diff --git "a/sf_log.txt" "b/sf_log.txt" new file mode 100644--- /dev/null +++ "b/sf_log.txt" @@ -0,0 +1,1290 @@ +[2023-05-31 15:54:56,445][00392] Saving configuration to /content/train_dir/default_experiment/config.json... +[2023-05-31 15:54:56,449][00392] Rollout worker 0 uses device cpu +[2023-05-31 15:54:56,450][00392] Rollout worker 1 uses device cpu +[2023-05-31 15:54:56,454][00392] Rollout worker 2 uses device cpu +[2023-05-31 15:54:56,457][00392] Rollout worker 3 uses device cpu +[2023-05-31 15:54:56,458][00392] Rollout worker 4 uses device cpu +[2023-05-31 15:54:56,460][00392] Rollout worker 5 uses device cpu +[2023-05-31 15:54:56,462][00392] Rollout worker 6 uses device cpu +[2023-05-31 15:54:56,464][00392] Rollout worker 7 uses device cpu +[2023-05-31 15:54:56,600][00392] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-05-31 15:54:56,602][00392] InferenceWorker_p0-w0: min num requests: 2 +[2023-05-31 15:54:56,633][00392] Starting all processes... +[2023-05-31 15:54:56,634][00392] Starting process learner_proc0 +[2023-05-31 15:54:56,683][00392] Starting all processes... +[2023-05-31 15:54:56,692][00392] Starting process inference_proc0-0 +[2023-05-31 15:54:56,693][00392] Starting process rollout_proc0 +[2023-05-31 15:54:56,697][00392] Starting process rollout_proc1 +[2023-05-31 15:54:56,697][00392] Starting process rollout_proc2 +[2023-05-31 15:54:56,697][00392] Starting process rollout_proc3 +[2023-05-31 15:54:56,697][00392] Starting process rollout_proc4 +[2023-05-31 15:54:56,698][00392] Starting process rollout_proc5 +[2023-05-31 15:54:56,698][00392] Starting process rollout_proc6 +[2023-05-31 15:54:56,698][00392] Starting process rollout_proc7 +[2023-05-31 15:55:08,741][13398] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-05-31 15:55:08,744][13398] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 +[2023-05-31 15:55:08,788][13398] Num visible devices: 1 +[2023-05-31 15:55:08,828][13412] Worker 0 uses CPU cores [0] +[2023-05-31 15:55:08,830][13398] Starting seed is not provided +[2023-05-31 15:55:08,831][13398] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-05-31 15:55:08,832][13398] Initializing actor-critic model on device cuda:0 +[2023-05-31 15:55:08,833][13398] RunningMeanStd input shape: (3, 72, 128) +[2023-05-31 15:55:08,834][13398] RunningMeanStd input shape: (1,) +[2023-05-31 15:55:08,840][13413] Worker 1 uses CPU cores [1] +[2023-05-31 15:55:08,903][13398] ConvEncoder: input_channels=3 +[2023-05-31 15:55:08,906][13416] Worker 4 uses CPU cores [0] +[2023-05-31 15:55:08,988][13418] Worker 6 uses CPU cores [0] +[2023-05-31 15:55:09,000][13415] Worker 3 uses CPU cores [1] +[2023-05-31 15:55:09,016][13414] Worker 2 uses CPU cores [0] +[2023-05-31 15:55:09,026][13417] Worker 5 uses CPU cores [1] +[2023-05-31 15:55:09,041][13419] Worker 7 uses CPU cores [1] +[2023-05-31 15:55:09,042][13411] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-05-31 15:55:09,043][13411] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 +[2023-05-31 15:55:09,061][13411] Num visible devices: 1 +[2023-05-31 15:55:09,176][13398] Conv encoder output size: 512 +[2023-05-31 15:55:09,176][13398] Policy head output size: 512 +[2023-05-31 15:55:09,192][13398] Created Actor Critic model with architecture: +[2023-05-31 15:55:09,192][13398] 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) + ) +) +[2023-05-31 15:55:14,165][13398] Using optimizer +[2023-05-31 15:55:14,166][13398] No checkpoints found +[2023-05-31 15:55:14,167][13398] Did not load from checkpoint, starting from scratch! +[2023-05-31 15:55:14,167][13398] Initialized policy 0 weights for model version 0 +[2023-05-31 15:55:14,169][13398] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-05-31 15:55:14,180][13398] LearnerWorker_p0 finished initialization! +[2023-05-31 15:55:14,352][13411] RunningMeanStd input shape: (3, 72, 128) +[2023-05-31 15:55:14,354][13411] RunningMeanStd input shape: (1,) +[2023-05-31 15:55:14,371][13411] ConvEncoder: input_channels=3 +[2023-05-31 15:55:14,471][13411] Conv encoder output size: 512 +[2023-05-31 15:55:14,471][13411] Policy head output size: 512 +[2023-05-31 15:55:16,033][00392] Inference worker 0-0 is ready! +[2023-05-31 15:55:16,039][00392] All inference workers are ready! Signal rollout workers to start! +[2023-05-31 15:55:16,171][13412] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-05-31 15:55:16,236][13416] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-05-31 15:55:16,231][13414] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-05-31 15:55:16,264][13418] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-05-31 15:55:16,298][13419] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-05-31 15:55:16,348][13417] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-05-31 15:55:16,359][13415] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-05-31 15:55:16,363][13413] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-05-31 15:55:16,593][00392] Heartbeat connected on Batcher_0 +[2023-05-31 15:55:16,596][00392] Heartbeat connected on LearnerWorker_p0 +[2023-05-31 15:55:16,650][00392] Heartbeat connected on InferenceWorker_p0-w0 +[2023-05-31 15:55:17,459][13417] Decorrelating experience for 0 frames... +[2023-05-31 15:55:17,460][13415] Decorrelating experience for 0 frames... +[2023-05-31 15:55:17,959][13412] Decorrelating experience for 0 frames... +[2023-05-31 15:55:17,960][13418] Decorrelating experience for 0 frames... +[2023-05-31 15:55:17,965][13414] Decorrelating experience for 0 frames... +[2023-05-31 15:55:18,211][00392] 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) +[2023-05-31 15:55:18,734][13417] Decorrelating experience for 32 frames... +[2023-05-31 15:55:18,744][13413] Decorrelating experience for 0 frames... +[2023-05-31 15:55:19,084][13419] Decorrelating experience for 0 frames... +[2023-05-31 15:55:19,115][13414] Decorrelating experience for 32 frames... +[2023-05-31 15:55:19,117][13418] Decorrelating experience for 32 frames... +[2023-05-31 15:55:19,973][13419] Decorrelating experience for 32 frames... +[2023-05-31 15:55:19,999][13418] Decorrelating experience for 64 frames... +[2023-05-31 15:55:20,046][13415] Decorrelating experience for 32 frames... +[2023-05-31 15:55:20,846][13417] Decorrelating experience for 64 frames... +[2023-05-31 15:55:20,916][13414] Decorrelating experience for 64 frames... +[2023-05-31 15:55:20,981][13419] Decorrelating experience for 64 frames... +[2023-05-31 15:55:22,032][13417] Decorrelating experience for 96 frames... +[2023-05-31 15:55:22,176][13415] Decorrelating experience for 64 frames... +[2023-05-31 15:55:22,237][00392] Heartbeat connected on RolloutWorker_w5 +[2023-05-31 15:55:22,311][13419] Decorrelating experience for 96 frames... +[2023-05-31 15:55:22,434][13412] Decorrelating experience for 32 frames... +[2023-05-31 15:55:22,454][13416] Decorrelating experience for 0 frames... +[2023-05-31 15:55:22,584][00392] Heartbeat connected on RolloutWorker_w7 +[2023-05-31 15:55:23,212][00392] 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) +[2023-05-31 15:55:23,382][13415] Decorrelating experience for 96 frames... +[2023-05-31 15:55:23,598][00392] Heartbeat connected on RolloutWorker_w3 +[2023-05-31 15:55:24,297][13414] Decorrelating experience for 96 frames... +[2023-05-31 15:55:24,420][13416] Decorrelating experience for 32 frames... +[2023-05-31 15:55:24,424][13418] Decorrelating experience for 96 frames... +[2023-05-31 15:55:24,605][00392] Heartbeat connected on RolloutWorker_w2 +[2023-05-31 15:55:24,791][00392] Heartbeat connected on RolloutWorker_w6 +[2023-05-31 15:55:24,828][13412] Decorrelating experience for 64 frames... +[2023-05-31 15:55:25,313][13413] Decorrelating experience for 32 frames... +[2023-05-31 15:55:26,303][13416] Decorrelating experience for 64 frames... +[2023-05-31 15:55:26,438][13412] Decorrelating experience for 96 frames... +[2023-05-31 15:55:26,704][00392] Heartbeat connected on RolloutWorker_w0 +[2023-05-31 15:55:28,211][00392] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 198.6. Samples: 1986. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) +[2023-05-31 15:55:28,215][00392] Avg episode reward: [(0, '2.459')] +[2023-05-31 15:55:28,919][13398] Signal inference workers to stop experience collection... +[2023-05-31 15:55:28,929][13411] InferenceWorker_p0-w0: stopping experience collection +[2023-05-31 15:55:29,072][13413] Decorrelating experience for 64 frames... +[2023-05-31 15:55:29,128][13416] Decorrelating experience for 96 frames... +[2023-05-31 15:55:29,475][00392] Heartbeat connected on RolloutWorker_w4 +[2023-05-31 15:55:29,495][13413] Decorrelating experience for 96 frames... +[2023-05-31 15:55:29,559][00392] Heartbeat connected on RolloutWorker_w1 +[2023-05-31 15:55:31,432][13398] Signal inference workers to resume experience collection... +[2023-05-31 15:55:31,433][13411] InferenceWorker_p0-w0: resuming experience collection +[2023-05-31 15:55:33,211][00392] Fps is (10 sec: 1228.9, 60 sec: 819.2, 300 sec: 819.2). Total num frames: 12288. Throughput: 0: 164.4. Samples: 2466. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-05-31 15:55:33,219][00392] Avg episode reward: [(0, '3.000')] +[2023-05-31 15:55:38,211][00392] Fps is (10 sec: 2457.6, 60 sec: 1228.8, 300 sec: 1228.8). Total num frames: 24576. Throughput: 0: 326.0. Samples: 6520. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 15:55:38,215][00392] Avg episode reward: [(0, '3.708')] +[2023-05-31 15:55:43,211][00392] Fps is (10 sec: 2457.6, 60 sec: 1474.6, 300 sec: 1474.6). Total num frames: 36864. Throughput: 0: 429.2. Samples: 10730. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 15:55:43,219][00392] Avg episode reward: [(0, '4.070')] +[2023-05-31 15:55:43,608][13411] Updated weights for policy 0, policy_version 10 (0.0020) +[2023-05-31 15:55:48,211][00392] Fps is (10 sec: 3276.8, 60 sec: 1911.5, 300 sec: 1911.5). Total num frames: 57344. Throughput: 0: 433.9. Samples: 13016. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 15:55:48,218][00392] Avg episode reward: [(0, '4.430')] +[2023-05-31 15:55:52,920][13411] Updated weights for policy 0, policy_version 20 (0.0020) +[2023-05-31 15:55:53,211][00392] Fps is (10 sec: 4505.6, 60 sec: 2340.6, 300 sec: 2340.6). Total num frames: 81920. Throughput: 0: 570.1. Samples: 19954. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-05-31 15:55:53,219][00392] Avg episode reward: [(0, '4.408')] +[2023-05-31 15:55:58,219][00392] Fps is (10 sec: 4093.0, 60 sec: 2457.1, 300 sec: 2457.1). Total num frames: 98304. Throughput: 0: 640.7. Samples: 25634. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 15:55:58,224][00392] Avg episode reward: [(0, '4.170')] +[2023-05-31 15:56:03,212][00392] Fps is (10 sec: 2867.1, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 110592. Throughput: 0: 616.7. Samples: 27752. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-05-31 15:56:03,216][00392] Avg episode reward: [(0, '4.198')] +[2023-05-31 15:56:03,230][13398] Saving new best policy, reward=4.198! +[2023-05-31 15:56:06,191][13411] Updated weights for policy 0, policy_version 30 (0.0015) +[2023-05-31 15:56:08,211][00392] Fps is (10 sec: 2869.3, 60 sec: 2539.5, 300 sec: 2539.5). Total num frames: 126976. Throughput: 0: 710.4. Samples: 31966. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 15:56:08,214][00392] Avg episode reward: [(0, '4.306')] +[2023-05-31 15:56:08,217][13398] Saving new best policy, reward=4.306! +[2023-05-31 15:56:13,211][00392] Fps is (10 sec: 4096.1, 60 sec: 2755.5, 300 sec: 2755.5). Total num frames: 151552. Throughput: 0: 809.7. Samples: 38422. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-05-31 15:56:13,219][00392] Avg episode reward: [(0, '4.319')] +[2023-05-31 15:56:13,228][13398] Saving new best policy, reward=4.319! +[2023-05-31 15:56:15,700][13411] Updated weights for policy 0, policy_version 40 (0.0020) +[2023-05-31 15:56:18,212][00392] Fps is (10 sec: 4505.4, 60 sec: 2867.2, 300 sec: 2867.2). Total num frames: 172032. Throughput: 0: 874.6. Samples: 41824. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-05-31 15:56:18,214][00392] Avg episode reward: [(0, '4.486')] +[2023-05-31 15:56:18,219][13398] Saving new best policy, reward=4.486! +[2023-05-31 15:56:23,211][00392] Fps is (10 sec: 3686.4, 60 sec: 3140.3, 300 sec: 2898.7). Total num frames: 188416. Throughput: 0: 896.0. Samples: 46842. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-05-31 15:56:23,214][00392] Avg episode reward: [(0, '4.495')] +[2023-05-31 15:56:23,231][13398] Saving new best policy, reward=4.495! +[2023-05-31 15:56:28,212][00392] Fps is (10 sec: 2867.3, 60 sec: 3345.1, 300 sec: 2867.2). Total num frames: 200704. Throughput: 0: 895.3. Samples: 51018. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-05-31 15:56:28,214][00392] Avg episode reward: [(0, '4.492')] +[2023-05-31 15:56:29,243][13411] Updated weights for policy 0, policy_version 50 (0.0016) +[2023-05-31 15:56:33,211][00392] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 2949.1). Total num frames: 221184. Throughput: 0: 905.6. Samples: 53766. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 15:56:33,216][00392] Avg episode reward: [(0, '4.322')] +[2023-05-31 15:56:38,211][00392] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3020.8). Total num frames: 241664. Throughput: 0: 905.0. Samples: 60680. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 15:56:38,218][00392] Avg episode reward: [(0, '4.268')] +[2023-05-31 15:56:38,373][13411] Updated weights for policy 0, policy_version 60 (0.0017) +[2023-05-31 15:56:43,211][00392] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3084.0). Total num frames: 262144. Throughput: 0: 898.5. Samples: 66058. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-05-31 15:56:43,214][00392] Avg episode reward: [(0, '4.377')] +[2023-05-31 15:56:48,211][00392] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3049.2). Total num frames: 274432. Throughput: 0: 899.2. Samples: 68214. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-05-31 15:56:48,221][00392] Avg episode reward: [(0, '4.510')] +[2023-05-31 15:56:48,227][13398] Saving new best policy, reward=4.510! +[2023-05-31 15:56:51,549][13411] Updated weights for policy 0, policy_version 70 (0.0029) +[2023-05-31 15:56:53,211][00392] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3061.2). Total num frames: 290816. Throughput: 0: 908.1. Samples: 72830. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 15:56:53,214][00392] Avg episode reward: [(0, '4.482')] +[2023-05-31 15:56:53,221][13398] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000071_290816.pth... +[2023-05-31 15:56:58,211][00392] Fps is (10 sec: 4095.9, 60 sec: 3618.6, 300 sec: 3153.9). Total num frames: 315392. Throughput: 0: 911.8. Samples: 79454. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 15:56:58,213][00392] Avg episode reward: [(0, '4.405')] +[2023-05-31 15:57:00,768][13411] Updated weights for policy 0, policy_version 80 (0.0019) +[2023-05-31 15:57:03,211][00392] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3159.8). Total num frames: 331776. Throughput: 0: 910.3. Samples: 82788. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 15:57:03,214][00392] Avg episode reward: [(0, '4.372')] +[2023-05-31 15:57:08,211][00392] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3165.1). Total num frames: 348160. Throughput: 0: 893.6. Samples: 87054. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 15:57:08,221][00392] Avg episode reward: [(0, '4.399')] +[2023-05-31 15:57:13,212][00392] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3134.3). Total num frames: 360448. Throughput: 0: 894.1. Samples: 91252. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 15:57:13,215][00392] Avg episode reward: [(0, '4.613')] +[2023-05-31 15:57:13,233][13398] Saving new best policy, reward=4.613! +[2023-05-31 15:57:14,694][13411] Updated weights for policy 0, policy_version 90 (0.0030) +[2023-05-31 15:57:18,211][00392] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3174.4). Total num frames: 380928. Throughput: 0: 900.8. Samples: 94304. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 15:57:18,218][00392] Avg episode reward: [(0, '4.686')] +[2023-05-31 15:57:18,220][13398] Saving new best policy, reward=4.686! +[2023-05-31 15:57:23,212][00392] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3244.0). Total num frames: 405504. Throughput: 0: 893.0. Samples: 100864. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 15:57:23,217][00392] Avg episode reward: [(0, '4.582')] +[2023-05-31 15:57:24,124][13411] Updated weights for policy 0, policy_version 100 (0.0015) +[2023-05-31 15:57:28,211][00392] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3213.8). Total num frames: 417792. Throughput: 0: 879.4. Samples: 105632. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 15:57:28,218][00392] Avg episode reward: [(0, '4.730')] +[2023-05-31 15:57:28,220][13398] Saving new best policy, reward=4.730! +[2023-05-31 15:57:33,212][00392] Fps is (10 sec: 2867.1, 60 sec: 3549.8, 300 sec: 3216.1). Total num frames: 434176. Throughput: 0: 877.3. Samples: 107694. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 15:57:33,221][00392] Avg episode reward: [(0, '4.657')] +[2023-05-31 15:57:37,506][13411] Updated weights for policy 0, policy_version 110 (0.0031) +[2023-05-31 15:57:38,211][00392] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3218.3). Total num frames: 450560. Throughput: 0: 883.3. Samples: 112578. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 15:57:38,217][00392] Avg episode reward: [(0, '4.538')] +[2023-05-31 15:57:43,211][00392] Fps is (10 sec: 4096.2, 60 sec: 3549.9, 300 sec: 3276.8). Total num frames: 475136. Throughput: 0: 885.2. Samples: 119288. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 15:57:43,215][00392] Avg episode reward: [(0, '4.505')] +[2023-05-31 15:57:47,794][13411] Updated weights for policy 0, policy_version 120 (0.0015) +[2023-05-31 15:57:48,211][00392] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3276.8). Total num frames: 491520. Throughput: 0: 877.8. Samples: 122290. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-05-31 15:57:48,216][00392] Avg episode reward: [(0, '4.327')] +[2023-05-31 15:57:53,215][00392] Fps is (10 sec: 2866.2, 60 sec: 3549.7, 300 sec: 3250.3). Total num frames: 503808. Throughput: 0: 877.0. Samples: 126520. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 15:57:53,217][00392] Avg episode reward: [(0, '4.346')] +[2023-05-31 15:57:58,211][00392] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3251.2). Total num frames: 520192. Throughput: 0: 882.0. Samples: 130944. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 15:57:58,216][00392] Avg episode reward: [(0, '4.740')] +[2023-05-31 15:57:58,224][13398] Saving new best policy, reward=4.740! +[2023-05-31 15:58:00,684][13411] Updated weights for policy 0, policy_version 130 (0.0012) +[2023-05-31 15:58:03,211][00392] Fps is (10 sec: 3687.6, 60 sec: 3481.6, 300 sec: 3276.8). Total num frames: 540672. Throughput: 0: 887.2. Samples: 134230. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-05-31 15:58:03,216][00392] Avg episode reward: [(0, '4.733')] +[2023-05-31 15:58:08,211][00392] Fps is (10 sec: 4096.1, 60 sec: 3549.9, 300 sec: 3300.9). Total num frames: 561152. Throughput: 0: 886.8. Samples: 140770. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-05-31 15:58:08,217][00392] Avg episode reward: [(0, '4.550')] +[2023-05-31 15:58:11,419][13411] Updated weights for policy 0, policy_version 140 (0.0023) +[2023-05-31 15:58:13,215][00392] Fps is (10 sec: 3685.1, 60 sec: 3617.9, 300 sec: 3300.1). Total num frames: 577536. Throughput: 0: 874.7. Samples: 144998. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 15:58:13,221][00392] Avg episode reward: [(0, '4.579')] +[2023-05-31 15:58:18,211][00392] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3276.8). Total num frames: 589824. Throughput: 0: 876.0. Samples: 147112. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 15:58:18,215][00392] Avg episode reward: [(0, '4.560')] +[2023-05-31 15:58:23,211][00392] Fps is (10 sec: 3277.9, 60 sec: 3413.3, 300 sec: 3298.9). Total num frames: 610304. Throughput: 0: 884.1. Samples: 152362. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-05-31 15:58:23,214][00392] Avg episode reward: [(0, '4.509')] +[2023-05-31 15:58:23,595][13411] Updated weights for policy 0, policy_version 150 (0.0026) +[2023-05-31 15:58:28,211][00392] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3341.5). Total num frames: 634880. Throughput: 0: 886.2. Samples: 159166. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 15:58:28,214][00392] Avg episode reward: [(0, '4.535')] +[2023-05-31 15:58:33,212][00392] Fps is (10 sec: 4095.8, 60 sec: 3618.1, 300 sec: 3339.8). Total num frames: 651264. Throughput: 0: 879.8. Samples: 161882. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 15:58:33,221][00392] Avg episode reward: [(0, '4.640')] +[2023-05-31 15:58:34,532][13411] Updated weights for policy 0, policy_version 160 (0.0030) +[2023-05-31 15:58:38,212][00392] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3317.8). Total num frames: 663552. Throughput: 0: 877.5. Samples: 166004. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-05-31 15:58:38,222][00392] Avg episode reward: [(0, '4.484')] +[2023-05-31 15:58:43,211][00392] Fps is (10 sec: 2867.3, 60 sec: 3413.3, 300 sec: 3316.8). Total num frames: 679936. Throughput: 0: 885.3. Samples: 170784. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-05-31 15:58:43,214][00392] Avg episode reward: [(0, '4.599')] +[2023-05-31 15:58:46,708][13411] Updated weights for policy 0, policy_version 170 (0.0031) +[2023-05-31 15:58:48,211][00392] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3335.3). Total num frames: 700416. Throughput: 0: 885.2. Samples: 174066. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-05-31 15:58:48,214][00392] Avg episode reward: [(0, '4.707')] +[2023-05-31 15:58:53,211][00392] Fps is (10 sec: 4096.0, 60 sec: 3618.3, 300 sec: 3353.0). Total num frames: 720896. Throughput: 0: 881.6. Samples: 180444. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 15:58:53,221][00392] Avg episode reward: [(0, '4.804')] +[2023-05-31 15:58:53,229][13398] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000176_720896.pth... +[2023-05-31 15:58:53,368][13398] Saving new best policy, reward=4.804! +[2023-05-31 15:58:58,214][00392] Fps is (10 sec: 3276.0, 60 sec: 3549.7, 300 sec: 3332.6). Total num frames: 733184. Throughput: 0: 875.0. Samples: 184370. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 15:58:58,221][00392] Avg episode reward: [(0, '4.866')] +[2023-05-31 15:58:58,223][13398] Saving new best policy, reward=4.866! +[2023-05-31 15:58:59,028][13411] Updated weights for policy 0, policy_version 180 (0.0023) +[2023-05-31 15:59:03,211][00392] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3331.4). Total num frames: 749568. Throughput: 0: 875.8. Samples: 186524. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 15:59:03,217][00392] Avg episode reward: [(0, '4.943')] +[2023-05-31 15:59:03,230][13398] Saving new best policy, reward=4.943! +[2023-05-31 15:59:08,211][00392] Fps is (10 sec: 3687.3, 60 sec: 3481.6, 300 sec: 3348.0). Total num frames: 770048. Throughput: 0: 882.4. Samples: 192070. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 15:59:08,217][00392] Avg episode reward: [(0, '4.933')] +[2023-05-31 15:59:09,782][13411] Updated weights for policy 0, policy_version 190 (0.0024) +[2023-05-31 15:59:13,212][00392] Fps is (10 sec: 4095.9, 60 sec: 3550.1, 300 sec: 3363.9). Total num frames: 790528. Throughput: 0: 881.1. Samples: 198816. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 15:59:13,217][00392] Avg episode reward: [(0, '4.979')] +[2023-05-31 15:59:13,227][13398] Saving new best policy, reward=4.979! +[2023-05-31 15:59:18,211][00392] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3362.1). Total num frames: 806912. Throughput: 0: 875.6. Samples: 201284. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 15:59:18,214][00392] Avg episode reward: [(0, '5.031')] +[2023-05-31 15:59:18,217][13398] Saving new best policy, reward=5.031! +[2023-05-31 15:59:21,825][13411] Updated weights for policy 0, policy_version 200 (0.0012) +[2023-05-31 15:59:23,212][00392] Fps is (10 sec: 3276.8, 60 sec: 3549.8, 300 sec: 3360.4). Total num frames: 823296. Throughput: 0: 876.6. Samples: 205452. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 15:59:23,223][00392] Avg episode reward: [(0, '4.948')] +[2023-05-31 15:59:28,211][00392] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3358.7). Total num frames: 839680. Throughput: 0: 884.7. Samples: 210594. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 15:59:28,214][00392] Avg episode reward: [(0, '5.212')] +[2023-05-31 15:59:28,220][13398] Saving new best policy, reward=5.212! +[2023-05-31 15:59:32,471][13411] Updated weights for policy 0, policy_version 210 (0.0025) +[2023-05-31 15:59:33,212][00392] Fps is (10 sec: 3686.5, 60 sec: 3481.6, 300 sec: 3373.2). Total num frames: 860160. Throughput: 0: 885.5. Samples: 213914. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 15:59:33,214][00392] Avg episode reward: [(0, '5.350')] +[2023-05-31 15:59:33,228][13398] Saving new best policy, reward=5.350! +[2023-05-31 15:59:38,216][00392] Fps is (10 sec: 4094.2, 60 sec: 3617.9, 300 sec: 3387.0). Total num frames: 880640. Throughput: 0: 886.2. Samples: 220326. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-05-31 15:59:38,221][00392] Avg episode reward: [(0, '5.348')] +[2023-05-31 15:59:43,211][00392] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3369.5). Total num frames: 892928. Throughput: 0: 894.1. Samples: 224604. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 15:59:43,213][00392] Avg episode reward: [(0, '5.330')] +[2023-05-31 15:59:44,945][13411] Updated weights for policy 0, policy_version 220 (0.0026) +[2023-05-31 15:59:48,211][00392] Fps is (10 sec: 2868.4, 60 sec: 3481.6, 300 sec: 3367.8). Total num frames: 909312. Throughput: 0: 892.2. Samples: 226672. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 15:59:48,217][00392] Avg episode reward: [(0, '5.171')] +[2023-05-31 15:59:53,211][00392] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3396.0). Total num frames: 933888. Throughput: 0: 904.7. Samples: 232782. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 15:59:53,217][00392] Avg episode reward: [(0, '5.520')] +[2023-05-31 15:59:53,229][13398] Saving new best policy, reward=5.520! +[2023-05-31 15:59:54,898][13411] Updated weights for policy 0, policy_version 230 (0.0015) +[2023-05-31 15:59:58,211][00392] Fps is (10 sec: 4505.6, 60 sec: 3686.5, 300 sec: 3408.5). Total num frames: 954368. Throughput: 0: 905.2. Samples: 239548. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-05-31 15:59:58,214][00392] Avg episode reward: [(0, '5.958')] +[2023-05-31 15:59:58,221][13398] Saving new best policy, reward=5.958! +[2023-05-31 16:00:03,216][00392] Fps is (10 sec: 3275.4, 60 sec: 3617.9, 300 sec: 3391.7). Total num frames: 966656. Throughput: 0: 895.6. Samples: 241590. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-05-31 16:00:03,218][00392] Avg episode reward: [(0, '5.900')] +[2023-05-31 16:00:07,883][13411] Updated weights for policy 0, policy_version 240 (0.0025) +[2023-05-31 16:00:08,214][00392] Fps is (10 sec: 2866.5, 60 sec: 3549.7, 300 sec: 3389.8). Total num frames: 983040. Throughput: 0: 898.5. Samples: 245884. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-05-31 16:00:08,224][00392] Avg episode reward: [(0, '5.924')] +[2023-05-31 16:00:13,211][00392] Fps is (10 sec: 3688.0, 60 sec: 3549.9, 300 sec: 3401.8). Total num frames: 1003520. Throughput: 0: 909.6. Samples: 251526. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:00:13,218][00392] Avg episode reward: [(0, '6.145')] +[2023-05-31 16:00:13,229][13398] Saving new best policy, reward=6.145! +[2023-05-31 16:00:17,595][13411] Updated weights for policy 0, policy_version 250 (0.0015) +[2023-05-31 16:00:18,211][00392] Fps is (10 sec: 4097.0, 60 sec: 3618.1, 300 sec: 3471.2). Total num frames: 1024000. Throughput: 0: 912.3. Samples: 254966. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:00:18,217][00392] Avg episode reward: [(0, '6.117')] +[2023-05-31 16:00:23,211][00392] Fps is (10 sec: 3686.4, 60 sec: 3618.2, 300 sec: 3526.7). Total num frames: 1040384. Throughput: 0: 902.1. Samples: 260918. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-05-31 16:00:23,216][00392] Avg episode reward: [(0, '6.366')] +[2023-05-31 16:00:23,238][13398] Saving new best policy, reward=6.366! +[2023-05-31 16:00:28,213][00392] Fps is (10 sec: 3276.3, 60 sec: 3618.0, 300 sec: 3540.6). Total num frames: 1056768. Throughput: 0: 900.9. Samples: 265144. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:00:28,215][00392] Avg episode reward: [(0, '6.581')] +[2023-05-31 16:00:28,226][13398] Saving new best policy, reward=6.581! +[2023-05-31 16:00:30,553][13411] Updated weights for policy 0, policy_version 260 (0.0022) +[2023-05-31 16:00:33,211][00392] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3554.5). Total num frames: 1073152. Throughput: 0: 899.0. Samples: 267126. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:00:33,213][00392] Avg episode reward: [(0, '6.921')] +[2023-05-31 16:00:33,223][13398] Saving new best policy, reward=6.921! +[2023-05-31 16:00:38,211][00392] Fps is (10 sec: 3686.9, 60 sec: 3550.1, 300 sec: 3582.3). Total num frames: 1093632. Throughput: 0: 907.3. Samples: 273612. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:00:38,214][00392] Avg episode reward: [(0, '7.035')] +[2023-05-31 16:00:38,216][13398] Saving new best policy, reward=7.035! +[2023-05-31 16:00:40,270][13411] Updated weights for policy 0, policy_version 270 (0.0014) +[2023-05-31 16:00:43,212][00392] Fps is (10 sec: 4095.8, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 1114112. Throughput: 0: 894.2. Samples: 279788. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-05-31 16:00:43,218][00392] Avg episode reward: [(0, '6.934')] +[2023-05-31 16:00:48,214][00392] Fps is (10 sec: 3685.4, 60 sec: 3686.2, 300 sec: 3554.5). Total num frames: 1130496. Throughput: 0: 895.8. Samples: 281900. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-05-31 16:00:48,218][00392] Avg episode reward: [(0, '6.785')] +[2023-05-31 16:00:53,207][13411] Updated weights for policy 0, policy_version 280 (0.0032) +[2023-05-31 16:00:53,211][00392] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3554.6). Total num frames: 1146880. Throughput: 0: 897.5. Samples: 286270. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-05-31 16:00:53,214][00392] Avg episode reward: [(0, '7.075')] +[2023-05-31 16:00:53,228][13398] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000280_1146880.pth... +[2023-05-31 16:00:53,417][13398] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000071_290816.pth +[2023-05-31 16:00:53,435][13398] Saving new best policy, reward=7.075! +[2023-05-31 16:00:58,212][00392] Fps is (10 sec: 3687.3, 60 sec: 3549.8, 300 sec: 3582.3). Total num frames: 1167360. Throughput: 0: 905.5. Samples: 292276. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:00:58,214][00392] Avg episode reward: [(0, '7.766')] +[2023-05-31 16:00:58,220][13398] Saving new best policy, reward=7.766! +[2023-05-31 16:01:02,739][13411] Updated weights for policy 0, policy_version 290 (0.0022) +[2023-05-31 16:01:03,216][00392] Fps is (10 sec: 4094.1, 60 sec: 3686.4, 300 sec: 3596.1). Total num frames: 1187840. Throughput: 0: 904.3. Samples: 295662. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:01:03,219][00392] Avg episode reward: [(0, '8.305')] +[2023-05-31 16:01:03,232][13398] Saving new best policy, reward=8.305! +[2023-05-31 16:01:08,212][00392] Fps is (10 sec: 3686.4, 60 sec: 3686.5, 300 sec: 3568.4). Total num frames: 1204224. Throughput: 0: 894.1. Samples: 301152. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:01:08,224][00392] Avg episode reward: [(0, '8.437')] +[2023-05-31 16:01:08,229][13398] Saving new best policy, reward=8.437! +[2023-05-31 16:01:13,212][00392] Fps is (10 sec: 2868.4, 60 sec: 3549.8, 300 sec: 3540.6). Total num frames: 1216512. Throughput: 0: 891.9. Samples: 305280. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:01:13,220][00392] Avg episode reward: [(0, '8.215')] +[2023-05-31 16:01:16,524][13411] Updated weights for policy 0, policy_version 300 (0.0012) +[2023-05-31 16:01:18,211][00392] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3554.5). Total num frames: 1236992. Throughput: 0: 896.5. Samples: 307468. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:01:18,214][00392] Avg episode reward: [(0, '8.399')] +[2023-05-31 16:01:23,211][00392] Fps is (10 sec: 4096.1, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 1257472. Throughput: 0: 901.1. Samples: 314162. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:01:23,217][00392] Avg episode reward: [(0, '8.394')] +[2023-05-31 16:01:25,481][13411] Updated weights for policy 0, policy_version 310 (0.0015) +[2023-05-31 16:01:28,211][00392] Fps is (10 sec: 4096.0, 60 sec: 3686.5, 300 sec: 3582.3). Total num frames: 1277952. Throughput: 0: 900.9. Samples: 320328. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:01:28,217][00392] Avg episode reward: [(0, '8.260')] +[2023-05-31 16:01:33,211][00392] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3554.5). Total num frames: 1290240. Throughput: 0: 902.1. Samples: 322494. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:01:33,215][00392] Avg episode reward: [(0, '9.042')] +[2023-05-31 16:01:33,229][13398] Saving new best policy, reward=9.042! +[2023-05-31 16:01:38,212][00392] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3540.6). Total num frames: 1306624. Throughput: 0: 899.9. Samples: 326766. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:01:38,219][00392] Avg episode reward: [(0, '9.171')] +[2023-05-31 16:01:38,226][13398] Saving new best policy, reward=9.171! +[2023-05-31 16:01:38,944][13411] Updated weights for policy 0, policy_version 320 (0.0024) +[2023-05-31 16:01:43,211][00392] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3568.4). Total num frames: 1327104. Throughput: 0: 902.9. Samples: 332908. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:01:43,218][00392] Avg episode reward: [(0, '9.948')] +[2023-05-31 16:01:43,228][13398] Saving new best policy, reward=9.948! +[2023-05-31 16:01:48,014][13411] Updated weights for policy 0, policy_version 330 (0.0023) +[2023-05-31 16:01:48,211][00392] Fps is (10 sec: 4505.7, 60 sec: 3686.6, 300 sec: 3596.2). Total num frames: 1351680. Throughput: 0: 902.6. Samples: 336274. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:01:48,214][00392] Avg episode reward: [(0, '9.843')] +[2023-05-31 16:01:53,211][00392] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3554.5). Total num frames: 1363968. Throughput: 0: 901.7. Samples: 341728. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-05-31 16:01:53,214][00392] Avg episode reward: [(0, '10.517')] +[2023-05-31 16:01:53,238][13398] Saving new best policy, reward=10.517! +[2023-05-31 16:01:58,211][00392] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3554.5). Total num frames: 1380352. Throughput: 0: 905.0. Samples: 346006. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 16:01:58,218][00392] Avg episode reward: [(0, '11.019')] +[2023-05-31 16:01:58,221][13398] Saving new best policy, reward=11.019! +[2023-05-31 16:02:01,312][13411] Updated weights for policy 0, policy_version 340 (0.0031) +[2023-05-31 16:02:03,214][00392] Fps is (10 sec: 3685.5, 60 sec: 3550.0, 300 sec: 3568.3). Total num frames: 1400832. Throughput: 0: 908.7. Samples: 348360. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:02:03,216][00392] Avg episode reward: [(0, '10.285')] +[2023-05-31 16:02:08,211][00392] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3596.2). Total num frames: 1421312. Throughput: 0: 909.1. Samples: 355070. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:02:08,214][00392] Avg episode reward: [(0, '10.441')] +[2023-05-31 16:02:10,427][13411] Updated weights for policy 0, policy_version 350 (0.0011) +[2023-05-31 16:02:13,212][00392] Fps is (10 sec: 4096.9, 60 sec: 3754.7, 300 sec: 3596.1). Total num frames: 1441792. Throughput: 0: 903.0. Samples: 360964. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-05-31 16:02:13,217][00392] Avg episode reward: [(0, '10.108')] +[2023-05-31 16:02:18,211][00392] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3554.5). Total num frames: 1454080. Throughput: 0: 901.1. Samples: 363042. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-05-31 16:02:18,217][00392] Avg episode reward: [(0, '10.519')] +[2023-05-31 16:02:23,211][00392] Fps is (10 sec: 2457.7, 60 sec: 3481.6, 300 sec: 3554.5). Total num frames: 1466368. Throughput: 0: 901.4. Samples: 367330. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-05-31 16:02:23,218][00392] Avg episode reward: [(0, '11.016')] +[2023-05-31 16:02:24,155][13411] Updated weights for policy 0, policy_version 360 (0.0021) +[2023-05-31 16:02:28,211][00392] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 1490944. Throughput: 0: 910.2. Samples: 373868. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:02:28,214][00392] Avg episode reward: [(0, '11.353')] +[2023-05-31 16:02:28,217][13398] Saving new best policy, reward=11.353! +[2023-05-31 16:02:33,211][00392] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3596.1). Total num frames: 1511424. Throughput: 0: 911.1. Samples: 377272. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:02:33,214][00392] Avg episode reward: [(0, '12.362')] +[2023-05-31 16:02:33,242][13398] Saving new best policy, reward=12.362! +[2023-05-31 16:02:33,241][13411] Updated weights for policy 0, policy_version 370 (0.0038) +[2023-05-31 16:02:38,217][00392] Fps is (10 sec: 3684.4, 60 sec: 3686.1, 300 sec: 3568.3). Total num frames: 1527808. Throughput: 0: 900.4. Samples: 382252. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-05-31 16:02:38,219][00392] Avg episode reward: [(0, '12.253')] +[2023-05-31 16:02:43,215][00392] Fps is (10 sec: 3275.7, 60 sec: 3617.9, 300 sec: 3568.3). Total num frames: 1544192. Throughput: 0: 903.3. Samples: 386656. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 16:02:43,217][00392] Avg episode reward: [(0, '12.533')] +[2023-05-31 16:02:43,230][13398] Saving new best policy, reward=12.533! +[2023-05-31 16:02:46,805][13411] Updated weights for policy 0, policy_version 380 (0.0012) +[2023-05-31 16:02:48,211][00392] Fps is (10 sec: 3278.6, 60 sec: 3481.6, 300 sec: 3582.3). Total num frames: 1560576. Throughput: 0: 903.2. Samples: 389002. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 16:02:48,213][00392] Avg episode reward: [(0, '13.224')] +[2023-05-31 16:02:48,220][13398] Saving new best policy, reward=13.224! +[2023-05-31 16:02:53,211][00392] Fps is (10 sec: 4097.3, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 1585152. Throughput: 0: 903.4. Samples: 395724. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:02:53,218][00392] Avg episode reward: [(0, '12.885')] +[2023-05-31 16:02:53,237][13398] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000387_1585152.pth... +[2023-05-31 16:02:53,347][13398] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000176_720896.pth +[2023-05-31 16:02:56,074][13411] Updated weights for policy 0, policy_version 390 (0.0012) +[2023-05-31 16:02:58,212][00392] Fps is (10 sec: 4095.6, 60 sec: 3686.3, 300 sec: 3596.1). Total num frames: 1601536. Throughput: 0: 895.1. Samples: 401244. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:02:58,218][00392] Avg episode reward: [(0, '12.860')] +[2023-05-31 16:03:03,212][00392] Fps is (10 sec: 2867.0, 60 sec: 3550.0, 300 sec: 3568.4). Total num frames: 1613824. Throughput: 0: 895.3. Samples: 403332. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:03:03,224][00392] Avg episode reward: [(0, '13.203')] +[2023-05-31 16:03:08,211][00392] Fps is (10 sec: 2867.5, 60 sec: 3481.6, 300 sec: 3568.4). Total num frames: 1630208. Throughput: 0: 891.3. Samples: 407438. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-05-31 16:03:08,213][00392] Avg episode reward: [(0, '14.316')] +[2023-05-31 16:03:08,222][13398] Saving new best policy, reward=14.316! +[2023-05-31 16:03:09,848][13411] Updated weights for policy 0, policy_version 400 (0.0014) +[2023-05-31 16:03:13,214][00392] Fps is (10 sec: 3685.7, 60 sec: 3481.5, 300 sec: 3596.1). Total num frames: 1650688. Throughput: 0: 892.1. Samples: 414016. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:03:13,217][00392] Avg episode reward: [(0, '15.936')] +[2023-05-31 16:03:13,230][13398] Saving new best policy, reward=15.936! +[2023-05-31 16:03:18,212][00392] Fps is (10 sec: 4505.5, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 1675264. Throughput: 0: 889.2. Samples: 417286. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:03:18,218][00392] Avg episode reward: [(0, '16.905')] +[2023-05-31 16:03:18,221][13398] Saving new best policy, reward=16.905! +[2023-05-31 16:03:19,647][13411] Updated weights for policy 0, policy_version 410 (0.0013) +[2023-05-31 16:03:23,211][00392] Fps is (10 sec: 3687.3, 60 sec: 3686.4, 300 sec: 3568.4). Total num frames: 1687552. Throughput: 0: 884.6. Samples: 422056. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 16:03:23,218][00392] Avg episode reward: [(0, '16.766')] +[2023-05-31 16:03:28,212][00392] Fps is (10 sec: 2457.6, 60 sec: 3481.6, 300 sec: 3554.5). Total num frames: 1699840. Throughput: 0: 880.1. Samples: 426260. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-05-31 16:03:28,216][00392] Avg episode reward: [(0, '17.681')] +[2023-05-31 16:03:28,220][13398] Saving new best policy, reward=17.681! +[2023-05-31 16:03:32,723][13411] Updated weights for policy 0, policy_version 420 (0.0015) +[2023-05-31 16:03:33,211][00392] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3582.3). Total num frames: 1720320. Throughput: 0: 885.8. Samples: 428864. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 16:03:33,213][00392] Avg episode reward: [(0, '16.208')] +[2023-05-31 16:03:38,211][00392] Fps is (10 sec: 4096.1, 60 sec: 3550.2, 300 sec: 3596.1). Total num frames: 1740800. Throughput: 0: 878.7. Samples: 435266. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-05-31 16:03:38,215][00392] Avg episode reward: [(0, '15.528')] +[2023-05-31 16:03:43,212][00392] Fps is (10 sec: 3686.4, 60 sec: 3550.0, 300 sec: 3582.3). Total num frames: 1757184. Throughput: 0: 869.1. Samples: 440352. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-05-31 16:03:43,214][00392] Avg episode reward: [(0, '16.022')] +[2023-05-31 16:03:43,781][13411] Updated weights for policy 0, policy_version 430 (0.0013) +[2023-05-31 16:03:48,213][00392] Fps is (10 sec: 2866.8, 60 sec: 3481.5, 300 sec: 3554.5). Total num frames: 1769472. Throughput: 0: 867.9. Samples: 442390. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:03:48,215][00392] Avg episode reward: [(0, '16.720')] +[2023-05-31 16:03:53,211][00392] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3568.4). Total num frames: 1785856. Throughput: 0: 874.0. Samples: 446768. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:03:53,217][00392] Avg episode reward: [(0, '17.605')] +[2023-05-31 16:03:56,034][13411] Updated weights for policy 0, policy_version 440 (0.0022) +[2023-05-31 16:03:58,211][00392] Fps is (10 sec: 4096.6, 60 sec: 3481.7, 300 sec: 3596.1). Total num frames: 1810432. Throughput: 0: 877.3. Samples: 453492. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:03:58,219][00392] Avg episode reward: [(0, '18.919')] +[2023-05-31 16:03:58,222][13398] Saving new best policy, reward=18.919! +[2023-05-31 16:04:03,211][00392] Fps is (10 sec: 4505.6, 60 sec: 3618.2, 300 sec: 3596.1). Total num frames: 1830912. Throughput: 0: 877.3. Samples: 456762. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-05-31 16:04:03,214][00392] Avg episode reward: [(0, '18.214')] +[2023-05-31 16:04:07,033][13411] Updated weights for policy 0, policy_version 450 (0.0014) +[2023-05-31 16:04:08,212][00392] Fps is (10 sec: 3276.7, 60 sec: 3549.9, 300 sec: 3568.4). Total num frames: 1843200. Throughput: 0: 871.4. Samples: 461268. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-05-31 16:04:08,224][00392] Avg episode reward: [(0, '16.727')] +[2023-05-31 16:04:13,212][00392] Fps is (10 sec: 2867.2, 60 sec: 3481.7, 300 sec: 3568.4). Total num frames: 1859584. Throughput: 0: 874.3. Samples: 465604. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:04:13,215][00392] Avg episode reward: [(0, '16.632')] +[2023-05-31 16:04:18,211][00392] Fps is (10 sec: 3686.5, 60 sec: 3413.4, 300 sec: 3582.3). Total num frames: 1880064. Throughput: 0: 882.8. Samples: 468590. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-05-31 16:04:18,215][00392] Avg episode reward: [(0, '16.795')] +[2023-05-31 16:04:18,699][13411] Updated weights for policy 0, policy_version 460 (0.0020) +[2023-05-31 16:04:23,211][00392] Fps is (10 sec: 4096.1, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 1900544. Throughput: 0: 892.6. Samples: 475434. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:04:23,214][00392] Avg episode reward: [(0, '16.743')] +[2023-05-31 16:04:28,213][00392] Fps is (10 sec: 3685.9, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 1916928. Throughput: 0: 894.2. Samples: 480594. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:04:28,215][00392] Avg episode reward: [(0, '17.378')] +[2023-05-31 16:04:29,827][13411] Updated weights for policy 0, policy_version 470 (0.0023) +[2023-05-31 16:04:33,212][00392] Fps is (10 sec: 3276.7, 60 sec: 3549.9, 300 sec: 3568.4). Total num frames: 1933312. Throughput: 0: 895.7. Samples: 482696. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 16:04:33,214][00392] Avg episode reward: [(0, '17.871')] +[2023-05-31 16:04:38,211][00392] Fps is (10 sec: 3277.3, 60 sec: 3481.6, 300 sec: 3582.3). Total num frames: 1949696. Throughput: 0: 898.8. Samples: 487212. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 16:04:38,220][00392] Avg episode reward: [(0, '18.680')] +[2023-05-31 16:04:41,412][13411] Updated weights for policy 0, policy_version 480 (0.0019) +[2023-05-31 16:04:43,212][00392] Fps is (10 sec: 4095.9, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 1974272. Throughput: 0: 902.4. Samples: 494102. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-05-31 16:04:43,219][00392] Avg episode reward: [(0, '17.958')] +[2023-05-31 16:04:48,216][00392] Fps is (10 sec: 4503.6, 60 sec: 3754.5, 300 sec: 3596.1). Total num frames: 1994752. Throughput: 0: 903.4. Samples: 497420. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:04:48,223][00392] Avg episode reward: [(0, '18.439')] +[2023-05-31 16:04:52,688][13411] Updated weights for policy 0, policy_version 490 (0.0018) +[2023-05-31 16:04:53,217][00392] Fps is (10 sec: 3275.1, 60 sec: 3686.1, 300 sec: 3568.3). Total num frames: 2007040. Throughput: 0: 902.3. Samples: 501878. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:04:53,224][00392] Avg episode reward: [(0, '19.037')] +[2023-05-31 16:04:53,240][13398] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000490_2007040.pth... +[2023-05-31 16:04:53,357][13398] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000280_1146880.pth +[2023-05-31 16:04:53,380][13398] Saving new best policy, reward=19.037! +[2023-05-31 16:04:58,211][00392] Fps is (10 sec: 2458.7, 60 sec: 3481.6, 300 sec: 3568.4). Total num frames: 2019328. Throughput: 0: 901.3. Samples: 506164. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:04:58,220][00392] Avg episode reward: [(0, '19.801')] +[2023-05-31 16:04:58,226][13398] Saving new best policy, reward=19.801! +[2023-05-31 16:05:03,211][00392] Fps is (10 sec: 3688.4, 60 sec: 3549.9, 300 sec: 3596.2). Total num frames: 2043904. Throughput: 0: 902.4. Samples: 509200. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:05:03,214][00392] Avg episode reward: [(0, '19.521')] +[2023-05-31 16:05:04,172][13411] Updated weights for policy 0, policy_version 500 (0.0016) +[2023-05-31 16:05:08,211][00392] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3596.1). Total num frames: 2064384. Throughput: 0: 899.2. Samples: 515896. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:05:08,218][00392] Avg episode reward: [(0, '18.085')] +[2023-05-31 16:05:13,211][00392] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 2080768. Throughput: 0: 893.1. Samples: 520784. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:05:13,218][00392] Avg episode reward: [(0, '18.491')] +[2023-05-31 16:05:15,955][13411] Updated weights for policy 0, policy_version 510 (0.0019) +[2023-05-31 16:05:18,211][00392] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3568.4). Total num frames: 2093056. Throughput: 0: 892.9. Samples: 522876. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 16:05:18,216][00392] Avg episode reward: [(0, '18.215')] +[2023-05-31 16:05:23,211][00392] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 2113536. Throughput: 0: 899.0. Samples: 527666. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 16:05:23,214][00392] Avg episode reward: [(0, '18.908')] +[2023-05-31 16:05:26,931][13411] Updated weights for policy 0, policy_version 520 (0.0023) +[2023-05-31 16:05:28,211][00392] Fps is (10 sec: 4096.0, 60 sec: 3618.2, 300 sec: 3596.1). Total num frames: 2134016. Throughput: 0: 895.9. Samples: 534418. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-05-31 16:05:28,216][00392] Avg episode reward: [(0, '18.649')] +[2023-05-31 16:05:33,211][00392] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3596.1). Total num frames: 2154496. Throughput: 0: 898.8. Samples: 537862. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:05:33,217][00392] Avg episode reward: [(0, '18.239')] +[2023-05-31 16:05:38,212][00392] Fps is (10 sec: 3276.7, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 2166784. Throughput: 0: 892.9. Samples: 542052. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-05-31 16:05:38,221][00392] Avg episode reward: [(0, '19.363')] +[2023-05-31 16:05:38,871][13411] Updated weights for policy 0, policy_version 530 (0.0016) +[2023-05-31 16:05:43,211][00392] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3568.4). Total num frames: 2183168. Throughput: 0: 893.3. Samples: 546364. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:05:43,214][00392] Avg episode reward: [(0, '17.995')] +[2023-05-31 16:05:48,211][00392] Fps is (10 sec: 3686.6, 60 sec: 3481.9, 300 sec: 3582.3). Total num frames: 2203648. Throughput: 0: 900.1. Samples: 549704. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-05-31 16:05:48,216][00392] Avg episode reward: [(0, '17.494')] +[2023-05-31 16:05:49,387][13411] Updated weights for policy 0, policy_version 540 (0.0038) +[2023-05-31 16:05:53,211][00392] Fps is (10 sec: 4505.6, 60 sec: 3686.7, 300 sec: 3596.2). Total num frames: 2228224. Throughput: 0: 901.9. Samples: 556482. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-05-31 16:05:53,218][00392] Avg episode reward: [(0, '18.658')] +[2023-05-31 16:05:58,212][00392] Fps is (10 sec: 3686.3, 60 sec: 3686.4, 300 sec: 3568.4). Total num frames: 2240512. Throughput: 0: 901.0. Samples: 561328. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-05-31 16:05:58,219][00392] Avg episode reward: [(0, '19.538')] +[2023-05-31 16:06:01,280][13411] Updated weights for policy 0, policy_version 550 (0.0049) +[2023-05-31 16:06:03,212][00392] Fps is (10 sec: 2867.1, 60 sec: 3549.9, 300 sec: 3568.4). Total num frames: 2256896. Throughput: 0: 901.2. Samples: 563430. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-05-31 16:06:03,219][00392] Avg episode reward: [(0, '20.600')] +[2023-05-31 16:06:03,231][13398] Saving new best policy, reward=20.600! +[2023-05-31 16:06:08,212][00392] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3582.3). Total num frames: 2273280. Throughput: 0: 904.0. Samples: 568346. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) +[2023-05-31 16:06:08,214][00392] Avg episode reward: [(0, '21.255')] +[2023-05-31 16:06:08,221][13398] Saving new best policy, reward=21.255! +[2023-05-31 16:06:12,197][13411] Updated weights for policy 0, policy_version 560 (0.0016) +[2023-05-31 16:06:13,211][00392] Fps is (10 sec: 4096.1, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 2297856. Throughput: 0: 901.1. Samples: 574966. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:06:13,214][00392] Avg episode reward: [(0, '22.239')] +[2023-05-31 16:06:13,221][13398] Saving new best policy, reward=22.239! +[2023-05-31 16:06:18,211][00392] Fps is (10 sec: 4096.1, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 2314240. Throughput: 0: 891.6. Samples: 577982. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:06:18,213][00392] Avg episode reward: [(0, '21.641')] +[2023-05-31 16:06:23,212][00392] Fps is (10 sec: 2866.9, 60 sec: 3549.8, 300 sec: 3554.5). Total num frames: 2326528. Throughput: 0: 891.2. Samples: 582156. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:06:23,219][00392] Avg episode reward: [(0, '20.720')] +[2023-05-31 16:06:25,243][13411] Updated weights for policy 0, policy_version 570 (0.0022) +[2023-05-31 16:06:28,212][00392] Fps is (10 sec: 2867.1, 60 sec: 3481.6, 300 sec: 3568.4). Total num frames: 2342912. Throughput: 0: 897.7. Samples: 586760. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-05-31 16:06:28,214][00392] Avg episode reward: [(0, '20.324')] +[2023-05-31 16:06:33,212][00392] Fps is (10 sec: 4096.0, 60 sec: 3549.8, 300 sec: 3596.1). Total num frames: 2367488. Throughput: 0: 898.8. Samples: 590150. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:06:33,215][00392] Avg episode reward: [(0, '20.254')] +[2023-05-31 16:06:34,993][13411] Updated weights for policy 0, policy_version 580 (0.0023) +[2023-05-31 16:06:38,214][00392] Fps is (10 sec: 4504.5, 60 sec: 3686.3, 300 sec: 3596.1). Total num frames: 2387968. Throughput: 0: 895.8. Samples: 596796. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:06:38,218][00392] Avg episode reward: [(0, '19.670')] +[2023-05-31 16:06:43,211][00392] Fps is (10 sec: 3277.1, 60 sec: 3618.1, 300 sec: 3554.5). Total num frames: 2400256. Throughput: 0: 883.2. Samples: 601074. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:06:43,216][00392] Avg episode reward: [(0, '19.075')] +[2023-05-31 16:06:48,020][13411] Updated weights for policy 0, policy_version 590 (0.0029) +[2023-05-31 16:06:48,211][00392] Fps is (10 sec: 2868.0, 60 sec: 3549.9, 300 sec: 3568.4). Total num frames: 2416640. Throughput: 0: 881.7. Samples: 603106. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 16:06:48,222][00392] Avg episode reward: [(0, '20.315')] +[2023-05-31 16:06:53,211][00392] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3582.3). Total num frames: 2437120. Throughput: 0: 895.8. Samples: 608656. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:06:53,219][00392] Avg episode reward: [(0, '19.878')] +[2023-05-31 16:06:53,230][13398] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000595_2437120.pth... +[2023-05-31 16:06:53,358][13398] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000387_1585152.pth +[2023-05-31 16:06:57,761][13411] Updated weights for policy 0, policy_version 600 (0.0016) +[2023-05-31 16:06:58,212][00392] Fps is (10 sec: 4095.9, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 2457600. Throughput: 0: 895.9. Samples: 615280. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-05-31 16:06:58,217][00392] Avg episode reward: [(0, '20.400')] +[2023-05-31 16:07:03,214][00392] Fps is (10 sec: 3685.5, 60 sec: 3618.0, 300 sec: 3568.3). Total num frames: 2473984. Throughput: 0: 887.3. Samples: 617914. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-05-31 16:07:03,217][00392] Avg episode reward: [(0, '20.394')] +[2023-05-31 16:07:08,213][00392] Fps is (10 sec: 2866.8, 60 sec: 3549.8, 300 sec: 3540.6). Total num frames: 2486272. Throughput: 0: 887.9. Samples: 622112. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:07:08,223][00392] Avg episode reward: [(0, '20.371')] +[2023-05-31 16:07:11,370][13411] Updated weights for policy 0, policy_version 610 (0.0029) +[2023-05-31 16:07:13,211][00392] Fps is (10 sec: 3277.6, 60 sec: 3481.6, 300 sec: 3568.4). Total num frames: 2506752. Throughput: 0: 898.1. Samples: 627174. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:07:13,218][00392] Avg episode reward: [(0, '20.191')] +[2023-05-31 16:07:18,211][00392] Fps is (10 sec: 4096.6, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 2527232. Throughput: 0: 898.7. Samples: 630590. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-05-31 16:07:18,215][00392] Avg episode reward: [(0, '20.568')] +[2023-05-31 16:07:20,362][13411] Updated weights for policy 0, policy_version 620 (0.0019) +[2023-05-31 16:07:23,211][00392] Fps is (10 sec: 4096.0, 60 sec: 3686.5, 300 sec: 3582.3). Total num frames: 2547712. Throughput: 0: 894.3. Samples: 637038. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:07:23,215][00392] Avg episode reward: [(0, '21.372')] +[2023-05-31 16:07:28,213][00392] Fps is (10 sec: 3276.3, 60 sec: 3618.1, 300 sec: 3554.5). Total num frames: 2560000. Throughput: 0: 891.5. Samples: 641194. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:07:28,219][00392] Avg episode reward: [(0, '21.655')] +[2023-05-31 16:07:33,211][00392] Fps is (10 sec: 2867.2, 60 sec: 3481.7, 300 sec: 3554.6). Total num frames: 2576384. Throughput: 0: 893.7. Samples: 643324. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:07:33,216][00392] Avg episode reward: [(0, '22.204')] +[2023-05-31 16:07:34,119][13411] Updated weights for policy 0, policy_version 630 (0.0015) +[2023-05-31 16:07:38,211][00392] Fps is (10 sec: 3686.9, 60 sec: 3481.8, 300 sec: 3568.4). Total num frames: 2596864. Throughput: 0: 896.4. Samples: 648992. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-05-31 16:07:38,214][00392] Avg episode reward: [(0, '22.976')] +[2023-05-31 16:07:38,217][13398] Saving new best policy, reward=22.976! +[2023-05-31 16:07:43,211][00392] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 2617344. Throughput: 0: 893.2. Samples: 655472. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:07:43,214][00392] Avg episode reward: [(0, '23.570')] +[2023-05-31 16:07:43,225][13398] Saving new best policy, reward=23.570! +[2023-05-31 16:07:43,549][13411] Updated weights for policy 0, policy_version 640 (0.0023) +[2023-05-31 16:07:48,211][00392] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3554.5). Total num frames: 2633728. Throughput: 0: 883.1. Samples: 657652. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-05-31 16:07:48,217][00392] Avg episode reward: [(0, '22.734')] +[2023-05-31 16:07:53,212][00392] Fps is (10 sec: 2867.1, 60 sec: 3481.6, 300 sec: 3540.6). Total num frames: 2646016. Throughput: 0: 882.2. Samples: 661810. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:07:53,214][00392] Avg episode reward: [(0, '21.789')] +[2023-05-31 16:07:57,482][13411] Updated weights for policy 0, policy_version 650 (0.0029) +[2023-05-31 16:07:58,211][00392] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3554.5). Total num frames: 2662400. Throughput: 0: 882.6. Samples: 666890. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:07:58,213][00392] Avg episode reward: [(0, '20.309')] +[2023-05-31 16:08:03,211][00392] Fps is (10 sec: 4096.1, 60 sec: 3550.0, 300 sec: 3582.3). Total num frames: 2686976. Throughput: 0: 880.4. Samples: 670210. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-05-31 16:08:03,218][00392] Avg episode reward: [(0, '19.967')] +[2023-05-31 16:08:07,528][13411] Updated weights for policy 0, policy_version 660 (0.0012) +[2023-05-31 16:08:08,217][00392] Fps is (10 sec: 4093.7, 60 sec: 3617.9, 300 sec: 3568.3). Total num frames: 2703360. Throughput: 0: 867.4. Samples: 676078. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:08:08,220][00392] Avg episode reward: [(0, '19.712')] +[2023-05-31 16:08:13,211][00392] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3526.7). Total num frames: 2715648. Throughput: 0: 864.9. Samples: 680112. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-05-31 16:08:13,214][00392] Avg episode reward: [(0, '19.293')] +[2023-05-31 16:08:18,211][00392] Fps is (10 sec: 2868.8, 60 sec: 3413.3, 300 sec: 3540.6). Total num frames: 2732032. Throughput: 0: 863.8. Samples: 682194. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:08:18,214][00392] Avg episode reward: [(0, '20.362')] +[2023-05-31 16:08:20,965][13411] Updated weights for policy 0, policy_version 670 (0.0047) +[2023-05-31 16:08:23,211][00392] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3568.4). Total num frames: 2752512. Throughput: 0: 863.3. Samples: 687840. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:08:23,214][00392] Avg episode reward: [(0, '20.609')] +[2023-05-31 16:08:28,211][00392] Fps is (10 sec: 4095.9, 60 sec: 3549.9, 300 sec: 3568.4). Total num frames: 2772992. Throughput: 0: 865.7. Samples: 694428. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:08:28,219][00392] Avg episode reward: [(0, '20.547')] +[2023-05-31 16:08:31,619][13411] Updated weights for policy 0, policy_version 680 (0.0013) +[2023-05-31 16:08:33,211][00392] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3554.5). Total num frames: 2789376. Throughput: 0: 862.1. Samples: 696446. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:08:33,219][00392] Avg episode reward: [(0, '20.588')] +[2023-05-31 16:08:38,211][00392] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3540.6). Total num frames: 2801664. Throughput: 0: 862.7. Samples: 700632. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:08:38,217][00392] Avg episode reward: [(0, '21.187')] +[2023-05-31 16:08:43,212][00392] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3554.5). Total num frames: 2818048. Throughput: 0: 865.6. Samples: 705840. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:08:43,214][00392] Avg episode reward: [(0, '20.814')] +[2023-05-31 16:08:44,327][13411] Updated weights for policy 0, policy_version 690 (0.0017) +[2023-05-31 16:08:48,211][00392] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3582.3). Total num frames: 2842624. Throughput: 0: 865.2. Samples: 709142. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:08:48,219][00392] Avg episode reward: [(0, '20.767')] +[2023-05-31 16:08:53,212][00392] Fps is (10 sec: 4095.8, 60 sec: 3549.8, 300 sec: 3554.5). Total num frames: 2859008. Throughput: 0: 866.6. Samples: 715072. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:08:53,220][00392] Avg episode reward: [(0, '21.251')] +[2023-05-31 16:08:53,235][13398] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000698_2859008.pth... +[2023-05-31 16:08:53,401][13398] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000490_2007040.pth +[2023-05-31 16:08:55,448][13411] Updated weights for policy 0, policy_version 700 (0.0014) +[2023-05-31 16:08:58,213][00392] Fps is (10 sec: 2866.8, 60 sec: 3481.5, 300 sec: 3526.7). Total num frames: 2871296. Throughput: 0: 866.5. Samples: 719104. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:08:58,221][00392] Avg episode reward: [(0, '21.868')] +[2023-05-31 16:09:03,211][00392] Fps is (10 sec: 2867.3, 60 sec: 3345.1, 300 sec: 3540.6). Total num frames: 2887680. Throughput: 0: 868.3. Samples: 721266. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:09:03,219][00392] Avg episode reward: [(0, '22.201')] +[2023-05-31 16:09:07,380][13411] Updated weights for policy 0, policy_version 710 (0.0018) +[2023-05-31 16:09:08,211][00392] Fps is (10 sec: 3686.9, 60 sec: 3413.7, 300 sec: 3554.5). Total num frames: 2908160. Throughput: 0: 875.5. Samples: 727236. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:09:08,218][00392] Avg episode reward: [(0, '23.119')] +[2023-05-31 16:09:13,211][00392] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3554.5). Total num frames: 2928640. Throughput: 0: 866.1. Samples: 733402. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:09:13,215][00392] Avg episode reward: [(0, '22.240')] +[2023-05-31 16:09:18,211][00392] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3540.6). Total num frames: 2945024. Throughput: 0: 866.9. Samples: 735456. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:09:18,221][00392] Avg episode reward: [(0, '23.921')] +[2023-05-31 16:09:18,224][13398] Saving new best policy, reward=23.921! +[2023-05-31 16:09:19,731][13411] Updated weights for policy 0, policy_version 720 (0.0016) +[2023-05-31 16:09:23,212][00392] Fps is (10 sec: 2867.1, 60 sec: 3413.3, 300 sec: 3526.7). Total num frames: 2957312. Throughput: 0: 865.3. Samples: 739572. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:09:23,218][00392] Avg episode reward: [(0, '24.856')] +[2023-05-31 16:09:23,235][13398] Saving new best policy, reward=24.856! +[2023-05-31 16:09:28,211][00392] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3540.6). Total num frames: 2977792. Throughput: 0: 872.8. Samples: 745118. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-05-31 16:09:28,216][00392] Avg episode reward: [(0, '24.317')] +[2023-05-31 16:09:30,707][13411] Updated weights for policy 0, policy_version 730 (0.0022) +[2023-05-31 16:09:33,211][00392] Fps is (10 sec: 4096.1, 60 sec: 3481.6, 300 sec: 3554.5). Total num frames: 2998272. Throughput: 0: 875.4. Samples: 748534. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-05-31 16:09:33,214][00392] Avg episode reward: [(0, '23.499')] +[2023-05-31 16:09:38,211][00392] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 3014656. Throughput: 0: 867.7. Samples: 754120. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:09:38,216][00392] Avg episode reward: [(0, '22.245')] +[2023-05-31 16:09:42,937][13411] Updated weights for policy 0, policy_version 740 (0.0012) +[2023-05-31 16:09:43,211][00392] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3512.9). Total num frames: 3031040. Throughput: 0: 871.1. Samples: 758302. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 16:09:43,214][00392] Avg episode reward: [(0, '21.831')] +[2023-05-31 16:09:48,211][00392] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3526.8). Total num frames: 3047424. Throughput: 0: 870.6. Samples: 760442. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-05-31 16:09:48,214][00392] Avg episode reward: [(0, '19.626')] +[2023-05-31 16:09:53,211][00392] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3554.5). Total num frames: 3067904. Throughput: 0: 884.4. Samples: 767034. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:09:53,213][00392] Avg episode reward: [(0, '19.325')] +[2023-05-31 16:09:53,346][13411] Updated weights for policy 0, policy_version 750 (0.0018) +[2023-05-31 16:09:58,211][00392] Fps is (10 sec: 4096.0, 60 sec: 3618.2, 300 sec: 3540.6). Total num frames: 3088384. Throughput: 0: 891.4. Samples: 773516. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 16:09:58,214][00392] Avg episode reward: [(0, '19.590')] +[2023-05-31 16:10:03,211][00392] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 3104768. Throughput: 0: 892.0. Samples: 775596. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 16:10:03,215][00392] Avg episode reward: [(0, '20.216')] +[2023-05-31 16:10:05,751][13411] Updated weights for policy 0, policy_version 760 (0.0016) +[2023-05-31 16:10:08,215][00392] Fps is (10 sec: 2866.2, 60 sec: 3481.4, 300 sec: 3512.8). Total num frames: 3117056. Throughput: 0: 893.9. Samples: 779800. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:10:08,217][00392] Avg episode reward: [(0, '21.092')] +[2023-05-31 16:10:13,211][00392] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3540.6). Total num frames: 3137536. Throughput: 0: 906.1. Samples: 785894. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 16:10:13,216][00392] Avg episode reward: [(0, '21.895')] +[2023-05-31 16:10:15,964][13411] Updated weights for policy 0, policy_version 770 (0.0019) +[2023-05-31 16:10:18,213][00392] Fps is (10 sec: 4506.3, 60 sec: 3618.0, 300 sec: 3554.5). Total num frames: 3162112. Throughput: 0: 904.9. Samples: 789258. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-05-31 16:10:18,216][00392] Avg episode reward: [(0, '23.631')] +[2023-05-31 16:10:23,211][00392] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3540.6). Total num frames: 3178496. Throughput: 0: 906.0. Samples: 794888. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:10:23,218][00392] Avg episode reward: [(0, '24.718')] +[2023-05-31 16:10:28,211][00392] Fps is (10 sec: 2867.7, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 3190784. Throughput: 0: 908.1. Samples: 799166. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 16:10:28,213][00392] Avg episode reward: [(0, '24.088')] +[2023-05-31 16:10:28,398][13411] Updated weights for policy 0, policy_version 780 (0.0031) +[2023-05-31 16:10:33,211][00392] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3540.6). Total num frames: 3211264. Throughput: 0: 910.5. Samples: 801414. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:10:33,214][00392] Avg episode reward: [(0, '24.264')] +[2023-05-31 16:10:38,211][00392] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3554.5). Total num frames: 3231744. Throughput: 0: 912.2. Samples: 808084. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-05-31 16:10:38,214][00392] Avg episode reward: [(0, '24.090')] +[2023-05-31 16:10:38,435][13411] Updated weights for policy 0, policy_version 790 (0.0016) +[2023-05-31 16:10:43,217][00392] Fps is (10 sec: 4093.8, 60 sec: 3686.1, 300 sec: 3554.4). Total num frames: 3252224. Throughput: 0: 902.0. Samples: 814112. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:10:43,219][00392] Avg episode reward: [(0, '23.024')] +[2023-05-31 16:10:48,211][00392] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3512.8). Total num frames: 3264512. Throughput: 0: 902.4. Samples: 816206. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:10:48,214][00392] Avg episode reward: [(0, '22.819')] +[2023-05-31 16:10:51,153][13411] Updated weights for policy 0, policy_version 800 (0.0027) +[2023-05-31 16:10:53,211][00392] Fps is (10 sec: 2868.7, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 3280896. Throughput: 0: 905.2. Samples: 820530. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-05-31 16:10:53,219][00392] Avg episode reward: [(0, '23.115')] +[2023-05-31 16:10:53,229][13398] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000801_3280896.pth... +[2023-05-31 16:10:53,349][13398] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000595_2437120.pth +[2023-05-31 16:10:58,211][00392] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3554.5). Total num frames: 3305472. Throughput: 0: 908.9. Samples: 826796. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:10:58,214][00392] Avg episode reward: [(0, '22.887')] +[2023-05-31 16:11:00,847][13411] Updated weights for policy 0, policy_version 810 (0.0019) +[2023-05-31 16:11:03,211][00392] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3568.4). Total num frames: 3325952. Throughput: 0: 910.9. Samples: 830248. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:11:03,213][00392] Avg episode reward: [(0, '23.367')] +[2023-05-31 16:11:08,216][00392] Fps is (10 sec: 3684.8, 60 sec: 3754.6, 300 sec: 3540.6). Total num frames: 3342336. Throughput: 0: 898.7. Samples: 835334. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-05-31 16:11:08,218][00392] Avg episode reward: [(0, '23.182')] +[2023-05-31 16:11:13,216][00392] Fps is (10 sec: 2865.9, 60 sec: 3617.9, 300 sec: 3526.7). Total num frames: 3354624. Throughput: 0: 897.1. Samples: 839540. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:11:13,224][00392] Avg episode reward: [(0, '23.579')] +[2023-05-31 16:11:14,128][13411] Updated weights for policy 0, policy_version 820 (0.0023) +[2023-05-31 16:11:18,211][00392] Fps is (10 sec: 3278.2, 60 sec: 3550.0, 300 sec: 3554.5). Total num frames: 3375104. Throughput: 0: 906.2. Samples: 842194. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:11:18,214][00392] Avg episode reward: [(0, '23.282')] +[2023-05-31 16:11:23,211][00392] Fps is (10 sec: 4097.8, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 3395584. Throughput: 0: 910.6. Samples: 849060. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-05-31 16:11:23,217][00392] Avg episode reward: [(0, '24.305')] +[2023-05-31 16:11:23,373][13411] Updated weights for policy 0, policy_version 830 (0.0012) +[2023-05-31 16:11:28,211][00392] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3554.5). Total num frames: 3416064. Throughput: 0: 896.9. Samples: 854466. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:11:28,218][00392] Avg episode reward: [(0, '24.698')] +[2023-05-31 16:11:33,212][00392] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3526.8). Total num frames: 3428352. Throughput: 0: 898.4. Samples: 856632. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:11:33,218][00392] Avg episode reward: [(0, '24.736')] +[2023-05-31 16:11:36,839][13411] Updated weights for policy 0, policy_version 840 (0.0017) +[2023-05-31 16:11:38,211][00392] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3540.6). Total num frames: 3444736. Throughput: 0: 899.6. Samples: 861010. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:11:38,217][00392] Avg episode reward: [(0, '24.354')] +[2023-05-31 16:11:43,211][00392] Fps is (10 sec: 4096.1, 60 sec: 3618.5, 300 sec: 3568.4). Total num frames: 3469312. Throughput: 0: 912.5. Samples: 867858. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-05-31 16:11:43,214][00392] Avg episode reward: [(0, '24.540')] +[2023-05-31 16:11:45,825][13411] Updated weights for policy 0, policy_version 850 (0.0013) +[2023-05-31 16:11:48,216][00392] Fps is (10 sec: 4094.2, 60 sec: 3686.1, 300 sec: 3554.4). Total num frames: 3485696. Throughput: 0: 912.0. Samples: 871292. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:11:48,226][00392] Avg episode reward: [(0, '22.334')] +[2023-05-31 16:11:53,211][00392] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3540.6). Total num frames: 3502080. Throughput: 0: 898.8. Samples: 875774. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:11:53,214][00392] Avg episode reward: [(0, '22.280')] +[2023-05-31 16:11:58,211][00392] Fps is (10 sec: 3278.3, 60 sec: 3549.9, 300 sec: 3540.6). Total num frames: 3518464. Throughput: 0: 902.5. Samples: 880148. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 16:11:58,219][00392] Avg episode reward: [(0, '21.459')] +[2023-05-31 16:11:59,119][13411] Updated weights for policy 0, policy_version 860 (0.0034) +[2023-05-31 16:12:03,211][00392] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3568.4). Total num frames: 3538944. Throughput: 0: 914.7. Samples: 883354. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-05-31 16:12:03,219][00392] Avg episode reward: [(0, '21.078')] +[2023-05-31 16:12:08,207][13411] Updated weights for policy 0, policy_version 870 (0.0033) +[2023-05-31 16:12:08,211][00392] Fps is (10 sec: 4505.6, 60 sec: 3686.7, 300 sec: 3582.3). Total num frames: 3563520. Throughput: 0: 912.4. Samples: 890118. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:12:08,215][00392] Avg episode reward: [(0, '21.480')] +[2023-05-31 16:12:13,211][00392] Fps is (10 sec: 3686.4, 60 sec: 3686.7, 300 sec: 3554.5). Total num frames: 3575808. Throughput: 0: 901.5. Samples: 895034. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:12:13,214][00392] Avg episode reward: [(0, '21.247')] +[2023-05-31 16:12:18,212][00392] Fps is (10 sec: 2867.0, 60 sec: 3618.1, 300 sec: 3540.6). Total num frames: 3592192. Throughput: 0: 900.3. Samples: 897144. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-05-31 16:12:18,220][00392] Avg episode reward: [(0, '21.592')] +[2023-05-31 16:12:21,601][13411] Updated weights for policy 0, policy_version 880 (0.0014) +[2023-05-31 16:12:23,211][00392] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3554.5). Total num frames: 3608576. Throughput: 0: 914.5. Samples: 902164. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 16:12:23,216][00392] Avg episode reward: [(0, '22.426')] +[2023-05-31 16:12:28,211][00392] Fps is (10 sec: 4096.2, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 3633152. Throughput: 0: 915.5. Samples: 909054. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:12:28,214][00392] Avg episode reward: [(0, '24.190')] +[2023-05-31 16:12:30,493][13411] Updated weights for policy 0, policy_version 890 (0.0017) +[2023-05-31 16:12:33,211][00392] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3568.4). Total num frames: 3649536. Throughput: 0: 913.2. Samples: 912380. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 16:12:33,216][00392] Avg episode reward: [(0, '24.480')] +[2023-05-31 16:12:38,211][00392] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3554.5). Total num frames: 3665920. Throughput: 0: 908.7. Samples: 916664. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:12:38,215][00392] Avg episode reward: [(0, '26.122')] +[2023-05-31 16:12:38,221][13398] Saving new best policy, reward=26.122! +[2023-05-31 16:12:43,211][00392] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3540.6). Total num frames: 3678208. Throughput: 0: 909.6. Samples: 921078. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:12:43,213][00392] Avg episode reward: [(0, '26.346')] +[2023-05-31 16:12:43,240][13398] Saving new best policy, reward=26.346! +[2023-05-31 16:12:44,218][13411] Updated weights for policy 0, policy_version 900 (0.0046) +[2023-05-31 16:12:48,211][00392] Fps is (10 sec: 3686.4, 60 sec: 3618.4, 300 sec: 3582.3). Total num frames: 3702784. Throughput: 0: 909.9. Samples: 924300. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-05-31 16:12:48,217][00392] Avg episode reward: [(0, '25.900')] +[2023-05-31 16:12:53,029][13411] Updated weights for policy 0, policy_version 910 (0.0020) +[2023-05-31 16:12:53,211][00392] Fps is (10 sec: 4915.1, 60 sec: 3754.7, 300 sec: 3610.0). Total num frames: 3727360. Throughput: 0: 914.5. Samples: 931270. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-05-31 16:12:53,217][00392] Avg episode reward: [(0, '26.179')] +[2023-05-31 16:12:53,234][13398] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000910_3727360.pth... +[2023-05-31 16:12:53,410][13398] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000698_2859008.pth +[2023-05-31 16:12:58,211][00392] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3568.4). Total num frames: 3739648. Throughput: 0: 907.5. Samples: 935872. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:12:58,217][00392] Avg episode reward: [(0, '25.647')] +[2023-05-31 16:13:03,212][00392] Fps is (10 sec: 2867.1, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 3756032. Throughput: 0: 908.4. Samples: 938020. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:13:03,213][00392] Avg episode reward: [(0, '25.249')] +[2023-05-31 16:13:06,690][13411] Updated weights for policy 0, policy_version 920 (0.0028) +[2023-05-31 16:13:08,212][00392] Fps is (10 sec: 3276.7, 60 sec: 3481.6, 300 sec: 3582.3). Total num frames: 3772416. Throughput: 0: 909.9. Samples: 943112. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 16:13:08,219][00392] Avg episode reward: [(0, '24.708')] +[2023-05-31 16:13:13,211][00392] Fps is (10 sec: 4096.2, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 3796992. Throughput: 0: 910.5. Samples: 950028. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:13:13,214][00392] Avg episode reward: [(0, '25.708')] +[2023-05-31 16:13:15,578][13411] Updated weights for policy 0, policy_version 930 (0.0014) +[2023-05-31 16:13:18,211][00392] Fps is (10 sec: 4096.2, 60 sec: 3686.4, 300 sec: 3596.2). Total num frames: 3813376. Throughput: 0: 907.5. Samples: 953218. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:13:18,220][00392] Avg episode reward: [(0, '26.676')] +[2023-05-31 16:13:18,224][13398] Saving new best policy, reward=26.676! +[2023-05-31 16:13:23,212][00392] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 3829760. Throughput: 0: 904.2. Samples: 957354. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:13:23,224][00392] Avg episode reward: [(0, '26.942')] +[2023-05-31 16:13:23,233][13398] Saving new best policy, reward=26.942! +[2023-05-31 16:13:28,211][00392] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3568.4). Total num frames: 3842048. Throughput: 0: 905.3. Samples: 961818. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-05-31 16:13:28,214][00392] Avg episode reward: [(0, '28.239')] +[2023-05-31 16:13:28,217][13398] Saving new best policy, reward=28.239! +[2023-05-31 16:13:29,260][13411] Updated weights for policy 0, policy_version 940 (0.0024) +[2023-05-31 16:13:33,211][00392] Fps is (10 sec: 3686.5, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 3866624. Throughput: 0: 907.1. Samples: 965120. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 16:13:33,220][00392] Avg episode reward: [(0, '28.386')] +[2023-05-31 16:13:33,228][13398] Saving new best policy, reward=28.386! +[2023-05-31 16:13:38,211][00392] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 3887104. Throughput: 0: 904.5. Samples: 971974. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:13:38,220][00392] Avg episode reward: [(0, '28.357')] +[2023-05-31 16:13:38,615][13411] Updated weights for policy 0, policy_version 950 (0.0024) +[2023-05-31 16:13:43,211][00392] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3596.1). Total num frames: 3903488. Throughput: 0: 900.4. Samples: 976390. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-05-31 16:13:43,219][00392] Avg episode reward: [(0, '27.520')] +[2023-05-31 16:13:48,212][00392] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 3915776. Throughput: 0: 901.5. Samples: 978586. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:13:48,220][00392] Avg episode reward: [(0, '27.984')] +[2023-05-31 16:13:51,570][13411] Updated weights for policy 0, policy_version 960 (0.0021) +[2023-05-31 16:13:53,211][00392] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3610.0). Total num frames: 3936256. Throughput: 0: 909.3. Samples: 984032. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-05-31 16:13:53,217][00392] Avg episode reward: [(0, '25.817')] +[2023-05-31 16:13:58,211][00392] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3960832. Throughput: 0: 908.1. Samples: 990894. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-05-31 16:13:58,216][00392] Avg episode reward: [(0, '24.385')] +[2023-05-31 16:14:01,584][13411] Updated weights for policy 0, policy_version 970 (0.0046) +[2023-05-31 16:14:03,211][00392] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 3977216. Throughput: 0: 896.0. Samples: 993536. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:14:03,219][00392] Avg episode reward: [(0, '22.831')] +[2023-05-31 16:14:08,211][00392] Fps is (10 sec: 2867.2, 60 sec: 3618.2, 300 sec: 3596.2). Total num frames: 3989504. Throughput: 0: 898.1. Samples: 997768. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-05-31 16:14:08,216][00392] Avg episode reward: [(0, '22.531')] +[2023-05-31 16:14:12,371][13398] Stopping Batcher_0... +[2023-05-31 16:14:12,372][13398] Loop batcher_evt_loop terminating... +[2023-05-31 16:14:12,373][00392] Component Batcher_0 stopped! +[2023-05-31 16:14:12,374][13398] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-05-31 16:14:12,433][13411] Weights refcount: 2 0 +[2023-05-31 16:14:12,445][00392] Component InferenceWorker_p0-w0 stopped! +[2023-05-31 16:14:12,447][13411] Stopping InferenceWorker_p0-w0... +[2023-05-31 16:14:12,448][13411] Loop inference_proc0-0_evt_loop terminating... +[2023-05-31 16:14:12,458][13414] Stopping RolloutWorker_w2... +[2023-05-31 16:14:12,458][00392] Component RolloutWorker_w2 stopped! +[2023-05-31 16:14:12,466][00392] Component RolloutWorker_w4 stopped! +[2023-05-31 16:14:12,468][00392] Component RolloutWorker_w7 stopped! +[2023-05-31 16:14:12,466][13416] Stopping RolloutWorker_w4... +[2023-05-31 16:14:12,480][00392] Component RolloutWorker_w1 stopped! +[2023-05-31 16:14:12,483][13413] Stopping RolloutWorker_w1... +[2023-05-31 16:14:12,475][13419] Stopping RolloutWorker_w7... +[2023-05-31 16:14:12,477][13414] Loop rollout_proc2_evt_loop terminating... +[2023-05-31 16:14:12,491][00392] Component RolloutWorker_w0 stopped! +[2023-05-31 16:14:12,490][13412] Stopping RolloutWorker_w0... +[2023-05-31 16:14:12,481][13416] Loop rollout_proc4_evt_loop terminating... +[2023-05-31 16:14:12,498][00392] Component RolloutWorker_w3 stopped! +[2023-05-31 16:14:12,499][13415] Stopping RolloutWorker_w3... +[2023-05-31 16:14:12,484][13413] Loop rollout_proc1_evt_loop terminating... +[2023-05-31 16:14:12,501][13415] Loop rollout_proc3_evt_loop terminating... +[2023-05-31 16:14:12,495][13412] Loop rollout_proc0_evt_loop terminating... +[2023-05-31 16:14:12,487][13419] Loop rollout_proc7_evt_loop terminating... +[2023-05-31 16:14:12,516][13418] Stopping RolloutWorker_w6... +[2023-05-31 16:14:12,516][00392] Component RolloutWorker_w6 stopped! +[2023-05-31 16:14:12,528][00392] Component RolloutWorker_w5 stopped! +[2023-05-31 16:14:12,530][13417] Stopping RolloutWorker_w5... +[2023-05-31 16:14:12,517][13418] Loop rollout_proc6_evt_loop terminating... +[2023-05-31 16:14:12,531][13417] Loop rollout_proc5_evt_loop terminating... +[2023-05-31 16:14:12,542][13398] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000801_3280896.pth +[2023-05-31 16:14:12,553][13398] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-05-31 16:14:12,741][13398] Stopping LearnerWorker_p0... +[2023-05-31 16:14:12,743][13398] Loop learner_proc0_evt_loop terminating... +[2023-05-31 16:14:12,741][00392] Component LearnerWorker_p0 stopped! +[2023-05-31 16:14:12,745][00392] Waiting for process learner_proc0 to stop... +[2023-05-31 16:14:14,408][00392] Waiting for process inference_proc0-0 to join... +[2023-05-31 16:14:14,410][00392] Waiting for process rollout_proc0 to join... +[2023-05-31 16:14:15,356][00392] Waiting for process rollout_proc1 to join... +[2023-05-31 16:14:15,378][00392] Waiting for process rollout_proc2 to join... +[2023-05-31 16:14:15,381][00392] Waiting for process rollout_proc3 to join... +[2023-05-31 16:14:15,384][00392] Waiting for process rollout_proc4 to join... +[2023-05-31 16:14:15,385][00392] Waiting for process rollout_proc5 to join... +[2023-05-31 16:14:15,387][00392] Waiting for process rollout_proc6 to join... +[2023-05-31 16:14:15,388][00392] Waiting for process rollout_proc7 to join... +[2023-05-31 16:14:15,390][00392] Batcher 0 profile tree view: +batching: 27.4360, releasing_batches: 0.0269 +[2023-05-31 16:14:15,391][00392] InferenceWorker_p0-w0 profile tree view: +wait_policy: 0.0005 + wait_policy_total: 532.2421 +update_model: 8.0550 + weight_update: 0.0027 +one_step: 0.0023 + handle_policy_step: 551.5068 + deserialize: 15.8435, stack: 3.1252, obs_to_device_normalize: 118.8903, forward: 275.4647, send_messages: 28.2081 + prepare_outputs: 82.4276 + to_cpu: 49.6597 +[2023-05-31 16:14:15,392][00392] Learner 0 profile tree view: +misc: 0.0052, prepare_batch: 15.9479 +train: 75.4698 + epoch_init: 0.0063, minibatch_init: 0.0079, losses_postprocess: 0.5953, kl_divergence: 0.5364, after_optimizer: 34.1062 + calculate_losses: 25.1453 + losses_init: 0.0244, forward_head: 1.7550, bptt_initial: 15.9254, tail: 1.1123, advantages_returns: 0.3575, losses: 3.2695 + bptt: 2.3565 + bptt_forward_core: 2.2556 + update: 14.4032 + clip: 1.4914 +[2023-05-31 16:14:15,393][00392] RolloutWorker_w0 profile tree view: +wait_for_trajectories: 0.3320, enqueue_policy_requests: 147.4280, env_step: 845.5407, overhead: 23.6638, complete_rollouts: 7.8396 +save_policy_outputs: 21.4435 + split_output_tensors: 10.0983 +[2023-05-31 16:14:15,394][00392] RolloutWorker_w7 profile tree view: +wait_for_trajectories: 0.3559, enqueue_policy_requests: 146.5745, env_step: 846.4428, overhead: 23.5905, complete_rollouts: 6.9284 +save_policy_outputs: 22.3383 + split_output_tensors: 10.6853 +[2023-05-31 16:14:15,396][00392] Loop Runner_EvtLoop terminating... +[2023-05-31 16:14:15,398][00392] Runner profile tree view: +main_loop: 1158.7647 +[2023-05-31 16:14:15,398][00392] Collected {0: 4005888}, FPS: 3457.0 +[2023-05-31 16:16:25,161][00392] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json +[2023-05-31 16:16:25,165][00392] Overriding arg 'num_workers' with value 1 passed from command line +[2023-05-31 16:16:25,167][00392] Adding new argument 'no_render'=True that is not in the saved config file! +[2023-05-31 16:16:25,170][00392] Adding new argument 'save_video'=True that is not in the saved config file! +[2023-05-31 16:16:25,174][00392] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! +[2023-05-31 16:16:25,179][00392] Adding new argument 'video_name'=None that is not in the saved config file! +[2023-05-31 16:16:25,180][00392] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! +[2023-05-31 16:16:25,185][00392] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! +[2023-05-31 16:16:25,187][00392] Adding new argument 'push_to_hub'=False that is not in the saved config file! +[2023-05-31 16:16:25,190][00392] Adding new argument 'hf_repository'=None that is not in the saved config file! +[2023-05-31 16:16:25,191][00392] Adding new argument 'policy_index'=0 that is not in the saved config file! +[2023-05-31 16:16:25,192][00392] Adding new argument 'eval_deterministic'=False that is not in the saved config file! +[2023-05-31 16:16:25,195][00392] Adding new argument 'train_script'=None that is not in the saved config file! +[2023-05-31 16:16:25,196][00392] Adding new argument 'enjoy_script'=None that is not in the saved config file! +[2023-05-31 16:16:25,198][00392] Using frameskip 1 and render_action_repeat=4 for evaluation +[2023-05-31 16:16:25,251][00392] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-05-31 16:16:25,254][00392] RunningMeanStd input shape: (3, 72, 128) +[2023-05-31 16:16:25,261][00392] RunningMeanStd input shape: (1,) +[2023-05-31 16:16:25,309][00392] ConvEncoder: input_channels=3 +[2023-05-31 16:16:25,841][00392] Conv encoder output size: 512 +[2023-05-31 16:16:25,845][00392] Policy head output size: 512 +[2023-05-31 16:16:30,583][00392] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-05-31 16:16:31,693][00392] Num frames 100... +[2023-05-31 16:16:31,812][00392] Num frames 200... +[2023-05-31 16:16:31,929][00392] Num frames 300... +[2023-05-31 16:16:32,047][00392] Num frames 400... +[2023-05-31 16:16:32,167][00392] Num frames 500... +[2023-05-31 16:16:32,286][00392] Num frames 600... +[2023-05-31 16:16:32,408][00392] Num frames 700... +[2023-05-31 16:16:32,505][00392] Avg episode rewards: #0: 13.350, true rewards: #0: 7.350 +[2023-05-31 16:16:32,507][00392] Avg episode reward: 13.350, avg true_objective: 7.350 +[2023-05-31 16:16:32,587][00392] Num frames 800... +[2023-05-31 16:16:32,713][00392] Num frames 900... +[2023-05-31 16:16:32,836][00392] Num frames 1000... +[2023-05-31 16:16:32,959][00392] Num frames 1100... +[2023-05-31 16:16:33,087][00392] Num frames 1200... +[2023-05-31 16:16:33,206][00392] Num frames 1300... +[2023-05-31 16:16:33,324][00392] Num frames 1400... +[2023-05-31 16:16:33,443][00392] Num frames 1500... +[2023-05-31 16:16:33,563][00392] Num frames 1600... +[2023-05-31 16:16:33,688][00392] Num frames 1700... +[2023-05-31 16:16:33,806][00392] Num frames 1800... +[2023-05-31 16:16:33,927][00392] Num frames 1900... +[2023-05-31 16:16:34,046][00392] Num frames 2000... +[2023-05-31 16:16:34,168][00392] Num frames 2100... +[2023-05-31 16:16:34,290][00392] Num frames 2200... +[2023-05-31 16:16:34,410][00392] Num frames 2300... +[2023-05-31 16:16:34,535][00392] Num frames 2400... +[2023-05-31 16:16:34,663][00392] Num frames 2500... +[2023-05-31 16:16:34,795][00392] Avg episode rewards: #0: 29.815, true rewards: #0: 12.815 +[2023-05-31 16:16:34,796][00392] Avg episode reward: 29.815, avg true_objective: 12.815 +[2023-05-31 16:16:34,848][00392] Num frames 2600... +[2023-05-31 16:16:34,971][00392] Num frames 2700... +[2023-05-31 16:16:35,096][00392] Num frames 2800... +[2023-05-31 16:16:35,216][00392] Num frames 2900... +[2023-05-31 16:16:35,333][00392] Num frames 3000... +[2023-05-31 16:16:35,476][00392] Avg episode rewards: #0: 22.583, true rewards: #0: 10.250 +[2023-05-31 16:16:35,478][00392] Avg episode reward: 22.583, avg true_objective: 10.250 +[2023-05-31 16:16:35,513][00392] Num frames 3100... +[2023-05-31 16:16:35,631][00392] Num frames 3200... +[2023-05-31 16:16:35,753][00392] Num frames 3300... +[2023-05-31 16:16:35,868][00392] Num frames 3400... +[2023-05-31 16:16:35,998][00392] Num frames 3500... +[2023-05-31 16:16:36,121][00392] Num frames 3600... +[2023-05-31 16:16:36,241][00392] Num frames 3700... +[2023-05-31 16:16:36,360][00392] Num frames 3800... +[2023-05-31 16:16:36,479][00392] Num frames 3900... +[2023-05-31 16:16:36,597][00392] Num frames 4000... +[2023-05-31 16:16:36,745][00392] Num frames 4100... +[2023-05-31 16:16:36,799][00392] Avg episode rewards: #0: 23.750, true rewards: #0: 10.250 +[2023-05-31 16:16:36,801][00392] Avg episode reward: 23.750, avg true_objective: 10.250 +[2023-05-31 16:16:36,922][00392] Num frames 4200... +[2023-05-31 16:16:37,042][00392] Num frames 4300... +[2023-05-31 16:16:37,163][00392] Num frames 4400... +[2023-05-31 16:16:37,283][00392] Num frames 4500... +[2023-05-31 16:16:37,399][00392] Num frames 4600... +[2023-05-31 16:16:37,515][00392] Num frames 4700... +[2023-05-31 16:16:37,637][00392] Num frames 4800... +[2023-05-31 16:16:37,765][00392] Num frames 4900... +[2023-05-31 16:16:37,881][00392] Num frames 5000... +[2023-05-31 16:16:38,000][00392] Num frames 5100... +[2023-05-31 16:16:38,120][00392] Num frames 5200... +[2023-05-31 16:16:38,239][00392] Num frames 5300... +[2023-05-31 16:16:38,356][00392] Num frames 5400... +[2023-05-31 16:16:38,471][00392] Num frames 5500... +[2023-05-31 16:16:38,590][00392] Num frames 5600... +[2023-05-31 16:16:38,729][00392] Avg episode rewards: #0: 26.136, true rewards: #0: 11.336 +[2023-05-31 16:16:38,731][00392] Avg episode reward: 26.136, avg true_objective: 11.336 +[2023-05-31 16:16:38,773][00392] Num frames 5700... +[2023-05-31 16:16:38,923][00392] Num frames 5800... +[2023-05-31 16:16:39,091][00392] Num frames 5900... +[2023-05-31 16:16:39,259][00392] Num frames 6000... +[2023-05-31 16:16:39,420][00392] Num frames 6100... +[2023-05-31 16:16:39,581][00392] Num frames 6200... +[2023-05-31 16:16:39,751][00392] Num frames 6300... +[2023-05-31 16:16:39,940][00392] Num frames 6400... +[2023-05-31 16:16:40,106][00392] Num frames 6500... +[2023-05-31 16:16:40,268][00392] Avg episode rewards: #0: 25.607, true rewards: #0: 10.940 +[2023-05-31 16:16:40,271][00392] Avg episode reward: 25.607, avg true_objective: 10.940 +[2023-05-31 16:16:40,335][00392] Num frames 6600... +[2023-05-31 16:16:40,500][00392] Num frames 6700... +[2023-05-31 16:16:40,674][00392] Num frames 6800... +[2023-05-31 16:16:40,846][00392] Num frames 6900... +[2023-05-31 16:16:41,020][00392] Num frames 7000... +[2023-05-31 16:16:41,189][00392] Num frames 7100... +[2023-05-31 16:16:41,357][00392] Num frames 7200... +[2023-05-31 16:16:41,534][00392] Num frames 7300... +[2023-05-31 16:17:25,579][00392] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json +[2023-05-31 16:17:25,581][00392] Overriding arg 'num_workers' with value 1 passed from command line +[2023-05-31 16:17:25,585][00392] Adding new argument 'no_render'=True that is not in the saved config file! +[2023-05-31 16:17:25,587][00392] Adding new argument 'save_video'=True that is not in the saved config file! +[2023-05-31 16:17:25,588][00392] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! +[2023-05-31 16:17:25,589][00392] Adding new argument 'video_name'=None that is not in the saved config file! +[2023-05-31 16:17:25,591][00392] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! +[2023-05-31 16:17:25,596][00392] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! +[2023-05-31 16:17:25,598][00392] Adding new argument 'push_to_hub'=False that is not in the saved config file! +[2023-05-31 16:17:25,600][00392] Adding new argument 'hf_repository'=None that is not in the saved config file! +[2023-05-31 16:17:25,601][00392] Adding new argument 'policy_index'=0 that is not in the saved config file! +[2023-05-31 16:17:25,602][00392] Adding new argument 'eval_deterministic'=False that is not in the saved config file! +[2023-05-31 16:17:25,604][00392] Adding new argument 'train_script'=None that is not in the saved config file! +[2023-05-31 16:17:25,606][00392] Adding new argument 'enjoy_script'=None that is not in the saved config file! +[2023-05-31 16:17:25,607][00392] Using frameskip 1 and render_action_repeat=4 for evaluation +[2023-05-31 16:17:25,634][00392] RunningMeanStd input shape: (3, 72, 128) +[2023-05-31 16:17:25,636][00392] RunningMeanStd input shape: (1,) +[2023-05-31 16:17:25,648][00392] ConvEncoder: input_channels=3 +[2023-05-31 16:17:25,683][00392] Conv encoder output size: 512 +[2023-05-31 16:17:25,685][00392] Policy head output size: 512 +[2023-05-31 16:17:25,704][00392] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-05-31 16:17:26,167][00392] Num frames 100... +[2023-05-31 16:17:26,284][00392] Num frames 200... +[2023-05-31 16:17:26,414][00392] Num frames 300... +[2023-05-31 16:17:26,536][00392] Num frames 400... +[2023-05-31 16:17:26,663][00392] Num frames 500... +[2023-05-31 16:17:26,788][00392] Num frames 600... +[2023-05-31 16:17:26,905][00392] Num frames 700... +[2023-05-31 16:17:27,025][00392] Num frames 800... +[2023-05-31 16:17:27,145][00392] Num frames 900... +[2023-05-31 16:17:27,264][00392] Num frames 1000... +[2023-05-31 16:17:27,390][00392] Avg episode rewards: #0: 24.560, true rewards: #0: 10.560 +[2023-05-31 16:17:27,393][00392] Avg episode reward: 24.560, avg true_objective: 10.560 +[2023-05-31 16:17:27,454][00392] Num frames 1100... +[2023-05-31 16:17:27,572][00392] Num frames 1200... +[2023-05-31 16:17:27,689][00392] Num frames 1300... +[2023-05-31 16:17:27,811][00392] Num frames 1400... +[2023-05-31 16:17:27,931][00392] Num frames 1500... +[2023-05-31 16:17:28,055][00392] Num frames 1600... +[2023-05-31 16:17:28,179][00392] Num frames 1700... +[2023-05-31 16:17:28,298][00392] Num frames 1800... +[2023-05-31 16:17:28,416][00392] Num frames 1900... +[2023-05-31 16:17:28,549][00392] Num frames 2000... +[2023-05-31 16:17:28,685][00392] Num frames 2100... +[2023-05-31 16:17:28,804][00392] Avg episode rewards: #0: 27.220, true rewards: #0: 10.720 +[2023-05-31 16:17:28,807][00392] Avg episode reward: 27.220, avg true_objective: 10.720 +[2023-05-31 16:17:28,877][00392] Num frames 2200... +[2023-05-31 16:17:28,997][00392] Num frames 2300... +[2023-05-31 16:17:29,126][00392] Num frames 2400... +[2023-05-31 16:17:29,246][00392] Num frames 2500... +[2023-05-31 16:17:29,366][00392] Num frames 2600... +[2023-05-31 16:17:29,491][00392] Num frames 2700... +[2023-05-31 16:17:29,608][00392] Num frames 2800... +[2023-05-31 16:17:29,729][00392] Num frames 2900... +[2023-05-31 16:17:29,846][00392] Num frames 3000... +[2023-05-31 16:17:29,969][00392] Num frames 3100... +[2023-05-31 16:17:30,092][00392] Num frames 3200... +[2023-05-31 16:17:30,212][00392] Num frames 3300... +[2023-05-31 16:17:30,329][00392] Num frames 3400... +[2023-05-31 16:17:30,452][00392] Num frames 3500... +[2023-05-31 16:17:30,584][00392] Num frames 3600... +[2023-05-31 16:17:30,702][00392] Num frames 3700... +[2023-05-31 16:17:30,822][00392] Num frames 3800... +[2023-05-31 16:17:30,946][00392] Num frames 3900... +[2023-05-31 16:17:31,067][00392] Num frames 4000... +[2023-05-31 16:17:31,195][00392] Num frames 4100... +[2023-05-31 16:17:31,314][00392] Num frames 4200... +[2023-05-31 16:17:31,422][00392] Avg episode rewards: #0: 37.146, true rewards: #0: 14.147 +[2023-05-31 16:17:31,423][00392] Avg episode reward: 37.146, avg true_objective: 14.147 +[2023-05-31 16:17:31,502][00392] Num frames 4300... +[2023-05-31 16:17:31,622][00392] Num frames 4400... +[2023-05-31 16:17:31,746][00392] Num frames 4500... +[2023-05-31 16:17:31,870][00392] Num frames 4600... +[2023-05-31 16:17:31,988][00392] Num frames 4700... +[2023-05-31 16:17:32,106][00392] Num frames 4800... +[2023-05-31 16:17:32,228][00392] Num frames 4900... +[2023-05-31 16:17:32,347][00392] Num frames 5000... +[2023-05-31 16:17:32,463][00392] Num frames 5100... +[2023-05-31 16:17:32,568][00392] Avg episode rewards: #0: 32.100, true rewards: #0: 12.850 +[2023-05-31 16:17:32,570][00392] Avg episode reward: 32.100, avg true_objective: 12.850 +[2023-05-31 16:17:32,643][00392] Num frames 5200... +[2023-05-31 16:17:32,766][00392] Num frames 5300... +[2023-05-31 16:17:32,883][00392] Num frames 5400... +[2023-05-31 16:17:33,002][00392] Num frames 5500... +[2023-05-31 16:17:33,125][00392] Avg episode rewards: #0: 26.912, true rewards: #0: 11.112 +[2023-05-31 16:17:33,127][00392] Avg episode reward: 26.912, avg true_objective: 11.112 +[2023-05-31 16:17:33,189][00392] Num frames 5600... +[2023-05-31 16:17:33,303][00392] Num frames 5700... +[2023-05-31 16:17:33,423][00392] Num frames 5800... +[2023-05-31 16:17:33,546][00392] Num frames 5900... +[2023-05-31 16:17:33,664][00392] Num frames 6000... +[2023-05-31 16:17:33,782][00392] Num frames 6100... +[2023-05-31 16:17:33,914][00392] Num frames 6200... +[2023-05-31 16:17:34,086][00392] Num frames 6300... +[2023-05-31 16:17:34,250][00392] Num frames 6400... +[2023-05-31 16:17:34,411][00392] Num frames 6500... +[2023-05-31 16:17:34,583][00392] Num frames 6600... +[2023-05-31 16:17:34,746][00392] Num frames 6700... +[2023-05-31 16:17:34,923][00392] Num frames 6800... +[2023-05-31 16:17:35,091][00392] Num frames 6900... +[2023-05-31 16:17:35,254][00392] Num frames 7000... +[2023-05-31 16:17:35,418][00392] Num frames 7100... +[2023-05-31 16:17:35,586][00392] Num frames 7200... +[2023-05-31 16:17:35,768][00392] Num frames 7300... +[2023-05-31 16:17:35,933][00392] Num frames 7400... +[2023-05-31 16:17:36,105][00392] Num frames 7500... +[2023-05-31 16:17:36,276][00392] Num frames 7600... +[2023-05-31 16:17:36,427][00392] Avg episode rewards: #0: 31.426, true rewards: #0: 12.760 +[2023-05-31 16:17:36,430][00392] Avg episode reward: 31.426, avg true_objective: 12.760 +[2023-05-31 16:17:36,511][00392] Num frames 7700... +[2023-05-31 16:17:36,680][00392] Num frames 7800... +[2023-05-31 16:17:36,846][00392] Num frames 7900... +[2023-05-31 16:17:37,012][00392] Num frames 8000... +[2023-05-31 16:17:37,187][00392] Num frames 8100... +[2023-05-31 16:17:37,355][00392] Num frames 8200... +[2023-05-31 16:17:37,522][00392] Num frames 8300... +[2023-05-31 16:17:37,693][00392] Num frames 8400... +[2023-05-31 16:17:37,866][00392] Num frames 8500... +[2023-05-31 16:17:38,037][00392] Num frames 8600... +[2023-05-31 16:17:38,231][00392] Avg episode rewards: #0: 29.828, true rewards: #0: 12.400 +[2023-05-31 16:17:38,233][00392] Avg episode reward: 29.828, avg true_objective: 12.400 +[2023-05-31 16:17:38,269][00392] Num frames 8700... +[2023-05-31 16:17:38,439][00392] Num frames 8800... +[2023-05-31 16:17:38,609][00392] Num frames 8900... +[2023-05-31 16:17:38,778][00392] Num frames 9000... +[2023-05-31 16:17:38,930][00392] Num frames 9100... +[2023-05-31 16:17:39,054][00392] Num frames 9200... +[2023-05-31 16:17:39,171][00392] Num frames 9300... +[2023-05-31 16:17:39,292][00392] Num frames 9400... +[2023-05-31 16:17:39,410][00392] Num frames 9500... +[2023-05-31 16:17:39,529][00392] Num frames 9600... +[2023-05-31 16:17:39,650][00392] Num frames 9700... +[2023-05-31 16:17:39,782][00392] Num frames 9800... +[2023-05-31 16:17:39,907][00392] Num frames 9900... +[2023-05-31 16:17:40,028][00392] Num frames 10000... +[2023-05-31 16:17:40,149][00392] Num frames 10100... +[2023-05-31 16:17:40,269][00392] Num frames 10200... +[2023-05-31 16:17:40,391][00392] Num frames 10300... +[2023-05-31 16:17:40,510][00392] Num frames 10400... +[2023-05-31 16:17:40,626][00392] Num frames 10500... +[2023-05-31 16:17:40,763][00392] Num frames 10600... +[2023-05-31 16:17:40,918][00392] Avg episode rewards: #0: 33.102, true rewards: #0: 13.353 +[2023-05-31 16:17:40,920][00392] Avg episode reward: 33.102, avg true_objective: 13.353 +[2023-05-31 16:17:40,944][00392] Num frames 10700... +[2023-05-31 16:17:41,061][00392] Num frames 10800... +[2023-05-31 16:17:41,178][00392] Num frames 10900... +[2023-05-31 16:17:41,297][00392] Num frames 11000... +[2023-05-31 16:17:41,357][00392] Avg episode rewards: #0: 29.891, true rewards: #0: 12.224 +[2023-05-31 16:17:41,359][00392] Avg episode reward: 29.891, avg true_objective: 12.224 +[2023-05-31 16:17:41,480][00392] Num frames 11100... +[2023-05-31 16:17:41,599][00392] Num frames 11200... +[2023-05-31 16:17:41,722][00392] Num frames 11300... +[2023-05-31 16:17:41,844][00392] Num frames 11400... +[2023-05-31 16:17:41,965][00392] Num frames 11500... +[2023-05-31 16:17:42,084][00392] Num frames 11600... +[2023-05-31 16:17:42,198][00392] Num frames 11700... +[2023-05-31 16:17:42,312][00392] Num frames 11800... +[2023-05-31 16:17:42,425][00392] Num frames 11900... +[2023-05-31 16:17:42,543][00392] Num frames 12000... +[2023-05-31 16:17:42,661][00392] Num frames 12100... +[2023-05-31 16:17:42,778][00392] Avg episode rewards: #0: 29.654, true rewards: #0: 12.154 +[2023-05-31 16:17:42,782][00392] Avg episode reward: 29.654, avg true_objective: 12.154 +[2023-05-31 16:18:59,087][00392] Replay video saved to /content/train_dir/default_experiment/replay.mp4! +[2023-05-31 16:25:22,695][00392] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json +[2023-05-31 16:25:22,697][00392] Overriding arg 'num_workers' with value 1 passed from command line +[2023-05-31 16:25:22,700][00392] Adding new argument 'no_render'=True that is not in the saved config file! +[2023-05-31 16:25:22,702][00392] Adding new argument 'save_video'=True that is not in the saved config file! +[2023-05-31 16:25:22,704][00392] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! +[2023-05-31 16:25:22,706][00392] Adding new argument 'video_name'=None that is not in the saved config file! +[2023-05-31 16:25:22,708][00392] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! +[2023-05-31 16:25:22,710][00392] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! +[2023-05-31 16:25:22,711][00392] Adding new argument 'push_to_hub'=True that is not in the saved config file! +[2023-05-31 16:25:22,713][00392] Adding new argument 'hf_repository'='eduiqe/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! +[2023-05-31 16:25:22,714][00392] Adding new argument 'policy_index'=0 that is not in the saved config file! +[2023-05-31 16:25:22,715][00392] Adding new argument 'eval_deterministic'=False that is not in the saved config file! +[2023-05-31 16:25:22,716][00392] Adding new argument 'train_script'=None that is not in the saved config file! +[2023-05-31 16:25:22,717][00392] Adding new argument 'enjoy_script'=None that is not in the saved config file! +[2023-05-31 16:25:22,719][00392] Using frameskip 1 and render_action_repeat=4 for evaluation +[2023-05-31 16:25:22,747][00392] RunningMeanStd input shape: (3, 72, 128) +[2023-05-31 16:25:22,750][00392] RunningMeanStd input shape: (1,) +[2023-05-31 16:25:22,792][00392] ConvEncoder: input_channels=3 +[2023-05-31 16:25:22,909][00392] Conv encoder output size: 512 +[2023-05-31 16:25:22,917][00392] Policy head output size: 512 +[2023-05-31 16:25:22,953][00392] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-05-31 16:25:23,627][00392] Num frames 100... +[2023-05-31 16:25:23,743][00392] Num frames 200... +[2023-05-31 16:25:23,861][00392] Num frames 300... +[2023-05-31 16:25:23,979][00392] Num frames 400... +[2023-05-31 16:25:24,102][00392] Num frames 500... +[2023-05-31 16:25:24,245][00392] Avg episode rewards: #0: 8.760, true rewards: #0: 5.760 +[2023-05-31 16:25:24,247][00392] Avg episode reward: 8.760, avg true_objective: 5.760 +[2023-05-31 16:25:24,281][00392] Num frames 600... +[2023-05-31 16:25:24,398][00392] Num frames 700... +[2023-05-31 16:25:24,528][00392] Num frames 800... +[2023-05-31 16:25:24,648][00392] Num frames 900... +[2023-05-31 16:25:24,780][00392] Num frames 1000... +[2023-05-31 16:25:24,896][00392] Num frames 1100... +[2023-05-31 16:25:25,023][00392] Num frames 1200... +[2023-05-31 16:25:25,140][00392] Num frames 1300... +[2023-05-31 16:25:25,263][00392] Num frames 1400... +[2023-05-31 16:25:25,383][00392] Num frames 1500... +[2023-05-31 16:25:25,498][00392] Num frames 1600... +[2023-05-31 16:25:25,616][00392] Num frames 1700... +[2023-05-31 16:25:25,705][00392] Avg episode rewards: #0: 18.640, true rewards: #0: 8.640 +[2023-05-31 16:25:25,707][00392] Avg episode reward: 18.640, avg true_objective: 8.640 +[2023-05-31 16:25:25,792][00392] Num frames 1800... +[2023-05-31 16:25:25,911][00392] Num frames 1900... +[2023-05-31 16:25:26,034][00392] Num frames 2000... +[2023-05-31 16:25:26,149][00392] Num frames 2100... +[2023-05-31 16:25:26,262][00392] Num frames 2200... +[2023-05-31 16:25:26,375][00392] Num frames 2300... +[2023-05-31 16:25:26,502][00392] Num frames 2400... +[2023-05-31 16:25:26,621][00392] Num frames 2500... +[2023-05-31 16:25:26,737][00392] Num frames 2600... +[2023-05-31 16:25:26,858][00392] Num frames 2700... +[2023-05-31 16:25:27,013][00392] Num frames 2800... +[2023-05-31 16:25:27,182][00392] Num frames 2900... +[2023-05-31 16:25:27,352][00392] Num frames 3000... +[2023-05-31 16:25:27,521][00392] Num frames 3100... +[2023-05-31 16:25:27,689][00392] Num frames 3200... +[2023-05-31 16:25:27,852][00392] Num frames 3300... +[2023-05-31 16:25:28,009][00392] Avg episode rewards: #0: 27.533, true rewards: #0: 11.200 +[2023-05-31 16:25:28,011][00392] Avg episode reward: 27.533, avg true_objective: 11.200 +[2023-05-31 16:25:28,093][00392] Num frames 3400... +[2023-05-31 16:25:28,256][00392] Num frames 3500... +[2023-05-31 16:25:28,421][00392] Num frames 3600... +[2023-05-31 16:25:28,590][00392] Num frames 3700... +[2023-05-31 16:25:28,762][00392] Num frames 3800... +[2023-05-31 16:25:28,927][00392] Num frames 3900... +[2023-05-31 16:25:29,096][00392] Num frames 4000... +[2023-05-31 16:25:29,273][00392] Num frames 4100... +[2023-05-31 16:25:29,450][00392] Num frames 4200... +[2023-05-31 16:25:29,621][00392] Num frames 4300... +[2023-05-31 16:25:29,790][00392] Num frames 4400... +[2023-05-31 16:25:29,965][00392] Num frames 4500... +[2023-05-31 16:25:30,143][00392] Num frames 4600... +[2023-05-31 16:25:30,319][00392] Num frames 4700... +[2023-05-31 16:25:30,484][00392] Num frames 4800... +[2023-05-31 16:25:30,661][00392] Num frames 4900... +[2023-05-31 16:25:30,832][00392] Num frames 5000... +[2023-05-31 16:25:31,004][00392] Num frames 5100... +[2023-05-31 16:25:31,179][00392] Num frames 5200... +[2023-05-31 16:25:31,356][00392] Num frames 5300... +[2023-05-31 16:25:31,529][00392] Num frames 5400... +[2023-05-31 16:25:31,689][00392] Avg episode rewards: #0: 36.150, true rewards: #0: 13.650 +[2023-05-31 16:25:31,692][00392] Avg episode reward: 36.150, avg true_objective: 13.650 +[2023-05-31 16:25:31,763][00392] Num frames 5500... +[2023-05-31 16:25:31,917][00392] Num frames 5600... +[2023-05-31 16:25:32,035][00392] Num frames 5700... +[2023-05-31 16:25:32,152][00392] Num frames 5800... +[2023-05-31 16:25:32,274][00392] Num frames 5900... +[2023-05-31 16:25:32,396][00392] Num frames 6000... +[2023-05-31 16:25:32,514][00392] Num frames 6100... +[2023-05-31 16:25:32,632][00392] Num frames 6200... +[2023-05-31 16:25:32,721][00392] Avg episode rewards: #0: 32.456, true rewards: #0: 12.456 +[2023-05-31 16:25:32,723][00392] Avg episode reward: 32.456, avg true_objective: 12.456 +[2023-05-31 16:25:32,810][00392] Num frames 6300... +[2023-05-31 16:25:32,931][00392] Num frames 6400... +[2023-05-31 16:25:33,050][00392] Num frames 6500... +[2023-05-31 16:25:33,170][00392] Num frames 6600... +[2023-05-31 16:25:33,296][00392] Num frames 6700... +[2023-05-31 16:25:33,414][00392] Num frames 6800... +[2023-05-31 16:25:33,532][00392] Num frames 6900... +[2023-05-31 16:25:33,651][00392] Num frames 7000... +[2023-05-31 16:25:33,778][00392] Num frames 7100... +[2023-05-31 16:25:33,896][00392] Num frames 7200... +[2023-05-31 16:25:34,016][00392] Num frames 7300... +[2023-05-31 16:25:34,140][00392] Num frames 7400... +[2023-05-31 16:25:34,266][00392] Num frames 7500... +[2023-05-31 16:25:34,384][00392] Num frames 7600... +[2023-05-31 16:25:34,501][00392] Num frames 7700... +[2023-05-31 16:25:34,621][00392] Num frames 7800... +[2023-05-31 16:25:34,741][00392] Num frames 7900... +[2023-05-31 16:25:34,857][00392] Num frames 8000... +[2023-05-31 16:25:34,980][00392] Num frames 8100... +[2023-05-31 16:25:35,099][00392] Num frames 8200... +[2023-05-31 16:25:35,217][00392] Num frames 8300... +[2023-05-31 16:25:35,306][00392] Avg episode rewards: #0: 34.713, true rewards: #0: 13.880 +[2023-05-31 16:25:35,309][00392] Avg episode reward: 34.713, avg true_objective: 13.880 +[2023-05-31 16:25:35,399][00392] Num frames 8400... +[2023-05-31 16:25:35,514][00392] Num frames 8500... +[2023-05-31 16:25:35,642][00392] Num frames 8600... +[2023-05-31 16:25:35,759][00392] Num frames 8700... +[2023-05-31 16:25:35,876][00392] Num frames 8800... +[2023-05-31 16:25:35,999][00392] Num frames 8900... +[2023-05-31 16:25:36,118][00392] Num frames 9000... +[2023-05-31 16:25:36,236][00392] Num frames 9100... +[2023-05-31 16:25:36,365][00392] Num frames 9200... +[2023-05-31 16:25:36,485][00392] Avg episode rewards: #0: 32.365, true rewards: #0: 13.223 +[2023-05-31 16:25:36,487][00392] Avg episode reward: 32.365, avg true_objective: 13.223 +[2023-05-31 16:25:36,543][00392] Num frames 9300... +[2023-05-31 16:25:36,663][00392] Num frames 9400... +[2023-05-31 16:25:36,785][00392] Num frames 9500... +[2023-05-31 16:25:36,902][00392] Num frames 9600... +[2023-05-31 16:25:37,028][00392] Num frames 9700... +[2023-05-31 16:25:37,148][00392] Num frames 9800... +[2023-05-31 16:25:37,287][00392] Num frames 9900... +[2023-05-31 16:25:37,413][00392] Num frames 10000... +[2023-05-31 16:25:37,541][00392] Num frames 10100... +[2023-05-31 16:25:37,661][00392] Num frames 10200... +[2023-05-31 16:25:37,780][00392] Num frames 10300... +[2023-05-31 16:25:37,889][00392] Avg episode rewards: #0: 31.055, true rewards: #0: 12.930 +[2023-05-31 16:25:37,891][00392] Avg episode reward: 31.055, avg true_objective: 12.930 +[2023-05-31 16:25:37,959][00392] Num frames 10400... +[2023-05-31 16:25:38,080][00392] Num frames 10500... +[2023-05-31 16:25:38,196][00392] Num frames 10600... +[2023-05-31 16:25:38,318][00392] Num frames 10700... +[2023-05-31 16:25:38,437][00392] Num frames 10800... +[2023-05-31 16:25:38,555][00392] Num frames 10900... +[2023-05-31 16:25:38,673][00392] Num frames 11000... +[2023-05-31 16:25:38,791][00392] Num frames 11100... +[2023-05-31 16:25:38,910][00392] Num frames 11200... +[2023-05-31 16:25:39,066][00392] Avg episode rewards: #0: 29.983, true rewards: #0: 12.539 +[2023-05-31 16:25:39,068][00392] Avg episode reward: 29.983, avg true_objective: 12.539 +[2023-05-31 16:25:39,091][00392] Num frames 11300... +[2023-05-31 16:25:39,208][00392] Num frames 11400... +[2023-05-31 16:25:39,339][00392] Num frames 11500... +[2023-05-31 16:25:39,458][00392] Num frames 11600... +[2023-05-31 16:25:39,578][00392] Num frames 11700... +[2023-05-31 16:25:39,703][00392] Num frames 11800... +[2023-05-31 16:25:39,826][00392] Num frames 11900... +[2023-05-31 16:25:39,942][00392] Num frames 12000... +[2023-05-31 16:25:40,068][00392] Avg episode rewards: #0: 28.453, true rewards: #0: 12.053 +[2023-05-31 16:25:40,070][00392] Avg episode reward: 28.453, avg true_objective: 12.053 +[2023-05-31 16:26:54,438][00392] Replay video saved to /content/train_dir/default_experiment/replay.mp4!