( | |
| (core): GRU(512, 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=5, bias=True) | |
| ) | |
| ) | |
| [2024-11-06 21:37:39,529][03111] Using optimizer <class 'torch.optim.adam.Adam'> | |
| [2024-11-06 21:37:39,530][03111] No checkpoints found | |
| [2024-11-06 21:37:39,530][03111] Did not load from checkpoint, starting from scratch! | |
| [2024-11-06 21:37:39,530][03111] Initialized policy 0 weights for model version 0 | |
| [2024-11-06 21:37:39,534][03111] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-11-06 21:37:39,544][03111] LearnerWorker_p0 finished initialization! | |
| [2024-11-06 21:37:39,653][03124] RunningMeanStd input shape: (3, 72, 128) | |
| [2024-11-06 21:37:39,655][03124] RunningMeanStd input shape: (1,) | |
| [2024-11-06 21:37:39,671][03124] ConvEncoder: input_channels=3 | |
| [2024-11-06 21:37:39,775][03124] Conv encoder output size: 512 | |
| [2024-11-06 21:37:39,776][03124] Policy head output size: 512 | |
| [2024-11-06 21:37:40,414][00300] 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) | |
| [2024-11-06 21:37:41,666][00300] Inference worker 0-0 is ready! | |
| [2024-11-06 21:37:41,669][00300] All inference workers are ready! Signal rollout workers to start! | |
| [2024-11-06 21:37:41,853][03129] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-11-06 21:37:41,850][03126] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-11-06 21:37:41,874][03135] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-11-06 21:37:41,890][03134] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-11-06 21:37:41,951][03125] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-11-06 21:37:41,953][03133] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-11-06 21:37:41,961][03136] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-11-06 21:37:41,966][03132] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-11-06 21:37:43,833][00300] Heartbeat connected on Batcher_0 | |
| [2024-11-06 21:37:43,837][00300] Heartbeat connected on LearnerWorker_p0 | |
| [2024-11-06 21:37:43,893][03125] Decorrelating experience for 0 frames... | |
| [2024-11-06 21:37:43,895][00300] Heartbeat connected on InferenceWorker_p0-w0 | |
| [2024-11-06 21:37:43,897][03126] Decorrelating experience for 0 frames... | |
| [2024-11-06 21:37:43,894][03133] Decorrelating experience for 0 frames... | |
| [2024-11-06 21:37:43,903][03129] Decorrelating experience for 0 frames... | |
| [2024-11-06 21:37:43,905][03135] Decorrelating experience for 0 frames... | |
| [2024-11-06 21:37:43,896][03134] Decorrelating experience for 0 frames... | |
| [2024-11-06 21:37:45,050][03135] Decorrelating experience for 32 frames... | |
| [2024-11-06 21:37:45,051][03129] Decorrelating experience for 32 frames... | |
| [2024-11-06 21:37:45,414][00300] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2024-11-06 21:37:45,753][03133] Decorrelating experience for 32 frames... | |
| [2024-11-06 21:37:45,752][03132] Decorrelating experience for 0 frames... | |
| [2024-11-06 21:37:45,766][03125] Decorrelating experience for 32 frames... | |
| [2024-11-06 21:37:45,827][03136] Decorrelating experience for 0 frames... | |
| [2024-11-06 21:37:46,088][03134] Decorrelating experience for 32 frames... | |
| [2024-11-06 21:37:46,290][03129] Decorrelating experience for 64 frames... | |
| [2024-11-06 21:37:46,631][03132] Decorrelating experience for 32 frames... | |
| [2024-11-06 21:37:46,735][03133] Decorrelating experience for 64 frames... | |
| [2024-11-06 21:37:47,023][03126] Decorrelating experience for 32 frames... | |
| [2024-11-06 21:37:47,419][03135] Decorrelating experience for 64 frames... | |
| [2024-11-06 21:37:47,598][03132] Decorrelating experience for 64 frames... | |
| [2024-11-06 21:37:47,709][03129] Decorrelating experience for 96 frames... | |
| [2024-11-06 21:37:47,732][03133] Decorrelating experience for 96 frames... | |
| [2024-11-06 21:37:47,921][00300] Heartbeat connected on RolloutWorker_w3 | |
| [2024-11-06 21:37:47,943][00300] Heartbeat connected on RolloutWorker_w2 | |
| [2024-11-06 21:37:48,521][03136] Decorrelating experience for 32 frames... | |
| [2024-11-06 21:37:48,579][03134] Decorrelating experience for 64 frames... | |
| [2024-11-06 21:37:48,737][03126] Decorrelating experience for 64 frames... | |
| [2024-11-06 21:37:48,855][03132] Decorrelating experience for 96 frames... | |
| [2024-11-06 21:37:49,164][00300] Heartbeat connected on RolloutWorker_w5 | |
| [2024-11-06 21:37:49,241][03135] Decorrelating experience for 96 frames... | |
| [2024-11-06 21:37:49,466][00300] Heartbeat connected on RolloutWorker_w6 | |
| [2024-11-06 21:37:49,910][03125] Decorrelating experience for 64 frames... | |
| [2024-11-06 21:37:49,918][03134] Decorrelating experience for 96 frames... | |
| [2024-11-06 21:37:50,052][03136] Decorrelating experience for 64 frames... | |
| [2024-11-06 21:37:50,072][03126] Decorrelating experience for 96 frames... | |
| [2024-11-06 21:37:50,104][00300] Heartbeat connected on RolloutWorker_w4 | |
| [2024-11-06 21:37:50,196][00300] Heartbeat connected on RolloutWorker_w0 | |
| [2024-11-06 21:37:50,414][00300] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2024-11-06 21:37:50,472][03125] Decorrelating experience for 96 frames... | |
| [2024-11-06 21:37:50,570][00300] Heartbeat connected on RolloutWorker_w1 | |
| [2024-11-06 21:37:51,362][03136] Decorrelating experience for 96 frames... | |
| [2024-11-06 21:37:51,933][00300] Heartbeat connected on RolloutWorker_w7 | |
| [2024-11-06 21:37:53,782][03111] Signal inference workers to stop experience collection... | |
| [2024-11-06 21:37:53,802][03124] InferenceWorker_p0-w0: stopping experience collection | |
| [2024-11-06 21:37:55,414][00300] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 174.4. Samples: 2616. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2024-11-06 21:37:55,421][00300] Avg episode reward: [(0, '2.352')] | |
| [2024-11-06 21:37:55,885][03111] Signal inference workers to resume experience collection... | |
| [2024-11-06 21:37:55,886][03124] InferenceWorker_p0-w0: resuming experience collection | |
| [2024-11-06 21:38:00,420][00300] Fps is (10 sec: 1637.5, 60 sec: 819.0, 300 sec: 819.0). Total num frames: 16384. Throughput: 0: 223.7. Samples: 4476. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) | |
| [2024-11-06 21:38:00,423][00300] Avg episode reward: [(0, '3.187')] | |
| [2024-11-06 21:38:05,414][00300] Fps is (10 sec: 3276.8, 60 sec: 1310.7, 300 sec: 1310.7). Total num frames: 32768. Throughput: 0: 271.9. Samples: 6798. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:38:05,421][00300] Avg episode reward: [(0, '3.826')] | |
| [2024-11-06 21:38:06,565][03124] Updated weights for policy 0, policy_version 10 (0.0018) | |
| [2024-11-06 21:38:10,414][00300] Fps is (10 sec: 3688.5, 60 sec: 1774.9, 300 sec: 1774.9). Total num frames: 53248. Throughput: 0: 409.4. Samples: 12282. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:38:10,418][00300] Avg episode reward: [(0, '4.334')] | |
| [2024-11-06 21:38:15,415][00300] Fps is (10 sec: 3276.7, 60 sec: 1872.4, 300 sec: 1872.4). Total num frames: 65536. Throughput: 0: 489.1. Samples: 17118. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-11-06 21:38:15,417][00300] Avg episode reward: [(0, '4.420')] | |
| [2024-11-06 21:38:20,414][00300] Fps is (10 sec: 2867.2, 60 sec: 2048.0, 300 sec: 2048.0). Total num frames: 81920. Throughput: 0: 472.8. Samples: 18912. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-11-06 21:38:20,417][00300] Avg episode reward: [(0, '4.304')] | |
| [2024-11-06 21:38:20,429][03124] Updated weights for policy 0, policy_version 20 (0.0030) | |
| [2024-11-06 21:38:25,414][00300] Fps is (10 sec: 3276.9, 60 sec: 2184.5, 300 sec: 2184.5). Total num frames: 98304. Throughput: 0: 523.6. Samples: 23564. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:38:25,417][00300] Avg episode reward: [(0, '4.307')] | |
| [2024-11-06 21:38:30,414][00300] Fps is (10 sec: 3686.4, 60 sec: 2375.7, 300 sec: 2375.7). Total num frames: 118784. Throughput: 0: 664.4. Samples: 29898. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:38:30,421][00300] Avg episode reward: [(0, '4.326')] | |
| [2024-11-06 21:38:30,443][03111] Saving new best policy, reward=4.326! | |
| [2024-11-06 21:38:31,746][03124] Updated weights for policy 0, policy_version 30 (0.0015) | |
| [2024-11-06 21:38:35,419][00300] Fps is (10 sec: 3275.1, 60 sec: 2382.9, 300 sec: 2382.9). Total num frames: 131072. Throughput: 0: 705.7. Samples: 31760. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-11-06 21:38:35,429][00300] Avg episode reward: [(0, '4.388')] | |
| [2024-11-06 21:38:35,434][03111] Saving new best policy, reward=4.388! | |
| [2024-11-06 21:38:40,414][00300] Fps is (10 sec: 2867.2, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 147456. Throughput: 0: 743.3. Samples: 36066. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:38:40,417][00300] Avg episode reward: [(0, '4.249')] | |
| [2024-11-06 21:38:44,052][03124] Updated weights for policy 0, policy_version 40 (0.0037) | |
| [2024-11-06 21:38:45,414][00300] Fps is (10 sec: 3688.3, 60 sec: 2798.9, 300 sec: 2583.6). Total num frames: 167936. Throughput: 0: 845.9. Samples: 42538. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-11-06 21:38:45,420][00300] Avg episode reward: [(0, '4.207')] | |
| [2024-11-06 21:38:50,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3072.0, 300 sec: 2633.1). Total num frames: 184320. Throughput: 0: 868.1. Samples: 45862. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-11-06 21:38:50,416][00300] Avg episode reward: [(0, '4.250')] | |
| [2024-11-06 21:38:55,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 2676.1). Total num frames: 200704. Throughput: 0: 841.4. Samples: 50146. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) | |
| [2024-11-06 21:38:55,421][00300] Avg episode reward: [(0, '4.294')] | |
| [2024-11-06 21:38:55,808][03124] Updated weights for policy 0, policy_version 50 (0.0028) | |
| [2024-11-06 21:39:00,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3481.9, 300 sec: 2816.0). Total num frames: 225280. Throughput: 0: 874.9. Samples: 56486. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-11-06 21:39:00,420][00300] Avg episode reward: [(0, '4.369')] | |
| [2024-11-06 21:39:04,735][03124] Updated weights for policy 0, policy_version 60 (0.0031) | |
| [2024-11-06 21:39:05,417][00300] Fps is (10 sec: 4504.5, 60 sec: 3549.7, 300 sec: 2891.2). Total num frames: 245760. Throughput: 0: 911.8. Samples: 59944. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-11-06 21:39:05,423][00300] Avg episode reward: [(0, '4.413')] | |
| [2024-11-06 21:39:05,426][03111] Saving new best policy, reward=4.413! | |
| [2024-11-06 21:39:10,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 2912.7). Total num frames: 262144. Throughput: 0: 923.7. Samples: 65130. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-11-06 21:39:10,418][00300] Avg episode reward: [(0, '4.635')] | |
| [2024-11-06 21:39:10,437][03111] Saving new best policy, reward=4.635! | |
| [2024-11-06 21:39:15,414][00300] Fps is (10 sec: 3277.6, 60 sec: 3549.9, 300 sec: 2931.9). Total num frames: 278528. Throughput: 0: 895.6. Samples: 70198. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:39:15,417][00300] Avg episode reward: [(0, '4.601')] | |
| [2024-11-06 21:39:16,547][03124] Updated weights for policy 0, policy_version 70 (0.0013) | |
| [2024-11-06 21:39:20,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3031.0). Total num frames: 303104. Throughput: 0: 930.1. Samples: 73608. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:39:20,420][00300] Avg episode reward: [(0, '4.495')] | |
| [2024-11-06 21:39:20,429][03111] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000074_303104.pth... | |
| [2024-11-06 21:39:25,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3042.7). Total num frames: 319488. Throughput: 0: 974.3. Samples: 79910. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-11-06 21:39:25,420][00300] Avg episode reward: [(0, '4.692')] | |
| [2024-11-06 21:39:25,424][03111] Saving new best policy, reward=4.692! | |
| [2024-11-06 21:39:27,504][03124] Updated weights for policy 0, policy_version 80 (0.0023) | |
| [2024-11-06 21:39:30,415][00300] Fps is (10 sec: 3276.7, 60 sec: 3618.1, 300 sec: 3053.4). Total num frames: 335872. Throughput: 0: 925.9. Samples: 84204. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:39:30,417][00300] Avg episode reward: [(0, '4.703')] | |
| [2024-11-06 21:39:30,423][03111] Saving new best policy, reward=4.703! | |
| [2024-11-06 21:39:35,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3755.0, 300 sec: 3098.7). Total num frames: 356352. Throughput: 0: 921.5. Samples: 87328. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:39:35,417][00300] Avg episode reward: [(0, '4.533')] | |
| [2024-11-06 21:39:37,634][03124] Updated weights for policy 0, policy_version 90 (0.0015) | |
| [2024-11-06 21:39:40,414][00300] Fps is (10 sec: 4505.7, 60 sec: 3891.2, 300 sec: 3174.4). Total num frames: 380928. Throughput: 0: 978.2. Samples: 94164. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) | |
| [2024-11-06 21:39:40,422][00300] Avg episode reward: [(0, '4.617')] | |
| [2024-11-06 21:39:45,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3145.7). Total num frames: 393216. Throughput: 0: 942.2. Samples: 98884. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:39:45,419][00300] Avg episode reward: [(0, '4.712')] | |
| [2024-11-06 21:39:45,427][03111] Saving new best policy, reward=4.712! | |
| [2024-11-06 21:39:49,565][03124] Updated weights for policy 0, policy_version 100 (0.0012) | |
| [2024-11-06 21:39:50,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3182.3). Total num frames: 413696. Throughput: 0: 911.3. Samples: 100948. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-11-06 21:39:50,418][00300] Avg episode reward: [(0, '4.639')] | |
| [2024-11-06 21:39:55,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3216.1). Total num frames: 434176. Throughput: 0: 950.5. Samples: 107904. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:39:55,418][00300] Avg episode reward: [(0, '4.837')] | |
| [2024-11-06 21:39:55,427][03111] Saving new best policy, reward=4.837! | |
| [2024-11-06 21:39:59,175][03124] Updated weights for policy 0, policy_version 110 (0.0019) | |
| [2024-11-06 21:40:00,418][00300] Fps is (10 sec: 3685.2, 60 sec: 3754.5, 300 sec: 3218.2). Total num frames: 450560. Throughput: 0: 967.0. Samples: 113718. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-11-06 21:40:00,423][00300] Avg episode reward: [(0, '4.723')] | |
| [2024-11-06 21:40:05,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3686.6, 300 sec: 3220.3). Total num frames: 466944. Throughput: 0: 938.3. Samples: 115830. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:40:05,416][00300] Avg episode reward: [(0, '4.616')] | |
| [2024-11-06 21:40:10,270][03124] Updated weights for policy 0, policy_version 120 (0.0012) | |
| [2024-11-06 21:40:10,415][00300] Fps is (10 sec: 4097.3, 60 sec: 3822.9, 300 sec: 3276.8). Total num frames: 491520. Throughput: 0: 931.1. Samples: 121810. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-11-06 21:40:10,416][00300] Avg episode reward: [(0, '4.533')] | |
| [2024-11-06 21:40:15,417][00300] Fps is (10 sec: 4504.2, 60 sec: 3891.0, 300 sec: 3303.2). Total num frames: 512000. Throughput: 0: 986.0. Samples: 128576. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-11-06 21:40:15,424][00300] Avg episode reward: [(0, '4.884')] | |
| [2024-11-06 21:40:15,428][03111] Saving new best policy, reward=4.884! | |
| [2024-11-06 21:40:20,416][00300] Fps is (10 sec: 3685.7, 60 sec: 3754.5, 300 sec: 3302.4). Total num frames: 528384. Throughput: 0: 966.3. Samples: 130812. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-11-06 21:40:20,423][00300] Avg episode reward: [(0, '4.803')] | |
| [2024-11-06 21:40:21,686][03124] Updated weights for policy 0, policy_version 130 (0.0014) | |
| [2024-11-06 21:40:25,414][00300] Fps is (10 sec: 3277.8, 60 sec: 3754.7, 300 sec: 3301.6). Total num frames: 544768. Throughput: 0: 919.9. Samples: 135560. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-11-06 21:40:25,419][00300] Avg episode reward: [(0, '4.673')] | |
| [2024-11-06 21:40:30,414][00300] Fps is (10 sec: 4096.9, 60 sec: 3891.2, 300 sec: 3349.1). Total num frames: 569344. Throughput: 0: 970.0. Samples: 142534. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-11-06 21:40:30,419][00300] Avg episode reward: [(0, '4.575')] | |
| [2024-11-06 21:40:30,826][03124] Updated weights for policy 0, policy_version 140 (0.0025) | |
| [2024-11-06 21:40:35,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3347.0). Total num frames: 585728. Throughput: 0: 997.5. Samples: 145836. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-11-06 21:40:35,418][00300] Avg episode reward: [(0, '4.462')] | |
| [2024-11-06 21:40:40,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3345.1). Total num frames: 602112. Throughput: 0: 937.0. Samples: 150070. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:40:40,417][00300] Avg episode reward: [(0, '4.375')] | |
| [2024-11-06 21:40:42,611][03124] Updated weights for policy 0, policy_version 150 (0.0019) | |
| [2024-11-06 21:40:45,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3387.5). Total num frames: 626688. Throughput: 0: 950.1. Samples: 156468. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:40:45,419][00300] Avg episode reward: [(0, '4.500')] | |
| [2024-11-06 21:40:50,416][00300] Fps is (10 sec: 4504.7, 60 sec: 3891.1, 300 sec: 3406.1). Total num frames: 647168. Throughput: 0: 980.8. Samples: 159970. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:40:50,420][00300] Avg episode reward: [(0, '4.630')] | |
| [2024-11-06 21:40:52,530][03124] Updated weights for policy 0, policy_version 160 (0.0018) | |
| [2024-11-06 21:40:55,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3381.8). Total num frames: 659456. Throughput: 0: 962.5. Samples: 165122. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-11-06 21:40:55,417][00300] Avg episode reward: [(0, '4.601')] | |
| [2024-11-06 21:41:00,414][00300] Fps is (10 sec: 3687.2, 60 sec: 3891.4, 300 sec: 3420.2). Total num frames: 684032. Throughput: 0: 936.2. Samples: 170700. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-11-06 21:41:00,417][00300] Avg episode reward: [(0, '4.801')] | |
| [2024-11-06 21:41:02,974][03124] Updated weights for policy 0, policy_version 170 (0.0014) | |
| [2024-11-06 21:41:05,414][00300] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3436.6). Total num frames: 704512. Throughput: 0: 965.6. Samples: 174260. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:41:05,418][00300] Avg episode reward: [(0, '4.928')] | |
| [2024-11-06 21:41:05,423][03111] Saving new best policy, reward=4.928! | |
| [2024-11-06 21:41:10,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3432.8). Total num frames: 720896. Throughput: 0: 992.5. Samples: 180224. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:41:10,419][00300] Avg episode reward: [(0, '5.236')] | |
| [2024-11-06 21:41:10,439][03111] Saving new best policy, reward=5.236! | |
| [2024-11-06 21:41:14,933][03124] Updated weights for policy 0, policy_version 180 (0.0020) | |
| [2024-11-06 21:41:15,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3754.9, 300 sec: 3429.2). Total num frames: 737280. Throughput: 0: 934.0. Samples: 184564. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:41:15,418][00300] Avg episode reward: [(0, '5.033')] | |
| [2024-11-06 21:41:20,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3891.3, 300 sec: 3463.0). Total num frames: 761856. Throughput: 0: 936.0. Samples: 187958. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:41:20,418][00300] Avg episode reward: [(0, '5.177')] | |
| [2024-11-06 21:41:20,435][03111] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000186_761856.pth... | |
| [2024-11-06 21:41:24,038][03124] Updated weights for policy 0, policy_version 190 (0.0016) | |
| [2024-11-06 21:41:25,414][00300] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3477.1). Total num frames: 782336. Throughput: 0: 995.0. Samples: 194846. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:41:25,420][00300] Avg episode reward: [(0, '5.474')] | |
| [2024-11-06 21:41:25,422][03111] Saving new best policy, reward=5.474! | |
| [2024-11-06 21:41:30,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3454.9). Total num frames: 794624. Throughput: 0: 951.1. Samples: 199266. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:41:30,417][00300] Avg episode reward: [(0, '5.753')] | |
| [2024-11-06 21:41:30,428][03111] Saving new best policy, reward=5.753! | |
| [2024-11-06 21:41:35,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3468.5). Total num frames: 815104. Throughput: 0: 927.4. Samples: 201702. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2024-11-06 21:41:35,425][00300] Avg episode reward: [(0, '5.689')] | |
| [2024-11-06 21:41:35,905][03124] Updated weights for policy 0, policy_version 200 (0.0013) | |
| [2024-11-06 21:41:40,414][00300] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3498.7). Total num frames: 839680. Throughput: 0: 967.3. Samples: 208652. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:41:40,417][00300] Avg episode reward: [(0, '5.628')] | |
| [2024-11-06 21:41:45,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3494.1). Total num frames: 856064. Throughput: 0: 967.8. Samples: 214250. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:41:45,417][00300] Avg episode reward: [(0, '5.385')] | |
| [2024-11-06 21:41:46,595][03124] Updated weights for policy 0, policy_version 210 (0.0014) | |
| [2024-11-06 21:41:50,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3754.8, 300 sec: 3489.8). Total num frames: 872448. Throughput: 0: 935.8. Samples: 216372. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:41:50,416][00300] Avg episode reward: [(0, '5.152')] | |
| [2024-11-06 21:41:55,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3501.7). Total num frames: 892928. Throughput: 0: 941.9. Samples: 222608. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:41:55,421][00300] Avg episode reward: [(0, '5.541')] | |
| [2024-11-06 21:41:56,447][03124] Updated weights for policy 0, policy_version 220 (0.0026) | |
| [2024-11-06 21:42:00,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3513.1). Total num frames: 913408. Throughput: 0: 996.7. Samples: 229414. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:42:00,420][00300] Avg episode reward: [(0, '5.772')] | |
| [2024-11-06 21:42:00,459][03111] Saving new best policy, reward=5.772! | |
| [2024-11-06 21:42:05,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3508.7). Total num frames: 929792. Throughput: 0: 965.2. Samples: 231394. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-11-06 21:42:05,421][00300] Avg episode reward: [(0, '5.698')] | |
| [2024-11-06 21:42:08,261][03124] Updated weights for policy 0, policy_version 230 (0.0030) | |
| [2024-11-06 21:42:10,415][00300] Fps is (10 sec: 3686.3, 60 sec: 3822.9, 300 sec: 3519.5). Total num frames: 950272. Throughput: 0: 927.9. Samples: 236600. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-11-06 21:42:10,417][00300] Avg episode reward: [(0, '5.433')] | |
| [2024-11-06 21:42:15,416][00300] Fps is (10 sec: 4095.3, 60 sec: 3891.1, 300 sec: 3530.0). Total num frames: 970752. Throughput: 0: 980.1. Samples: 243372. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:42:15,418][00300] Avg episode reward: [(0, '5.586')] | |
| [2024-11-06 21:42:17,522][03124] Updated weights for policy 0, policy_version 240 (0.0028) | |
| [2024-11-06 21:42:20,414][00300] Fps is (10 sec: 3686.5, 60 sec: 3754.7, 300 sec: 3525.5). Total num frames: 987136. Throughput: 0: 994.3. Samples: 246444. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:42:20,417][00300] Avg episode reward: [(0, '5.937')] | |
| [2024-11-06 21:42:20,458][03111] Saving new best policy, reward=5.937! | |
| [2024-11-06 21:42:25,414][00300] Fps is (10 sec: 3687.0, 60 sec: 3754.7, 300 sec: 3535.5). Total num frames: 1007616. Throughput: 0: 935.7. Samples: 250760. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-11-06 21:42:25,417][00300] Avg episode reward: [(0, '5.822')] | |
| [2024-11-06 21:42:28,846][03124] Updated weights for policy 0, policy_version 250 (0.0012) | |
| [2024-11-06 21:42:30,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3545.2). Total num frames: 1028096. Throughput: 0: 962.4. Samples: 257558. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:42:30,417][00300] Avg episode reward: [(0, '6.770')] | |
| [2024-11-06 21:42:30,425][03111] Saving new best policy, reward=6.770! | |
| [2024-11-06 21:42:35,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3554.5). Total num frames: 1048576. Throughput: 0: 990.8. Samples: 260958. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:42:35,419][00300] Avg episode reward: [(0, '7.284')] | |
| [2024-11-06 21:42:35,423][03111] Saving new best policy, reward=7.284! | |
| [2024-11-06 21:42:40,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3596.1). Total num frames: 1060864. Throughput: 0: 952.7. Samples: 265480. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-11-06 21:42:40,417][00300] Avg episode reward: [(0, '7.327')] | |
| [2024-11-06 21:42:40,427][03111] Saving new best policy, reward=7.327! | |
| [2024-11-06 21:42:40,736][03124] Updated weights for policy 0, policy_version 260 (0.0017) | |
| [2024-11-06 21:42:45,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3679.5). Total num frames: 1085440. Throughput: 0: 928.7. Samples: 271206. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:42:45,417][00300] Avg episode reward: [(0, '7.468')] | |
| [2024-11-06 21:42:45,423][03111] Saving new best policy, reward=7.468! | |
| [2024-11-06 21:42:50,064][03124] Updated weights for policy 0, policy_version 270 (0.0022) | |
| [2024-11-06 21:42:50,414][00300] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3748.9). Total num frames: 1105920. Throughput: 0: 959.2. Samples: 274560. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-11-06 21:42:50,418][00300] Avg episode reward: [(0, '7.619')] | |
| [2024-11-06 21:42:50,426][03111] Saving new best policy, reward=7.619! | |
| [2024-11-06 21:42:55,419][00300] Fps is (10 sec: 3684.8, 60 sec: 3822.7, 300 sec: 3748.9). Total num frames: 1122304. Throughput: 0: 965.1. Samples: 280032. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:42:55,421][00300] Avg episode reward: [(0, '7.354')] | |
| [2024-11-06 21:43:00,415][00300] Fps is (10 sec: 3276.7, 60 sec: 3754.6, 300 sec: 3748.9). Total num frames: 1138688. Throughput: 0: 925.9. Samples: 285034. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-11-06 21:43:00,417][00300] Avg episode reward: [(0, '7.938')] | |
| [2024-11-06 21:43:00,426][03111] Saving new best policy, reward=7.938! | |
| [2024-11-06 21:43:01,826][03124] Updated weights for policy 0, policy_version 280 (0.0017) | |
| [2024-11-06 21:43:05,414][00300] Fps is (10 sec: 4097.8, 60 sec: 3891.2, 300 sec: 3762.8). Total num frames: 1163264. Throughput: 0: 930.7. Samples: 288326. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:43:05,418][00300] Avg episode reward: [(0, '8.309')] | |
| [2024-11-06 21:43:05,422][03111] Saving new best policy, reward=8.309! | |
| [2024-11-06 21:43:10,415][00300] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 1179648. Throughput: 0: 982.1. Samples: 294954. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:43:10,419][00300] Avg episode reward: [(0, '8.316')] | |
| [2024-11-06 21:43:10,430][03111] Saving new best policy, reward=8.316! | |
| [2024-11-06 21:43:12,438][03124] Updated weights for policy 0, policy_version 290 (0.0017) | |
| [2024-11-06 21:43:15,422][00300] Fps is (10 sec: 3274.4, 60 sec: 3754.3, 300 sec: 3776.6). Total num frames: 1196032. Throughput: 0: 922.3. Samples: 299070. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-11-06 21:43:15,424][00300] Avg episode reward: [(0, '7.868')] | |
| [2024-11-06 21:43:20,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 1216512. Throughput: 0: 912.6. Samples: 302024. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-11-06 21:43:20,422][00300] Avg episode reward: [(0, '7.972')] | |
| [2024-11-06 21:43:20,436][03111] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000297_1216512.pth... | |
| [2024-11-06 21:43:20,588][03111] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000074_303104.pth | |
| [2024-11-06 21:43:22,794][03124] Updated weights for policy 0, policy_version 300 (0.0016) | |
| [2024-11-06 21:43:25,414][00300] Fps is (10 sec: 4098.9, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 1236992. Throughput: 0: 962.7. Samples: 308800. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:43:25,417][00300] Avg episode reward: [(0, '7.934')] | |
| [2024-11-06 21:43:30,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3804.5). Total num frames: 1253376. Throughput: 0: 949.1. Samples: 313914. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2024-11-06 21:43:30,417][00300] Avg episode reward: [(0, '8.194')] | |
| [2024-11-06 21:43:34,334][03124] Updated weights for policy 0, policy_version 310 (0.0020) | |
| [2024-11-06 21:43:35,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 1273856. Throughput: 0: 923.1. Samples: 316100. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-11-06 21:43:35,417][00300] Avg episode reward: [(0, '8.744')] | |
| [2024-11-06 21:43:35,419][03111] Saving new best policy, reward=8.744! | |
| [2024-11-06 21:43:40,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 1294336. Throughput: 0: 950.5. Samples: 322800. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-11-06 21:43:40,425][00300] Avg episode reward: [(0, '9.016')] | |
| [2024-11-06 21:43:40,433][03111] Saving new best policy, reward=9.016! | |
| [2024-11-06 21:43:43,615][03124] Updated weights for policy 0, policy_version 320 (0.0015) | |
| [2024-11-06 21:43:45,417][00300] Fps is (10 sec: 4095.1, 60 sec: 3822.8, 300 sec: 3832.2). Total num frames: 1314816. Throughput: 0: 973.2. Samples: 328830. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-11-06 21:43:45,422][00300] Avg episode reward: [(0, '9.352')] | |
| [2024-11-06 21:43:45,427][03111] Saving new best policy, reward=9.352! | |
| [2024-11-06 21:43:50,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3818.3). Total num frames: 1327104. Throughput: 0: 943.9. Samples: 330800. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-11-06 21:43:50,419][00300] Avg episode reward: [(0, '8.991')] | |
| [2024-11-06 21:43:55,398][03124] Updated weights for policy 0, policy_version 330 (0.0037) | |
| [2024-11-06 21:43:55,414][00300] Fps is (10 sec: 3687.2, 60 sec: 3823.2, 300 sec: 3818.3). Total num frames: 1351680. Throughput: 0: 922.9. Samples: 336486. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-11-06 21:43:55,417][00300] Avg episode reward: [(0, '9.500')] | |
| [2024-11-06 21:43:55,419][03111] Saving new best policy, reward=9.500! | |
| [2024-11-06 21:44:00,414][00300] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 1372160. Throughput: 0: 986.0. Samples: 343432. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-11-06 21:44:00,416][00300] Avg episode reward: [(0, '10.331')] | |
| [2024-11-06 21:44:00,433][03111] Saving new best policy, reward=10.331! | |
| [2024-11-06 21:44:05,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 1388544. Throughput: 0: 975.7. Samples: 345930. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:44:05,417][00300] Avg episode reward: [(0, '10.391')] | |
| [2024-11-06 21:44:05,420][03111] Saving new best policy, reward=10.391! | |
| [2024-11-06 21:44:06,720][03124] Updated weights for policy 0, policy_version 340 (0.0014) | |
| [2024-11-06 21:44:10,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 1404928. Throughput: 0: 923.1. Samples: 350338. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-11-06 21:44:10,420][00300] Avg episode reward: [(0, '11.518')] | |
| [2024-11-06 21:44:10,431][03111] Saving new best policy, reward=11.518! | |
| [2024-11-06 21:44:15,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3823.4, 300 sec: 3804.4). Total num frames: 1425408. Throughput: 0: 960.0. Samples: 357112. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-11-06 21:44:15,421][00300] Avg episode reward: [(0, '11.853')] | |
| [2024-11-06 21:44:15,435][03111] Saving new best policy, reward=11.853! | |
| [2024-11-06 21:44:16,350][03124] Updated weights for policy 0, policy_version 350 (0.0018) | |
| [2024-11-06 21:44:20,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 1445888. Throughput: 0: 984.4. Samples: 360396. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:44:20,421][00300] Avg episode reward: [(0, '11.280')] | |
| [2024-11-06 21:44:25,419][00300] Fps is (10 sec: 3684.7, 60 sec: 3754.4, 300 sec: 3818.2). Total num frames: 1462272. Throughput: 0: 932.1. Samples: 364748. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-11-06 21:44:25,422][00300] Avg episode reward: [(0, '10.468')] | |
| [2024-11-06 21:44:28,087][03124] Updated weights for policy 0, policy_version 360 (0.0013) | |
| [2024-11-06 21:44:30,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 1482752. Throughput: 0: 939.4. Samples: 371100. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-11-06 21:44:30,417][00300] Avg episode reward: [(0, '9.492')] | |
| [2024-11-06 21:44:35,415][00300] Fps is (10 sec: 4507.2, 60 sec: 3891.1, 300 sec: 3818.3). Total num frames: 1507328. Throughput: 0: 969.0. Samples: 374404. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:44:35,420][00300] Avg episode reward: [(0, '10.025')] | |
| [2024-11-06 21:44:38,071][03124] Updated weights for policy 0, policy_version 370 (0.0027) | |
| [2024-11-06 21:44:40,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 1519616. Throughput: 0: 965.8. Samples: 379948. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:44:40,422][00300] Avg episode reward: [(0, '10.582')] | |
| [2024-11-06 21:44:45,414][00300] Fps is (10 sec: 3277.1, 60 sec: 3754.8, 300 sec: 3818.3). Total num frames: 1540096. Throughput: 0: 926.3. Samples: 385116. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:44:45,416][00300] Avg episode reward: [(0, '10.823')] | |
| [2024-11-06 21:44:48,718][03124] Updated weights for policy 0, policy_version 380 (0.0014) | |
| [2024-11-06 21:44:50,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 1560576. Throughput: 0: 945.6. Samples: 388482. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-11-06 21:44:50,422][00300] Avg episode reward: [(0, '11.451')] | |
| [2024-11-06 21:44:55,416][00300] Fps is (10 sec: 4095.3, 60 sec: 3822.8, 300 sec: 3832.2). Total num frames: 1581056. Throughput: 0: 993.3. Samples: 395040. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:44:55,419][00300] Avg episode reward: [(0, '11.685')] | |
| [2024-11-06 21:45:00,369][03124] Updated weights for policy 0, policy_version 390 (0.0027) | |
| [2024-11-06 21:45:00,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3832.2). Total num frames: 1597440. Throughput: 0: 937.4. Samples: 399296. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:45:00,417][00300] Avg episode reward: [(0, '11.734')] | |
| [2024-11-06 21:45:05,414][00300] Fps is (10 sec: 3687.0, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 1617920. Throughput: 0: 937.3. Samples: 402576. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2024-11-06 21:45:05,419][00300] Avg episode reward: [(0, '11.584')] | |
| [2024-11-06 21:45:09,227][03124] Updated weights for policy 0, policy_version 400 (0.0013) | |
| [2024-11-06 21:45:10,415][00300] Fps is (10 sec: 4505.5, 60 sec: 3959.5, 300 sec: 3832.2). Total num frames: 1642496. Throughput: 0: 992.1. Samples: 409390. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-11-06 21:45:10,422][00300] Avg episode reward: [(0, '11.283')] | |
| [2024-11-06 21:45:15,416][00300] Fps is (10 sec: 3685.7, 60 sec: 3822.8, 300 sec: 3818.3). Total num frames: 1654784. Throughput: 0: 961.5. Samples: 414368. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-11-06 21:45:15,418][00300] Avg episode reward: [(0, '11.243')] | |
| [2024-11-06 21:45:20,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 1675264. Throughput: 0: 936.0. Samples: 416522. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:45:20,419][00300] Avg episode reward: [(0, '12.068')] | |
| [2024-11-06 21:45:20,431][03111] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000409_1675264.pth... | |
| [2024-11-06 21:45:20,558][03111] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000186_761856.pth | |
| [2024-11-06 21:45:20,573][03111] Saving new best policy, reward=12.068! | |
| [2024-11-06 21:45:21,436][03124] Updated weights for policy 0, policy_version 410 (0.0013) | |
| [2024-11-06 21:45:25,414][00300] Fps is (10 sec: 4096.8, 60 sec: 3891.5, 300 sec: 3818.3). Total num frames: 1695744. Throughput: 0: 961.0. Samples: 423194. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-11-06 21:45:25,421][00300] Avg episode reward: [(0, '12.931')] | |
| [2024-11-06 21:45:25,428][03111] Saving new best policy, reward=12.931! | |
| [2024-11-06 21:45:30,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 1712128. Throughput: 0: 974.9. Samples: 428986. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:45:30,419][00300] Avg episode reward: [(0, '13.240')] | |
| [2024-11-06 21:45:30,439][03111] Saving new best policy, reward=13.240! | |
| [2024-11-06 21:45:32,011][03124] Updated weights for policy 0, policy_version 420 (0.0017) | |
| [2024-11-06 21:45:35,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3686.5, 300 sec: 3818.3). Total num frames: 1728512. Throughput: 0: 947.3. Samples: 431112. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:45:35,416][00300] Avg episode reward: [(0, '13.540')] | |
| [2024-11-06 21:45:35,425][03111] Saving new best policy, reward=13.540! | |
| [2024-11-06 21:45:40,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 1753088. Throughput: 0: 938.5. Samples: 437272. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:45:40,423][00300] Avg episode reward: [(0, '13.712')] | |
| [2024-11-06 21:45:40,432][03111] Saving new best policy, reward=13.712! | |
| [2024-11-06 21:45:41,829][03124] Updated weights for policy 0, policy_version 430 (0.0025) | |
| [2024-11-06 21:45:45,419][00300] Fps is (10 sec: 4503.3, 60 sec: 3890.9, 300 sec: 3818.3). Total num frames: 1773568. Throughput: 0: 994.6. Samples: 444058. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:45:45,422][00300] Avg episode reward: [(0, '13.536')] | |
| [2024-11-06 21:45:50,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 1785856. Throughput: 0: 967.6. Samples: 446118. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:45:50,420][00300] Avg episode reward: [(0, '14.706')] | |
| [2024-11-06 21:45:50,434][03111] Saving new best policy, reward=14.706! | |
| [2024-11-06 21:45:53,728][03124] Updated weights for policy 0, policy_version 440 (0.0017) | |
| [2024-11-06 21:45:55,414][00300] Fps is (10 sec: 3278.4, 60 sec: 3754.8, 300 sec: 3804.4). Total num frames: 1806336. Throughput: 0: 927.2. Samples: 451114. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:45:55,422][00300] Avg episode reward: [(0, '15.344')] | |
| [2024-11-06 21:45:55,480][03111] Saving new best policy, reward=15.344! | |
| [2024-11-06 21:46:00,414][00300] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 1830912. Throughput: 0: 969.1. Samples: 457976. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-11-06 21:46:00,421][00300] Avg episode reward: [(0, '13.896')] | |
| [2024-11-06 21:46:03,017][03124] Updated weights for policy 0, policy_version 450 (0.0016) | |
| [2024-11-06 21:46:05,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 1847296. Throughput: 0: 990.1. Samples: 461078. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:46:05,418][00300] Avg episode reward: [(0, '14.022')] | |
| [2024-11-06 21:46:10,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3818.3). Total num frames: 1863680. Throughput: 0: 936.8. Samples: 465348. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-11-06 21:46:10,420][00300] Avg episode reward: [(0, '13.913')] | |
| [2024-11-06 21:46:13,929][03124] Updated weights for policy 0, policy_version 460 (0.0015) | |
| [2024-11-06 21:46:15,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3891.3, 300 sec: 3818.3). Total num frames: 1888256. Throughput: 0: 963.6. Samples: 472350. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-11-06 21:46:15,416][00300] Avg episode reward: [(0, '13.938')] | |
| [2024-11-06 21:46:20,414][00300] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 1908736. Throughput: 0: 990.7. Samples: 475692. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-11-06 21:46:20,417][00300] Avg episode reward: [(0, '14.521')] | |
| [2024-11-06 21:46:25,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 1921024. Throughput: 0: 959.8. Samples: 480462. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-11-06 21:46:25,417][00300] Avg episode reward: [(0, '14.412')] | |
| [2024-11-06 21:46:25,434][03124] Updated weights for policy 0, policy_version 470 (0.0013) | |
| [2024-11-06 21:46:30,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 1945600. Throughput: 0: 945.7. Samples: 486608. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-11-06 21:46:30,416][00300] Avg episode reward: [(0, '14.901')] | |
| [2024-11-06 21:46:34,533][03124] Updated weights for policy 0, policy_version 480 (0.0031) | |
| [2024-11-06 21:46:35,414][00300] Fps is (10 sec: 4915.2, 60 sec: 4027.7, 300 sec: 3832.2). Total num frames: 1970176. Throughput: 0: 976.7. Samples: 490068. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-11-06 21:46:35,416][00300] Avg episode reward: [(0, '15.504')] | |
| [2024-11-06 21:46:35,424][03111] Saving new best policy, reward=15.504! | |
| [2024-11-06 21:46:40,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 1982464. Throughput: 0: 987.7. Samples: 495560. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:46:40,425][00300] Avg episode reward: [(0, '15.798')] | |
| [2024-11-06 21:46:40,437][03111] Saving new best policy, reward=15.798! | |
| [2024-11-06 21:46:45,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3823.3, 300 sec: 3832.2). Total num frames: 2002944. Throughput: 0: 948.9. Samples: 500676. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-11-06 21:46:45,417][00300] Avg episode reward: [(0, '16.844')] | |
| [2024-11-06 21:46:45,419][03111] Saving new best policy, reward=16.844! | |
| [2024-11-06 21:46:46,102][03124] Updated weights for policy 0, policy_version 490 (0.0031) | |
| [2024-11-06 21:46:50,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3832.2). Total num frames: 2023424. Throughput: 0: 952.6. Samples: 503946. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-11-06 21:46:50,417][00300] Avg episode reward: [(0, '16.252')] | |
| [2024-11-06 21:46:55,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3832.2). Total num frames: 2043904. Throughput: 0: 1003.8. Samples: 510518. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-11-06 21:46:55,417][00300] Avg episode reward: [(0, '15.709')] | |
| [2024-11-06 21:46:56,487][03124] Updated weights for policy 0, policy_version 500 (0.0025) | |
| [2024-11-06 21:47:00,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 2060288. Throughput: 0: 944.5. Samples: 514854. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-11-06 21:47:00,421][00300] Avg episode reward: [(0, '14.703')] | |
| [2024-11-06 21:47:05,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 2080768. Throughput: 0: 943.7. Samples: 518158. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:47:05,417][00300] Avg episode reward: [(0, '14.431')] | |
| [2024-11-06 21:47:06,570][03124] Updated weights for policy 0, policy_version 510 (0.0023) | |
| [2024-11-06 21:47:10,414][00300] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3846.1). Total num frames: 2105344. Throughput: 0: 995.1. Samples: 525240. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:47:10,417][00300] Avg episode reward: [(0, '14.272')] | |
| [2024-11-06 21:47:15,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 2117632. Throughput: 0: 965.4. Samples: 530052. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:47:15,425][00300] Avg episode reward: [(0, '14.937')] | |
| [2024-11-06 21:47:18,115][03124] Updated weights for policy 0, policy_version 520 (0.0019) | |
| [2024-11-06 21:47:20,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 2138112. Throughput: 0: 946.5. Samples: 532660. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:47:20,417][00300] Avg episode reward: [(0, '15.326')] | |
| [2024-11-06 21:47:20,430][03111] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000522_2138112.pth... | |
| [2024-11-06 21:47:20,560][03111] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000297_1216512.pth | |
| [2024-11-06 21:47:25,414][00300] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3846.1). Total num frames: 2162688. Throughput: 0: 973.3. Samples: 539358. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-11-06 21:47:25,422][00300] Avg episode reward: [(0, '15.744')] | |
| [2024-11-06 21:47:27,011][03124] Updated weights for policy 0, policy_version 530 (0.0018) | |
| [2024-11-06 21:47:30,415][00300] Fps is (10 sec: 4095.9, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 2179072. Throughput: 0: 989.3. Samples: 545196. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:47:30,422][00300] Avg episode reward: [(0, '15.662')] | |
| [2024-11-06 21:47:35,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3846.1). Total num frames: 2195456. Throughput: 0: 963.5. Samples: 547304. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-11-06 21:47:35,419][00300] Avg episode reward: [(0, '17.277')] | |
| [2024-11-06 21:47:35,422][03111] Saving new best policy, reward=17.277! | |
| [2024-11-06 21:47:38,535][03124] Updated weights for policy 0, policy_version 540 (0.0015) | |
| [2024-11-06 21:47:40,414][00300] Fps is (10 sec: 4096.1, 60 sec: 3959.5, 300 sec: 3846.1). Total num frames: 2220032. Throughput: 0: 957.0. Samples: 553582. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-11-06 21:47:40,422][00300] Avg episode reward: [(0, '17.211')] | |
| [2024-11-06 21:47:45,415][00300] Fps is (10 sec: 4095.5, 60 sec: 3891.1, 300 sec: 3832.2). Total num frames: 2236416. Throughput: 0: 1003.1. Samples: 559994. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:47:45,419][00300] Avg episode reward: [(0, '16.621')] | |
| [2024-11-06 21:47:49,944][03124] Updated weights for policy 0, policy_version 550 (0.0032) | |
| [2024-11-06 21:47:50,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 2252800. Throughput: 0: 975.7. Samples: 562066. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2024-11-06 21:47:50,422][00300] Avg episode reward: [(0, '17.040')] | |
| [2024-11-06 21:47:55,414][00300] Fps is (10 sec: 3686.8, 60 sec: 3822.9, 300 sec: 3846.1). Total num frames: 2273280. Throughput: 0: 939.8. Samples: 567530. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-11-06 21:47:55,422][00300] Avg episode reward: [(0, '17.057')] | |
| [2024-11-06 21:47:59,168][03124] Updated weights for policy 0, policy_version 560 (0.0025) | |
| [2024-11-06 21:48:00,414][00300] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3846.1). Total num frames: 2297856. Throughput: 0: 989.2. Samples: 574566. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:48:00,423][00300] Avg episode reward: [(0, '16.694')] | |
| [2024-11-06 21:48:05,415][00300] Fps is (10 sec: 4095.8, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 2314240. Throughput: 0: 990.2. Samples: 577220. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-11-06 21:48:05,419][00300] Avg episode reward: [(0, '17.718')] | |
| [2024-11-06 21:48:05,424][03111] Saving new best policy, reward=17.718! | |
| [2024-11-06 21:48:10,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3846.2). Total num frames: 2330624. Throughput: 0: 943.4. Samples: 581810. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-11-06 21:48:10,423][00300] Avg episode reward: [(0, '19.548')] | |
| [2024-11-06 21:48:10,434][03111] Saving new best policy, reward=19.548! | |
| [2024-11-06 21:48:10,950][03124] Updated weights for policy 0, policy_version 570 (0.0013) | |
| [2024-11-06 21:48:15,414][00300] Fps is (10 sec: 4096.2, 60 sec: 3959.5, 300 sec: 3860.0). Total num frames: 2355200. Throughput: 0: 963.2. Samples: 588538. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-11-06 21:48:15,416][00300] Avg episode reward: [(0, '19.935')] | |
| [2024-11-06 21:48:15,420][03111] Saving new best policy, reward=19.935! | |
| [2024-11-06 21:48:20,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 2371584. Throughput: 0: 992.8. Samples: 591982. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:48:20,417][00300] Avg episode reward: [(0, '20.087')] | |
| [2024-11-06 21:48:20,443][03111] Saving new best policy, reward=20.087! | |
| [2024-11-06 21:48:21,288][03124] Updated weights for policy 0, policy_version 580 (0.0024) | |
| [2024-11-06 21:48:25,414][00300] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3832.2). Total num frames: 2383872. Throughput: 0: 949.9. Samples: 596328. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-11-06 21:48:25,423][00300] Avg episode reward: [(0, '21.021')] | |
| [2024-11-06 21:48:25,443][03111] Saving new best policy, reward=21.021! | |
| [2024-11-06 21:48:30,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3846.1). Total num frames: 2408448. Throughput: 0: 946.5. Samples: 602586. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:48:30,416][00300] Avg episode reward: [(0, '20.519')] | |
| [2024-11-06 21:48:31,681][03124] Updated weights for policy 0, policy_version 590 (0.0017) | |
| [2024-11-06 21:48:35,415][00300] Fps is (10 sec: 4915.0, 60 sec: 3959.4, 300 sec: 3860.0). Total num frames: 2433024. Throughput: 0: 977.9. Samples: 606072. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-11-06 21:48:35,421][00300] Avg episode reward: [(0, '20.212')] | |
| [2024-11-06 21:48:40,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3832.2). Total num frames: 2445312. Throughput: 0: 978.1. Samples: 611544. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-11-06 21:48:40,417][00300] Avg episode reward: [(0, '19.279')] | |
| [2024-11-06 21:48:43,030][03124] Updated weights for policy 0, policy_version 600 (0.0014) | |
| [2024-11-06 21:48:45,414][00300] Fps is (10 sec: 3276.9, 60 sec: 3823.0, 300 sec: 3860.0). Total num frames: 2465792. Throughput: 0: 943.0. Samples: 617002. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-11-06 21:48:45,417][00300] Avg episode reward: [(0, '20.912')] | |
| [2024-11-06 21:48:50,414][00300] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3860.0). Total num frames: 2490368. Throughput: 0: 962.1. Samples: 620514. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:48:50,418][00300] Avg episode reward: [(0, '20.792')] | |
| [2024-11-06 21:48:51,902][03124] Updated weights for policy 0, policy_version 610 (0.0013) | |
| [2024-11-06 21:48:55,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 2506752. Throughput: 0: 995.9. Samples: 626626. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-11-06 21:48:55,423][00300] Avg episode reward: [(0, '19.627')] | |
| [2024-11-06 21:49:00,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3846.1). Total num frames: 2523136. Throughput: 0: 948.5. Samples: 631220. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2024-11-06 21:49:00,416][00300] Avg episode reward: [(0, '19.972')] | |
| [2024-11-06 21:49:03,373][03124] Updated weights for policy 0, policy_version 620 (0.0015) | |
| [2024-11-06 21:49:05,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 2547712. Throughput: 0: 949.0. Samples: 634686. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-11-06 21:49:05,417][00300] Avg episode reward: [(0, '17.843')] | |
| [2024-11-06 21:49:10,414][00300] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3873.8). Total num frames: 2568192. Throughput: 0: 1004.3. Samples: 641520. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:49:10,417][00300] Avg episode reward: [(0, '17.674')] | |
| [2024-11-06 21:49:13,799][03124] Updated weights for policy 0, policy_version 630 (0.0019) | |
| [2024-11-06 21:49:15,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 2584576. Throughput: 0: 969.5. Samples: 646214. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-11-06 21:49:15,421][00300] Avg episode reward: [(0, '17.567')] | |
| [2024-11-06 21:49:20,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3873.9). Total num frames: 2605056. Throughput: 0: 953.2. Samples: 648966. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-11-06 21:49:20,421][00300] Avg episode reward: [(0, '18.470')] | |
| [2024-11-06 21:49:20,437][03111] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000636_2605056.pth... | |
| [2024-11-06 21:49:20,548][03111] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000409_1675264.pth | |
| [2024-11-06 21:49:23,863][03124] Updated weights for policy 0, policy_version 640 (0.0016) | |
| [2024-11-06 21:49:25,414][00300] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3873.8). Total num frames: 2625536. Throughput: 0: 983.9. Samples: 655820. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:49:25,419][00300] Avg episode reward: [(0, '19.712')] | |
| [2024-11-06 21:49:30,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 2641920. Throughput: 0: 984.4. Samples: 661300. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:49:30,423][00300] Avg episode reward: [(0, '20.000')] | |
| [2024-11-06 21:49:35,087][03124] Updated weights for policy 0, policy_version 650 (0.0018) | |
| [2024-11-06 21:49:35,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3823.0, 300 sec: 3873.8). Total num frames: 2662400. Throughput: 0: 955.4. Samples: 663508. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-11-06 21:49:35,426][00300] Avg episode reward: [(0, '20.058')] | |
| [2024-11-06 21:49:40,414][00300] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3887.7). Total num frames: 2686976. Throughput: 0: 970.4. Samples: 670294. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:49:40,421][00300] Avg episode reward: [(0, '19.684')] | |
| [2024-11-06 21:49:44,371][03124] Updated weights for policy 0, policy_version 660 (0.0028) | |
| [2024-11-06 21:49:45,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3873.8). Total num frames: 2703360. Throughput: 0: 1007.7. Samples: 676568. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-11-06 21:49:45,417][00300] Avg episode reward: [(0, '19.925')] | |
| [2024-11-06 21:49:50,415][00300] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 2719744. Throughput: 0: 978.7. Samples: 678728. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:49:50,423][00300] Avg episode reward: [(0, '18.999')] | |
| [2024-11-06 21:49:55,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 2740224. Throughput: 0: 950.3. Samples: 684282. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:49:55,417][00300] Avg episode reward: [(0, '19.643')] | |
| [2024-11-06 21:49:55,932][03124] Updated weights for policy 0, policy_version 670 (0.0024) | |
| [2024-11-06 21:50:00,415][00300] Fps is (10 sec: 4095.9, 60 sec: 3959.4, 300 sec: 3873.8). Total num frames: 2760704. Throughput: 0: 993.6. Samples: 690924. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:50:00,417][00300] Avg episode reward: [(0, '19.132')] | |
| [2024-11-06 21:50:05,415][00300] Fps is (10 sec: 3686.3, 60 sec: 3822.9, 300 sec: 3846.1). Total num frames: 2777088. Throughput: 0: 981.4. Samples: 693128. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:50:05,420][00300] Avg episode reward: [(0, '19.711')] | |
| [2024-11-06 21:50:07,669][03124] Updated weights for policy 0, policy_version 680 (0.0026) | |
| [2024-11-06 21:50:10,414][00300] Fps is (10 sec: 3686.5, 60 sec: 3822.9, 300 sec: 3873.9). Total num frames: 2797568. Throughput: 0: 939.7. Samples: 698108. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:50:10,417][00300] Avg episode reward: [(0, '18.533')] | |
| [2024-11-06 21:50:15,414][00300] Fps is (10 sec: 4096.1, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 2818048. Throughput: 0: 970.6. Samples: 704978. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-11-06 21:50:15,419][00300] Avg episode reward: [(0, '19.698')] | |
| [2024-11-06 21:50:16,671][03124] Updated weights for policy 0, policy_version 690 (0.0020) | |
| [2024-11-06 21:50:20,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 2834432. Throughput: 0: 991.2. Samples: 708112. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-11-06 21:50:20,421][00300] Avg episode reward: [(0, '21.395')] | |
| [2024-11-06 21:50:20,433][03111] Saving new best policy, reward=21.395! | |
| [2024-11-06 21:50:25,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3860.0). Total num frames: 2850816. Throughput: 0: 932.1. Samples: 712238. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-11-06 21:50:25,417][00300] Avg episode reward: [(0, '21.603')] | |
| [2024-11-06 21:50:25,421][03111] Saving new best policy, reward=21.603! | |
| [2024-11-06 21:50:28,485][03124] Updated weights for policy 0, policy_version 700 (0.0016) | |
| [2024-11-06 21:50:30,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3887.7). Total num frames: 2875392. Throughput: 0: 939.8. Samples: 718860. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:50:30,418][00300] Avg episode reward: [(0, '20.933')] | |
| [2024-11-06 21:50:35,414][00300] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 2895872. Throughput: 0: 970.4. Samples: 722396. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-11-06 21:50:35,424][00300] Avg episode reward: [(0, '21.039')] | |
| [2024-11-06 21:50:38,964][03124] Updated weights for policy 0, policy_version 710 (0.0018) | |
| [2024-11-06 21:50:40,415][00300] Fps is (10 sec: 3686.2, 60 sec: 3754.6, 300 sec: 3860.0). Total num frames: 2912256. Throughput: 0: 959.7. Samples: 727470. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:50:40,420][00300] Avg episode reward: [(0, '21.815')] | |
| [2024-11-06 21:50:40,429][03111] Saving new best policy, reward=21.815! | |
| [2024-11-06 21:50:45,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3887.7). Total num frames: 2932736. Throughput: 0: 943.2. Samples: 733366. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:50:45,421][00300] Avg episode reward: [(0, '19.425')] | |
| [2024-11-06 21:50:48,581][03124] Updated weights for policy 0, policy_version 720 (0.0017) | |
| [2024-11-06 21:50:50,414][00300] Fps is (10 sec: 4505.8, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 2957312. Throughput: 0: 971.9. Samples: 736862. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:50:50,421][00300] Avg episode reward: [(0, '18.659')] | |
| [2024-11-06 21:50:55,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 2969600. Throughput: 0: 988.8. Samples: 742602. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:50:55,420][00300] Avg episode reward: [(0, '19.275')] | |
| [2024-11-06 21:50:59,949][03124] Updated weights for policy 0, policy_version 730 (0.0021) | |
| [2024-11-06 21:51:00,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3823.0, 300 sec: 3873.8). Total num frames: 2990080. Throughput: 0: 948.5. Samples: 747660. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:51:00,417][00300] Avg episode reward: [(0, '19.578')] | |
| [2024-11-06 21:51:05,414][00300] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 3014656. Throughput: 0: 956.2. Samples: 751140. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:51:05,417][00300] Avg episode reward: [(0, '19.280')] | |
| [2024-11-06 21:51:09,210][03124] Updated weights for policy 0, policy_version 740 (0.0012) | |
| [2024-11-06 21:51:10,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 3031040. Throughput: 0: 1016.4. Samples: 757976. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:51:10,421][00300] Avg episode reward: [(0, '19.697')] | |
| [2024-11-06 21:51:15,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 3047424. Throughput: 0: 965.8. Samples: 762322. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-11-06 21:51:15,417][00300] Avg episode reward: [(0, '20.922')] | |
| [2024-11-06 21:51:20,300][03124] Updated weights for policy 0, policy_version 750 (0.0014) | |
| [2024-11-06 21:51:20,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 3072000. Throughput: 0: 959.4. Samples: 765568. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:51:20,422][00300] Avg episode reward: [(0, '21.380')] | |
| [2024-11-06 21:51:20,436][03111] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000750_3072000.pth... | |
| [2024-11-06 21:51:20,563][03111] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000522_2138112.pth | |
| [2024-11-06 21:51:25,414][00300] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3887.7). Total num frames: 3092480. Throughput: 0: 1003.0. Samples: 772604. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:51:25,416][00300] Avg episode reward: [(0, '20.994')] | |
| [2024-11-06 21:51:30,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 3108864. Throughput: 0: 979.7. Samples: 777452. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-11-06 21:51:30,428][00300] Avg episode reward: [(0, '20.276')] | |
| [2024-11-06 21:51:31,508][03124] Updated weights for policy 0, policy_version 760 (0.0024) | |
| [2024-11-06 21:51:35,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3887.7). Total num frames: 3129344. Throughput: 0: 955.2. Samples: 779848. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-11-06 21:51:35,423][00300] Avg episode reward: [(0, '19.867')] | |
| [2024-11-06 21:51:40,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3887.7). Total num frames: 3149824. Throughput: 0: 985.3. Samples: 786940. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-11-06 21:51:40,424][00300] Avg episode reward: [(0, '18.922')] | |
| [2024-11-06 21:51:40,508][03124] Updated weights for policy 0, policy_version 770 (0.0013) | |
| [2024-11-06 21:51:45,414][00300] Fps is (10 sec: 4095.9, 60 sec: 3959.5, 300 sec: 3887.7). Total num frames: 3170304. Throughput: 0: 1004.1. Samples: 792844. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:51:45,417][00300] Avg episode reward: [(0, '18.917')] | |
| [2024-11-06 21:51:50,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3873.8). Total num frames: 3186688. Throughput: 0: 974.4. Samples: 794988. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:51:50,421][00300] Avg episode reward: [(0, '21.483')] | |
| [2024-11-06 21:51:51,953][03124] Updated weights for policy 0, policy_version 780 (0.0020) | |
| [2024-11-06 21:51:55,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3887.7). Total num frames: 3207168. Throughput: 0: 963.1. Samples: 801316. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:51:55,417][00300] Avg episode reward: [(0, '21.941')] | |
| [2024-11-06 21:51:55,420][03111] Saving new best policy, reward=21.941! | |
| [2024-11-06 21:52:00,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3887.7). Total num frames: 3227648. Throughput: 0: 1009.1. Samples: 807730. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-11-06 21:52:00,417][00300] Avg episode reward: [(0, '21.583')] | |
| [2024-11-06 21:52:02,232][03124] Updated weights for policy 0, policy_version 790 (0.0020) | |
| [2024-11-06 21:52:05,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 3244032. Throughput: 0: 984.3. Samples: 809862. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-11-06 21:52:05,425][00300] Avg episode reward: [(0, '20.688')] | |
| [2024-11-06 21:52:10,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3887.7). Total num frames: 3264512. Throughput: 0: 950.7. Samples: 815384. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-11-06 21:52:10,419][00300] Avg episode reward: [(0, '21.726')] | |
| [2024-11-06 21:52:12,534][03124] Updated weights for policy 0, policy_version 800 (0.0026) | |
| [2024-11-06 21:52:15,414][00300] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3901.6). Total num frames: 3289088. Throughput: 0: 997.1. Samples: 822320. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:52:15,420][00300] Avg episode reward: [(0, '20.460')] | |
| [2024-11-06 21:52:20,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 3305472. Throughput: 0: 1003.0. Samples: 824982. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:52:20,418][00300] Avg episode reward: [(0, '18.649')] | |
| [2024-11-06 21:52:23,888][03124] Updated weights for policy 0, policy_version 810 (0.0020) | |
| [2024-11-06 21:52:25,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3873.8). Total num frames: 3321856. Throughput: 0: 953.1. Samples: 829830. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:52:25,417][00300] Avg episode reward: [(0, '18.858')] | |
| [2024-11-06 21:52:30,415][00300] Fps is (10 sec: 4095.9, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 3346432. Throughput: 0: 974.3. Samples: 836686. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:52:30,417][00300] Avg episode reward: [(0, '18.582')] | |
| [2024-11-06 21:52:32,728][03124] Updated weights for policy 0, policy_version 820 (0.0034) | |
| [2024-11-06 21:52:35,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 3362816. Throughput: 0: 1004.7. Samples: 840200. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:52:35,420][00300] Avg episode reward: [(0, '19.378')] | |
| [2024-11-06 21:52:40,414][00300] Fps is (10 sec: 3276.9, 60 sec: 3822.9, 300 sec: 3873.9). Total num frames: 3379200. Throughput: 0: 961.8. Samples: 844598. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:52:40,422][00300] Avg episode reward: [(0, '20.316')] | |
| [2024-11-06 21:52:44,242][03124] Updated weights for policy 0, policy_version 830 (0.0022) | |
| [2024-11-06 21:52:45,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3901.6). Total num frames: 3403776. Throughput: 0: 965.0. Samples: 851154. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:52:45,416][00300] Avg episode reward: [(0, '22.260')] | |
| [2024-11-06 21:52:45,426][03111] Saving new best policy, reward=22.260! | |
| [2024-11-06 21:52:50,415][00300] Fps is (10 sec: 4505.1, 60 sec: 3959.4, 300 sec: 3901.6). Total num frames: 3424256. Throughput: 0: 993.5. Samples: 854570. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-11-06 21:52:50,419][00300] Avg episode reward: [(0, '23.584')] | |
| [2024-11-06 21:52:50,436][03111] Saving new best policy, reward=23.584! | |
| [2024-11-06 21:52:55,104][03124] Updated weights for policy 0, policy_version 840 (0.0017) | |
| [2024-11-06 21:52:55,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 3440640. Throughput: 0: 983.8. Samples: 859656. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:52:55,420][00300] Avg episode reward: [(0, '24.068')] | |
| [2024-11-06 21:52:55,426][03111] Saving new best policy, reward=24.068! | |
| [2024-11-06 21:53:00,414][00300] Fps is (10 sec: 3686.8, 60 sec: 3891.2, 300 sec: 3887.7). Total num frames: 3461120. Throughput: 0: 953.7. Samples: 865238. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-11-06 21:53:00,423][00300] Avg episode reward: [(0, '23.685')] | |
| [2024-11-06 21:53:04,636][03124] Updated weights for policy 0, policy_version 850 (0.0018) | |
| [2024-11-06 21:53:05,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 3481600. Throughput: 0: 972.8. Samples: 868756. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-11-06 21:53:05,423][00300] Avg episode reward: [(0, '23.078')] | |
| [2024-11-06 21:53:10,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3887.7). Total num frames: 3502080. Throughput: 0: 1000.4. Samples: 874846. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:53:10,417][00300] Avg episode reward: [(0, '23.462')] | |
| [2024-11-06 21:53:15,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3887.7). Total num frames: 3518464. Throughput: 0: 958.0. Samples: 879796. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:53:15,424][00300] Avg episode reward: [(0, '22.344')] | |
| [2024-11-06 21:53:15,939][03124] Updated weights for policy 0, policy_version 860 (0.0015) | |
| [2024-11-06 21:53:20,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3929.4). Total num frames: 3543040. Throughput: 0: 957.0. Samples: 883266. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-11-06 21:53:20,423][00300] Avg episode reward: [(0, '22.389')] | |
| [2024-11-06 21:53:20,436][03111] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000865_3543040.pth... | |
| [2024-11-06 21:53:20,597][03111] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000636_2605056.pth | |
| [2024-11-06 21:53:25,413][03124] Updated weights for policy 0, policy_version 870 (0.0020) | |
| [2024-11-06 21:53:25,415][00300] Fps is (10 sec: 4505.1, 60 sec: 4027.7, 300 sec: 3915.5). Total num frames: 3563520. Throughput: 0: 1013.0. Samples: 890182. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-11-06 21:53:25,420][00300] Avg episode reward: [(0, '21.965')] | |
| [2024-11-06 21:53:30,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3873.8). Total num frames: 3575808. Throughput: 0: 961.6. Samples: 894426. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-11-06 21:53:30,421][00300] Avg episode reward: [(0, '23.579')] | |
| [2024-11-06 21:53:35,414][00300] Fps is (10 sec: 3686.8, 60 sec: 3959.5, 300 sec: 3915.5). Total num frames: 3600384. Throughput: 0: 954.3. Samples: 897514. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:53:35,422][00300] Avg episode reward: [(0, '23.481')] | |
| [2024-11-06 21:53:36,266][03124] Updated weights for policy 0, policy_version 880 (0.0026) | |
| [2024-11-06 21:53:40,414][00300] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3915.5). Total num frames: 3620864. Throughput: 0: 1000.0. Samples: 904656. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-11-06 21:53:40,424][00300] Avg episode reward: [(0, '24.592')] | |
| [2024-11-06 21:53:40,438][03111] Saving new best policy, reward=24.592! | |
| [2024-11-06 21:53:45,414][00300] Fps is (10 sec: 3686.3, 60 sec: 3891.2, 300 sec: 3887.7). Total num frames: 3637248. Throughput: 0: 989.7. Samples: 909774. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:53:45,419][00300] Avg episode reward: [(0, '24.163')] | |
| [2024-11-06 21:53:47,510][03124] Updated weights for policy 0, policy_version 890 (0.0015) | |
| [2024-11-06 21:53:50,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3891.3, 300 sec: 3901.6). Total num frames: 3657728. Throughput: 0: 961.7. Samples: 912032. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-11-06 21:53:50,418][00300] Avg episode reward: [(0, '24.178')] | |
| [2024-11-06 21:53:55,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3915.5). Total num frames: 3678208. Throughput: 0: 984.4. Samples: 919142. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-11-06 21:53:55,417][00300] Avg episode reward: [(0, '23.278')] | |
| [2024-11-06 21:53:56,342][03124] Updated weights for policy 0, policy_version 900 (0.0023) | |
| [2024-11-06 21:54:00,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 3698688. Throughput: 0: 1005.6. Samples: 925050. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-11-06 21:54:00,422][00300] Avg episode reward: [(0, '23.201')] | |
| [2024-11-06 21:54:05,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3887.7). Total num frames: 3715072. Throughput: 0: 976.5. Samples: 927210. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-11-06 21:54:05,419][00300] Avg episode reward: [(0, '21.942')] | |
| [2024-11-06 21:54:07,811][03124] Updated weights for policy 0, policy_version 910 (0.0016) | |
| [2024-11-06 21:54:10,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3915.5). Total num frames: 3739648. Throughput: 0: 960.8. Samples: 933418. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:54:10,420][00300] Avg episode reward: [(0, '22.543')] | |
| [2024-11-06 21:54:15,414][00300] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3915.5). Total num frames: 3760128. Throughput: 0: 1022.7. Samples: 940448. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:54:15,417][00300] Avg episode reward: [(0, '23.168')] | |
| [2024-11-06 21:54:17,791][03124] Updated weights for policy 0, policy_version 920 (0.0014) | |
| [2024-11-06 21:54:20,414][00300] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3887.7). Total num frames: 3772416. Throughput: 0: 1002.1. Samples: 942608. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:54:20,424][00300] Avg episode reward: [(0, '23.218')] | |
| [2024-11-06 21:54:25,416][00300] Fps is (10 sec: 3686.0, 60 sec: 3891.2, 300 sec: 3915.5). Total num frames: 3796992. Throughput: 0: 962.6. Samples: 947976. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:54:25,423][00300] Avg episode reward: [(0, '23.235')] | |
| [2024-11-06 21:54:27,965][03124] Updated weights for policy 0, policy_version 930 (0.0026) | |
| [2024-11-06 21:54:30,414][00300] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3915.5). Total num frames: 3817472. Throughput: 0: 1004.1. Samples: 954960. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:54:30,421][00300] Avg episode reward: [(0, '22.795')] | |
| [2024-11-06 21:54:35,414][00300] Fps is (10 sec: 3686.8, 60 sec: 3891.2, 300 sec: 3887.7). Total num frames: 3833856. Throughput: 0: 1016.0. Samples: 957754. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-11-06 21:54:35,417][00300] Avg episode reward: [(0, '23.031')] | |
| [2024-11-06 21:54:39,410][03124] Updated weights for policy 0, policy_version 940 (0.0023) | |
| [2024-11-06 21:54:40,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3901.6). Total num frames: 3854336. Throughput: 0: 958.8. Samples: 962288. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:54:40,417][00300] Avg episode reward: [(0, '23.293')] | |
| [2024-11-06 21:54:45,414][00300] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3915.5). Total num frames: 3874816. Throughput: 0: 984.6. Samples: 969358. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:54:45,416][00300] Avg episode reward: [(0, '22.732')] | |
| [2024-11-06 21:54:48,167][03124] Updated weights for policy 0, policy_version 950 (0.0023) | |
| [2024-11-06 21:54:50,416][00300] Fps is (10 sec: 4095.1, 60 sec: 3959.3, 300 sec: 3915.5). Total num frames: 3895296. Throughput: 0: 1013.9. Samples: 972838. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:54:50,421][00300] Avg episode reward: [(0, '22.900')] | |
| [2024-11-06 21:54:55,414][00300] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3901.6). Total num frames: 3911680. Throughput: 0: 978.6. Samples: 977454. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-11-06 21:54:55,417][00300] Avg episode reward: [(0, '23.323')] | |
| [2024-11-06 21:54:59,751][03124] Updated weights for policy 0, policy_version 960 (0.0018) | |
| [2024-11-06 21:55:00,414][00300] Fps is (10 sec: 3687.2, 60 sec: 3891.2, 300 sec: 3915.5). Total num frames: 3932160. Throughput: 0: 960.0. Samples: 983648. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-11-06 21:55:00,422][00300] Avg episode reward: [(0, '22.401')] | |
| [2024-11-06 21:55:05,416][00300] Fps is (10 sec: 4504.7, 60 sec: 4027.6, 300 sec: 3929.4). Total num frames: 3956736. Throughput: 0: 990.5. Samples: 987184. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-11-06 21:55:05,420][00300] Avg episode reward: [(0, '21.932')] | |
| [2024-11-06 21:55:10,415][00300] Fps is (10 sec: 3686.3, 60 sec: 3822.9, 300 sec: 3901.6). Total num frames: 3969024. Throughput: 0: 992.3. Samples: 992630. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:55:10,420][00300] Avg episode reward: [(0, '21.944')] | |
| [2024-11-06 21:55:10,479][03124] Updated weights for policy 0, policy_version 970 (0.0018) | |
| [2024-11-06 21:55:15,414][00300] Fps is (10 sec: 3687.1, 60 sec: 3891.2, 300 sec: 3929.4). Total num frames: 3993600. Throughput: 0: 960.1. Samples: 998164. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-11-06 21:55:15,424][00300] Avg episode reward: [(0, '22.384')] | |
| [2024-11-06 21:55:17,970][03111] Stopping Batcher_0... | |
| [2024-11-06 21:55:17,971][03111] Loop batcher_evt_loop terminating... | |
| [2024-11-06 21:55:17,972][03111] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2024-11-06 21:55:17,978][00300] Component Batcher_0 stopped! | |
| [2024-11-06 21:55:18,034][03124] Weights refcount: 2 0 | |
| [2024-11-06 21:55:18,037][00300] Component InferenceWorker_p0-w0 stopped! | |
| [2024-11-06 21:55:18,042][03124] Stopping InferenceWorker_p0-w0... | |
| [2024-11-06 21:55:18,042][03124] Loop inference_proc0-0_evt_loop terminating... | |
| [2024-11-06 21:55:18,104][03111] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000750_3072000.pth | |
| [2024-11-06 21:55:18,115][03111] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2024-11-06 21:55:18,307][00300] Component LearnerWorker_p0 stopped! | |
| [2024-11-06 21:55:18,312][03111] Stopping LearnerWorker_p0... | |
| [2024-11-06 21:55:18,312][03111] Loop learner_proc0_evt_loop terminating... | |
| [2024-11-06 21:55:18,386][03136] Stopping RolloutWorker_w7... | |
| [2024-11-06 21:55:18,387][00300] Component RolloutWorker_w7 stopped! | |
| [2024-11-06 21:55:18,388][03136] Loop rollout_proc7_evt_loop terminating... | |
| [2024-11-06 21:55:18,410][03125] Stopping RolloutWorker_w1... | |
| [2024-11-06 21:55:18,409][00300] Component RolloutWorker_w5 stopped! | |
| [2024-11-06 21:55:18,412][00300] Component RolloutWorker_w1 stopped! | |
| [2024-11-06 21:55:18,408][03132] Stopping RolloutWorker_w5... | |
| [2024-11-06 21:55:18,417][03132] Loop rollout_proc5_evt_loop terminating... | |
| [2024-11-06 21:55:18,420][03125] Loop rollout_proc1_evt_loop terminating... | |
| [2024-11-06 21:55:18,450][03133] Stopping RolloutWorker_w3... | |
| [2024-11-06 21:55:18,450][00300] Component RolloutWorker_w3 stopped! | |
| [2024-11-06 21:55:18,451][03133] Loop rollout_proc3_evt_loop terminating... | |
| [2024-11-06 21:55:18,565][00300] Component RolloutWorker_w0 stopped! | |
| [2024-11-06 21:55:18,572][03126] Stopping RolloutWorker_w0... | |
| [2024-11-06 21:55:18,578][00300] Component RolloutWorker_w4 stopped! | |
| [2024-11-06 21:55:18,585][03134] Stopping RolloutWorker_w4... | |
| [2024-11-06 21:55:18,586][03134] Loop rollout_proc4_evt_loop terminating... | |
| [2024-11-06 21:55:18,593][03126] Loop rollout_proc0_evt_loop terminating... | |
| [2024-11-06 21:55:18,605][00300] Component RolloutWorker_w2 stopped! | |
| [2024-11-06 21:55:18,611][03129] Stopping RolloutWorker_w2... | |
| [2024-11-06 21:55:18,612][03129] Loop rollout_proc2_evt_loop terminating... | |
| [2024-11-06 21:55:18,617][00300] Component RolloutWorker_w6 stopped! | |
| [2024-11-06 21:55:18,623][00300] Waiting for process learner_proc0 to stop... | |
| [2024-11-06 21:55:18,629][03135] Stopping RolloutWorker_w6... | |
| [2024-11-06 21:55:18,631][03135] Loop rollout_proc6_evt_loop terminating... | |
| [2024-11-06 21:55:19,918][00300] Waiting for process inference_proc0-0 to join... | |
| [2024-11-06 21:55:20,038][00300] Waiting for process rollout_proc0 to join... | |
| [2024-11-06 21:55:21,455][00300] Waiting for process rollout_proc1 to join... | |
| [2024-11-06 21:55:21,468][00300] Waiting for process rollout_proc2 to join... | |
| [2024-11-06 21:55:21,475][00300] Waiting for process rollout_proc3 to join... | |
| [2024-11-06 21:55:21,483][00300] Waiting for process rollout_proc4 to join... | |
| [2024-11-06 21:55:21,486][00300] Waiting for process rollout_proc5 to join... | |
| [2024-11-06 21:55:21,491][00300] Waiting for process rollout_proc6 to join... | |
| [2024-11-06 21:55:21,495][00300] Waiting for process rollout_proc7 to join... | |
| [2024-11-06 21:55:21,500][00300] Batcher 0 profile tree view: | |
| batching: 26.1201, releasing_batches: 0.0229 | |
| [2024-11-06 21:55:21,502][00300] InferenceWorker_p0-w0 profile tree view: | |
| wait_policy: 0.0000 | |
| wait_policy_total: 454.8841 | |
| update_model: 7.5429 | |
| weight_update: 0.0028 | |
| one_step: 0.0026 | |
| handle_policy_step: 549.6425 | |
| deserialize: 14.2964, stack: 2.8409, obs_to_device_normalize: 113.9823, forward: 275.7001, send_messages: 27.5176 | |
| prepare_outputs: 87.2238 | |
| to_cpu: 54.5264 | |
| [2024-11-06 21:55:21,504][00300] Learner 0 profile tree view: | |
| misc: 0.0057, prepare_batch: 16.1782 | |
| train: 73.3230 | |
| epoch_init: 0.0059, minibatch_init: 0.0165, losses_postprocess: 0.5650, kl_divergence: 0.6361, after_optimizer: 32.6590 | |
| calculate_losses: 24.6392 | |
| losses_init: 0.0057, forward_head: 1.8155, bptt_initial: 15.7321, tail: 1.2067, advantages_returns: 0.3239, losses: 2.9433 | |
| bptt: 2.2568 | |
| bptt_forward_core: 2.1714 | |
| update: 14.1923 | |
| clip: 1.4605 | |
| [2024-11-06 21:55:21,506][00300] RolloutWorker_w0 profile tree view: | |
| wait_for_trajectories: 0.3040, enqueue_policy_requests: 113.4285, env_step: 820.7355, overhead: 13.2954, complete_rollouts: 6.8615 | |
| save_policy_outputs: 24.1083 | |
| split_output_tensors: 7.7895 | |
| [2024-11-06 21:55:21,508][00300] RolloutWorker_w7 profile tree view: | |
| wait_for_trajectories: 0.4231, enqueue_policy_requests: 109.6972, env_step: 821.4177, overhead: 13.5272, complete_rollouts: 7.4959 | |
| save_policy_outputs: 24.0075 | |
| split_output_tensors: 8.2156 | |
| [2024-11-06 21:55:21,511][00300] Loop Runner_EvtLoop terminating... | |
| [2024-11-06 21:55:21,513][00300] Runner profile tree view: | |
| main_loop: 1077.6373 | |
| [2024-11-06 21:55:21,514][00300] Collected {0: 4005888}, FPS: 3717.3 | |
| [2024-11-06 21:55:46,725][00300] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2024-11-06 21:55:46,732][00300] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2024-11-06 21:55:46,737][00300] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2024-11-06 21:55:46,741][00300] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2024-11-06 21:55:46,743][00300] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2024-11-06 21:55:46,747][00300] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2024-11-06 21:55:46,750][00300] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! | |
| [2024-11-06 21:55:46,752][00300] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2024-11-06 21:55:46,752][00300] Adding new argument 'push_to_hub'=False that is not in the saved config file! | |
| [2024-11-06 21:55:46,753][00300] Adding new argument 'hf_repository'=None that is not in the saved config file! | |
| [2024-11-06 21:55:46,754][00300] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2024-11-06 21:55:46,755][00300] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2024-11-06 21:55:46,756][00300] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2024-11-06 21:55:46,770][00300] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2024-11-06 21:55:46,771][00300] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2024-11-06 21:55:46,810][00300] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-11-06 21:55:46,828][00300] RunningMeanStd input shape: (3, 72, 128) | |
| [2024-11-06 21:55:46,840][00300] RunningMeanStd input shape: (1,) | |
| [2024-11-06 21:55:46,917][00300] ConvEncoder: input_channels=3 | |
| [2024-11-06 21:55:47,385][00300] Conv encoder output size: 512 | |
| [2024-11-06 21:55:47,389][00300] Policy head output size: 512 | |
| [2024-11-06 21:55:49,310][00300] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2024-11-06 21:55:50,157][00300] Num frames 100... | |
| [2024-11-06 21:55:50,276][00300] Num frames 200... | |
| [2024-11-06 21:55:50,396][00300] Num frames 300... | |
| [2024-11-06 21:55:50,521][00300] Num frames 400... | |
| [2024-11-06 21:55:50,644][00300] Num frames 500... | |
| [2024-11-06 21:55:50,764][00300] Num frames 600... | |
| [2024-11-06 21:55:50,884][00300] Num frames 700... | |
| [2024-11-06 21:55:51,002][00300] Num frames 800... | |
| [2024-11-06 21:55:51,117][00300] Num frames 900... | |
| [2024-11-06 21:55:51,241][00300] Num frames 1000... | |
| [2024-11-06 21:55:51,358][00300] Num frames 1100... | |
| [2024-11-06 21:55:51,483][00300] Num frames 1200... | |
| [2024-11-06 21:55:51,606][00300] Num frames 1300... | |
| [2024-11-06 21:55:51,723][00300] Num frames 1400... | |
| [2024-11-06 21:55:51,844][00300] Num frames 1500... | |
| [2024-11-06 21:55:51,964][00300] Num frames 1600... | |
| [2024-11-06 21:55:52,094][00300] Num frames 1700... | |
| [2024-11-06 21:55:52,226][00300] Num frames 1800... | |
| [2024-11-06 21:55:52,345][00300] Num frames 1900... | |
| [2024-11-06 21:55:52,455][00300] Avg episode rewards: #0: 52.459, true rewards: #0: 19.460 | |
| [2024-11-06 21:55:52,457][00300] Avg episode reward: 52.459, avg true_objective: 19.460 | |
| [2024-11-06 21:55:52,525][00300] Num frames 2000... | |
| [2024-11-06 21:55:52,644][00300] Num frames 2100... | |
| [2024-11-06 21:55:52,764][00300] Num frames 2200... | |
| [2024-11-06 21:55:52,883][00300] Num frames 2300... | |
| [2024-11-06 21:55:53,001][00300] Num frames 2400... | |
| [2024-11-06 21:55:53,118][00300] Num frames 2500... | |
| [2024-11-06 21:55:53,244][00300] Num frames 2600... | |
| [2024-11-06 21:55:53,360][00300] Num frames 2700... | |
| [2024-11-06 21:55:53,492][00300] Num frames 2800... | |
| [2024-11-06 21:55:53,618][00300] Num frames 2900... | |
| [2024-11-06 21:55:53,737][00300] Num frames 3000... | |
| [2024-11-06 21:55:53,854][00300] Num frames 3100... | |
| [2024-11-06 21:55:53,977][00300] Num frames 3200... | |
| [2024-11-06 21:55:54,093][00300] Num frames 3300... | |
| [2024-11-06 21:55:54,208][00300] Num frames 3400... | |
| [2024-11-06 21:55:54,336][00300] Num frames 3500... | |
| [2024-11-06 21:55:54,463][00300] Num frames 3600... | |
| [2024-11-06 21:55:54,589][00300] Num frames 3700... | |
| [2024-11-06 21:55:54,672][00300] Avg episode rewards: #0: 49.609, true rewards: #0: 18.610 | |
| [2024-11-06 21:55:54,674][00300] Avg episode reward: 49.609, avg true_objective: 18.610 | |
| [2024-11-06 21:55:54,764][00300] Num frames 3800... | |
| [2024-11-06 21:55:54,879][00300] Num frames 3900... | |
| [2024-11-06 21:55:55,002][00300] Num frames 4000... | |
| [2024-11-06 21:55:55,119][00300] Num frames 4100... | |
| [2024-11-06 21:55:55,254][00300] Avg episode rewards: #0: 34.899, true rewards: #0: 13.900 | |
| [2024-11-06 21:55:55,256][00300] Avg episode reward: 34.899, avg true_objective: 13.900 | |
| [2024-11-06 21:55:55,300][00300] Num frames 4200... | |
| [2024-11-06 21:55:55,419][00300] Num frames 4300... | |
| [2024-11-06 21:55:55,546][00300] Num frames 4400... | |
| [2024-11-06 21:55:55,665][00300] Num frames 4500... | |
| [2024-11-06 21:55:55,783][00300] Num frames 4600... | |
| [2024-11-06 21:55:55,900][00300] Num frames 4700... | |
| [2024-11-06 21:55:56,020][00300] Num frames 4800... | |
| [2024-11-06 21:55:56,110][00300] Avg episode rewards: #0: 28.817, true rewards: #0: 12.068 | |
| [2024-11-06 21:55:56,111][00300] Avg episode reward: 28.817, avg true_objective: 12.068 | |
| [2024-11-06 21:55:56,197][00300] Num frames 4900... | |
| [2024-11-06 21:55:56,323][00300] Num frames 5000... | |
| [2024-11-06 21:55:56,448][00300] Num frames 5100... | |
| [2024-11-06 21:55:56,567][00300] Num frames 5200... | |
| [2024-11-06 21:55:56,677][00300] Avg episode rewards: #0: 24.486, true rewards: #0: 10.486 | |
| [2024-11-06 21:55:56,680][00300] Avg episode reward: 24.486, avg true_objective: 10.486 | |
| [2024-11-06 21:55:56,751][00300] Num frames 5300... | |
| [2024-11-06 21:55:56,867][00300] Num frames 5400... | |
| [2024-11-06 21:55:56,987][00300] Num frames 5500... | |
| [2024-11-06 21:55:57,108][00300] Num frames 5600... | |
| [2024-11-06 21:55:57,227][00300] Num frames 5700... | |
| [2024-11-06 21:55:57,393][00300] Avg episode rewards: #0: 22.311, true rewards: #0: 9.645 | |
| [2024-11-06 21:55:57,395][00300] Avg episode reward: 22.311, avg true_objective: 9.645 | |
| [2024-11-06 21:55:57,415][00300] Num frames 5800... | |
| [2024-11-06 21:55:57,581][00300] Num frames 5900... | |
| [2024-11-06 21:55:57,742][00300] Num frames 6000... | |
| [2024-11-06 21:55:57,896][00300] Num frames 6100... | |
| [2024-11-06 21:55:58,071][00300] Num frames 6200... | |
| [2024-11-06 21:55:58,236][00300] Avg episode rewards: #0: 19.953, true rewards: #0: 8.953 | |
| [2024-11-06 21:55:58,238][00300] Avg episode reward: 19.953, avg true_objective: 8.953 | |
| [2024-11-06 21:55:58,308][00300] Num frames 6300... | |
| [2024-11-06 21:55:58,515][00300] Num frames 6400... | |
| [2024-11-06 21:55:58,687][00300] Num frames 6500... | |
| [2024-11-06 21:55:58,869][00300] Num frames 6600... | |
| [2024-11-06 21:55:59,047][00300] Num frames 6700... | |
| [2024-11-06 21:55:59,217][00300] Num frames 6800... | |
| [2024-11-06 21:55:59,384][00300] Num frames 6900... | |
| [2024-11-06 21:55:59,565][00300] Num frames 7000... | |
| [2024-11-06 21:55:59,629][00300] Avg episode rewards: #0: 19.504, true rewards: #0: 8.754 | |
| [2024-11-06 21:55:59,630][00300] Avg episode reward: 19.504, avg true_objective: 8.754 | |
| [2024-11-06 21:55:59,794][00300] Num frames 7100... | |
| [2024-11-06 21:55:59,975][00300] Num frames 7200... | |
| [2024-11-06 21:56:00,144][00300] Num frames 7300... | |
| [2024-11-06 21:56:00,314][00300] Num frames 7400... | |
| [2024-11-06 21:56:00,503][00300] Num frames 7500... | |
| [2024-11-06 21:56:00,631][00300] Num frames 7600... | |
| [2024-11-06 21:56:00,753][00300] Num frames 7700... | |
| [2024-11-06 21:56:00,871][00300] Num frames 7800... | |
| [2024-11-06 21:56:00,993][00300] Num frames 7900... | |
| [2024-11-06 21:56:01,110][00300] Num frames 8000... | |
| [2024-11-06 21:56:01,231][00300] Num frames 8100... | |
| [2024-11-06 21:56:01,348][00300] Num frames 8200... | |
| [2024-11-06 21:56:01,483][00300] Num frames 8300... | |
| [2024-11-06 21:56:01,601][00300] Num frames 8400... | |
| [2024-11-06 21:56:01,720][00300] Num frames 8500... | |
| [2024-11-06 21:56:01,836][00300] Num frames 8600... | |
| [2024-11-06 21:56:01,954][00300] Num frames 8700... | |
| [2024-11-06 21:56:02,075][00300] Num frames 8800... | |
| [2024-11-06 21:56:02,192][00300] Num frames 8900... | |
| [2024-11-06 21:56:02,315][00300] Num frames 9000... | |
| [2024-11-06 21:56:02,382][00300] Avg episode rewards: #0: 23.450, true rewards: #0: 10.006 | |
| [2024-11-06 21:56:02,384][00300] Avg episode reward: 23.450, avg true_objective: 10.006 | |
| [2024-11-06 21:56:02,515][00300] Num frames 9100... | |
| [2024-11-06 21:56:02,637][00300] Num frames 9200... | |
| [2024-11-06 21:56:02,757][00300] Num frames 9300... | |
| [2024-11-06 21:56:02,875][00300] Num frames 9400... | |
| [2024-11-06 21:56:02,998][00300] Num frames 9500... | |
| [2024-11-06 21:56:03,117][00300] Num frames 9600... | |
| [2024-11-06 21:56:03,234][00300] Num frames 9700... | |
| [2024-11-06 21:56:03,303][00300] Avg episode rewards: #0: 22.709, true rewards: #0: 9.709 | |
| [2024-11-06 21:56:03,305][00300] Avg episode reward: 22.709, avg true_objective: 9.709 | |
| [2024-11-06 21:57:04,120][00300] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |
| [2024-11-06 21:57:53,990][00300] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2024-11-06 21:57:53,992][00300] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2024-11-06 21:57:53,994][00300] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2024-11-06 21:57:53,996][00300] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2024-11-06 21:57:53,997][00300] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2024-11-06 21:57:53,998][00300] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2024-11-06 21:57:54,000][00300] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! | |
| [2024-11-06 21:57:54,001][00300] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2024-11-06 21:57:54,002][00300] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2024-11-06 21:57:54,006][00300] Adding new argument 'hf_repository'='mnnee/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2024-11-06 21:57:54,007][00300] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2024-11-06 21:57:54,008][00300] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2024-11-06 21:57:54,009][00300] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2024-11-06 21:57:54,013][00300] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2024-11-06 21:57:54,014][00300] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2024-11-06 21:57:54,023][00300] RunningMeanStd input shape: (3, 72, 128) | |
| [2024-11-06 21:57:54,027][00300] RunningMeanStd input shape: (1,) | |
| [2024-11-06 21:57:54,041][00300] ConvEncoder: input_channels=3 | |
| [2024-11-06 21:57:54,075][00300] Conv encoder output size: 512 | |
| [2024-11-06 21:57:54,078][00300] Policy head output size: 512 | |
| [2024-11-06 21:57:54,095][00300] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2024-11-06 21:57:54,569][00300] Num frames 100... | |
| [2024-11-06 21:57:54,688][00300] Num frames 200... | |
| [2024-11-06 21:57:54,811][00300] Num frames 300... | |
| [2024-11-06 21:57:54,927][00300] Num frames 400... | |
| [2024-11-06 21:57:55,044][00300] Num frames 500... | |
| [2024-11-06 21:57:55,157][00300] Num frames 600... | |
| [2024-11-06 21:57:55,271][00300] Num frames 700... | |
| [2024-11-06 21:57:55,369][00300] Avg episode rewards: #0: 13.360, true rewards: #0: 7.360 | |
| [2024-11-06 21:57:55,370][00300] Avg episode reward: 13.360, avg true_objective: 7.360 | |
| [2024-11-06 21:57:55,460][00300] Num frames 800... | |
| [2024-11-06 21:57:55,582][00300] Num frames 900... | |
| [2024-11-06 21:57:55,702][00300] Num frames 1000... | |
| [2024-11-06 21:57:55,831][00300] Num frames 1100... | |
| [2024-11-06 21:57:55,949][00300] Num frames 1200... | |
| [2024-11-06 21:57:56,073][00300] Num frames 1300... | |
| [2024-11-06 21:57:56,191][00300] Num frames 1400... | |
| [2024-11-06 21:57:56,312][00300] Num frames 1500... | |
| [2024-11-06 21:57:56,435][00300] Num frames 1600... | |
| [2024-11-06 21:57:56,555][00300] Num frames 1700... | |
| [2024-11-06 21:57:56,677][00300] Num frames 1800... | |
| [2024-11-06 21:57:56,762][00300] Avg episode rewards: #0: 18.620, true rewards: #0: 9.120 | |
| [2024-11-06 21:57:56,763][00300] Avg episode reward: 18.620, avg true_objective: 9.120 | |
| [2024-11-06 21:57:56,855][00300] Num frames 1900... | |
| [2024-11-06 21:57:56,975][00300] Num frames 2000... | |
| [2024-11-06 21:57:57,090][00300] Num frames 2100... | |
| [2024-11-06 21:57:57,222][00300] Num frames 2200... | |
| [2024-11-06 21:57:57,339][00300] Num frames 2300... | |
| [2024-11-06 21:57:57,468][00300] Num frames 2400... | |
| [2024-11-06 21:57:57,589][00300] Num frames 2500... | |
| [2024-11-06 21:57:57,706][00300] Num frames 2600... | |
| [2024-11-06 21:57:57,832][00300] Num frames 2700... | |
| [2024-11-06 21:57:57,912][00300] Avg episode rewards: #0: 18.733, true rewards: #0: 9.067 | |
| [2024-11-06 21:57:57,916][00300] Avg episode reward: 18.733, avg true_objective: 9.067 | |
| [2024-11-06 21:57:58,012][00300] Num frames 2800... | |
| [2024-11-06 21:57:58,127][00300] Num frames 2900... | |
| [2024-11-06 21:57:58,245][00300] Num frames 3000... | |
| [2024-11-06 21:57:58,364][00300] Num frames 3100... | |
| [2024-11-06 21:57:58,490][00300] Num frames 3200... | |
| [2024-11-06 21:57:58,605][00300] Num frames 3300... | |
| [2024-11-06 21:57:58,721][00300] Num frames 3400... | |
| [2024-11-06 21:57:58,847][00300] Num frames 3500... | |
| [2024-11-06 21:57:58,966][00300] Num frames 3600... | |
| [2024-11-06 21:57:59,082][00300] Num frames 3700... | |
| [2024-11-06 21:57:59,195][00300] Num frames 3800... | |
| [2024-11-06 21:57:59,316][00300] Num frames 3900... | |
| [2024-11-06 21:57:59,436][00300] Num frames 4000... | |
| [2024-11-06 21:57:59,558][00300] Num frames 4100... | |
| [2024-11-06 21:57:59,687][00300] Num frames 4200... | |
| [2024-11-06 21:57:59,807][00300] Num frames 4300... | |
| [2024-11-06 21:57:59,937][00300] Num frames 4400... | |
| [2024-11-06 21:58:00,057][00300] Num frames 4500... | |
| [2024-11-06 21:58:00,175][00300] Num frames 4600... | |
| [2024-11-06 21:58:00,295][00300] Num frames 4700... | |
| [2024-11-06 21:58:00,455][00300] Num frames 4800... | |
| [2024-11-06 21:58:00,540][00300] Avg episode rewards: #0: 29.800, true rewards: #0: 12.050 | |
| [2024-11-06 21:58:00,541][00300] Avg episode reward: 29.800, avg true_objective: 12.050 | |
| [2024-11-06 21:58:00,635][00300] Num frames 4900... | |
| [2024-11-06 21:58:00,751][00300] Num frames 5000... | |
| [2024-11-06 21:58:00,879][00300] Num frames 5100... | |
| [2024-11-06 21:58:01,001][00300] Num frames 5200... | |
| [2024-11-06 21:58:01,120][00300] Num frames 5300... | |
| [2024-11-06 21:58:01,253][00300] Num frames 5400... | |
| [2024-11-06 21:58:01,416][00300] Num frames 5500... | |
| [2024-11-06 21:58:01,588][00300] Num frames 5600... | |
| [2024-11-06 21:58:01,748][00300] Num frames 5700... | |
| [2024-11-06 21:58:01,925][00300] Num frames 5800... | |
| [2024-11-06 21:58:02,092][00300] Num frames 5900... | |
| [2024-11-06 21:58:02,248][00300] Num frames 6000... | |
| [2024-11-06 21:58:02,363][00300] Avg episode rewards: #0: 29.672, true rewards: #0: 12.072 | |
| [2024-11-06 21:58:02,365][00300] Avg episode reward: 29.672, avg true_objective: 12.072 | |
| [2024-11-06 21:58:02,468][00300] Num frames 6100... | |
| [2024-11-06 21:58:02,635][00300] Num frames 6200... | |
| [2024-11-06 21:58:02,799][00300] Num frames 6300... | |
| [2024-11-06 21:58:02,974][00300] Num frames 6400... | |
| [2024-11-06 21:58:03,146][00300] Num frames 6500... | |
| [2024-11-06 21:58:03,311][00300] Num frames 6600... | |
| [2024-11-06 21:58:03,482][00300] Num frames 6700... | |
| [2024-11-06 21:58:03,607][00300] Avg episode rewards: #0: 26.733, true rewards: #0: 11.233 | |
| [2024-11-06 21:58:03,610][00300] Avg episode reward: 26.733, avg true_objective: 11.233 | |
| [2024-11-06 21:58:03,714][00300] Num frames 6800... | |
| [2024-11-06 21:58:03,828][00300] Num frames 6900... | |
| [2024-11-06 21:58:03,946][00300] Num frames 7000... | |
| [2024-11-06 21:58:04,071][00300] Num frames 7100... | |
| [2024-11-06 21:58:04,185][00300] Num frames 7200... | |
| [2024-11-06 21:58:04,302][00300] Num frames 7300... | |
| [2024-11-06 21:58:04,421][00300] Num frames 7400... | |
| [2024-11-06 21:58:04,543][00300] Num frames 7500... | |
| [2024-11-06 21:58:04,658][00300] Num frames 7600... | |
| [2024-11-06 21:58:04,793][00300] Avg episode rewards: #0: 25.954, true rewards: #0: 10.954 | |
| [2024-11-06 21:58:04,795][00300] Avg episode reward: 25.954, avg true_objective: 10.954 | |
| [2024-11-06 21:58:04,834][00300] Num frames 7700... | |
| [2024-11-06 21:58:04,951][00300] Num frames 7800... | |
| [2024-11-06 21:58:05,078][00300] Num frames 7900... | |
| [2024-11-06 21:58:05,194][00300] Num frames 8000... | |
| [2024-11-06 21:58:05,325][00300] Num frames 8100... | |
| [2024-11-06 21:58:05,459][00300] Num frames 8200... | |
| [2024-11-06 21:58:05,602][00300] Avg episode rewards: #0: 23.845, true rewards: #0: 10.345 | |
| [2024-11-06 21:58:05,603][00300] Avg episode reward: 23.845, avg true_objective: 10.345 | |
| [2024-11-06 21:58:05,637][00300] Num frames 8300... | |
| [2024-11-06 21:58:05,759][00300] Num frames 8400... | |
| [2024-11-06 21:58:05,875][00300] Num frames 8500... | |
| [2024-11-06 21:58:05,994][00300] Num frames 8600... | |
| [2024-11-06 21:58:06,122][00300] Num frames 8700... | |
| [2024-11-06 21:58:06,238][00300] Num frames 8800... | |
| [2024-11-06 21:58:06,354][00300] Num frames 8900... | |
| [2024-11-06 21:58:06,511][00300] Avg episode rewards: #0: 22.756, true rewards: #0: 9.978 | |
| [2024-11-06 21:58:06,515][00300] Avg episode reward: 22.756, avg true_objective: 9.978 | |
| [2024-11-06 21:58:06,541][00300] Num frames 9000... | |
| [2024-11-06 21:58:06,660][00300] Num frames 9100... | |
| [2024-11-06 21:58:06,778][00300] Num frames 9200... | |
| [2024-11-06 21:58:06,895][00300] Num frames 9300... | |
| [2024-11-06 21:58:07,015][00300] Num frames 9400... | |
| [2024-11-06 21:58:07,144][00300] Num frames 9500... | |
| [2024-11-06 21:58:07,228][00300] Avg episode rewards: #0: 21.424, true rewards: #0: 9.524 | |
| [2024-11-06 21:58:07,229][00300] Avg episode reward: 21.424, avg true_objective: 9.524 | |
| [2024-11-06 21:59:07,149][00300] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |
| [2024-11-06 21:59:26,084][00300] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2024-11-06 21:59:26,086][00300] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2024-11-06 21:59:26,087][00300] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2024-11-06 21:59:26,089][00300] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2024-11-06 21:59:26,091][00300] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2024-11-06 21:59:26,092][00300] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2024-11-06 21:59:26,094][00300] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! | |
| [2024-11-06 21:59:26,095][00300] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2024-11-06 21:59:26,098][00300] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2024-11-06 21:59:26,099][00300] Adding new argument 'hf_repository'='mnneely/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2024-11-06 21:59:26,101][00300] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2024-11-06 21:59:26,103][00300] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2024-11-06 21:59:26,104][00300] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2024-11-06 21:59:26,106][00300] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2024-11-06 21:59:26,107][00300] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2024-11-06 21:59:26,120][00300] RunningMeanStd input shape: (3, 72, 128) | |
| [2024-11-06 21:59:26,123][00300] RunningMeanStd input shape: (1,) | |
| [2024-11-06 21:59:26,137][00300] ConvEncoder: input_channels=3 | |
| [2024-11-06 21:59:26,172][00300] Conv encoder output size: 512 | |
| [2024-11-06 21:59:26,174][00300] Policy head output size: 512 | |
| [2024-11-06 21:59:26,192][00300] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2024-11-06 21:59:26,664][00300] Num frames 100... | |
| [2024-11-06 21:59:26,789][00300] Num frames 200... | |
| [2024-11-06 21:59:26,910][00300] Num frames 300... | |
| [2024-11-06 21:59:27,026][00300] Num frames 400... | |
| [2024-11-06 21:59:27,174][00300] Avg episode rewards: #0: 7.800, true rewards: #0: 4.800 | |
| [2024-11-06 21:59:27,176][00300] Avg episode reward: 7.800, avg true_objective: 4.800 | |
| [2024-11-06 21:59:27,203][00300] Num frames 500... | |
| [2024-11-06 21:59:27,323][00300] Num frames 600... | |
| [2024-11-06 21:59:27,452][00300] Num frames 700... | |
| [2024-11-06 21:59:27,569][00300] Num frames 800... | |
| [2024-11-06 21:59:27,662][00300] Avg episode rewards: #0: 6.660, true rewards: #0: 4.160 | |
| [2024-11-06 21:59:27,664][00300] Avg episode reward: 6.660, avg true_objective: 4.160 | |
| [2024-11-06 21:59:27,745][00300] Num frames 900... | |
| [2024-11-06 21:59:27,872][00300] Num frames 1000... | |
| [2024-11-06 21:59:27,993][00300] Num frames 1100... | |
| [2024-11-06 21:59:28,115][00300] Num frames 1200... | |
| [2024-11-06 21:59:28,235][00300] Num frames 1300... | |
| [2024-11-06 21:59:28,381][00300] Avg episode rewards: #0: 8.920, true rewards: #0: 4.587 | |
| [2024-11-06 21:59:28,383][00300] Avg episode reward: 8.920, avg true_objective: 4.587 | |
| [2024-11-06 21:59:28,414][00300] Num frames 1400... | |
| [2024-11-06 21:59:28,544][00300] Num frames 1500... | |
| [2024-11-06 21:59:28,663][00300] Num frames 1600... | |
| [2024-11-06 21:59:28,780][00300] Num frames 1700... | |
| [2024-11-06 21:59:28,904][00300] Num frames 1800... | |
| [2024-11-06 21:59:29,024][00300] Num frames 1900... | |
| [2024-11-06 21:59:29,141][00300] Num frames 2000... | |
| [2024-11-06 21:59:29,261][00300] Num frames 2100... | |
| [2024-11-06 21:59:29,379][00300] Num frames 2200... | |
| [2024-11-06 21:59:29,491][00300] Avg episode rewards: #0: 10.350, true rewards: #0: 5.600 | |
| [2024-11-06 21:59:29,493][00300] Avg episode reward: 10.350, avg true_objective: 5.600 | |
| [2024-11-06 21:59:29,565][00300] Num frames 2300... | |
| [2024-11-06 21:59:29,691][00300] Num frames 2400... | |
| [2024-11-06 21:59:29,811][00300] Num frames 2500... | |
| [2024-11-06 21:59:29,937][00300] Num frames 2600... | |
| [2024-11-06 21:59:30,099][00300] Num frames 2700... | |
| [2024-11-06 21:59:30,265][00300] Num frames 2800... | |
| [2024-11-06 21:59:30,432][00300] Num frames 2900... | |
| [2024-11-06 21:59:30,599][00300] Num frames 3000... | |
| [2024-11-06 21:59:30,761][00300] Num frames 3100... | |
| [2024-11-06 21:59:30,933][00300] Num frames 3200... | |
| [2024-11-06 21:59:31,099][00300] Num frames 3300... | |
| [2024-11-06 21:59:31,262][00300] Num frames 3400... | |
| [2024-11-06 21:59:31,463][00300] Num frames 3500... | |
| [2024-11-06 21:59:31,633][00300] Num frames 3600... | |
| [2024-11-06 21:59:31,805][00300] Num frames 3700... | |
| [2024-11-06 21:59:31,943][00300] Avg episode rewards: #0: 14.688, true rewards: #0: 7.488 | |
| [2024-11-06 21:59:31,945][00300] Avg episode reward: 14.688, avg true_objective: 7.488 | |
| [2024-11-06 21:59:32,051][00300] Num frames 3800... | |
| [2024-11-06 21:59:32,217][00300] Num frames 3900... | |
| [2024-11-06 21:59:32,383][00300] Num frames 4000... | |
| [2024-11-06 21:59:32,596][00300] Num frames 4100... | |
| [2024-11-06 21:59:32,737][00300] Num frames 4200... | |
| [2024-11-06 21:59:32,864][00300] Avg episode rewards: #0: 13.260, true rewards: #0: 7.093 | |
| [2024-11-06 21:59:32,867][00300] Avg episode reward: 13.260, avg true_objective: 7.093 | |
| [2024-11-06 21:59:32,922][00300] Num frames 4300... | |
| [2024-11-06 21:59:33,050][00300] Num frames 4400... | |
| [2024-11-06 21:59:33,169][00300] Num frames 4500... | |
| [2024-11-06 21:59:33,285][00300] Num frames 4600... | |
| [2024-11-06 21:59:33,407][00300] Num frames 4700... | |
| [2024-11-06 21:59:33,540][00300] Num frames 4800... | |
| [2024-11-06 21:59:33,659][00300] Num frames 4900... | |
| [2024-11-06 21:59:33,779][00300] Num frames 5000... | |
| [2024-11-06 21:59:33,898][00300] Num frames 5100... | |
| [2024-11-06 21:59:34,022][00300] Avg episode rewards: #0: 14.217, true rewards: #0: 7.360 | |
| [2024-11-06 21:59:34,024][00300] Avg episode reward: 14.217, avg true_objective: 7.360 | |
| [2024-11-06 21:59:34,080][00300] Num frames 5200... | |
| [2024-11-06 21:59:34,199][00300] Num frames 5300... | |
| [2024-11-06 21:59:34,322][00300] Num frames 5400... | |
| [2024-11-06 21:59:34,447][00300] Num frames 5500... | |
| [2024-11-06 21:59:34,579][00300] Num frames 5600... | |
| [2024-11-06 21:59:34,711][00300] Avg episode rewards: #0: 13.330, true rewards: #0: 7.080 | |
| [2024-11-06 21:59:34,713][00300] Avg episode reward: 13.330, avg true_objective: 7.080 | |
| [2024-11-06 21:59:34,760][00300] Num frames 5700... | |
| [2024-11-06 21:59:34,876][00300] Num frames 5800... | |
| [2024-11-06 21:59:35,001][00300] Num frames 5900... | |
| [2024-11-06 21:59:35,122][00300] Num frames 6000... | |
| [2024-11-06 21:59:35,234][00300] Avg episode rewards: #0: 12.276, true rewards: #0: 6.720 | |
| [2024-11-06 21:59:35,235][00300] Avg episode reward: 12.276, avg true_objective: 6.720 | |
| [2024-11-06 21:59:35,300][00300] Num frames 6100... | |
| [2024-11-06 21:59:35,420][00300] Num frames 6200... | |
| [2024-11-06 21:59:35,551][00300] Num frames 6300... | |
| [2024-11-06 21:59:35,669][00300] Num frames 6400... | |
| [2024-11-06 21:59:35,788][00300] Num frames 6500... | |
| [2024-11-06 21:59:35,953][00300] Avg episode rewards: #0: 12.392, true rewards: #0: 6.592 | |
| [2024-11-06 21:59:35,954][00300] Avg episode reward: 12.392, avg true_objective: 6.592 | |
| [2024-11-06 22:00:16,452][00300] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |
| [2024-11-06 22:00:27,843][00300] The model has been pushed to https://huggingface.co/mnneely/rl_course_vizdoom_health_gathering_supreme | |
| [2024-11-06 22:03:47,970][00300] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2024-11-06 22:03:47,972][00300] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2024-11-06 22:03:47,974][00300] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2024-11-06 22:03:47,976][00300] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2024-11-06 22:03:47,978][00300] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2024-11-06 22:03:47,980][00300] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2024-11-06 22:03:47,981][00300] Adding new argument 'max_num_frames'=1000000 that is not in the saved config file! | |
| [2024-11-06 22:03:47,982][00300] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2024-11-06 22:03:47,983][00300] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2024-11-06 22:03:47,984][00300] Adding new argument 'hf_repository'='mnneely/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2024-11-06 22:03:47,985][00300] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2024-11-06 22:03:47,987][00300] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2024-11-06 22:03:47,988][00300] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2024-11-06 22:03:47,989][00300] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2024-11-06 22:03:47,990][00300] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2024-11-06 22:03:48,002][00300] RunningMeanStd input shape: (3, 72, 128) | |
| [2024-11-06 22:03:48,004][00300] RunningMeanStd input shape: (1,) | |
| [2024-11-06 22:03:48,020][00300] ConvEncoder: input_channels=3 | |
| [2024-11-06 22:03:48,058][00300] Conv encoder output size: 512 | |
| [2024-11-06 22:03:48,060][00300] Policy head output size: 512 | |
| [2024-11-06 22:03:48,077][00300] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2024-11-06 22:03:48,578][00300] Num frames 100... | |
| [2024-11-06 22:03:48,746][00300] Num frames 200... | |
| [2024-11-06 22:03:48,906][00300] Num frames 300... | |
| [2024-11-06 22:03:49,064][00300] Num frames 400... | |
| [2024-11-06 22:03:49,227][00300] Num frames 500... | |
| [2024-11-06 22:03:49,390][00300] Num frames 600... | |
| [2024-11-06 22:03:49,555][00300] Num frames 700... | |
| [2024-11-06 22:03:49,711][00300] Num frames 800... | |
| [2024-11-06 22:03:49,869][00300] Num frames 900... | |
| [2024-11-06 22:03:50,030][00300] Num frames 1000... | |
| [2024-11-06 22:03:50,194][00300] Num frames 1100... | |
| [2024-11-06 22:03:50,356][00300] Avg episode rewards: #0: 25.550, true rewards: #0: 11.550 | |
| [2024-11-06 22:03:50,358][00300] Avg episode reward: 25.550, avg true_objective: 11.550 | |
| [2024-11-06 22:03:50,447][00300] Num frames 1200... | |
| [2024-11-06 22:03:50,610][00300] Num frames 1300... | |
| [2024-11-06 22:03:50,780][00300] Num frames 1400... | |
| [2024-11-06 22:03:50,948][00300] Num frames 1500... | |
| [2024-11-06 22:03:51,097][00300] Num frames 1600... | |
| [2024-11-06 22:03:51,215][00300] Num frames 1700... | |
| [2024-11-06 22:03:51,387][00300] Avg episode rewards: #0: 18.475, true rewards: #0: 8.975 | |
| [2024-11-06 22:03:51,390][00300] Avg episode reward: 18.475, avg true_objective: 8.975 | |
| [2024-11-06 22:03:51,399][00300] Num frames 1800... | |
| [2024-11-06 22:03:51,527][00300] Num frames 1900... | |
| [2024-11-06 22:03:51,646][00300] Num frames 2000... | |
| [2024-11-06 22:03:51,761][00300] Num frames 2100... | |
| [2024-11-06 22:03:51,882][00300] Num frames 2200... | |
| [2024-11-06 22:03:52,001][00300] Num frames 2300... | |
| [2024-11-06 22:03:52,117][00300] Num frames 2400... | |
| [2024-11-06 22:03:52,236][00300] Num frames 2500... | |
| [2024-11-06 22:03:52,364][00300] Num frames 2600... | |
| [2024-11-06 22:03:52,491][00300] Num frames 2700... | |
| [2024-11-06 22:03:52,616][00300] Num frames 2800... | |
| [2024-11-06 22:03:52,734][00300] Num frames 2900... | |
| [2024-11-06 22:03:52,853][00300] Num frames 3000... | |
| [2024-11-06 22:03:52,978][00300] Num frames 3100... | |
| [2024-11-06 22:03:53,097][00300] Num frames 3200... | |
| [2024-11-06 22:03:53,216][00300] Num frames 3300... | |
| [2024-11-06 22:03:53,333][00300] Num frames 3400... | |
| [2024-11-06 22:03:53,443][00300] Avg episode rewards: #0: 27.467, true rewards: #0: 11.467 | |
| [2024-11-06 22:03:53,444][00300] Avg episode reward: 27.467, avg true_objective: 11.467 | |
| [2024-11-06 22:03:53,522][00300] Num frames 3500... | |
| [2024-11-06 22:03:53,639][00300] Num frames 3600... | |
| [2024-11-06 22:03:53,756][00300] Num frames 3700... | |
| [2024-11-06 22:03:53,873][00300] Num frames 3800... | |
| [2024-11-06 22:03:53,993][00300] Num frames 3900... | |
| [2024-11-06 22:03:54,108][00300] Num frames 4000... | |
| [2024-11-06 22:03:54,223][00300] Num frames 4100... | |
| [2024-11-06 22:03:54,340][00300] Num frames 4200... | |
| [2024-11-06 22:03:54,406][00300] Avg episode rewards: #0: 24.270, true rewards: #0: 10.520 | |
| [2024-11-06 22:03:54,408][00300] Avg episode reward: 24.270, avg true_objective: 10.520 | |
| [2024-11-06 22:03:54,526][00300] Num frames 4300... | |
| [2024-11-06 22:03:54,647][00300] Num frames 4400... | |
| [2024-11-06 22:03:54,761][00300] Num frames 4500... | |
| [2024-11-06 22:03:54,880][00300] Num frames 4600... | |
| [2024-11-06 22:03:54,999][00300] Num frames 4700... | |
| [2024-11-06 22:03:55,116][00300] Num frames 4800... | |
| [2024-11-06 22:03:55,234][00300] Num frames 4900... | |
| [2024-11-06 22:03:55,348][00300] Num frames 5000... | |
| [2024-11-06 22:03:55,487][00300] Num frames 5100... | |
| [2024-11-06 22:03:55,571][00300] Avg episode rewards: #0: 23.244, true rewards: #0: 10.244 | |
| [2024-11-06 22:03:55,573][00300] Avg episode reward: 23.244, avg true_objective: 10.244 | |
| [2024-11-06 22:03:55,665][00300] Num frames 5200... | |
| [2024-11-06 22:03:55,783][00300] Num frames 5300... | |
| [2024-11-06 22:03:55,898][00300] Num frames 5400... | |
| [2024-11-06 22:03:56,016][00300] Num frames 5500... | |
| [2024-11-06 22:03:56,115][00300] Avg episode rewards: #0: 20.397, true rewards: #0: 9.230 | |
| [2024-11-06 22:03:56,116][00300] Avg episode reward: 20.397, avg true_objective: 9.230 | |
| [2024-11-06 22:03:56,190][00300] Num frames 5600... | |
| [2024-11-06 22:03:56,305][00300] Num frames 5700... | |
| [2024-11-06 22:03:56,450][00300] Num frames 5800... | |
| [2024-11-06 22:03:56,574][00300] Num frames 5900... | |
| [2024-11-06 22:03:56,692][00300] Num frames 6000... | |
| [2024-11-06 22:03:56,817][00300] Num frames 6100... | |
| [2024-11-06 22:03:56,939][00300] Num frames 6200... | |
| [2024-11-06 22:03:57,059][00300] Num frames 6300... | |
| [2024-11-06 22:03:57,178][00300] Num frames 6400... | |
| [2024-11-06 22:03:57,303][00300] Num frames 6500... | |
| [2024-11-06 22:03:57,429][00300] Num frames 6600... | |
| [2024-11-06 22:03:57,494][00300] Avg episode rewards: #0: 21.579, true rewards: #0: 9.436 | |
| [2024-11-06 22:03:57,496][00300] Avg episode reward: 21.579, avg true_objective: 9.436 | |
| [2024-11-06 22:03:57,610][00300] Num frames 6700... | |
| [2024-11-06 22:03:57,726][00300] Num frames 6800... | |
| [2024-11-06 22:03:57,842][00300] Num frames 6900... | |
| [2024-11-06 22:03:57,961][00300] Num frames 7000... | |
| [2024-11-06 22:03:58,079][00300] Avg episode rewards: #0: 19.941, true rewards: #0: 8.816 | |
| [2024-11-06 22:03:58,080][00300] Avg episode reward: 19.941, avg true_objective: 8.816 | |
| [2024-11-06 22:03:58,136][00300] Num frames 7100... | |
| [2024-11-06 22:03:58,252][00300] Num frames 7200... | |
| [2024-11-06 22:03:58,373][00300] Num frames 7300... | |
| [2024-11-06 22:03:58,512][00300] Num frames 7400... | |
| [2024-11-06 22:03:58,631][00300] Num frames 7500... | |
| [2024-11-06 22:03:58,756][00300] Num frames 7600... | |
| [2024-11-06 22:03:58,875][00300] Num frames 7700... | |
| [2024-11-06 22:03:58,994][00300] Num frames 7800... | |
| [2024-11-06 22:03:59,110][00300] Num frames 7900... | |
| [2024-11-06 22:03:59,232][00300] Num frames 8000... | |
| [2024-11-06 22:03:59,349][00300] Num frames 8100... | |
| [2024-11-06 22:03:59,453][00300] Avg episode rewards: #0: 20.157, true rewards: #0: 9.046 | |
| [2024-11-06 22:03:59,455][00300] Avg episode reward: 20.157, avg true_objective: 9.046 | |
| [2024-11-06 22:03:59,533][00300] Num frames 8200... | |
| [2024-11-06 22:03:59,648][00300] Num frames 8300... | |
| [2024-11-06 22:03:59,768][00300] Num frames 8400... | |
| [2024-11-06 22:03:59,888][00300] Num frames 8500... | |
| [2024-11-06 22:04:00,006][00300] Num frames 8600... | |
| [2024-11-06 22:04:00,122][00300] Num frames 8700... | |
| [2024-11-06 22:04:00,242][00300] Num frames 8800... | |
| [2024-11-06 22:04:00,364][00300] Num frames 8900... | |
| [2024-11-06 22:04:00,493][00300] Num frames 9000... | |
| [2024-11-06 22:04:00,623][00300] Num frames 9100... | |
| [2024-11-06 22:04:00,742][00300] Num frames 9200... | |
| [2024-11-06 22:04:00,860][00300] Num frames 9300... | |
| [2024-11-06 22:04:00,981][00300] Num frames 9400... | |
| [2024-11-06 22:04:01,125][00300] Num frames 9500... | |
| [2024-11-06 22:04:01,295][00300] Num frames 9600... | |
| [2024-11-06 22:04:01,371][00300] Avg episode rewards: #0: 21.811, true rewards: #0: 9.611 | |
| [2024-11-06 22:04:01,373][00300] Avg episode reward: 21.811, avg true_objective: 9.611 | |
| [2024-11-06 22:04:58,942][00300] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |