|
[2023-02-22 17:08:06,788][00238] Saving configuration to /content/train_dir/default_experiment/config.json... |
|
[2023-02-22 17:08:06,791][00238] Rollout worker 0 uses device cpu |
|
[2023-02-22 17:08:06,793][00238] Rollout worker 1 uses device cpu |
|
[2023-02-22 17:08:06,795][00238] Rollout worker 2 uses device cpu |
|
[2023-02-22 17:08:06,797][00238] Rollout worker 3 uses device cpu |
|
[2023-02-22 17:08:06,800][00238] Rollout worker 4 uses device cpu |
|
[2023-02-22 17:08:06,801][00238] Rollout worker 5 uses device cpu |
|
[2023-02-22 17:08:06,803][00238] Rollout worker 6 uses device cpu |
|
[2023-02-22 17:08:06,805][00238] Rollout worker 7 uses device cpu |
|
[2023-02-22 17:08:07,008][00238] Using GPUs [0] for process 0 (actually maps to GPUs [0]) |
|
[2023-02-22 17:08:07,011][00238] InferenceWorker_p0-w0: min num requests: 2 |
|
[2023-02-22 17:08:07,046][00238] Starting all processes... |
|
[2023-02-22 17:08:07,047][00238] Starting process learner_proc0 |
|
[2023-02-22 17:08:07,105][00238] Starting all processes... |
|
[2023-02-22 17:08:07,121][00238] Starting process inference_proc0-0 |
|
[2023-02-22 17:08:07,122][00238] Starting process rollout_proc0 |
|
[2023-02-22 17:08:07,123][00238] Starting process rollout_proc1 |
|
[2023-02-22 17:08:07,129][00238] Starting process rollout_proc2 |
|
[2023-02-22 17:08:07,165][00238] Starting process rollout_proc4 |
|
[2023-02-22 17:08:07,161][00238] Starting process rollout_proc3 |
|
[2023-02-22 17:08:07,166][00238] Starting process rollout_proc5 |
|
[2023-02-22 17:08:07,167][00238] Starting process rollout_proc6 |
|
[2023-02-22 17:08:07,172][00238] Starting process rollout_proc7 |
|
[2023-02-22 17:08:17,921][17475] Using GPUs [0] for process 0 (actually maps to GPUs [0]) |
|
[2023-02-22 17:08:17,921][17475] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 |
|
[2023-02-22 17:08:18,129][17489] Worker 0 uses CPU cores [0] |
|
[2023-02-22 17:08:18,573][17493] Worker 4 uses CPU cores [0] |
|
[2023-02-22 17:08:18,614][17492] Worker 1 uses CPU cores [1] |
|
[2023-02-22 17:08:18,635][17491] Worker 2 uses CPU cores [0] |
|
[2023-02-22 17:08:18,979][17495] Worker 6 uses CPU cores [0] |
|
[2023-02-22 17:08:19,002][17496] Worker 3 uses CPU cores [1] |
|
[2023-02-22 17:08:19,024][17494] Worker 5 uses CPU cores [1] |
|
[2023-02-22 17:08:19,099][17490] Using GPUs [0] for process 0 (actually maps to GPUs [0]) |
|
[2023-02-22 17:08:19,104][17490] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 |
|
[2023-02-22 17:08:19,316][17497] Worker 7 uses CPU cores [1] |
|
[2023-02-22 17:08:19,428][17490] Num visible devices: 1 |
|
[2023-02-22 17:08:19,428][17475] Num visible devices: 1 |
|
[2023-02-22 17:08:19,433][17475] Starting seed is not provided |
|
[2023-02-22 17:08:19,433][17475] Using GPUs [0] for process 0 (actually maps to GPUs [0]) |
|
[2023-02-22 17:08:19,433][17475] Initializing actor-critic model on device cuda:0 |
|
[2023-02-22 17:08:19,434][17475] RunningMeanStd input shape: (3, 72, 128) |
|
[2023-02-22 17:08:19,438][17475] RunningMeanStd input shape: (1,) |
|
[2023-02-22 17:08:19,460][17475] ConvEncoder: input_channels=3 |
|
[2023-02-22 17:08:19,798][17475] Conv encoder output size: 512 |
|
[2023-02-22 17:08:19,798][17475] Policy head output size: 512 |
|
[2023-02-22 17:08:19,845][17475] Created Actor Critic model with architecture: |
|
[2023-02-22 17:08:19,845][17475] 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) |
|
) |
|
) |
|
[2023-02-22 17:08:26,564][17475] Using optimizer <class 'torch.optim.adam.Adam'> |
|
[2023-02-22 17:08:26,566][17475] No checkpoints found |
|
[2023-02-22 17:08:26,566][17475] Did not load from checkpoint, starting from scratch! |
|
[2023-02-22 17:08:26,567][17475] Initialized policy 0 weights for model version 0 |
|
[2023-02-22 17:08:26,570][17475] Using GPUs [0] for process 0 (actually maps to GPUs [0]) |
|
[2023-02-22 17:08:26,577][17475] LearnerWorker_p0 finished initialization! |
|
[2023-02-22 17:08:26,785][17490] RunningMeanStd input shape: (3, 72, 128) |
|
[2023-02-22 17:08:26,786][17490] RunningMeanStd input shape: (1,) |
|
[2023-02-22 17:08:26,800][17490] ConvEncoder: input_channels=3 |
|
[2023-02-22 17:08:26,903][17490] Conv encoder output size: 512 |
|
[2023-02-22 17:08:26,903][17490] Policy head output size: 512 |
|
[2023-02-22 17:08:27,000][00238] Heartbeat connected on Batcher_0 |
|
[2023-02-22 17:08:27,009][00238] Heartbeat connected on LearnerWorker_p0 |
|
[2023-02-22 17:08:27,020][00238] Heartbeat connected on RolloutWorker_w0 |
|
[2023-02-22 17:08:27,025][00238] Heartbeat connected on RolloutWorker_w1 |
|
[2023-02-22 17:08:27,028][00238] Heartbeat connected on RolloutWorker_w2 |
|
[2023-02-22 17:08:27,033][00238] Heartbeat connected on RolloutWorker_w3 |
|
[2023-02-22 17:08:27,036][00238] Heartbeat connected on RolloutWorker_w4 |
|
[2023-02-22 17:08:27,039][00238] Heartbeat connected on RolloutWorker_w5 |
|
[2023-02-22 17:08:27,043][00238] Heartbeat connected on RolloutWorker_w6 |
|
[2023-02-22 17:08:27,046][00238] Heartbeat connected on RolloutWorker_w7 |
|
[2023-02-22 17:08:27,685][00238] 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) |
|
[2023-02-22 17:08:29,203][00238] Inference worker 0-0 is ready! |
|
[2023-02-22 17:08:29,205][00238] All inference workers are ready! Signal rollout workers to start! |
|
[2023-02-22 17:08:29,207][00238] Heartbeat connected on InferenceWorker_p0-w0 |
|
[2023-02-22 17:08:29,298][17492] Doom resolution: 160x120, resize resolution: (128, 72) |
|
[2023-02-22 17:08:29,300][17496] Doom resolution: 160x120, resize resolution: (128, 72) |
|
[2023-02-22 17:08:29,313][17494] Doom resolution: 160x120, resize resolution: (128, 72) |
|
[2023-02-22 17:08:29,325][17497] Doom resolution: 160x120, resize resolution: (128, 72) |
|
[2023-02-22 17:08:29,344][17493] Doom resolution: 160x120, resize resolution: (128, 72) |
|
[2023-02-22 17:08:29,354][17491] Doom resolution: 160x120, resize resolution: (128, 72) |
|
[2023-02-22 17:08:29,375][17489] Doom resolution: 160x120, resize resolution: (128, 72) |
|
[2023-02-22 17:08:29,383][17495] Doom resolution: 160x120, resize resolution: (128, 72) |
|
[2023-02-22 17:08:30,590][17489] Decorrelating experience for 0 frames... |
|
[2023-02-22 17:08:30,595][17491] Decorrelating experience for 0 frames... |
|
[2023-02-22 17:08:31,379][17496] Decorrelating experience for 0 frames... |
|
[2023-02-22 17:08:31,376][17494] Decorrelating experience for 0 frames... |
|
[2023-02-22 17:08:31,382][17497] Decorrelating experience for 0 frames... |
|
[2023-02-22 17:08:31,384][17492] Decorrelating experience for 0 frames... |
|
[2023-02-22 17:08:31,783][17491] Decorrelating experience for 32 frames... |
|
[2023-02-22 17:08:31,786][17489] Decorrelating experience for 32 frames... |
|
[2023-02-22 17:08:32,686][00238] 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) |
|
[2023-02-22 17:08:32,842][17494] Decorrelating experience for 32 frames... |
|
[2023-02-22 17:08:32,872][17492] Decorrelating experience for 32 frames... |
|
[2023-02-22 17:08:33,021][17493] Decorrelating experience for 0 frames... |
|
[2023-02-22 17:08:33,053][17495] Decorrelating experience for 0 frames... |
|
[2023-02-22 17:08:33,492][17496] Decorrelating experience for 32 frames... |
|
[2023-02-22 17:08:33,665][17489] Decorrelating experience for 64 frames... |
|
[2023-02-22 17:08:34,352][17497] Decorrelating experience for 32 frames... |
|
[2023-02-22 17:08:34,624][17492] Decorrelating experience for 64 frames... |
|
[2023-02-22 17:08:34,743][17495] Decorrelating experience for 32 frames... |
|
[2023-02-22 17:08:34,744][17491] Decorrelating experience for 64 frames... |
|
[2023-02-22 17:08:35,158][17493] Decorrelating experience for 32 frames... |
|
[2023-02-22 17:08:35,937][17496] Decorrelating experience for 64 frames... |
|
[2023-02-22 17:08:36,146][17497] Decorrelating experience for 64 frames... |
|
[2023-02-22 17:08:36,292][17492] Decorrelating experience for 96 frames... |
|
[2023-02-22 17:08:36,320][17489] Decorrelating experience for 96 frames... |
|
[2023-02-22 17:08:36,749][17491] Decorrelating experience for 96 frames... |
|
[2023-02-22 17:08:36,928][17493] Decorrelating experience for 64 frames... |
|
[2023-02-22 17:08:37,290][17495] Decorrelating experience for 64 frames... |
|
[2023-02-22 17:08:37,685][00238] 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) |
|
[2023-02-22 17:08:37,710][17494] Decorrelating experience for 64 frames... |
|
[2023-02-22 17:08:38,101][17496] Decorrelating experience for 96 frames... |
|
[2023-02-22 17:08:38,244][17493] Decorrelating experience for 96 frames... |
|
[2023-02-22 17:08:38,304][17495] Decorrelating experience for 96 frames... |
|
[2023-02-22 17:08:38,685][17494] Decorrelating experience for 96 frames... |
|
[2023-02-22 17:08:38,862][17497] Decorrelating experience for 96 frames... |
|
[2023-02-22 17:08:42,685][00238] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 51.2. Samples: 768. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) |
|
[2023-02-22 17:08:42,690][00238] Avg episode reward: [(0, '1.163')] |
|
[2023-02-22 17:08:43,046][17475] Signal inference workers to stop experience collection... |
|
[2023-02-22 17:08:43,066][17490] InferenceWorker_p0-w0: stopping experience collection |
|
[2023-02-22 17:08:45,437][17475] Signal inference workers to resume experience collection... |
|
[2023-02-22 17:08:45,439][17490] InferenceWorker_p0-w0: resuming experience collection |
|
[2023-02-22 17:08:47,685][00238] Fps is (10 sec: 1228.8, 60 sec: 614.4, 300 sec: 614.4). Total num frames: 12288. Throughput: 0: 163.5. Samples: 3270. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) |
|
[2023-02-22 17:08:47,692][00238] Avg episode reward: [(0, '2.720')] |
|
[2023-02-22 17:08:52,685][00238] Fps is (10 sec: 2457.6, 60 sec: 983.0, 300 sec: 983.0). Total num frames: 24576. Throughput: 0: 225.1. Samples: 5628. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) |
|
[2023-02-22 17:08:52,688][00238] Avg episode reward: [(0, '3.480')] |
|
[2023-02-22 17:08:57,019][17490] Updated weights for policy 0, policy_version 10 (0.0020) |
|
[2023-02-22 17:08:57,685][00238] Fps is (10 sec: 2867.2, 60 sec: 1365.3, 300 sec: 1365.3). Total num frames: 40960. Throughput: 0: 334.1. Samples: 10024. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) |
|
[2023-02-22 17:08:57,687][00238] Avg episode reward: [(0, '3.973')] |
|
[2023-02-22 17:09:02,685][00238] Fps is (10 sec: 4096.1, 60 sec: 1872.5, 300 sec: 1872.5). Total num frames: 65536. Throughput: 0: 466.5. Samples: 16326. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) |
|
[2023-02-22 17:09:02,692][00238] Avg episode reward: [(0, '4.268')] |
|
[2023-02-22 17:09:07,159][17490] Updated weights for policy 0, policy_version 20 (0.0021) |
|
[2023-02-22 17:09:07,685][00238] Fps is (10 sec: 4096.0, 60 sec: 2048.0, 300 sec: 2048.0). Total num frames: 81920. Throughput: 0: 481.0. Samples: 19240. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:09:07,691][00238] Avg episode reward: [(0, '4.312')] |
|
[2023-02-22 17:09:12,685][00238] Fps is (10 sec: 2867.2, 60 sec: 2093.5, 300 sec: 2093.5). Total num frames: 94208. Throughput: 0: 529.5. Samples: 23828. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:09:12,688][00238] Avg episode reward: [(0, '4.373')] |
|
[2023-02-22 17:09:17,685][00238] Fps is (10 sec: 2867.2, 60 sec: 2211.8, 300 sec: 2211.8). Total num frames: 110592. Throughput: 0: 627.5. Samples: 28238. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) |
|
[2023-02-22 17:09:17,690][00238] Avg episode reward: [(0, '4.414')] |
|
[2023-02-22 17:09:17,693][17475] Saving new best policy, reward=4.414! |
|
[2023-02-22 17:09:19,962][17490] Updated weights for policy 0, policy_version 30 (0.0032) |
|
[2023-02-22 17:09:22,685][00238] Fps is (10 sec: 4096.0, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 135168. Throughput: 0: 701.6. Samples: 31572. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:09:22,692][00238] Avg episode reward: [(0, '4.313')] |
|
[2023-02-22 17:09:27,685][00238] Fps is (10 sec: 4505.6, 60 sec: 2594.1, 300 sec: 2594.1). Total num frames: 155648. Throughput: 0: 838.0. Samples: 38480. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:09:27,687][00238] Avg episode reward: [(0, '4.275')] |
|
[2023-02-22 17:09:29,461][17490] Updated weights for policy 0, policy_version 40 (0.0023) |
|
[2023-02-22 17:09:32,685][00238] Fps is (10 sec: 3686.4, 60 sec: 2867.3, 300 sec: 2646.6). Total num frames: 172032. Throughput: 0: 892.0. Samples: 43412. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) |
|
[2023-02-22 17:09:32,687][00238] Avg episode reward: [(0, '4.384')] |
|
[2023-02-22 17:09:37,685][00238] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 2633.1). Total num frames: 184320. Throughput: 0: 887.5. Samples: 45564. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) |
|
[2023-02-22 17:09:37,687][00238] Avg episode reward: [(0, '4.468')] |
|
[2023-02-22 17:09:37,689][17475] Saving new best policy, reward=4.468! |
|
[2023-02-22 17:09:41,453][17490] Updated weights for policy 0, policy_version 50 (0.0021) |
|
[2023-02-22 17:09:42,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 2785.3). Total num frames: 208896. Throughput: 0: 920.6. Samples: 51452. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) |
|
[2023-02-22 17:09:42,688][00238] Avg episode reward: [(0, '4.465')] |
|
[2023-02-22 17:09:47,685][00238] Fps is (10 sec: 4915.0, 60 sec: 3686.4, 300 sec: 2918.4). Total num frames: 233472. Throughput: 0: 934.2. Samples: 58366. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:09:47,688][00238] Avg episode reward: [(0, '4.382')] |
|
[2023-02-22 17:09:51,948][17490] Updated weights for policy 0, policy_version 60 (0.0015) |
|
[2023-02-22 17:09:52,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 2891.3). Total num frames: 245760. Throughput: 0: 922.0. Samples: 60730. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) |
|
[2023-02-22 17:09:52,687][00238] Avg episode reward: [(0, '4.387')] |
|
[2023-02-22 17:09:57,687][00238] Fps is (10 sec: 2457.1, 60 sec: 3618.0, 300 sec: 2867.1). Total num frames: 258048. Throughput: 0: 911.5. Samples: 64846. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) |
|
[2023-02-22 17:09:57,690][00238] Avg episode reward: [(0, '4.550')] |
|
[2023-02-22 17:09:57,699][17475] Saving new best policy, reward=4.550! |
|
[2023-02-22 17:10:02,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 2975.0). Total num frames: 282624. Throughput: 0: 950.2. Samples: 70996. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) |
|
[2023-02-22 17:10:02,690][00238] Avg episode reward: [(0, '4.420')] |
|
[2023-02-22 17:10:02,704][17475] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000069_282624.pth... |
|
[2023-02-22 17:10:03,564][17490] Updated weights for policy 0, policy_version 70 (0.0012) |
|
[2023-02-22 17:10:07,685][00238] Fps is (10 sec: 4096.9, 60 sec: 3618.1, 300 sec: 2990.1). Total num frames: 299008. Throughput: 0: 942.5. Samples: 73986. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:10:07,691][00238] Avg episode reward: [(0, '4.453')] |
|
[2023-02-22 17:10:12,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3003.7). Total num frames: 315392. Throughput: 0: 895.2. Samples: 78762. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:10:12,692][00238] Avg episode reward: [(0, '4.510')] |
|
[2023-02-22 17:10:16,453][17490] Updated weights for policy 0, policy_version 80 (0.0017) |
|
[2023-02-22 17:10:17,685][00238] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 2978.9). Total num frames: 327680. Throughput: 0: 883.6. Samples: 83174. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:10:17,687][00238] Avg episode reward: [(0, '4.668')] |
|
[2023-02-22 17:10:17,694][17475] Saving new best policy, reward=4.668! |
|
[2023-02-22 17:10:22,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3063.1). Total num frames: 352256. Throughput: 0: 903.2. Samples: 86210. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) |
|
[2023-02-22 17:10:22,694][00238] Avg episode reward: [(0, '4.499')] |
|
[2023-02-22 17:10:25,673][17490] Updated weights for policy 0, policy_version 90 (0.0020) |
|
[2023-02-22 17:10:27,685][00238] Fps is (10 sec: 4915.2, 60 sec: 3686.4, 300 sec: 3140.3). Total num frames: 376832. Throughput: 0: 932.6. Samples: 93420. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:10:27,693][00238] Avg episode reward: [(0, '4.375')] |
|
[2023-02-22 17:10:32,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3145.7). Total num frames: 393216. Throughput: 0: 899.7. Samples: 98852. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:10:32,687][00238] Avg episode reward: [(0, '4.384')] |
|
[2023-02-22 17:10:37,686][00238] Fps is (10 sec: 2866.9, 60 sec: 3686.3, 300 sec: 3119.2). Total num frames: 405504. Throughput: 0: 896.1. Samples: 101056. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:10:37,689][00238] Avg episode reward: [(0, '4.564')] |
|
[2023-02-22 17:10:37,836][17490] Updated weights for policy 0, policy_version 100 (0.0018) |
|
[2023-02-22 17:10:42,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3185.8). Total num frames: 430080. Throughput: 0: 941.0. Samples: 107190. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) |
|
[2023-02-22 17:10:42,692][00238] Avg episode reward: [(0, '4.528')] |
|
[2023-02-22 17:10:46,199][17490] Updated weights for policy 0, policy_version 110 (0.0016) |
|
[2023-02-22 17:10:47,685][00238] Fps is (10 sec: 4915.8, 60 sec: 3686.4, 300 sec: 3247.5). Total num frames: 454656. Throughput: 0: 960.9. Samples: 114238. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:10:47,686][00238] Avg episode reward: [(0, '4.395')] |
|
[2023-02-22 17:10:52,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3248.6). Total num frames: 471040. Throughput: 0: 951.0. Samples: 116782. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:10:52,693][00238] Avg episode reward: [(0, '4.314')] |
|
[2023-02-22 17:10:57,685][00238] Fps is (10 sec: 3276.7, 60 sec: 3823.1, 300 sec: 3249.5). Total num frames: 487424. Throughput: 0: 947.0. Samples: 121378. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:10:57,693][00238] Avg episode reward: [(0, '4.334')] |
|
[2023-02-22 17:10:58,584][17490] Updated weights for policy 0, policy_version 120 (0.0027) |
|
[2023-02-22 17:11:02,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3276.8). Total num frames: 507904. Throughput: 0: 987.8. Samples: 127624. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:11:02,690][00238] Avg episode reward: [(0, '4.466')] |
|
[2023-02-22 17:11:07,685][00238] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3302.4). Total num frames: 528384. Throughput: 0: 987.3. Samples: 130640. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:11:07,688][00238] Avg episode reward: [(0, '4.615')] |
|
[2023-02-22 17:11:08,919][17490] Updated weights for policy 0, policy_version 130 (0.0030) |
|
[2023-02-22 17:11:12,686][00238] Fps is (10 sec: 3276.5, 60 sec: 3754.6, 300 sec: 3276.8). Total num frames: 540672. Throughput: 0: 933.2. Samples: 135416. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:11:12,688][00238] Avg episode reward: [(0, '4.703')] |
|
[2023-02-22 17:11:12,704][17475] Saving new best policy, reward=4.703! |
|
[2023-02-22 17:11:17,685][00238] Fps is (10 sec: 2867.2, 60 sec: 3822.9, 300 sec: 3276.8). Total num frames: 557056. Throughput: 0: 910.4. Samples: 139820. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) |
|
[2023-02-22 17:11:17,687][00238] Avg episode reward: [(0, '4.722')] |
|
[2023-02-22 17:11:17,691][17475] Saving new best policy, reward=4.722! |
|
[2023-02-22 17:11:20,896][17490] Updated weights for policy 0, policy_version 140 (0.0021) |
|
[2023-02-22 17:11:22,685][00238] Fps is (10 sec: 4096.4, 60 sec: 3822.9, 300 sec: 3323.6). Total num frames: 581632. Throughput: 0: 933.8. Samples: 143076. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) |
|
[2023-02-22 17:11:22,688][00238] Avg episode reward: [(0, '4.663')] |
|
[2023-02-22 17:11:27,685][00238] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3345.1). Total num frames: 602112. Throughput: 0: 959.5. Samples: 150368. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) |
|
[2023-02-22 17:11:27,691][00238] Avg episode reward: [(0, '4.393')] |
|
[2023-02-22 17:11:30,376][17490] Updated weights for policy 0, policy_version 150 (0.0015) |
|
[2023-02-22 17:11:32,690][00238] Fps is (10 sec: 3684.5, 60 sec: 3754.3, 300 sec: 3343.1). Total num frames: 618496. Throughput: 0: 919.0. Samples: 155598. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) |
|
[2023-02-22 17:11:32,692][00238] Avg episode reward: [(0, '4.385')] |
|
[2023-02-22 17:11:37,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3823.0, 300 sec: 3341.5). Total num frames: 634880. Throughput: 0: 912.1. Samples: 157828. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) |
|
[2023-02-22 17:11:37,688][00238] Avg episode reward: [(0, '4.420')] |
|
[2023-02-22 17:11:41,547][17490] Updated weights for policy 0, policy_version 160 (0.0016) |
|
[2023-02-22 17:11:42,685][00238] Fps is (10 sec: 4098.1, 60 sec: 3822.9, 300 sec: 3381.8). Total num frames: 659456. Throughput: 0: 948.1. Samples: 164044. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) |
|
[2023-02-22 17:11:42,686][00238] Avg episode reward: [(0, '4.488')] |
|
[2023-02-22 17:11:47,685][00238] Fps is (10 sec: 4915.2, 60 sec: 3822.9, 300 sec: 3420.2). Total num frames: 684032. Throughput: 0: 968.3. Samples: 171198. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:11:47,694][00238] Avg episode reward: [(0, '4.588')] |
|
[2023-02-22 17:11:51,302][17490] Updated weights for policy 0, policy_version 170 (0.0027) |
|
[2023-02-22 17:11:52,685][00238] Fps is (10 sec: 4095.9, 60 sec: 3822.9, 300 sec: 3416.7). Total num frames: 700416. Throughput: 0: 956.1. Samples: 173664. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) |
|
[2023-02-22 17:11:52,692][00238] Avg episode reward: [(0, '4.587')] |
|
[2023-02-22 17:11:57,685][00238] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3393.8). Total num frames: 712704. Throughput: 0: 951.6. Samples: 178238. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) |
|
[2023-02-22 17:11:57,689][00238] Avg episode reward: [(0, '4.697')] |
|
[2023-02-22 17:12:02,384][17490] Updated weights for policy 0, policy_version 180 (0.0021) |
|
[2023-02-22 17:12:02,685][00238] Fps is (10 sec: 3686.5, 60 sec: 3822.9, 300 sec: 3429.2). Total num frames: 737280. Throughput: 0: 997.4. Samples: 184704. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:12:02,688][00238] Avg episode reward: [(0, '4.728')] |
|
[2023-02-22 17:12:02,697][17475] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000180_737280.pth... |
|
[2023-02-22 17:12:02,846][17475] Saving new best policy, reward=4.728! |
|
[2023-02-22 17:12:07,685][00238] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3444.4). Total num frames: 757760. Throughput: 0: 990.1. Samples: 187632. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:12:07,689][00238] Avg episode reward: [(0, '4.725')] |
|
[2023-02-22 17:12:12,691][00238] Fps is (10 sec: 3274.8, 60 sec: 3822.6, 300 sec: 3422.3). Total num frames: 770048. Throughput: 0: 936.9. Samples: 192536. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) |
|
[2023-02-22 17:12:12,694][00238] Avg episode reward: [(0, '4.757')] |
|
[2023-02-22 17:12:12,709][17475] Saving new best policy, reward=4.757! |
|
[2023-02-22 17:12:15,077][17490] Updated weights for policy 0, policy_version 190 (0.0012) |
|
[2023-02-22 17:12:17,685][00238] Fps is (10 sec: 2457.6, 60 sec: 3754.7, 300 sec: 3401.5). Total num frames: 782336. Throughput: 0: 914.7. Samples: 196756. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:12:17,687][00238] Avg episode reward: [(0, '4.796')] |
|
[2023-02-22 17:12:17,691][17475] Saving new best policy, reward=4.796! |
|
[2023-02-22 17:12:22,685][00238] Fps is (10 sec: 3688.7, 60 sec: 3754.7, 300 sec: 3433.7). Total num frames: 806912. Throughput: 0: 933.3. Samples: 199828. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:12:22,693][00238] Avg episode reward: [(0, '4.838')] |
|
[2023-02-22 17:12:22,704][17475] Saving new best policy, reward=4.838! |
|
[2023-02-22 17:12:25,114][17490] Updated weights for policy 0, policy_version 200 (0.0026) |
|
[2023-02-22 17:12:27,685][00238] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3447.5). Total num frames: 827392. Throughput: 0: 941.9. Samples: 206430. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) |
|
[2023-02-22 17:12:27,690][00238] Avg episode reward: [(0, '4.640')] |
|
[2023-02-22 17:12:32,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3755.0, 300 sec: 3444.0). Total num frames: 843776. Throughput: 0: 898.2. Samples: 211618. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) |
|
[2023-02-22 17:12:32,691][00238] Avg episode reward: [(0, '4.864')] |
|
[2023-02-22 17:12:32,704][17475] Saving new best policy, reward=4.864! |
|
[2023-02-22 17:12:37,350][17490] Updated weights for policy 0, policy_version 210 (0.0034) |
|
[2023-02-22 17:12:37,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3440.6). Total num frames: 860160. Throughput: 0: 892.8. Samples: 213840. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:12:37,688][00238] Avg episode reward: [(0, '4.874')] |
|
[2023-02-22 17:12:37,691][17475] Saving new best policy, reward=4.874! |
|
[2023-02-22 17:12:42,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3453.5). Total num frames: 880640. Throughput: 0: 921.4. Samples: 219702. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:12:42,689][00238] Avg episode reward: [(0, '4.745')] |
|
[2023-02-22 17:12:46,420][17490] Updated weights for policy 0, policy_version 220 (0.0015) |
|
[2023-02-22 17:12:47,685][00238] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3481.6). Total num frames: 905216. Throughput: 0: 939.4. Samples: 226976. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) |
|
[2023-02-22 17:12:47,687][00238] Avg episode reward: [(0, '4.765')] |
|
[2023-02-22 17:12:52,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3462.3). Total num frames: 917504. Throughput: 0: 924.8. Samples: 229246. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:12:52,693][00238] Avg episode reward: [(0, '4.799')] |
|
[2023-02-22 17:12:57,685][00238] Fps is (10 sec: 2457.6, 60 sec: 3618.1, 300 sec: 3443.7). Total num frames: 929792. Throughput: 0: 897.4. Samples: 232914. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:12:57,692][00238] Avg episode reward: [(0, '4.832')] |
|
[2023-02-22 17:13:01,236][17490] Updated weights for policy 0, policy_version 230 (0.0036) |
|
[2023-02-22 17:13:02,685][00238] Fps is (10 sec: 2457.6, 60 sec: 3413.3, 300 sec: 3425.7). Total num frames: 942080. Throughput: 0: 885.2. Samples: 236592. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:13:02,688][00238] Avg episode reward: [(0, '4.570')] |
|
[2023-02-22 17:13:07,685][00238] Fps is (10 sec: 3276.7, 60 sec: 3413.3, 300 sec: 3437.7). Total num frames: 962560. Throughput: 0: 873.7. Samples: 239144. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) |
|
[2023-02-22 17:13:07,688][00238] Avg episode reward: [(0, '4.859')] |
|
[2023-02-22 17:13:11,934][17490] Updated weights for policy 0, policy_version 240 (0.0027) |
|
[2023-02-22 17:13:12,685][00238] Fps is (10 sec: 4096.1, 60 sec: 3550.2, 300 sec: 3449.3). Total num frames: 983040. Throughput: 0: 868.0. Samples: 245488. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:13:12,687][00238] Avg episode reward: [(0, '5.080')] |
|
[2023-02-22 17:13:12,756][17475] Saving new best policy, reward=5.080! |
|
[2023-02-22 17:13:17,685][00238] Fps is (10 sec: 3686.5, 60 sec: 3618.1, 300 sec: 3446.3). Total num frames: 999424. Throughput: 0: 874.8. Samples: 250984. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) |
|
[2023-02-22 17:13:17,692][00238] Avg episode reward: [(0, '5.072')] |
|
[2023-02-22 17:13:22,688][00238] Fps is (10 sec: 3275.7, 60 sec: 3481.4, 300 sec: 3443.4). Total num frames: 1015808. Throughput: 0: 876.0. Samples: 253262. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) |
|
[2023-02-22 17:13:22,696][00238] Avg episode reward: [(0, '5.059')] |
|
[2023-02-22 17:13:23,950][17490] Updated weights for policy 0, policy_version 250 (0.0028) |
|
[2023-02-22 17:13:27,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 1040384. Throughput: 0: 878.1. Samples: 259216. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) |
|
[2023-02-22 17:13:27,692][00238] Avg episode reward: [(0, '5.281')] |
|
[2023-02-22 17:13:27,695][17475] Saving new best policy, reward=5.281! |
|
[2023-02-22 17:13:32,443][17490] Updated weights for policy 0, policy_version 260 (0.0017) |
|
[2023-02-22 17:13:32,685][00238] Fps is (10 sec: 4916.9, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 1064960. Throughput: 0: 876.6. Samples: 266422. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) |
|
[2023-02-22 17:13:32,692][00238] Avg episode reward: [(0, '5.117')] |
|
[2023-02-22 17:13:37,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1081344. Throughput: 0: 888.1. Samples: 269212. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:13:37,690][00238] Avg episode reward: [(0, '5.299')] |
|
[2023-02-22 17:13:37,695][17475] Saving new best policy, reward=5.299! |
|
[2023-02-22 17:13:42,685][00238] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3665.6). Total num frames: 1093632. Throughput: 0: 907.1. Samples: 273734. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) |
|
[2023-02-22 17:13:42,691][00238] Avg episode reward: [(0, '5.426')] |
|
[2023-02-22 17:13:42,710][17475] Saving new best policy, reward=5.426! |
|
[2023-02-22 17:13:44,829][17490] Updated weights for policy 0, policy_version 270 (0.0026) |
|
[2023-02-22 17:13:47,685][00238] Fps is (10 sec: 3686.3, 60 sec: 3549.9, 300 sec: 3707.2). Total num frames: 1118208. Throughput: 0: 965.2. Samples: 280026. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:13:47,691][00238] Avg episode reward: [(0, '5.682')] |
|
[2023-02-22 17:13:47,697][17475] Saving new best policy, reward=5.682! |
|
[2023-02-22 17:13:52,685][00238] Fps is (10 sec: 4915.2, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 1142784. Throughput: 0: 988.4. Samples: 283620. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:13:52,687][00238] Avg episode reward: [(0, '5.636')] |
|
[2023-02-22 17:13:53,286][17490] Updated weights for policy 0, policy_version 280 (0.0017) |
|
[2023-02-22 17:13:57,685][00238] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3707.2). Total num frames: 1159168. Throughput: 0: 978.0. Samples: 289498. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) |
|
[2023-02-22 17:13:57,691][00238] Avg episode reward: [(0, '5.455')] |
|
[2023-02-22 17:14:02,685][00238] Fps is (10 sec: 2867.1, 60 sec: 3822.9, 300 sec: 3693.3). Total num frames: 1171456. Throughput: 0: 956.4. Samples: 294022. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:14:02,691][00238] Avg episode reward: [(0, '5.144')] |
|
[2023-02-22 17:14:02,704][17475] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000286_1171456.pth... |
|
[2023-02-22 17:14:02,879][17475] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000069_282624.pth |
|
[2023-02-22 17:14:06,215][17490] Updated weights for policy 0, policy_version 290 (0.0017) |
|
[2023-02-22 17:14:07,685][00238] Fps is (10 sec: 3276.7, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 1191936. Throughput: 0: 962.2. Samples: 296556. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:14:07,693][00238] Avg episode reward: [(0, '5.374')] |
|
[2023-02-22 17:14:12,685][00238] Fps is (10 sec: 4505.7, 60 sec: 3891.2, 300 sec: 3748.9). Total num frames: 1216512. Throughput: 0: 972.3. Samples: 302970. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:14:12,691][00238] Avg episode reward: [(0, '5.580')] |
|
[2023-02-22 17:14:16,248][17490] Updated weights for policy 0, policy_version 300 (0.0018) |
|
[2023-02-22 17:14:17,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3707.2). Total num frames: 1228800. Throughput: 0: 932.4. Samples: 308378. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) |
|
[2023-02-22 17:14:17,687][00238] Avg episode reward: [(0, '5.724')] |
|
[2023-02-22 17:14:17,715][17475] Saving new best policy, reward=5.724! |
|
[2023-02-22 17:14:22,685][00238] Fps is (10 sec: 2867.2, 60 sec: 3823.2, 300 sec: 3693.3). Total num frames: 1245184. Throughput: 0: 919.8. Samples: 310604. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:14:22,690][00238] Avg episode reward: [(0, '5.974')] |
|
[2023-02-22 17:14:22,704][17475] Saving new best policy, reward=5.974! |
|
[2023-02-22 17:14:27,589][17490] Updated weights for policy 0, policy_version 310 (0.0013) |
|
[2023-02-22 17:14:27,685][00238] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 1269760. Throughput: 0: 948.8. Samples: 316428. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) |
|
[2023-02-22 17:14:27,687][00238] Avg episode reward: [(0, '6.014')] |
|
[2023-02-22 17:14:27,691][17475] Saving new best policy, reward=6.014! |
|
[2023-02-22 17:14:32,689][00238] Fps is (10 sec: 4503.8, 60 sec: 3754.4, 300 sec: 3748.8). Total num frames: 1290240. Throughput: 0: 967.0. Samples: 323546. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) |
|
[2023-02-22 17:14:32,691][00238] Avg episode reward: [(0, '6.496')] |
|
[2023-02-22 17:14:32,753][17475] Saving new best policy, reward=6.496! |
|
[2023-02-22 17:14:37,692][00238] Fps is (10 sec: 3683.7, 60 sec: 3754.2, 300 sec: 3721.0). Total num frames: 1306624. Throughput: 0: 946.0. Samples: 326196. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:14:37,695][00238] Avg episode reward: [(0, '6.873')] |
|
[2023-02-22 17:14:37,702][17475] Saving new best policy, reward=6.873! |
|
[2023-02-22 17:14:38,097][17490] Updated weights for policy 0, policy_version 320 (0.0028) |
|
[2023-02-22 17:14:42,685][00238] Fps is (10 sec: 3278.1, 60 sec: 3822.9, 300 sec: 3693.3). Total num frames: 1323008. Throughput: 0: 913.9. Samples: 330626. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:14:42,688][00238] Avg episode reward: [(0, '6.610')] |
|
[2023-02-22 17:14:47,685][00238] Fps is (10 sec: 3689.1, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 1343488. Throughput: 0: 949.0. Samples: 336726. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) |
|
[2023-02-22 17:14:47,687][00238] Avg episode reward: [(0, '6.584')] |
|
[2023-02-22 17:14:48,728][17490] Updated weights for policy 0, policy_version 330 (0.0018) |
|
[2023-02-22 17:14:52,685][00238] Fps is (10 sec: 4505.7, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 1368064. Throughput: 0: 971.1. Samples: 340254. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:14:52,687][00238] Avg episode reward: [(0, '6.918')] |
|
[2023-02-22 17:14:52,696][17475] Saving new best policy, reward=6.918! |
|
[2023-02-22 17:14:57,691][00238] Fps is (10 sec: 4093.4, 60 sec: 3754.3, 300 sec: 3734.9). Total num frames: 1384448. Throughput: 0: 956.7. Samples: 346026. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) |
|
[2023-02-22 17:14:57,694][00238] Avg episode reward: [(0, '6.930')] |
|
[2023-02-22 17:14:57,699][17475] Saving new best policy, reward=6.930! |
|
[2023-02-22 17:15:00,105][17490] Updated weights for policy 0, policy_version 340 (0.0018) |
|
[2023-02-22 17:15:02,688][00238] Fps is (10 sec: 2866.4, 60 sec: 3754.5, 300 sec: 3721.1). Total num frames: 1396736. Throughput: 0: 935.5. Samples: 350480. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) |
|
[2023-02-22 17:15:02,696][00238] Avg episode reward: [(0, '6.576')] |
|
[2023-02-22 17:15:07,685][00238] Fps is (10 sec: 3278.9, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 1417216. Throughput: 0: 942.4. Samples: 353014. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) |
|
[2023-02-22 17:15:07,688][00238] Avg episode reward: [(0, '6.648')] |
|
[2023-02-22 17:15:11,005][17490] Updated weights for policy 0, policy_version 350 (0.0014) |
|
[2023-02-22 17:15:12,685][00238] Fps is (10 sec: 4506.9, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 1441792. Throughput: 0: 952.4. Samples: 359284. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:15:12,692][00238] Avg episode reward: [(0, '6.703')] |
|
[2023-02-22 17:15:17,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 1458176. Throughput: 0: 921.9. Samples: 365028. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:15:17,687][00238] Avg episode reward: [(0, '6.894')] |
|
[2023-02-22 17:15:22,653][17490] Updated weights for policy 0, policy_version 360 (0.0019) |
|
[2023-02-22 17:15:22,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 1474560. Throughput: 0: 912.2. Samples: 367238. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) |
|
[2023-02-22 17:15:22,688][00238] Avg episode reward: [(0, '7.038')] |
|
[2023-02-22 17:15:22,702][17475] Saving new best policy, reward=7.038! |
|
[2023-02-22 17:15:27,687][00238] Fps is (10 sec: 3685.6, 60 sec: 3754.5, 300 sec: 3735.0). Total num frames: 1495040. Throughput: 0: 939.4. Samples: 372900. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) |
|
[2023-02-22 17:15:27,691][00238] Avg episode reward: [(0, '7.149')] |
|
[2023-02-22 17:15:27,694][17475] Saving new best policy, reward=7.149! |
|
[2023-02-22 17:15:31,758][17490] Updated weights for policy 0, policy_version 370 (0.0015) |
|
[2023-02-22 17:15:32,685][00238] Fps is (10 sec: 4505.7, 60 sec: 3823.2, 300 sec: 3776.7). Total num frames: 1519616. Throughput: 0: 962.0. Samples: 380018. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:15:32,687][00238] Avg episode reward: [(0, '7.430')] |
|
[2023-02-22 17:15:32,700][17475] Saving new best policy, reward=7.430! |
|
[2023-02-22 17:15:37,685][00238] Fps is (10 sec: 4096.9, 60 sec: 3823.4, 300 sec: 3748.9). Total num frames: 1536000. Throughput: 0: 948.4. Samples: 382930. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:15:37,696][00238] Avg episode reward: [(0, '7.617')] |
|
[2023-02-22 17:15:37,699][17475] Saving new best policy, reward=7.617! |
|
[2023-02-22 17:15:42,685][00238] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 1548288. Throughput: 0: 919.8. Samples: 387410. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:15:42,693][00238] Avg episode reward: [(0, '7.885')] |
|
[2023-02-22 17:15:42,807][17475] Saving new best policy, reward=7.885! |
|
[2023-02-22 17:15:44,022][17490] Updated weights for policy 0, policy_version 380 (0.0023) |
|
[2023-02-22 17:15:47,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 1572864. Throughput: 0: 957.8. Samples: 393580. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:15:47,695][00238] Avg episode reward: [(0, '8.603')] |
|
[2023-02-22 17:15:47,696][17475] Saving new best policy, reward=8.603! |
|
[2023-02-22 17:15:52,490][17490] Updated weights for policy 0, policy_version 390 (0.0024) |
|
[2023-02-22 17:15:52,685][00238] Fps is (10 sec: 4915.2, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 1597440. Throughput: 0: 980.0. Samples: 397116. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:15:52,692][00238] Avg episode reward: [(0, '8.876')] |
|
[2023-02-22 17:15:52,707][17475] Saving new best policy, reward=8.876! |
|
[2023-02-22 17:15:57,692][00238] Fps is (10 sec: 4093.1, 60 sec: 3822.9, 300 sec: 3748.8). Total num frames: 1613824. Throughput: 0: 974.4. Samples: 403140. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:15:57,694][00238] Avg episode reward: [(0, '8.958')] |
|
[2023-02-22 17:15:57,696][17475] Saving new best policy, reward=8.958! |
|
[2023-02-22 17:16:02,685][00238] Fps is (10 sec: 2867.2, 60 sec: 3823.1, 300 sec: 3721.1). Total num frames: 1626112. Throughput: 0: 947.9. Samples: 407682. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:16:02,692][00238] Avg episode reward: [(0, '8.921')] |
|
[2023-02-22 17:16:02,705][17475] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000397_1626112.pth... |
|
[2023-02-22 17:16:02,874][17475] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000180_737280.pth |
|
[2023-02-22 17:16:05,386][17490] Updated weights for policy 0, policy_version 400 (0.0037) |
|
[2023-02-22 17:16:07,685][00238] Fps is (10 sec: 3279.2, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 1646592. Throughput: 0: 952.2. Samples: 410086. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:16:07,687][00238] Avg episode reward: [(0, '8.806')] |
|
[2023-02-22 17:16:12,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 1667072. Throughput: 0: 966.2. Samples: 416378. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:16:12,687][00238] Avg episode reward: [(0, '9.416')] |
|
[2023-02-22 17:16:12,789][17475] Saving new best policy, reward=9.416! |
|
[2023-02-22 17:16:15,054][17490] Updated weights for policy 0, policy_version 410 (0.0017) |
|
[2023-02-22 17:16:17,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 1687552. Throughput: 0: 935.3. Samples: 422108. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:16:17,690][00238] Avg episode reward: [(0, '9.607')] |
|
[2023-02-22 17:16:17,694][17475] Saving new best policy, reward=9.607! |
|
[2023-02-22 17:16:22,685][00238] Fps is (10 sec: 3276.6, 60 sec: 3754.6, 300 sec: 3721.1). Total num frames: 1699840. Throughput: 0: 919.8. Samples: 424322. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:16:22,690][00238] Avg episode reward: [(0, '10.540')] |
|
[2023-02-22 17:16:22,700][17475] Saving new best policy, reward=10.540! |
|
[2023-02-22 17:16:26,549][17490] Updated weights for policy 0, policy_version 420 (0.0019) |
|
[2023-02-22 17:16:27,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3823.1, 300 sec: 3748.9). Total num frames: 1724416. Throughput: 0: 950.8. Samples: 430196. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:16:27,691][00238] Avg episode reward: [(0, '10.032')] |
|
[2023-02-22 17:16:32,686][00238] Fps is (10 sec: 4914.9, 60 sec: 3822.8, 300 sec: 3776.6). Total num frames: 1748992. Throughput: 0: 980.3. Samples: 437694. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:16:32,688][00238] Avg episode reward: [(0, '9.555')] |
|
[2023-02-22 17:16:35,675][17490] Updated weights for policy 0, policy_version 430 (0.0030) |
|
[2023-02-22 17:16:37,685][00238] Fps is (10 sec: 4095.8, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 1765376. Throughput: 0: 967.8. Samples: 440668. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) |
|
[2023-02-22 17:16:37,692][00238] Avg episode reward: [(0, '9.564')] |
|
[2023-02-22 17:16:42,685][00238] Fps is (10 sec: 3277.1, 60 sec: 3891.2, 300 sec: 3721.1). Total num frames: 1781760. Throughput: 0: 937.7. Samples: 445328. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) |
|
[2023-02-22 17:16:42,692][00238] Avg episode reward: [(0, '9.309')] |
|
[2023-02-22 17:16:46,832][17490] Updated weights for policy 0, policy_version 440 (0.0035) |
|
[2023-02-22 17:16:47,685][00238] Fps is (10 sec: 3686.6, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 1802240. Throughput: 0: 978.8. Samples: 451730. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:16:47,691][00238] Avg episode reward: [(0, '9.550')] |
|
[2023-02-22 17:16:52,685][00238] Fps is (10 sec: 4915.4, 60 sec: 3891.2, 300 sec: 3790.5). Total num frames: 1830912. Throughput: 0: 1006.6. Samples: 455382. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:16:52,691][00238] Avg episode reward: [(0, '10.577')] |
|
[2023-02-22 17:16:52,701][17475] Saving new best policy, reward=10.577! |
|
[2023-02-22 17:16:55,988][17490] Updated weights for policy 0, policy_version 450 (0.0017) |
|
[2023-02-22 17:16:57,685][00238] Fps is (10 sec: 4505.5, 60 sec: 3891.7, 300 sec: 3762.8). Total num frames: 1847296. Throughput: 0: 1005.2. Samples: 461612. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) |
|
[2023-02-22 17:16:57,692][00238] Avg episode reward: [(0, '11.426')] |
|
[2023-02-22 17:16:57,694][17475] Saving new best policy, reward=11.426! |
|
[2023-02-22 17:17:02,685][00238] Fps is (10 sec: 3276.6, 60 sec: 3959.4, 300 sec: 3748.9). Total num frames: 1863680. Throughput: 0: 979.5. Samples: 466188. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:17:02,693][00238] Avg episode reward: [(0, '11.336')] |
|
[2023-02-22 17:17:07,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3762.8). Total num frames: 1880064. Throughput: 0: 989.8. Samples: 468864. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:17:07,695][00238] Avg episode reward: [(0, '11.188')] |
|
[2023-02-22 17:17:08,031][17490] Updated weights for policy 0, policy_version 460 (0.0024) |
|
[2023-02-22 17:17:12,685][00238] Fps is (10 sec: 4096.2, 60 sec: 3959.5, 300 sec: 3804.4). Total num frames: 1904640. Throughput: 0: 1001.6. Samples: 475266. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) |
|
[2023-02-22 17:17:12,687][00238] Avg episode reward: [(0, '11.304')] |
|
[2023-02-22 17:17:17,685][00238] Fps is (10 sec: 4095.9, 60 sec: 3891.2, 300 sec: 3776.6). Total num frames: 1921024. Throughput: 0: 960.2. Samples: 480904. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:17:17,699][00238] Avg episode reward: [(0, '11.488')] |
|
[2023-02-22 17:17:17,705][17475] Saving new best policy, reward=11.488! |
|
[2023-02-22 17:17:18,429][17490] Updated weights for policy 0, policy_version 470 (0.0019) |
|
[2023-02-22 17:17:22,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3762.8). Total num frames: 1937408. Throughput: 0: 942.9. Samples: 483096. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) |
|
[2023-02-22 17:17:22,687][00238] Avg episode reward: [(0, '13.259')] |
|
[2023-02-22 17:17:22,701][17475] Saving new best policy, reward=13.259! |
|
[2023-02-22 17:17:27,685][00238] Fps is (10 sec: 4096.1, 60 sec: 3959.5, 300 sec: 3790.5). Total num frames: 1961984. Throughput: 0: 979.5. Samples: 489406. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:17:27,692][00238] Avg episode reward: [(0, '12.872')] |
|
[2023-02-22 17:17:28,381][17490] Updated weights for policy 0, policy_version 480 (0.0023) |
|
[2023-02-22 17:17:32,685][00238] Fps is (10 sec: 4915.1, 60 sec: 3959.5, 300 sec: 3818.3). Total num frames: 1986560. Throughput: 0: 1004.4. Samples: 496928. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:17:32,687][00238] Avg episode reward: [(0, '13.302')] |
|
[2023-02-22 17:17:32,696][17475] Saving new best policy, reward=13.302! |
|
[2023-02-22 17:17:37,687][00238] Fps is (10 sec: 4095.2, 60 sec: 3959.4, 300 sec: 3804.4). Total num frames: 2002944. Throughput: 0: 981.0. Samples: 499530. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:17:37,690][00238] Avg episode reward: [(0, '12.795')] |
|
[2023-02-22 17:17:38,836][17490] Updated weights for policy 0, policy_version 490 (0.0017) |
|
[2023-02-22 17:17:42,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3776.7). Total num frames: 2019328. Throughput: 0: 948.3. Samples: 504286. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) |
|
[2023-02-22 17:17:42,693][00238] Avg episode reward: [(0, '13.052')] |
|
[2023-02-22 17:17:47,685][00238] Fps is (10 sec: 3687.1, 60 sec: 3959.5, 300 sec: 3804.4). Total num frames: 2039808. Throughput: 0: 997.3. Samples: 511068. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:17:47,687][00238] Avg episode reward: [(0, '14.671')] |
|
[2023-02-22 17:17:47,714][17475] Saving new best policy, reward=14.671! |
|
[2023-02-22 17:17:48,676][17490] Updated weights for policy 0, policy_version 500 (0.0037) |
|
[2023-02-22 17:17:52,685][00238] Fps is (10 sec: 4915.2, 60 sec: 3959.5, 300 sec: 3860.0). Total num frames: 2068480. Throughput: 0: 1018.7. Samples: 514706. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) |
|
[2023-02-22 17:17:52,689][00238] Avg episode reward: [(0, '14.953')] |
|
[2023-02-22 17:17:52,699][17475] Saving new best policy, reward=14.953! |
|
[2023-02-22 17:17:57,687][00238] Fps is (10 sec: 4095.0, 60 sec: 3891.1, 300 sec: 3859.9). Total num frames: 2080768. Throughput: 0: 1007.5. Samples: 520608. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:17:57,694][00238] Avg episode reward: [(0, '13.942')] |
|
[2023-02-22 17:17:59,237][17490] Updated weights for policy 0, policy_version 510 (0.0016) |
|
[2023-02-22 17:18:02,685][00238] Fps is (10 sec: 2867.2, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 2097152. Throughput: 0: 985.1. Samples: 525234. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) |
|
[2023-02-22 17:18:02,687][00238] Avg episode reward: [(0, '13.886')] |
|
[2023-02-22 17:18:02,701][17475] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000512_2097152.pth... |
|
[2023-02-22 17:18:02,816][17475] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000286_1171456.pth |
|
[2023-02-22 17:18:07,685][00238] Fps is (10 sec: 3687.3, 60 sec: 3959.5, 300 sec: 3846.1). Total num frames: 2117632. Throughput: 0: 998.9. Samples: 528046. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) |
|
[2023-02-22 17:18:07,688][00238] Avg episode reward: [(0, '13.182')] |
|
[2023-02-22 17:18:10,095][17490] Updated weights for policy 0, policy_version 520 (0.0012) |
|
[2023-02-22 17:18:12,685][00238] Fps is (10 sec: 4505.4, 60 sec: 3959.4, 300 sec: 3873.8). Total num frames: 2142208. Throughput: 0: 1003.1. Samples: 534544. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:18:12,688][00238] Avg episode reward: [(0, '13.255')] |
|
[2023-02-22 17:18:17,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3873.9). Total num frames: 2158592. Throughput: 0: 956.3. Samples: 539962. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) |
|
[2023-02-22 17:18:17,687][00238] Avg episode reward: [(0, '14.100')] |
|
[2023-02-22 17:18:21,328][17490] Updated weights for policy 0, policy_version 530 (0.0022) |
|
[2023-02-22 17:18:22,685][00238] Fps is (10 sec: 3277.0, 60 sec: 3959.5, 300 sec: 3846.1). Total num frames: 2174976. Throughput: 0: 948.8. Samples: 542222. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) |
|
[2023-02-22 17:18:22,687][00238] Avg episode reward: [(0, '13.187')] |
|
[2023-02-22 17:18:27,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3846.1). Total num frames: 2199552. Throughput: 0: 986.1. Samples: 548660. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:18:27,687][00238] Avg episode reward: [(0, '13.973')] |
|
[2023-02-22 17:18:30,100][17490] Updated weights for policy 0, policy_version 540 (0.0017) |
|
[2023-02-22 17:18:32,685][00238] Fps is (10 sec: 4505.5, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 2220032. Throughput: 0: 1003.0. Samples: 556204. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:18:32,688][00238] Avg episode reward: [(0, '13.946')] |
|
[2023-02-22 17:18:37,688][00238] Fps is (10 sec: 3685.2, 60 sec: 3891.1, 300 sec: 3873.8). Total num frames: 2236416. Throughput: 0: 978.2. Samples: 558730. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) |
|
[2023-02-22 17:18:37,699][00238] Avg episode reward: [(0, '14.762')] |
|
[2023-02-22 17:18:41,735][17490] Updated weights for policy 0, policy_version 550 (0.0022) |
|
[2023-02-22 17:18:42,689][00238] Fps is (10 sec: 3275.5, 60 sec: 3890.9, 300 sec: 3846.0). Total num frames: 2252800. Throughput: 0: 951.5. Samples: 563426. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) |
|
[2023-02-22 17:18:42,691][00238] Avg episode reward: [(0, '15.970')] |
|
[2023-02-22 17:18:42,710][17475] Saving new best policy, reward=15.970! |
|
[2023-02-22 17:18:47,687][00238] Fps is (10 sec: 4505.9, 60 sec: 4027.6, 300 sec: 3859.9). Total num frames: 2281472. Throughput: 0: 1003.6. Samples: 570400. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:18:47,693][00238] Avg episode reward: [(0, '16.793')] |
|
[2023-02-22 17:18:47,701][17475] Saving new best policy, reward=16.793! |
|
[2023-02-22 17:18:50,227][17490] Updated weights for policy 0, policy_version 560 (0.0025) |
|
[2023-02-22 17:18:52,685][00238] Fps is (10 sec: 4917.3, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 2301952. Throughput: 0: 1021.9. Samples: 574032. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:18:52,693][00238] Avg episode reward: [(0, '17.725')] |
|
[2023-02-22 17:18:52,710][17475] Saving new best policy, reward=17.725! |
|
[2023-02-22 17:18:57,685][00238] Fps is (10 sec: 3687.3, 60 sec: 3959.6, 300 sec: 3887.7). Total num frames: 2318336. Throughput: 0: 1002.9. Samples: 579674. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:18:57,692][00238] Avg episode reward: [(0, '17.752')] |
|
[2023-02-22 17:18:57,698][17475] Saving new best policy, reward=17.752! |
|
[2023-02-22 17:19:02,086][17490] Updated weights for policy 0, policy_version 570 (0.0017) |
|
[2023-02-22 17:19:02,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3873.8). Total num frames: 2334720. Throughput: 0: 988.0. Samples: 584420. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:19:02,694][00238] Avg episode reward: [(0, '18.938')] |
|
[2023-02-22 17:19:02,702][17475] Saving new best policy, reward=18.938! |
|
[2023-02-22 17:19:07,685][00238] Fps is (10 sec: 3276.9, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 2351104. Throughput: 0: 997.9. Samples: 587128. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:19:07,689][00238] Avg episode reward: [(0, '19.535')] |
|
[2023-02-22 17:19:07,695][17475] Saving new best policy, reward=19.535! |
|
[2023-02-22 17:19:12,685][00238] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3846.1). Total num frames: 2363392. Throughput: 0: 945.6. Samples: 591212. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:19:12,687][00238] Avg episode reward: [(0, '20.093')] |
|
[2023-02-22 17:19:12,699][17475] Saving new best policy, reward=20.093! |
|
[2023-02-22 17:19:16,163][17490] Updated weights for policy 0, policy_version 580 (0.0035) |
|
[2023-02-22 17:19:17,685][00238] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3846.1). Total num frames: 2379776. Throughput: 0: 870.6. Samples: 595382. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:19:17,693][00238] Avg episode reward: [(0, '18.368')] |
|
[2023-02-22 17:19:22,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3818.3). Total num frames: 2396160. Throughput: 0: 865.7. Samples: 597682. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:19:22,692][00238] Avg episode reward: [(0, '19.091')] |
|
[2023-02-22 17:19:26,654][17490] Updated weights for policy 0, policy_version 590 (0.0026) |
|
[2023-02-22 17:19:27,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3832.2). Total num frames: 2420736. Throughput: 0: 905.8. Samples: 604184. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:19:27,687][00238] Avg episode reward: [(0, '18.661')] |
|
[2023-02-22 17:19:32,687][00238] Fps is (10 sec: 4914.1, 60 sec: 3754.5, 300 sec: 3860.0). Total num frames: 2445312. Throughput: 0: 918.9. Samples: 611748. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) |
|
[2023-02-22 17:19:32,689][00238] Avg episode reward: [(0, '17.727')] |
|
[2023-02-22 17:19:36,272][17490] Updated weights for policy 0, policy_version 600 (0.0020) |
|
[2023-02-22 17:19:37,686][00238] Fps is (10 sec: 3686.0, 60 sec: 3686.5, 300 sec: 3846.1). Total num frames: 2457600. Throughput: 0: 892.0. Samples: 614172. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:19:37,688][00238] Avg episode reward: [(0, '18.220')] |
|
[2023-02-22 17:19:42,685][00238] Fps is (10 sec: 2867.8, 60 sec: 3686.7, 300 sec: 3832.2). Total num frames: 2473984. Throughput: 0: 870.8. Samples: 618858. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:19:42,687][00238] Avg episode reward: [(0, '17.422')] |
|
[2023-02-22 17:19:46,772][17490] Updated weights for policy 0, policy_version 610 (0.0013) |
|
[2023-02-22 17:19:47,685][00238] Fps is (10 sec: 4506.0, 60 sec: 3686.6, 300 sec: 3846.1). Total num frames: 2502656. Throughput: 0: 919.2. Samples: 625786. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:19:47,692][00238] Avg episode reward: [(0, '17.940')] |
|
[2023-02-22 17:19:52,687][00238] Fps is (10 sec: 5323.6, 60 sec: 3754.5, 300 sec: 3873.9). Total num frames: 2527232. Throughput: 0: 941.0. Samples: 629474. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:19:52,689][00238] Avg episode reward: [(0, '19.356')] |
|
[2023-02-22 17:19:56,417][17490] Updated weights for policy 0, policy_version 620 (0.0027) |
|
[2023-02-22 17:19:57,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3873.9). Total num frames: 2539520. Throughput: 0: 978.6. Samples: 635250. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:19:57,689][00238] Avg episode reward: [(0, '20.813')] |
|
[2023-02-22 17:19:57,698][17475] Saving new best policy, reward=20.813! |
|
[2023-02-22 17:20:02,685][00238] Fps is (10 sec: 2867.8, 60 sec: 3686.4, 300 sec: 3860.0). Total num frames: 2555904. Throughput: 0: 989.2. Samples: 639894. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:20:02,687][00238] Avg episode reward: [(0, '20.903')] |
|
[2023-02-22 17:20:02,700][17475] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000624_2555904.pth... |
|
[2023-02-22 17:20:02,814][17475] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000397_1626112.pth |
|
[2023-02-22 17:20:02,824][17475] Saving new best policy, reward=20.903! |
|
[2023-02-22 17:20:07,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3846.1). Total num frames: 2576384. Throughput: 0: 1004.8. Samples: 642898. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:20:07,690][00238] Avg episode reward: [(0, '22.217')] |
|
[2023-02-22 17:20:07,694][17475] Saving new best policy, reward=22.217! |
|
[2023-02-22 17:20:08,080][17490] Updated weights for policy 0, policy_version 630 (0.0012) |
|
[2023-02-22 17:20:12,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 2596864. Throughput: 0: 998.6. Samples: 649120. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:20:12,688][00238] Avg episode reward: [(0, '22.377')] |
|
[2023-02-22 17:20:12,705][17475] Saving new best policy, reward=22.377! |
|
[2023-02-22 17:20:17,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 2613248. Throughput: 0: 939.7. Samples: 654034. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:20:17,692][00238] Avg episode reward: [(0, '21.309')] |
|
[2023-02-22 17:20:19,556][17490] Updated weights for policy 0, policy_version 640 (0.0027) |
|
[2023-02-22 17:20:22,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 2629632. Throughput: 0: 936.3. Samples: 656306. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) |
|
[2023-02-22 17:20:22,687][00238] Avg episode reward: [(0, '20.285')] |
|
[2023-02-22 17:20:27,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 2654208. Throughput: 0: 985.0. Samples: 663182. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:20:27,687][00238] Avg episode reward: [(0, '19.473')] |
|
[2023-02-22 17:20:28,676][17490] Updated weights for policy 0, policy_version 650 (0.0015) |
|
[2023-02-22 17:20:32,685][00238] Fps is (10 sec: 4915.2, 60 sec: 3891.3, 300 sec: 3873.8). Total num frames: 2678784. Throughput: 0: 993.5. Samples: 670494. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:20:32,695][00238] Avg episode reward: [(0, '18.216')] |
|
[2023-02-22 17:20:37,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3887.7). Total num frames: 2695168. Throughput: 0: 962.4. Samples: 672782. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:20:37,690][00238] Avg episode reward: [(0, '17.894')] |
|
[2023-02-22 17:20:39,775][17490] Updated weights for policy 0, policy_version 660 (0.0011) |
|
[2023-02-22 17:20:42,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3860.0). Total num frames: 2711552. Throughput: 0: 938.5. Samples: 677482. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:20:42,689][00238] Avg episode reward: [(0, '17.989')] |
|
[2023-02-22 17:20:47,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 2736128. Throughput: 0: 999.6. Samples: 684874. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:20:47,692][00238] Avg episode reward: [(0, '18.739')] |
|
[2023-02-22 17:20:48,648][17490] Updated weights for policy 0, policy_version 670 (0.0015) |
|
[2023-02-22 17:20:52,685][00238] Fps is (10 sec: 4915.1, 60 sec: 3891.3, 300 sec: 3887.8). Total num frames: 2760704. Throughput: 0: 1015.7. Samples: 688606. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:20:52,687][00238] Avg episode reward: [(0, '18.376')] |
|
[2023-02-22 17:20:57,688][00238] Fps is (10 sec: 4094.6, 60 sec: 3959.2, 300 sec: 3901.6). Total num frames: 2777088. Throughput: 0: 995.3. Samples: 693910. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) |
|
[2023-02-22 17:20:57,692][00238] Avg episode reward: [(0, '18.546')] |
|
[2023-02-22 17:21:00,125][17490] Updated weights for policy 0, policy_version 680 (0.0036) |
|
[2023-02-22 17:21:02,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3887.7). Total num frames: 2793472. Throughput: 0: 1000.7. Samples: 699066. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) |
|
[2023-02-22 17:21:02,688][00238] Avg episode reward: [(0, '18.798')] |
|
[2023-02-22 17:21:07,685][00238] Fps is (10 sec: 3687.6, 60 sec: 3959.5, 300 sec: 3887.7). Total num frames: 2813952. Throughput: 0: 1019.6. Samples: 702188. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:21:07,688][00238] Avg episode reward: [(0, '17.964')] |
|
[2023-02-22 17:21:09,977][17490] Updated weights for policy 0, policy_version 690 (0.0019) |
|
[2023-02-22 17:21:12,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3887.7). Total num frames: 2834432. Throughput: 0: 1007.9. Samples: 708536. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:21:12,690][00238] Avg episode reward: [(0, '18.064')] |
|
[2023-02-22 17:21:17,687][00238] Fps is (10 sec: 3685.6, 60 sec: 3959.3, 300 sec: 3901.6). Total num frames: 2850816. Throughput: 0: 949.2. Samples: 713212. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:21:17,695][00238] Avg episode reward: [(0, '18.554')] |
|
[2023-02-22 17:21:21,892][17490] Updated weights for policy 0, policy_version 700 (0.0014) |
|
[2023-02-22 17:21:22,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3873.8). Total num frames: 2867200. Throughput: 0: 951.0. Samples: 715578. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:21:22,687][00238] Avg episode reward: [(0, '19.220')] |
|
[2023-02-22 17:21:27,685][00238] Fps is (10 sec: 4506.6, 60 sec: 4027.7, 300 sec: 3887.7). Total num frames: 2895872. Throughput: 0: 1004.7. Samples: 722694. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:21:27,687][00238] Avg episode reward: [(0, '20.236')] |
|
[2023-02-22 17:21:30,076][17490] Updated weights for policy 0, policy_version 710 (0.0012) |
|
[2023-02-22 17:21:32,685][00238] Fps is (10 sec: 4915.2, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 2916352. Throughput: 0: 996.5. Samples: 729716. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:21:32,687][00238] Avg episode reward: [(0, '20.865')] |
|
[2023-02-22 17:21:37,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 2932736. Throughput: 0: 966.2. Samples: 732084. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:21:37,691][00238] Avg episode reward: [(0, '21.422')] |
|
[2023-02-22 17:21:41,933][17490] Updated weights for policy 0, policy_version 720 (0.0021) |
|
[2023-02-22 17:21:42,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3887.7). Total num frames: 2949120. Throughput: 0: 955.6. Samples: 736908. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:21:42,692][00238] Avg episode reward: [(0, '21.739')] |
|
[2023-02-22 17:21:47,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3873.8). Total num frames: 2973696. Throughput: 0: 1008.6. Samples: 744452. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:21:47,687][00238] Avg episode reward: [(0, '21.641')] |
|
[2023-02-22 17:21:50,185][17490] Updated weights for policy 0, policy_version 730 (0.0023) |
|
[2023-02-22 17:21:52,685][00238] Fps is (10 sec: 4915.2, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 2998272. Throughput: 0: 1020.4. Samples: 748108. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:21:52,691][00238] Avg episode reward: [(0, '21.539')] |
|
[2023-02-22 17:21:57,685][00238] Fps is (10 sec: 4095.9, 60 sec: 3959.7, 300 sec: 3901.6). Total num frames: 3014656. Throughput: 0: 993.0. Samples: 753220. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:21:57,689][00238] Avg episode reward: [(0, '21.156')] |
|
[2023-02-22 17:22:02,009][17490] Updated weights for policy 0, policy_version 740 (0.0024) |
|
[2023-02-22 17:22:02,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 3031040. Throughput: 0: 1007.7. Samples: 758558. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:22:02,690][00238] Avg episode reward: [(0, '20.613')] |
|
[2023-02-22 17:22:02,700][17475] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000740_3031040.pth... |
|
[2023-02-22 17:22:02,823][17475] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000512_2097152.pth |
|
[2023-02-22 17:22:07,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3887.7). Total num frames: 3051520. Throughput: 0: 1023.8. Samples: 761648. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:22:07,691][00238] Avg episode reward: [(0, '19.956')] |
|
[2023-02-22 17:22:12,253][17490] Updated weights for policy 0, policy_version 750 (0.0015) |
|
[2023-02-22 17:22:12,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 3072000. Throughput: 0: 1002.7. Samples: 767814. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) |
|
[2023-02-22 17:22:12,690][00238] Avg episode reward: [(0, '20.563')] |
|
[2023-02-22 17:22:17,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3959.6, 300 sec: 3901.6). Total num frames: 3088384. Throughput: 0: 949.5. Samples: 772442. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:22:17,687][00238] Avg episode reward: [(0, '20.306')] |
|
[2023-02-22 17:22:22,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3873.8). Total num frames: 3104768. Throughput: 0: 948.4. Samples: 774764. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:22:22,687][00238] Avg episode reward: [(0, '21.763')] |
|
[2023-02-22 17:22:23,619][17490] Updated weights for policy 0, policy_version 760 (0.0011) |
|
[2023-02-22 17:22:27,685][00238] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 3129344. Throughput: 0: 1003.8. Samples: 782080. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:22:27,686][00238] Avg episode reward: [(0, '21.634')] |
|
[2023-02-22 17:22:32,690][00238] Fps is (10 sec: 4503.2, 60 sec: 3890.9, 300 sec: 3887.7). Total num frames: 3149824. Throughput: 0: 984.0. Samples: 788738. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:22:32,705][00238] Avg episode reward: [(0, '22.197')] |
|
[2023-02-22 17:22:32,727][17490] Updated weights for policy 0, policy_version 770 (0.0031) |
|
[2023-02-22 17:22:37,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3887.7). Total num frames: 3166208. Throughput: 0: 955.8. Samples: 791118. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) |
|
[2023-02-22 17:22:37,686][00238] Avg episode reward: [(0, '21.919')] |
|
[2023-02-22 17:22:42,688][00238] Fps is (10 sec: 3687.1, 60 sec: 3959.3, 300 sec: 3887.7). Total num frames: 3186688. Throughput: 0: 955.4. Samples: 796214. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:22:42,694][00238] Avg episode reward: [(0, '21.380')] |
|
[2023-02-22 17:22:43,695][17490] Updated weights for policy 0, policy_version 780 (0.0016) |
|
[2023-02-22 17:22:47,685][00238] Fps is (10 sec: 4915.1, 60 sec: 4027.7, 300 sec: 3887.7). Total num frames: 3215360. Throughput: 0: 1006.5. Samples: 803852. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:22:47,687][00238] Avg episode reward: [(0, '21.215')] |
|
[2023-02-22 17:22:52,375][17490] Updated weights for policy 0, policy_version 790 (0.0015) |
|
[2023-02-22 17:22:52,686][00238] Fps is (10 sec: 4916.7, 60 sec: 3959.4, 300 sec: 3915.5). Total num frames: 3235840. Throughput: 0: 1020.3. Samples: 807560. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:22:52,689][00238] Avg episode reward: [(0, '21.510')] |
|
[2023-02-22 17:22:57,686][00238] Fps is (10 sec: 3276.4, 60 sec: 3891.1, 300 sec: 3901.6). Total num frames: 3248128. Throughput: 0: 991.7. Samples: 812442. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) |
|
[2023-02-22 17:22:57,689][00238] Avg episode reward: [(0, '21.099')] |
|
[2023-02-22 17:23:02,685][00238] Fps is (10 sec: 3276.9, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 3268608. Throughput: 0: 1010.5. Samples: 817916. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:23:02,691][00238] Avg episode reward: [(0, '21.396')] |
|
[2023-02-22 17:23:03,896][17490] Updated weights for policy 0, policy_version 800 (0.0018) |
|
[2023-02-22 17:23:07,685][00238] Fps is (10 sec: 4096.5, 60 sec: 3959.5, 300 sec: 3887.7). Total num frames: 3289088. Throughput: 0: 1027.7. Samples: 821010. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:23:07,687][00238] Avg episode reward: [(0, '21.600')] |
|
[2023-02-22 17:23:12,689][00238] Fps is (10 sec: 4094.2, 60 sec: 3959.2, 300 sec: 3901.6). Total num frames: 3309568. Throughput: 0: 1001.8. Samples: 827164. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:23:12,696][00238] Avg episode reward: [(0, '22.072')] |
|
[2023-02-22 17:23:14,914][17490] Updated weights for policy 0, policy_version 810 (0.0025) |
|
[2023-02-22 17:23:17,689][00238] Fps is (10 sec: 3684.8, 60 sec: 3959.2, 300 sec: 3901.6). Total num frames: 3325952. Throughput: 0: 958.0. Samples: 831848. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:23:17,691][00238] Avg episode reward: [(0, '22.259')] |
|
[2023-02-22 17:23:22,685][00238] Fps is (10 sec: 3688.0, 60 sec: 4027.7, 300 sec: 3887.7). Total num frames: 3346432. Throughput: 0: 958.8. Samples: 834262. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:23:22,687][00238] Avg episode reward: [(0, '22.668')] |
|
[2023-02-22 17:23:22,700][17475] Saving new best policy, reward=22.668! |
|
[2023-02-22 17:23:25,132][17490] Updated weights for policy 0, policy_version 820 (0.0020) |
|
[2023-02-22 17:23:27,685][00238] Fps is (10 sec: 4507.5, 60 sec: 4027.7, 300 sec: 3901.6). Total num frames: 3371008. Throughput: 0: 1009.0. Samples: 841614. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) |
|
[2023-02-22 17:23:27,687][00238] Avg episode reward: [(0, '22.371')] |
|
[2023-02-22 17:23:32,687][00238] Fps is (10 sec: 4504.7, 60 sec: 4027.9, 300 sec: 3915.5). Total num frames: 3391488. Throughput: 0: 987.7. Samples: 848302. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:23:32,694][00238] Avg episode reward: [(0, '19.841')] |
|
[2023-02-22 17:23:34,744][17490] Updated weights for policy 0, policy_version 830 (0.0012) |
|
[2023-02-22 17:23:37,685][00238] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3915.6). Total num frames: 3407872. Throughput: 0: 958.5. Samples: 850692. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) |
|
[2023-02-22 17:23:37,689][00238] Avg episode reward: [(0, '18.614')] |
|
[2023-02-22 17:23:42,685][00238] Fps is (10 sec: 3687.2, 60 sec: 4028.0, 300 sec: 3887.8). Total num frames: 3428352. Throughput: 0: 967.9. Samples: 855996. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) |
|
[2023-02-22 17:23:42,687][00238] Avg episode reward: [(0, '18.305')] |
|
[2023-02-22 17:23:44,999][17490] Updated weights for policy 0, policy_version 840 (0.0012) |
|
[2023-02-22 17:23:47,685][00238] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 3452928. Throughput: 0: 1012.7. Samples: 863486. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:23:47,693][00238] Avg episode reward: [(0, '18.609')] |
|
[2023-02-22 17:23:52,685][00238] Fps is (10 sec: 4505.3, 60 sec: 3959.4, 300 sec: 3915.5). Total num frames: 3473408. Throughput: 0: 1024.1. Samples: 867094. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:23:52,689][00238] Avg episode reward: [(0, '19.289')] |
|
[2023-02-22 17:23:54,868][17490] Updated weights for policy 0, policy_version 850 (0.0029) |
|
[2023-02-22 17:23:57,685][00238] Fps is (10 sec: 3686.4, 60 sec: 4027.8, 300 sec: 3915.5). Total num frames: 3489792. Throughput: 0: 994.2. Samples: 871900. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) |
|
[2023-02-22 17:23:57,691][00238] Avg episode reward: [(0, '20.332')] |
|
[2023-02-22 17:24:02,685][00238] Fps is (10 sec: 3686.7, 60 sec: 4027.7, 300 sec: 3929.4). Total num frames: 3510272. Throughput: 0: 1020.4. Samples: 877762. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:24:02,692][00238] Avg episode reward: [(0, '20.552')] |
|
[2023-02-22 17:24:02,708][17475] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000857_3510272.pth... |
|
[2023-02-22 17:24:02,851][17475] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000624_2555904.pth |
|
[2023-02-22 17:24:05,616][17490] Updated weights for policy 0, policy_version 860 (0.0015) |
|
[2023-02-22 17:24:07,685][00238] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3957.2). Total num frames: 3530752. Throughput: 0: 1034.8. Samples: 880830. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:24:07,687][00238] Avg episode reward: [(0, '21.995')] |
|
[2023-02-22 17:24:12,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3959.7, 300 sec: 3957.2). Total num frames: 3547136. Throughput: 0: 1000.8. Samples: 886648. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:24:12,687][00238] Avg episode reward: [(0, '22.720')] |
|
[2023-02-22 17:24:12,706][17475] Saving new best policy, reward=22.720! |
|
[2023-02-22 17:24:17,527][17490] Updated weights for policy 0, policy_version 870 (0.0012) |
|
[2023-02-22 17:24:17,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3959.7, 300 sec: 3957.2). Total num frames: 3563520. Throughput: 0: 956.3. Samples: 891332. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) |
|
[2023-02-22 17:24:17,691][00238] Avg episode reward: [(0, '20.908')] |
|
[2023-02-22 17:24:22,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 3584000. Throughput: 0: 957.5. Samples: 893780. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) |
|
[2023-02-22 17:24:22,687][00238] Avg episode reward: [(0, '21.421')] |
|
[2023-02-22 17:24:26,591][17490] Updated weights for policy 0, policy_version 880 (0.0015) |
|
[2023-02-22 17:24:27,685][00238] Fps is (10 sec: 4505.5, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 3608576. Throughput: 0: 1007.8. Samples: 901346. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) |
|
[2023-02-22 17:24:27,687][00238] Avg episode reward: [(0, '20.722')] |
|
[2023-02-22 17:24:32,692][00238] Fps is (10 sec: 4502.4, 60 sec: 3959.1, 300 sec: 3971.0). Total num frames: 3629056. Throughput: 0: 985.0. Samples: 907820. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) |
|
[2023-02-22 17:24:32,695][00238] Avg episode reward: [(0, '19.621')] |
|
[2023-02-22 17:24:37,586][17490] Updated weights for policy 0, policy_version 890 (0.0023) |
|
[2023-02-22 17:24:37,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3971.0). Total num frames: 3645440. Throughput: 0: 957.7. Samples: 910190. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) |
|
[2023-02-22 17:24:37,687][00238] Avg episode reward: [(0, '19.681')] |
|
[2023-02-22 17:24:42,685][00238] Fps is (10 sec: 3689.1, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 3665920. Throughput: 0: 970.4. Samples: 915570. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) |
|
[2023-02-22 17:24:42,689][00238] Avg episode reward: [(0, '20.281')] |
|
[2023-02-22 17:24:46,605][17490] Updated weights for policy 0, policy_version 900 (0.0012) |
|
[2023-02-22 17:24:47,685][00238] Fps is (10 sec: 4505.7, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 3690496. Throughput: 0: 1006.7. Samples: 923064. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) |
|
[2023-02-22 17:24:47,686][00238] Avg episode reward: [(0, '22.170')] |
|
[2023-02-22 17:24:52,685][00238] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3971.0). Total num frames: 3710976. Throughput: 0: 1014.6. Samples: 926486. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:24:52,687][00238] Avg episode reward: [(0, '22.098')] |
|
[2023-02-22 17:24:57,516][17490] Updated weights for policy 0, policy_version 910 (0.0032) |
|
[2023-02-22 17:24:57,685][00238] Fps is (10 sec: 3686.3, 60 sec: 3959.4, 300 sec: 3971.0). Total num frames: 3727360. Throughput: 0: 990.7. Samples: 931230. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:24:57,692][00238] Avg episode reward: [(0, '22.821')] |
|
[2023-02-22 17:24:57,694][17475] Saving new best policy, reward=22.821! |
|
[2023-02-22 17:25:02,685][00238] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3971.0). Total num frames: 3747840. Throughput: 0: 1018.0. Samples: 937140. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) |
|
[2023-02-22 17:25:02,692][00238] Avg episode reward: [(0, '23.553')] |
|
[2023-02-22 17:25:02,700][17475] Saving new best policy, reward=23.553! |
|
[2023-02-22 17:25:07,596][17490] Updated weights for policy 0, policy_version 920 (0.0018) |
|
[2023-02-22 17:25:07,685][00238] Fps is (10 sec: 4096.1, 60 sec: 3959.5, 300 sec: 3971.0). Total num frames: 3768320. Throughput: 0: 1030.3. Samples: 940144. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) |
|
[2023-02-22 17:25:07,692][00238] Avg episode reward: [(0, '24.198')] |
|
[2023-02-22 17:25:07,698][17475] Saving new best policy, reward=24.198! |
|
[2023-02-22 17:25:12,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3957.2). Total num frames: 3780608. Throughput: 0: 976.3. Samples: 945280. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) |
|
[2023-02-22 17:25:12,691][00238] Avg episode reward: [(0, '25.125')] |
|
[2023-02-22 17:25:12,704][17475] Saving new best policy, reward=25.125! |
|
[2023-02-22 17:25:17,685][00238] Fps is (10 sec: 2457.6, 60 sec: 3822.9, 300 sec: 3943.3). Total num frames: 3792896. Throughput: 0: 914.1. Samples: 948950. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) |
|
[2023-02-22 17:25:17,689][00238] Avg episode reward: [(0, '24.629')] |
|
[2023-02-22 17:25:22,685][00238] Fps is (10 sec: 2457.6, 60 sec: 3686.4, 300 sec: 3901.6). Total num frames: 3805184. Throughput: 0: 901.6. Samples: 950760. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:25:22,688][00238] Avg episode reward: [(0, '24.062')] |
|
[2023-02-22 17:25:23,253][17490] Updated weights for policy 0, policy_version 930 (0.0055) |
|
[2023-02-22 17:25:27,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3887.7). Total num frames: 3825664. Throughput: 0: 893.0. Samples: 955756. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:25:27,687][00238] Avg episode reward: [(0, '24.958')] |
|
[2023-02-22 17:25:32,110][17490] Updated weights for policy 0, policy_version 940 (0.0015) |
|
[2023-02-22 17:25:32,685][00238] Fps is (10 sec: 4505.6, 60 sec: 3686.8, 300 sec: 3915.5). Total num frames: 3850240. Throughput: 0: 892.8. Samples: 963238. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:25:32,689][00238] Avg episode reward: [(0, '23.170')] |
|
[2023-02-22 17:25:37,685][00238] Fps is (10 sec: 4505.4, 60 sec: 3754.6, 300 sec: 3929.4). Total num frames: 3870720. Throughput: 0: 896.1. Samples: 966810. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:25:37,688][00238] Avg episode reward: [(0, '21.971')] |
|
[2023-02-22 17:25:42,685][00238] Fps is (10 sec: 3686.3, 60 sec: 3686.4, 300 sec: 3901.6). Total num frames: 3887104. Throughput: 0: 894.3. Samples: 971474. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) |
|
[2023-02-22 17:25:42,695][00238] Avg episode reward: [(0, '22.026')] |
|
[2023-02-22 17:25:43,425][17490] Updated weights for policy 0, policy_version 950 (0.0020) |
|
[2023-02-22 17:25:47,685][00238] Fps is (10 sec: 3686.6, 60 sec: 3618.1, 300 sec: 3887.7). Total num frames: 3907584. Throughput: 0: 895.6. Samples: 977444. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) |
|
[2023-02-22 17:25:47,690][00238] Avg episode reward: [(0, '20.046')] |
|
[2023-02-22 17:25:52,176][17490] Updated weights for policy 0, policy_version 960 (0.0021) |
|
[2023-02-22 17:25:52,685][00238] Fps is (10 sec: 4505.7, 60 sec: 3686.4, 300 sec: 3915.5). Total num frames: 3932160. Throughput: 0: 911.3. Samples: 981152. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) |
|
[2023-02-22 17:25:52,687][00238] Avg episode reward: [(0, '20.134')] |
|
[2023-02-22 17:25:57,688][00238] Fps is (10 sec: 4504.8, 60 sec: 3754.6, 300 sec: 3929.4). Total num frames: 3952640. Throughput: 0: 945.6. Samples: 987834. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) |
|
[2023-02-22 17:25:57,690][00238] Avg episode reward: [(0, '20.555')] |
|
[2023-02-22 17:26:02,685][00238] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3901.6). Total num frames: 3964928. Throughput: 0: 966.9. Samples: 992462. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) |
|
[2023-02-22 17:26:02,688][00238] Avg episode reward: [(0, '20.993')] |
|
[2023-02-22 17:26:02,790][17475] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000969_3969024.pth... |
|
[2023-02-22 17:26:02,937][17475] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000740_3031040.pth |
|
[2023-02-22 17:26:04,599][17490] Updated weights for policy 0, policy_version 970 (0.0015) |
|
[2023-02-22 17:26:07,685][00238] Fps is (10 sec: 3277.4, 60 sec: 3618.1, 300 sec: 3901.6). Total num frames: 3985408. Throughput: 0: 974.4. Samples: 994608. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) |
|
[2023-02-22 17:26:07,686][00238] Avg episode reward: [(0, '21.267')] |
|
[2023-02-22 17:26:12,031][17475] Stopping Batcher_0... |
|
[2023-02-22 17:26:12,032][17475] Loop batcher_evt_loop terminating... |
|
[2023-02-22 17:26:12,033][00238] Component Batcher_0 stopped! |
|
[2023-02-22 17:26:12,035][17475] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... |
|
[2023-02-22 17:26:12,093][00238] Component RolloutWorker_w5 stopped! |
|
[2023-02-22 17:26:12,093][17496] Stopping RolloutWorker_w3... |
|
[2023-02-22 17:26:12,102][17491] Stopping RolloutWorker_w2... |
|
[2023-02-22 17:26:12,095][00238] Component RolloutWorker_w3 stopped! |
|
[2023-02-22 17:26:12,102][17491] Loop rollout_proc2_evt_loop terminating... |
|
[2023-02-22 17:26:12,102][00238] Component RolloutWorker_w2 stopped! |
|
[2023-02-22 17:26:12,095][17494] Stopping RolloutWorker_w5... |
|
[2023-02-22 17:26:12,106][17493] Stopping RolloutWorker_w4... |
|
[2023-02-22 17:26:12,108][17493] Loop rollout_proc4_evt_loop terminating... |
|
[2023-02-22 17:26:12,112][00238] Component RolloutWorker_w4 stopped! |
|
[2023-02-22 17:26:12,125][00238] Component RolloutWorker_w1 stopped! |
|
[2023-02-22 17:26:12,097][17496] Loop rollout_proc3_evt_loop terminating... |
|
[2023-02-22 17:26:12,129][00238] Component RolloutWorker_w0 stopped! |
|
[2023-02-22 17:26:12,131][17489] Stopping RolloutWorker_w0... |
|
[2023-02-22 17:26:12,136][17490] Weights refcount: 2 0 |
|
[2023-02-22 17:26:12,141][17490] Stopping InferenceWorker_p0-w0... |
|
[2023-02-22 17:26:12,125][17492] Stopping RolloutWorker_w1... |
|
[2023-02-22 17:26:12,126][17494] Loop rollout_proc5_evt_loop terminating... |
|
[2023-02-22 17:26:12,141][00238] Component RolloutWorker_w6 stopped! |
|
[2023-02-22 17:26:12,144][00238] Component InferenceWorker_p0-w0 stopped! |
|
[2023-02-22 17:26:12,146][17495] Stopping RolloutWorker_w6... |
|
[2023-02-22 17:26:12,131][17489] Loop rollout_proc0_evt_loop terminating... |
|
[2023-02-22 17:26:12,150][17490] Loop inference_proc0-0_evt_loop terminating... |
|
[2023-02-22 17:26:12,154][17492] Loop rollout_proc1_evt_loop terminating... |
|
[2023-02-22 17:26:12,155][17497] Stopping RolloutWorker_w7... |
|
[2023-02-22 17:26:12,155][00238] Component RolloutWorker_w7 stopped! |
|
[2023-02-22 17:26:12,152][17495] Loop rollout_proc6_evt_loop terminating... |
|
[2023-02-22 17:26:12,164][17497] Loop rollout_proc7_evt_loop terminating... |
|
[2023-02-22 17:26:12,226][17475] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000857_3510272.pth |
|
[2023-02-22 17:26:12,242][17475] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... |
|
[2023-02-22 17:26:12,409][00238] Component LearnerWorker_p0 stopped! |
|
[2023-02-22 17:26:12,410][00238] Waiting for process learner_proc0 to stop... |
|
[2023-02-22 17:26:12,408][17475] Stopping LearnerWorker_p0... |
|
[2023-02-22 17:26:12,423][17475] Loop learner_proc0_evt_loop terminating... |
|
[2023-02-22 17:26:14,126][00238] Waiting for process inference_proc0-0 to join... |
|
[2023-02-22 17:26:14,562][00238] Waiting for process rollout_proc0 to join... |
|
[2023-02-22 17:26:14,799][00238] Waiting for process rollout_proc1 to join... |
|
[2023-02-22 17:26:15,137][00238] Waiting for process rollout_proc2 to join... |
|
[2023-02-22 17:26:15,141][00238] Waiting for process rollout_proc3 to join... |
|
[2023-02-22 17:26:15,142][00238] Waiting for process rollout_proc4 to join... |
|
[2023-02-22 17:26:15,143][00238] Waiting for process rollout_proc5 to join... |
|
[2023-02-22 17:26:15,145][00238] Waiting for process rollout_proc6 to join... |
|
[2023-02-22 17:26:15,148][00238] Waiting for process rollout_proc7 to join... |
|
[2023-02-22 17:26:15,149][00238] Batcher 0 profile tree view: |
|
batching: 25.6537, releasing_batches: 0.0283 |
|
[2023-02-22 17:26:15,150][00238] InferenceWorker_p0-w0 profile tree view: |
|
wait_policy: 0.0000 |
|
wait_policy_total: 505.7360 |
|
update_model: 7.5130 |
|
weight_update: 0.0016 |
|
one_step: 0.0090 |
|
handle_policy_step: 507.4398 |
|
deserialize: 14.8855, stack: 2.9028, obs_to_device_normalize: 113.7429, forward: 242.3296, send_messages: 26.2909 |
|
prepare_outputs: 82.1078 |
|
to_cpu: 50.6604 |
|
[2023-02-22 17:26:15,153][00238] Learner 0 profile tree view: |
|
misc: 0.0057, prepare_batch: 15.5572 |
|
train: 76.2907 |
|
epoch_init: 0.0059, minibatch_init: 0.0075, losses_postprocess: 0.6440, kl_divergence: 0.5798, after_optimizer: 33.1588 |
|
calculate_losses: 26.9921 |
|
losses_init: 0.0036, forward_head: 1.6895, bptt_initial: 17.8884, tail: 1.0892, advantages_returns: 0.2423, losses: 3.5040 |
|
bptt: 2.2078 |
|
bptt_forward_core: 2.1317 |
|
update: 14.3101 |
|
clip: 1.3961 |
|
[2023-02-22 17:26:15,154][00238] RolloutWorker_w0 profile tree view: |
|
wait_for_trajectories: 0.3761, enqueue_policy_requests: 130.4311, env_step: 804.8662, overhead: 19.5726, complete_rollouts: 6.9588 |
|
save_policy_outputs: 20.0405 |
|
split_output_tensors: 9.6544 |
|
[2023-02-22 17:26:15,156][00238] RolloutWorker_w7 profile tree view: |
|
wait_for_trajectories: 0.3353, enqueue_policy_requests: 133.7615, env_step: 801.4917, overhead: 19.6378, complete_rollouts: 6.9079 |
|
save_policy_outputs: 19.9991 |
|
split_output_tensors: 9.7333 |
|
[2023-02-22 17:26:15,158][00238] Loop Runner_EvtLoop terminating... |
|
[2023-02-22 17:26:15,160][00238] Runner profile tree view: |
|
main_loop: 1088.1145 |
|
[2023-02-22 17:26:15,163][00238] Collected {0: 4005888}, FPS: 3681.5 |
|
[2023-02-22 17:32:44,396][00238] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json |
|
[2023-02-22 17:32:44,398][00238] Overriding arg 'num_workers' with value 1 passed from command line |
|
[2023-02-22 17:32:44,400][00238] Adding new argument 'no_render'=True that is not in the saved config file! |
|
[2023-02-22 17:32:44,402][00238] Adding new argument 'save_video'=True that is not in the saved config file! |
|
[2023-02-22 17:32:44,404][00238] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! |
|
[2023-02-22 17:32:44,406][00238] Adding new argument 'video_name'=None that is not in the saved config file! |
|
[2023-02-22 17:32:44,407][00238] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! |
|
[2023-02-22 17:32:44,410][00238] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! |
|
[2023-02-22 17:32:44,411][00238] Adding new argument 'push_to_hub'=True that is not in the saved config file! |
|
[2023-02-22 17:32:44,413][00238] Adding new argument 'hf_repository'='cmenasse/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! |
|
[2023-02-22 17:32:44,414][00238] Adding new argument 'policy_index'=0 that is not in the saved config file! |
|
[2023-02-22 17:32:44,415][00238] Adding new argument 'eval_deterministic'=False that is not in the saved config file! |
|
[2023-02-22 17:32:44,416][00238] Adding new argument 'train_script'=None that is not in the saved config file! |
|
[2023-02-22 17:32:44,418][00238] Adding new argument 'enjoy_script'=None that is not in the saved config file! |
|
[2023-02-22 17:32:44,420][00238] Using frameskip 1 and render_action_repeat=4 for evaluation |
|
[2023-02-22 17:32:44,451][00238] Doom resolution: 160x120, resize resolution: (128, 72) |
|
[2023-02-22 17:32:44,454][00238] RunningMeanStd input shape: (3, 72, 128) |
|
[2023-02-22 17:32:44,457][00238] RunningMeanStd input shape: (1,) |
|
[2023-02-22 17:32:44,473][00238] ConvEncoder: input_channels=3 |
|
[2023-02-22 17:32:45,150][00238] Conv encoder output size: 512 |
|
[2023-02-22 17:32:45,151][00238] Policy head output size: 512 |
|
[2023-02-22 17:32:47,521][00238] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... |
|
[2023-02-22 17:32:48,778][00238] Num frames 100... |
|
[2023-02-22 17:32:48,893][00238] Num frames 200... |
|
[2023-02-22 17:32:49,005][00238] Num frames 300... |
|
[2023-02-22 17:32:49,123][00238] Num frames 400... |
|
[2023-02-22 17:32:49,248][00238] Num frames 500... |
|
[2023-02-22 17:32:49,374][00238] Num frames 600... |
|
[2023-02-22 17:32:49,475][00238] Avg episode rewards: #0: 14.290, true rewards: #0: 6.290 |
|
[2023-02-22 17:32:49,477][00238] Avg episode reward: 14.290, avg true_objective: 6.290 |
|
[2023-02-22 17:32:49,571][00238] Num frames 700... |
|
[2023-02-22 17:32:49,680][00238] Num frames 800... |
|
[2023-02-22 17:32:49,796][00238] Num frames 900... |
|
[2023-02-22 17:32:49,916][00238] Num frames 1000... |
|
[2023-02-22 17:32:50,026][00238] Num frames 1100... |
|
[2023-02-22 17:32:50,138][00238] Num frames 1200... |
|
[2023-02-22 17:32:50,251][00238] Num frames 1300... |
|
[2023-02-22 17:32:50,343][00238] Avg episode rewards: #0: 13.665, true rewards: #0: 6.665 |
|
[2023-02-22 17:32:50,345][00238] Avg episode reward: 13.665, avg true_objective: 6.665 |
|
[2023-02-22 17:32:50,419][00238] Num frames 1400... |
|
[2023-02-22 17:32:50,530][00238] Num frames 1500... |
|
[2023-02-22 17:32:50,642][00238] Num frames 1600... |
|
[2023-02-22 17:32:50,753][00238] Num frames 1700... |
|
[2023-02-22 17:32:50,862][00238] Num frames 1800... |
|
[2023-02-22 17:32:50,972][00238] Num frames 1900... |
|
[2023-02-22 17:32:51,079][00238] Num frames 2000... |
|
[2023-02-22 17:32:51,196][00238] Num frames 2100... |
|
[2023-02-22 17:32:51,334][00238] Num frames 2200... |
|
[2023-02-22 17:32:51,491][00238] Num frames 2300... |
|
[2023-02-22 17:32:51,652][00238] Num frames 2400... |
|
[2023-02-22 17:32:51,808][00238] Num frames 2500... |
|
[2023-02-22 17:32:51,958][00238] Num frames 2600... |
|
[2023-02-22 17:32:52,120][00238] Num frames 2700... |
|
[2023-02-22 17:32:52,273][00238] Num frames 2800... |
|
[2023-02-22 17:32:52,433][00238] Num frames 2900... |
|
[2023-02-22 17:32:52,588][00238] Num frames 3000... |
|
[2023-02-22 17:32:52,752][00238] Num frames 3100... |
|
[2023-02-22 17:32:52,946][00238] Avg episode rewards: #0: 22.630, true rewards: #0: 10.630 |
|
[2023-02-22 17:32:52,948][00238] Avg episode reward: 22.630, avg true_objective: 10.630 |
|
[2023-02-22 17:32:52,966][00238] Num frames 3200... |
|
[2023-02-22 17:32:53,115][00238] Num frames 3300... |
|
[2023-02-22 17:32:53,267][00238] Num frames 3400... |
|
[2023-02-22 17:32:53,415][00238] Num frames 3500... |
|
[2023-02-22 17:32:53,571][00238] Num frames 3600... |
|
[2023-02-22 17:32:53,732][00238] Num frames 3700... |
|
[2023-02-22 17:32:53,894][00238] Num frames 3800... |
|
[2023-02-22 17:32:54,052][00238] Num frames 3900... |
|
[2023-02-22 17:32:54,246][00238] Avg episode rewards: #0: 20.972, true rewards: #0: 9.972 |
|
[2023-02-22 17:32:54,249][00238] Avg episode reward: 20.972, avg true_objective: 9.972 |
|
[2023-02-22 17:32:54,267][00238] Num frames 4000... |
|
[2023-02-22 17:32:54,423][00238] Num frames 4100... |
|
[2023-02-22 17:32:54,580][00238] Num frames 4200... |
|
[2023-02-22 17:32:54,739][00238] Num frames 4300... |
|
[2023-02-22 17:32:54,872][00238] Num frames 4400... |
|
[2023-02-22 17:32:54,982][00238] Num frames 4500... |
|
[2023-02-22 17:32:55,097][00238] Num frames 4600... |
|
[2023-02-22 17:32:55,208][00238] Num frames 4700... |
|
[2023-02-22 17:32:55,323][00238] Num frames 4800... |
|
[2023-02-22 17:32:55,433][00238] Num frames 4900... |
|
[2023-02-22 17:32:55,541][00238] Num frames 5000... |
|
[2023-02-22 17:32:55,651][00238] Num frames 5100... |
|
[2023-02-22 17:32:55,767][00238] Num frames 5200... |
|
[2023-02-22 17:32:55,880][00238] Num frames 5300... |
|
[2023-02-22 17:32:55,991][00238] Num frames 5400... |
|
[2023-02-22 17:32:56,101][00238] Num frames 5500... |
|
[2023-02-22 17:32:56,214][00238] Num frames 5600... |
|
[2023-02-22 17:32:56,322][00238] Num frames 5700... |
|
[2023-02-22 17:32:56,439][00238] Num frames 5800... |
|
[2023-02-22 17:32:56,548][00238] Num frames 5900... |
|
[2023-02-22 17:32:56,672][00238] Num frames 6000... |
|
[2023-02-22 17:32:56,848][00238] Avg episode rewards: #0: 27.778, true rewards: #0: 12.178 |
|
[2023-02-22 17:32:56,850][00238] Avg episode reward: 27.778, avg true_objective: 12.178 |
|
[2023-02-22 17:32:56,865][00238] Num frames 6100... |
|
[2023-02-22 17:32:56,977][00238] Num frames 6200... |
|
[2023-02-22 17:32:57,094][00238] Num frames 6300... |
|
[2023-02-22 17:32:57,219][00238] Num frames 6400... |
|
[2023-02-22 17:32:57,329][00238] Num frames 6500... |
|
[2023-02-22 17:32:57,451][00238] Num frames 6600... |
|
[2023-02-22 17:32:57,580][00238] Num frames 6700... |
|
[2023-02-22 17:32:57,700][00238] Num frames 6800... |
|
[2023-02-22 17:32:57,817][00238] Num frames 6900... |
|
[2023-02-22 17:32:57,928][00238] Avg episode rewards: #0: 25.921, true rewards: #0: 11.588 |
|
[2023-02-22 17:32:57,930][00238] Avg episode reward: 25.921, avg true_objective: 11.588 |
|
[2023-02-22 17:32:57,984][00238] Num frames 7000... |
|
[2023-02-22 17:32:58,091][00238] Num frames 7100... |
|
[2023-02-22 17:32:58,201][00238] Num frames 7200... |
|
[2023-02-22 17:32:58,307][00238] Num frames 7300... |
|
[2023-02-22 17:32:58,414][00238] Num frames 7400... |
|
[2023-02-22 17:32:58,572][00238] Avg episode rewards: #0: 23.281, true rewards: #0: 10.710 |
|
[2023-02-22 17:32:58,574][00238] Avg episode reward: 23.281, avg true_objective: 10.710 |
|
[2023-02-22 17:32:58,581][00238] Num frames 7500... |
|
[2023-02-22 17:32:58,690][00238] Num frames 7600... |
|
[2023-02-22 17:32:58,815][00238] Num frames 7700... |
|
[2023-02-22 17:32:58,935][00238] Num frames 7800... |
|
[2023-02-22 17:32:59,051][00238] Num frames 7900... |
|
[2023-02-22 17:32:59,162][00238] Num frames 8000... |
|
[2023-02-22 17:32:59,276][00238] Num frames 8100... |
|
[2023-02-22 17:32:59,385][00238] Num frames 8200... |
|
[2023-02-22 17:32:59,497][00238] Num frames 8300... |
|
[2023-02-22 17:32:59,610][00238] Num frames 8400... |
|
[2023-02-22 17:32:59,718][00238] Num frames 8500... |
|
[2023-02-22 17:32:59,839][00238] Num frames 8600... |
|
[2023-02-22 17:32:59,950][00238] Num frames 8700... |
|
[2023-02-22 17:33:00,063][00238] Num frames 8800... |
|
[2023-02-22 17:33:00,200][00238] Avg episode rewards: #0: 24.091, true rewards: #0: 11.091 |
|
[2023-02-22 17:33:00,201][00238] Avg episode reward: 24.091, avg true_objective: 11.091 |
|
[2023-02-22 17:33:00,234][00238] Num frames 8900... |
|
[2023-02-22 17:33:00,347][00238] Num frames 9000... |
|
[2023-02-22 17:33:00,454][00238] Num frames 9100... |
|
[2023-02-22 17:33:00,564][00238] Num frames 9200... |
|
[2023-02-22 17:33:00,673][00238] Num frames 9300... |
|
[2023-02-22 17:33:00,788][00238] Num frames 9400... |
|
[2023-02-22 17:33:00,898][00238] Num frames 9500... |
|
[2023-02-22 17:33:01,008][00238] Num frames 9600... |
|
[2023-02-22 17:33:01,128][00238] Num frames 9700... |
|
[2023-02-22 17:33:01,241][00238] Num frames 9800... |
|
[2023-02-22 17:33:01,350][00238] Num frames 9900... |
|
[2023-02-22 17:33:01,477][00238] Num frames 10000... |
|
[2023-02-22 17:33:01,605][00238] Num frames 10100... |
|
[2023-02-22 17:33:01,736][00238] Num frames 10200... |
|
[2023-02-22 17:33:01,864][00238] Num frames 10300... |
|
[2023-02-22 17:33:01,980][00238] Num frames 10400... |
|
[2023-02-22 17:33:02,106][00238] Avg episode rewards: #0: 25.728, true rewards: #0: 11.617 |
|
[2023-02-22 17:33:02,109][00238] Avg episode reward: 25.728, avg true_objective: 11.617 |
|
[2023-02-22 17:33:02,166][00238] Num frames 10500... |
|
[2023-02-22 17:33:02,284][00238] Num frames 10600... |
|
[2023-02-22 17:33:02,403][00238] Num frames 10700... |
|
[2023-02-22 17:33:02,517][00238] Num frames 10800... |
|
[2023-02-22 17:33:02,636][00238] Num frames 10900... |
|
[2023-02-22 17:33:02,752][00238] Num frames 11000... |
|
[2023-02-22 17:33:02,872][00238] Num frames 11100... |
|
[2023-02-22 17:33:02,987][00238] Num frames 11200... |
|
[2023-02-22 17:33:03,102][00238] Num frames 11300... |
|
[2023-02-22 17:33:03,220][00238] Num frames 11400... |
|
[2023-02-22 17:33:03,339][00238] Num frames 11500... |
|
[2023-02-22 17:33:03,458][00238] Num frames 11600... |
|
[2023-02-22 17:33:03,585][00238] Num frames 11700... |
|
[2023-02-22 17:33:03,707][00238] Num frames 11800... |
|
[2023-02-22 17:33:03,813][00238] Avg episode rewards: #0: 26.541, true rewards: #0: 11.841 |
|
[2023-02-22 17:33:03,815][00238] Avg episode reward: 26.541, avg true_objective: 11.841 |
|
[2023-02-22 17:34:13,172][00238] Replay video saved to /content/train_dir/default_experiment/replay.mp4! |
|
|