[2024-12-02 14:19:31,745][00408] Saving configuration to /content/train_dir/default_experiment/config.json...
[2024-12-02 14:19:31,748][00408] Rollout worker 0 uses device cpu
[2024-12-02 14:19:31,750][00408] Rollout worker 1 uses device cpu
[2024-12-02 14:19:31,753][00408] Rollout worker 2 uses device cpu
[2024-12-02 14:19:31,754][00408] Rollout worker 3 uses device cpu
[2024-12-02 14:19:31,757][00408] Rollout worker 4 uses device cpu
[2024-12-02 14:19:31,758][00408] Rollout worker 5 uses device cpu
[2024-12-02 14:19:31,761][00408] Rollout worker 6 uses device cpu
[2024-12-02 14:19:31,762][00408] Rollout worker 7 uses device cpu
[2024-12-02 14:19:31,909][00408] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-12-02 14:19:31,910][00408] InferenceWorker_p0-w0: min num requests: 2
[2024-12-02 14:19:31,945][00408] Starting all processes...
[2024-12-02 14:19:31,946][00408] Starting process learner_proc0
[2024-12-02 14:19:32,002][00408] Starting all processes...
[2024-12-02 14:19:32,012][00408] Starting process inference_proc0-0
[2024-12-02 14:19:32,013][00408] Starting process rollout_proc0
[2024-12-02 14:19:32,015][00408] Starting process rollout_proc1
[2024-12-02 14:19:32,015][00408] Starting process rollout_proc2
[2024-12-02 14:19:32,015][00408] Starting process rollout_proc3
[2024-12-02 14:19:32,015][00408] Starting process rollout_proc4
[2024-12-02 14:19:32,015][00408] Starting process rollout_proc5
[2024-12-02 14:19:32,015][00408] Starting process rollout_proc6
[2024-12-02 14:19:32,015][00408] Starting process rollout_proc7
[2024-12-02 14:19:52,123][05234] Worker 1 uses CPU cores [1]
[2024-12-02 14:19:52,318][00408] Heartbeat connected on RolloutWorker_w1
[2024-12-02 14:19:52,402][05219] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-12-02 14:19:52,408][05219] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
[2024-12-02 14:19:52,504][05219] Num visible devices: 1
[2024-12-02 14:19:52,544][00408] Heartbeat connected on Batcher_0
[2024-12-02 14:19:52,548][05219] Starting seed is not provided
[2024-12-02 14:19:52,548][05219] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-12-02 14:19:52,549][05219] Initializing actor-critic model on device cuda:0
[2024-12-02 14:19:52,551][05219] RunningMeanStd input shape: (3, 72, 128)
[2024-12-02 14:19:52,555][05219] RunningMeanStd input shape: (1,)
[2024-12-02 14:19:52,629][05232] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-12-02 14:19:52,637][05232] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
[2024-12-02 14:19:52,667][05239] Worker 5 uses CPU cores [1]
[2024-12-02 14:19:52,689][05219] ConvEncoder: input_channels=3
[2024-12-02 14:19:52,725][05233] Worker 0 uses CPU cores [0]
[2024-12-02 14:19:52,755][05232] Num visible devices: 1
[2024-12-02 14:19:52,800][00408] Heartbeat connected on RolloutWorker_w5
[2024-12-02 14:19:52,805][00408] Heartbeat connected on InferenceWorker_p0-w0
[2024-12-02 14:19:52,863][00408] Heartbeat connected on RolloutWorker_w0
[2024-12-02 14:19:52,869][05240] Worker 7 uses CPU cores [1]
[2024-12-02 14:19:52,876][05237] Worker 4 uses CPU cores [0]
[2024-12-02 14:19:52,888][05235] Worker 3 uses CPU cores [1]
[2024-12-02 14:19:52,890][00408] Heartbeat connected on RolloutWorker_w4
[2024-12-02 14:19:52,911][05238] Worker 6 uses CPU cores [0]
[2024-12-02 14:19:52,915][00408] Heartbeat connected on RolloutWorker_w7
[2024-12-02 14:19:52,916][00408] Heartbeat connected on RolloutWorker_w3
[2024-12-02 14:19:52,937][00408] Heartbeat connected on RolloutWorker_w6
[2024-12-02 14:19:52,945][05236] Worker 2 uses CPU cores [0]
[2024-12-02 14:19:52,955][00408] Heartbeat connected on RolloutWorker_w2
[2024-12-02 14:19:53,068][05219] Conv encoder output size: 512
[2024-12-02 14:19:53,069][05219] Policy head output size: 512
[2024-12-02 14:19:53,129][05219] Created Actor Critic model with architecture:
[2024-12-02 14:19:53,130][05219] ActorCriticSharedWeights(
  (obs_normalizer): ObservationNormalizer(
    (running_mean_std): RunningMeanStdDictInPlace(
      (running_mean_std): ModuleDict(
        (obs): RunningMeanStdInPlace()
      )
    )
  )
  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
  (encoder): VizdoomEncoder(
    (basic_encoder): ConvEncoder(
      (enc): RecursiveScriptModule(
        original_name=ConvEncoderImpl
        (conv_head): RecursiveScriptModule(
          original_name=Sequential
          (0): RecursiveScriptModule(original_name=Conv2d)
          (1): RecursiveScriptModule(original_name=ELU)
          (2): RecursiveScriptModule(original_name=Conv2d)
          (3): RecursiveScriptModule(original_name=ELU)
          (4): RecursiveScriptModule(original_name=Conv2d)
          (5): RecursiveScriptModule(original_name=ELU)
        )
        (mlp_layers): RecursiveScriptModule(
          original_name=Sequential
          (0): RecursiveScriptModule(original_name=Linear)
          (1): RecursiveScriptModule(original_name=ELU)
        )
      )
    )
  )
  (core): ModelCoreRNN(
    (core): GRU(512, 512)
  )
  (decoder): MlpDecoder(
    (mlp): Identity()
  )
  (critic_linear): Linear(in_features=512, out_features=1, bias=True)
  (action_parameterization): ActionParameterizationDefault(
    (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
  )
)
[2024-12-02 14:19:53,428][05219] Using optimizer <class 'torch.optim.adam.Adam'>
[2024-12-02 14:19:56,853][05219] No checkpoints found
[2024-12-02 14:19:56,854][05219] Did not load from checkpoint, starting from scratch!
[2024-12-02 14:19:56,854][05219] Initialized policy 0 weights for model version 0
[2024-12-02 14:19:56,857][05219] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-12-02 14:19:56,864][05219] LearnerWorker_p0 finished initialization!
[2024-12-02 14:19:56,867][00408] Heartbeat connected on LearnerWorker_p0
[2024-12-02 14:19:56,956][05232] RunningMeanStd input shape: (3, 72, 128)
[2024-12-02 14:19:56,957][05232] RunningMeanStd input shape: (1,)
[2024-12-02 14:19:56,969][05232] ConvEncoder: input_channels=3
[2024-12-02 14:19:57,072][05232] Conv encoder output size: 512
[2024-12-02 14:19:57,072][05232] Policy head output size: 512
[2024-12-02 14:19:57,127][00408] Inference worker 0-0 is ready!
[2024-12-02 14:19:57,128][00408] All inference workers are ready! Signal rollout workers to start!
[2024-12-02 14:19:57,364][05240] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-12-02 14:19:57,370][05237] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-12-02 14:19:57,370][05235] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-12-02 14:19:57,372][05238] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-12-02 14:19:57,366][05239] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-12-02 14:19:57,366][05233] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-12-02 14:19:57,362][05234] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-12-02 14:19:57,379][05236] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-12-02 14:19:58,018][05237] Decorrelating experience for 0 frames...
[2024-12-02 14:19:58,565][05235] Decorrelating experience for 0 frames...
[2024-12-02 14:19:58,570][05240] Decorrelating experience for 0 frames...
[2024-12-02 14:19:58,579][05239] Decorrelating experience for 0 frames...
[2024-12-02 14:19:59,033][05234] Decorrelating experience for 0 frames...
[2024-12-02 14:19:59,668][05237] Decorrelating experience for 32 frames...
[2024-12-02 14:19:59,679][05240] Decorrelating experience for 32 frames...
[2024-12-02 14:19:59,681][05239] Decorrelating experience for 32 frames...
[2024-12-02 14:19:59,779][05238] Decorrelating experience for 0 frames...
[2024-12-02 14:19:59,782][05233] Decorrelating experience for 0 frames...
[2024-12-02 14:20:00,220][05235] Decorrelating experience for 32 frames...
[2024-12-02 14:20:00,781][00408] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2024-12-02 14:20:01,461][05238] Decorrelating experience for 32 frames...
[2024-12-02 14:20:01,463][05236] Decorrelating experience for 0 frames...
[2024-12-02 14:20:01,466][05233] Decorrelating experience for 32 frames...
[2024-12-02 14:20:01,873][05237] Decorrelating experience for 64 frames...
[2024-12-02 14:20:02,035][05239] Decorrelating experience for 64 frames...
[2024-12-02 14:20:02,043][05240] Decorrelating experience for 64 frames...
[2024-12-02 14:20:02,298][05234] Decorrelating experience for 32 frames...
[2024-12-02 14:20:03,373][05236] Decorrelating experience for 32 frames...
[2024-12-02 14:20:03,820][05238] Decorrelating experience for 64 frames...
[2024-12-02 14:20:03,823][05237] Decorrelating experience for 96 frames...
[2024-12-02 14:20:04,115][05233] Decorrelating experience for 64 frames...
[2024-12-02 14:20:04,318][05240] Decorrelating experience for 96 frames...
[2024-12-02 14:20:05,328][05234] Decorrelating experience for 64 frames...
[2024-12-02 14:20:05,781][00408] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2024-12-02 14:20:05,846][05238] Decorrelating experience for 96 frames...
[2024-12-02 14:20:06,029][05235] Decorrelating experience for 64 frames...
[2024-12-02 14:20:06,167][05236] Decorrelating experience for 64 frames...
[2024-12-02 14:20:07,716][05233] Decorrelating experience for 96 frames...
[2024-12-02 14:20:07,916][05234] Decorrelating experience for 96 frames...
[2024-12-02 14:20:08,318][05235] Decorrelating experience for 96 frames...
[2024-12-02 14:20:09,128][05236] Decorrelating experience for 96 frames...
[2024-12-02 14:20:09,953][05239] Decorrelating experience for 96 frames...
[2024-12-02 14:20:10,623][05219] Signal inference workers to stop experience collection...
[2024-12-02 14:20:10,648][05232] InferenceWorker_p0-w0: stopping experience collection
[2024-12-02 14:20:10,781][00408] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 156.8. Samples: 1568. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2024-12-02 14:20:10,783][00408] Avg episode reward: [(0, '2.562')]
[2024-12-02 14:20:13,823][05219] Signal inference workers to resume experience collection...
[2024-12-02 14:20:13,825][05232] InferenceWorker_p0-w0: resuming experience collection
[2024-12-02 14:20:15,781][00408] Fps is (10 sec: 1228.8, 60 sec: 819.2, 300 sec: 819.2). Total num frames: 12288. Throughput: 0: 240.4. Samples: 3606. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2024-12-02 14:20:15,785][00408] Avg episode reward: [(0, '3.063')]
[2024-12-02 14:20:20,782][00408] Fps is (10 sec: 2866.8, 60 sec: 1433.5, 300 sec: 1433.5). Total num frames: 28672. Throughput: 0: 334.2. Samples: 6684. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-12-02 14:20:20,787][00408] Avg episode reward: [(0, '3.658')]
[2024-12-02 14:20:24,187][05232] Updated weights for policy 0, policy_version 10 (0.0158)
[2024-12-02 14:20:25,781][00408] Fps is (10 sec: 3276.8, 60 sec: 1802.2, 300 sec: 1802.2). Total num frames: 45056. Throughput: 0: 439.1. Samples: 10978. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-12-02 14:20:25,784][00408] Avg episode reward: [(0, '4.136')]
[2024-12-02 14:20:30,781][00408] Fps is (10 sec: 3686.9, 60 sec: 2184.5, 300 sec: 2184.5). Total num frames: 65536. Throughput: 0: 573.5. Samples: 17204. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:20:30,783][00408] Avg episode reward: [(0, '4.381')]
[2024-12-02 14:20:33,518][05232] Updated weights for policy 0, policy_version 20 (0.0020)
[2024-12-02 14:20:35,781][00408] Fps is (10 sec: 4096.0, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 86016. Throughput: 0: 591.1. Samples: 20688. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:20:35,783][00408] Avg episode reward: [(0, '4.254')]
[2024-12-02 14:20:40,781][00408] Fps is (10 sec: 3686.4, 60 sec: 2560.0, 300 sec: 2560.0). Total num frames: 102400. Throughput: 0: 635.7. Samples: 25426. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:20:40,787][00408] Avg episode reward: [(0, '4.215')]
[2024-12-02 14:20:40,791][05219] Saving new best policy, reward=4.215!
[2024-12-02 14:20:44,967][05232] Updated weights for policy 0, policy_version 30 (0.0032)
[2024-12-02 14:20:45,781][00408] Fps is (10 sec: 4096.0, 60 sec: 2821.7, 300 sec: 2821.7). Total num frames: 126976. Throughput: 0: 700.5. Samples: 31524. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-12-02 14:20:45,787][00408] Avg episode reward: [(0, '4.506')]
[2024-12-02 14:20:45,802][05219] Saving new best policy, reward=4.506!
[2024-12-02 14:20:50,781][00408] Fps is (10 sec: 4505.6, 60 sec: 2949.1, 300 sec: 2949.1). Total num frames: 147456. Throughput: 0: 777.9. Samples: 35004. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:20:50,784][00408] Avg episode reward: [(0, '4.691')]
[2024-12-02 14:20:50,788][05219] Saving new best policy, reward=4.691!
[2024-12-02 14:20:55,606][05232] Updated weights for policy 0, policy_version 40 (0.0023)
[2024-12-02 14:20:55,781][00408] Fps is (10 sec: 3686.4, 60 sec: 2978.9, 300 sec: 2978.9). Total num frames: 163840. Throughput: 0: 865.2. Samples: 40504. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:20:55,791][00408] Avg episode reward: [(0, '4.691')]
[2024-12-02 14:21:00,781][00408] Fps is (10 sec: 3276.7, 60 sec: 3003.7, 300 sec: 3003.7). Total num frames: 180224. Throughput: 0: 938.5. Samples: 45840. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-12-02 14:21:00,788][00408] Avg episode reward: [(0, '4.363')]
[2024-12-02 14:21:05,095][05232] Updated weights for policy 0, policy_version 50 (0.0023)
[2024-12-02 14:21:05,781][00408] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3150.8). Total num frames: 204800. Throughput: 0: 948.0. Samples: 49344. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:21:05,788][00408] Avg episode reward: [(0, '4.547')]
[2024-12-02 14:21:10,781][00408] Fps is (10 sec: 4505.7, 60 sec: 3754.7, 300 sec: 3218.3). Total num frames: 225280. Throughput: 0: 997.5. Samples: 55866. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:21:10,786][00408] Avg episode reward: [(0, '4.609')]
[2024-12-02 14:21:15,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3167.6). Total num frames: 237568. Throughput: 0: 957.7. Samples: 60300. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-12-02 14:21:15,783][00408] Avg episode reward: [(0, '4.217')]
[2024-12-02 14:21:16,562][05232] Updated weights for policy 0, policy_version 60 (0.0023)
[2024-12-02 14:21:20,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3891.3, 300 sec: 3276.8). Total num frames: 262144. Throughput: 0: 960.3. Samples: 63902. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:21:20,787][00408] Avg episode reward: [(0, '4.381')]
[2024-12-02 14:21:25,422][05232] Updated weights for policy 0, policy_version 70 (0.0016)
[2024-12-02 14:21:25,788][00408] Fps is (10 sec: 4911.5, 60 sec: 4027.2, 300 sec: 3372.9). Total num frames: 286720. Throughput: 0: 1009.9. Samples: 70878. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:21:25,791][00408] Avg episode reward: [(0, '4.474')]
[2024-12-02 14:21:25,806][05219] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000070_286720.pth...
[2024-12-02 14:21:30,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3322.3). Total num frames: 299008. Throughput: 0: 977.3. Samples: 75504. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:21:30,785][00408] Avg episode reward: [(0, '4.415')]
[2024-12-02 14:21:35,782][00408] Fps is (10 sec: 3279.0, 60 sec: 3891.2, 300 sec: 3363.0). Total num frames: 319488. Throughput: 0: 959.7. Samples: 78190. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:21:35,788][00408] Avg episode reward: [(0, '4.433')]
[2024-12-02 14:21:37,091][05232] Updated weights for policy 0, policy_version 80 (0.0022)
[2024-12-02 14:21:40,781][00408] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3399.7). Total num frames: 339968. Throughput: 0: 975.4. Samples: 84396. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:21:40,783][00408] Avg episode reward: [(0, '4.421')]
[2024-12-02 14:21:45,781][00408] Fps is (10 sec: 3686.6, 60 sec: 3822.9, 300 sec: 3393.8). Total num frames: 356352. Throughput: 0: 967.4. Samples: 89372. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-12-02 14:21:45,788][00408] Avg episode reward: [(0, '4.381')]
[2024-12-02 14:21:49,516][05232] Updated weights for policy 0, policy_version 90 (0.0019)
[2024-12-02 14:21:50,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3388.5). Total num frames: 372736. Throughput: 0: 936.4. Samples: 91482. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:21:50,788][00408] Avg episode reward: [(0, '4.484')]
[2024-12-02 14:21:55,784][00408] Fps is (10 sec: 4094.8, 60 sec: 3891.0, 300 sec: 3454.8). Total num frames: 397312. Throughput: 0: 939.1. Samples: 98128. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-12-02 14:21:55,786][00408] Avg episode reward: [(0, '4.698')]
[2024-12-02 14:21:55,794][05219] Saving new best policy, reward=4.698!
[2024-12-02 14:21:58,354][05232] Updated weights for policy 0, policy_version 100 (0.0021)
[2024-12-02 14:22:00,783][00408] Fps is (10 sec: 4095.1, 60 sec: 3891.1, 300 sec: 3447.4). Total num frames: 413696. Throughput: 0: 980.7. Samples: 104432. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-12-02 14:22:00,786][00408] Avg episode reward: [(0, '4.670')]
[2024-12-02 14:22:05,791][00408] Fps is (10 sec: 3274.4, 60 sec: 3754.0, 300 sec: 3440.3). Total num frames: 430080. Throughput: 0: 946.4. Samples: 106500. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:22:05,795][00408] Avg episode reward: [(0, '4.603')]
[2024-12-02 14:22:10,204][05232] Updated weights for policy 0, policy_version 110 (0.0017)
[2024-12-02 14:22:10,781][00408] Fps is (10 sec: 3687.3, 60 sec: 3754.7, 300 sec: 3465.8). Total num frames: 450560. Throughput: 0: 913.4. Samples: 111976. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:22:10,783][00408] Avg episode reward: [(0, '4.721')]
[2024-12-02 14:22:10,786][05219] Saving new best policy, reward=4.721!
[2024-12-02 14:22:15,781][00408] Fps is (10 sec: 4510.4, 60 sec: 3959.5, 300 sec: 3519.5). Total num frames: 475136. Throughput: 0: 960.6. Samples: 118730. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:22:15,786][00408] Avg episode reward: [(0, '4.764')]
[2024-12-02 14:22:15,793][05219] Saving new best policy, reward=4.764!
[2024-12-02 14:22:20,782][00408] Fps is (10 sec: 3686.1, 60 sec: 3754.6, 300 sec: 3481.6). Total num frames: 487424. Throughput: 0: 952.6. Samples: 121056. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:22:20,790][00408] Avg episode reward: [(0, '4.784')]
[2024-12-02 14:22:20,792][05219] Saving new best policy, reward=4.784!
[2024-12-02 14:22:21,879][05232] Updated weights for policy 0, policy_version 120 (0.0044)
[2024-12-02 14:22:25,781][00408] Fps is (10 sec: 2867.2, 60 sec: 3618.6, 300 sec: 3474.5). Total num frames: 503808. Throughput: 0: 912.9. Samples: 125476. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:22:25,786][00408] Avg episode reward: [(0, '4.985')]
[2024-12-02 14:22:25,794][05219] Saving new best policy, reward=4.985!
[2024-12-02 14:22:30,781][00408] Fps is (10 sec: 3686.7, 60 sec: 3754.7, 300 sec: 3495.3). Total num frames: 524288. Throughput: 0: 946.9. Samples: 131982. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:22:30,788][00408] Avg episode reward: [(0, '5.063')]
[2024-12-02 14:22:30,792][05219] Saving new best policy, reward=5.063!
[2024-12-02 14:22:31,748][05232] Updated weights for policy 0, policy_version 130 (0.0026)
[2024-12-02 14:22:35,783][00408] Fps is (10 sec: 4095.0, 60 sec: 3754.6, 300 sec: 3514.6). Total num frames: 544768. Throughput: 0: 970.1. Samples: 135140. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:22:35,788][00408] Avg episode reward: [(0, '4.925')]
[2024-12-02 14:22:40,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3507.2). Total num frames: 561152. Throughput: 0: 916.7. Samples: 139378. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:22:40,783][00408] Avg episode reward: [(0, '5.038')]
[2024-12-02 14:22:43,201][05232] Updated weights for policy 0, policy_version 140 (0.0023)
[2024-12-02 14:22:45,781][00408] Fps is (10 sec: 3687.3, 60 sec: 3754.7, 300 sec: 3525.0). Total num frames: 581632. Throughput: 0: 921.3. Samples: 145890. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:22:45,784][00408] Avg episode reward: [(0, '5.395')]
[2024-12-02 14:22:45,793][05219] Saving new best policy, reward=5.395!
[2024-12-02 14:22:50,782][00408] Fps is (10 sec: 4095.4, 60 sec: 3822.8, 300 sec: 3541.8). Total num frames: 602112. Throughput: 0: 951.0. Samples: 149286. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:22:50,792][00408] Avg episode reward: [(0, '5.372')]
[2024-12-02 14:22:54,087][05232] Updated weights for policy 0, policy_version 150 (0.0030)
[2024-12-02 14:22:55,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3686.6, 300 sec: 3534.3). Total num frames: 618496. Throughput: 0: 936.4. Samples: 154112. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:22:55,788][00408] Avg episode reward: [(0, '5.075')]
[2024-12-02 14:23:00,781][00408] Fps is (10 sec: 3686.9, 60 sec: 3754.8, 300 sec: 3549.9). Total num frames: 638976. Throughput: 0: 914.1. Samples: 159866. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:23:00,785][00408] Avg episode reward: [(0, '5.247')]
[2024-12-02 14:23:04,052][05232] Updated weights for policy 0, policy_version 160 (0.0029)
[2024-12-02 14:23:05,781][00408] Fps is (10 sec: 4095.9, 60 sec: 3823.6, 300 sec: 3564.6). Total num frames: 659456. Throughput: 0: 939.6. Samples: 163336. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:23:05,785][00408] Avg episode reward: [(0, '5.403')]
[2024-12-02 14:23:05,819][05219] Saving new best policy, reward=5.403!
[2024-12-02 14:23:10,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3557.1). Total num frames: 675840. Throughput: 0: 968.4. Samples: 169052. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:23:10,784][00408] Avg episode reward: [(0, '5.529')]
[2024-12-02 14:23:10,786][05219] Saving new best policy, reward=5.529!
[2024-12-02 14:23:15,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3549.9). Total num frames: 692224. Throughput: 0: 929.5. Samples: 173810. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:23:15,788][00408] Avg episode reward: [(0, '5.369')]
[2024-12-02 14:23:15,798][05232] Updated weights for policy 0, policy_version 170 (0.0022)
[2024-12-02 14:23:20,781][00408] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 3584.0). Total num frames: 716800. Throughput: 0: 934.2. Samples: 177178. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
[2024-12-02 14:23:20,788][00408] Avg episode reward: [(0, '5.288')]
[2024-12-02 14:23:25,172][05232] Updated weights for policy 0, policy_version 180 (0.0033)
[2024-12-02 14:23:25,781][00408] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3596.5). Total num frames: 737280. Throughput: 0: 990.0. Samples: 183926. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
[2024-12-02 14:23:25,787][00408] Avg episode reward: [(0, '5.501')]
[2024-12-02 14:23:25,799][05219] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000180_737280.pth...
[2024-12-02 14:23:30,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3569.4). Total num frames: 749568. Throughput: 0: 937.8. Samples: 188092. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
[2024-12-02 14:23:30,788][00408] Avg episode reward: [(0, '5.621')]
[2024-12-02 14:23:30,792][05219] Saving new best policy, reward=5.621!
[2024-12-02 14:23:35,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3823.1, 300 sec: 3600.7). Total num frames: 774144. Throughput: 0: 931.3. Samples: 191194. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:23:35,785][00408] Avg episode reward: [(0, '5.810')]
[2024-12-02 14:23:35,797][05219] Saving new best policy, reward=5.810!
[2024-12-02 14:23:36,588][05232] Updated weights for policy 0, policy_version 190 (0.0019)
[2024-12-02 14:23:40,781][00408] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3611.9). Total num frames: 794624. Throughput: 0: 977.6. Samples: 198102. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:23:40,786][00408] Avg episode reward: [(0, '5.684')]
[2024-12-02 14:23:45,790][00408] Fps is (10 sec: 3683.0, 60 sec: 3822.3, 300 sec: 3604.3). Total num frames: 811008. Throughput: 0: 954.3. Samples: 202818. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:23:45,795][00408] Avg episode reward: [(0, '5.593')]
[2024-12-02 14:23:48,240][05232] Updated weights for policy 0, policy_version 200 (0.0018)
[2024-12-02 14:23:50,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3754.8, 300 sec: 3597.4). Total num frames: 827392. Throughput: 0: 930.7. Samples: 205218. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:23:50,783][00408] Avg episode reward: [(0, '5.803')]
[2024-12-02 14:23:55,781][00408] Fps is (10 sec: 4099.8, 60 sec: 3891.2, 300 sec: 3625.4). Total num frames: 851968. Throughput: 0: 955.9. Samples: 212068. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:23:55,784][00408] Avg episode reward: [(0, '6.399')]
[2024-12-02 14:23:55,796][05219] Saving new best policy, reward=6.399!
[2024-12-02 14:23:57,349][05232] Updated weights for policy 0, policy_version 210 (0.0020)
[2024-12-02 14:24:00,781][00408] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3618.1). Total num frames: 868352. Throughput: 0: 973.6. Samples: 217624. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:24:00,785][00408] Avg episode reward: [(0, '6.043')]
[2024-12-02 14:24:05,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3611.2). Total num frames: 884736. Throughput: 0: 944.5. Samples: 219682. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:24:05,784][00408] Avg episode reward: [(0, '6.253')]
[2024-12-02 14:24:08,943][05232] Updated weights for policy 0, policy_version 220 (0.0022)
[2024-12-02 14:24:10,781][00408] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3637.2). Total num frames: 909312. Throughput: 0: 937.3. Samples: 226104. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:24:10,788][00408] Avg episode reward: [(0, '6.113')]
[2024-12-02 14:24:15,781][00408] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3646.2). Total num frames: 929792. Throughput: 0: 996.4. Samples: 232930. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:24:15,785][00408] Avg episode reward: [(0, '5.694')]
[2024-12-02 14:24:19,526][05232] Updated weights for policy 0, policy_version 230 (0.0030)
[2024-12-02 14:24:20,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3623.4). Total num frames: 942080. Throughput: 0: 973.6. Samples: 235008. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:24:20,784][00408] Avg episode reward: [(0, '5.788')]
[2024-12-02 14:24:25,781][00408] Fps is (10 sec: 3686.3, 60 sec: 3822.9, 300 sec: 3647.8). Total num frames: 966656. Throughput: 0: 945.3. Samples: 240640. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:24:25,783][00408] Avg episode reward: [(0, '5.833')]
[2024-12-02 14:24:29,141][05232] Updated weights for policy 0, policy_version 240 (0.0030)
[2024-12-02 14:24:30,781][00408] Fps is (10 sec: 4915.2, 60 sec: 4027.7, 300 sec: 3671.2). Total num frames: 991232. Throughput: 0: 996.3. Samples: 247640. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:24:30,784][00408] Avg episode reward: [(0, '5.905')]
[2024-12-02 14:24:35,781][00408] Fps is (10 sec: 3686.3, 60 sec: 3822.9, 300 sec: 3649.2). Total num frames: 1003520. Throughput: 0: 1003.6. Samples: 250382. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:24:35,783][00408] Avg episode reward: [(0, '6.358')]
[2024-12-02 14:24:40,441][05232] Updated weights for policy 0, policy_version 250 (0.0017)
[2024-12-02 14:24:40,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3657.1). Total num frames: 1024000. Throughput: 0: 955.8. Samples: 255080. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:24:40,788][00408] Avg episode reward: [(0, '7.028')]
[2024-12-02 14:24:40,790][05219] Saving new best policy, reward=7.028!
[2024-12-02 14:24:45,782][00408] Fps is (10 sec: 4505.8, 60 sec: 3960.1, 300 sec: 3679.2). Total num frames: 1048576. Throughput: 0: 990.1. Samples: 262178. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:24:45,784][00408] Avg episode reward: [(0, '7.633')]
[2024-12-02 14:24:45,790][05219] Saving new best policy, reward=7.633!
[2024-12-02 14:24:49,819][05232] Updated weights for policy 0, policy_version 260 (0.0017)
[2024-12-02 14:24:50,781][00408] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3672.3). Total num frames: 1064960. Throughput: 0: 1018.1. Samples: 265498. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:24:50,785][00408] Avg episode reward: [(0, '7.838')]
[2024-12-02 14:24:50,791][05219] Saving new best policy, reward=7.838!
[2024-12-02 14:24:55,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3665.6). Total num frames: 1081344. Throughput: 0: 971.2. Samples: 269810. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:24:55,786][00408] Avg episode reward: [(0, '7.421')]
[2024-12-02 14:25:00,662][05232] Updated weights for policy 0, policy_version 270 (0.0027)
[2024-12-02 14:25:00,781][00408] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3748.9). Total num frames: 1105920. Throughput: 0: 964.1. Samples: 276314. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:25:00,783][00408] Avg episode reward: [(0, '7.901')]
[2024-12-02 14:25:00,786][05219] Saving new best policy, reward=7.901!
[2024-12-02 14:25:05,782][00408] Fps is (10 sec: 4505.0, 60 sec: 4027.6, 300 sec: 3818.3). Total num frames: 1126400. Throughput: 0: 995.5. Samples: 279806. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-12-02 14:25:05,786][00408] Avg episode reward: [(0, '8.354')]
[2024-12-02 14:25:05,799][05219] Saving new best policy, reward=8.354!
[2024-12-02 14:25:10,783][00408] Fps is (10 sec: 3275.9, 60 sec: 3822.8, 300 sec: 3818.3). Total num frames: 1138688. Throughput: 0: 986.5. Samples: 285034. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-12-02 14:25:10,802][00408] Avg episode reward: [(0, '9.215')]
[2024-12-02 14:25:10,809][05219] Saving new best policy, reward=9.215!
[2024-12-02 14:25:12,469][05232] Updated weights for policy 0, policy_version 280 (0.0013)
[2024-12-02 14:25:15,781][00408] Fps is (10 sec: 3686.9, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 1163264. Throughput: 0: 955.2. Samples: 290624. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-12-02 14:25:15,786][00408] Avg episode reward: [(0, '9.104')]
[2024-12-02 14:25:20,781][00408] Fps is (10 sec: 4506.8, 60 sec: 4027.7, 300 sec: 3860.0). Total num frames: 1183744. Throughput: 0: 971.7. Samples: 294110. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:25:20,786][00408] Avg episode reward: [(0, '9.673')]
[2024-12-02 14:25:20,790][05219] Saving new best policy, reward=9.673!
[2024-12-02 14:25:21,046][05232] Updated weights for policy 0, policy_version 290 (0.0028)
[2024-12-02 14:25:25,781][00408] Fps is (10 sec: 3686.3, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 1200128. Throughput: 0: 1003.4. Samples: 300232. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:25:25,785][00408] Avg episode reward: [(0, '9.353')]
[2024-12-02 14:25:25,797][05219] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000293_1200128.pth...
[2024-12-02 14:25:25,974][05219] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000070_286720.pth
[2024-12-02 14:25:30,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3846.1). Total num frames: 1220608. Throughput: 0: 952.5. Samples: 305040. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:25:30,783][00408] Avg episode reward: [(0, '9.626')]
[2024-12-02 14:25:32,446][05232] Updated weights for policy 0, policy_version 300 (0.0026)
[2024-12-02 14:25:35,781][00408] Fps is (10 sec: 4096.1, 60 sec: 3959.5, 300 sec: 3860.0). Total num frames: 1241088. Throughput: 0: 957.8. Samples: 308600. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:25:35,786][00408] Avg episode reward: [(0, '8.856')]
[2024-12-02 14:25:40,785][00408] Fps is (10 sec: 4503.5, 60 sec: 4027.4, 300 sec: 3859.9). Total num frames: 1265664. Throughput: 0: 1022.2. Samples: 315812. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-12-02 14:25:40,793][00408] Avg episode reward: [(0, '8.758')]
[2024-12-02 14:25:42,165][05232] Updated weights for policy 0, policy_version 310 (0.0024)
[2024-12-02 14:25:45,781][00408] Fps is (10 sec: 3686.2, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 1277952. Throughput: 0: 975.9. Samples: 320228. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-12-02 14:25:45,784][00408] Avg episode reward: [(0, '8.919')]
[2024-12-02 14:25:50,793][00408] Fps is (10 sec: 3683.8, 60 sec: 3958.7, 300 sec: 3859.8). Total num frames: 1302528. Throughput: 0: 966.6. Samples: 323314. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:25:50,796][00408] Avg episode reward: [(0, '9.597')]
[2024-12-02 14:25:52,132][05232] Updated weights for policy 0, policy_version 320 (0.0018)
[2024-12-02 14:25:55,781][00408] Fps is (10 sec: 4915.4, 60 sec: 4096.0, 300 sec: 3887.7). Total num frames: 1327104. Throughput: 0: 1010.4. Samples: 330500. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-12-02 14:25:55,783][00408] Avg episode reward: [(0, '10.264')]
[2024-12-02 14:25:55,789][05219] Saving new best policy, reward=10.264!
[2024-12-02 14:26:00,781][00408] Fps is (10 sec: 3690.6, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 1339392. Throughput: 0: 1001.2. Samples: 335678. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0)
[2024-12-02 14:26:00,786][00408] Avg episode reward: [(0, '10.727')]
[2024-12-02 14:26:00,789][05219] Saving new best policy, reward=10.727!
[2024-12-02 14:26:03,762][05232] Updated weights for policy 0, policy_version 330 (0.0027)
[2024-12-02 14:26:05,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3891.3, 300 sec: 3846.1). Total num frames: 1359872. Throughput: 0: 975.7. Samples: 338018. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2024-12-02 14:26:05,787][00408] Avg episode reward: [(0, '12.009')]
[2024-12-02 14:26:05,796][05219] Saving new best policy, reward=12.009!
[2024-12-02 14:26:10,781][00408] Fps is (10 sec: 4505.8, 60 sec: 4096.2, 300 sec: 3887.7). Total num frames: 1384448. Throughput: 0: 994.9. Samples: 345002. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
[2024-12-02 14:26:10,786][00408] Avg episode reward: [(0, '12.302')]
[2024-12-02 14:26:10,790][05219] Saving new best policy, reward=12.302!
[2024-12-02 14:26:12,411][05232] Updated weights for policy 0, policy_version 340 (0.0021)
[2024-12-02 14:26:15,781][00408] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3860.0). Total num frames: 1400832. Throughput: 0: 1022.9. Samples: 351072. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
[2024-12-02 14:26:15,787][00408] Avg episode reward: [(0, '13.142')]
[2024-12-02 14:26:15,795][05219] Saving new best policy, reward=13.142!
[2024-12-02 14:26:20,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3832.3). Total num frames: 1417216. Throughput: 0: 989.6. Samples: 353130. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:26:20,783][00408] Avg episode reward: [(0, '14.257')]
[2024-12-02 14:26:20,785][05219] Saving new best policy, reward=14.257!
[2024-12-02 14:26:23,699][05232] Updated weights for policy 0, policy_version 350 (0.0016)
[2024-12-02 14:26:25,782][00408] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3873.8). Total num frames: 1441792. Throughput: 0: 970.2. Samples: 359468. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:26:25,785][00408] Avg episode reward: [(0, '13.805')]
[2024-12-02 14:26:30,781][00408] Fps is (10 sec: 4505.4, 60 sec: 4027.7, 300 sec: 3873.8). Total num frames: 1462272. Throughput: 0: 1027.2. Samples: 366454. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:26:30,789][00408] Avg episode reward: [(0, '13.373')]
[2024-12-02 14:26:33,795][05232] Updated weights for policy 0, policy_version 360 (0.0022)
[2024-12-02 14:26:35,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3860.0). Total num frames: 1478656. Throughput: 0: 1005.0. Samples: 368526. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
[2024-12-02 14:26:35,783][00408] Avg episode reward: [(0, '12.954')]
[2024-12-02 14:26:40,781][00408] Fps is (10 sec: 3686.5, 60 sec: 3891.5, 300 sec: 3873.8). Total num frames: 1499136. Throughput: 0: 972.2. Samples: 374250. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
[2024-12-02 14:26:40,783][00408] Avg episode reward: [(0, '13.307')]
[2024-12-02 14:26:43,346][05232] Updated weights for policy 0, policy_version 370 (0.0032)
[2024-12-02 14:26:45,781][00408] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 3901.6). Total num frames: 1523712. Throughput: 0: 1014.1. Samples: 381310. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
[2024-12-02 14:26:45,789][00408] Avg episode reward: [(0, '14.126')]
[2024-12-02 14:26:50,781][00408] Fps is (10 sec: 4096.0, 60 sec: 3960.2, 300 sec: 3873.9). Total num frames: 1540096. Throughput: 0: 1021.7. Samples: 383996. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
[2024-12-02 14:26:50,784][00408] Avg episode reward: [(0, '14.604')]
[2024-12-02 14:26:50,788][05219] Saving new best policy, reward=14.604!
[2024-12-02 14:26:54,941][05232] Updated weights for policy 0, policy_version 380 (0.0032)
[2024-12-02 14:26:55,797][00408] Fps is (10 sec: 3271.6, 60 sec: 3821.9, 300 sec: 3873.7). Total num frames: 1556480. Throughput: 0: 968.5. Samples: 388602. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-12-02 14:26:55,799][00408] Avg episode reward: [(0, '15.415')]
[2024-12-02 14:26:55,864][05219] Saving new best policy, reward=15.415!
[2024-12-02 14:27:00,781][00408] Fps is (10 sec: 4096.0, 60 sec: 4027.8, 300 sec: 3901.8). Total num frames: 1581056. Throughput: 0: 991.0. Samples: 395668. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:27:00,783][00408] Avg episode reward: [(0, '16.166')]
[2024-12-02 14:27:00,788][05219] Saving new best policy, reward=16.166!
[2024-12-02 14:27:04,057][05232] Updated weights for policy 0, policy_version 390 (0.0028)
[2024-12-02 14:27:05,782][00408] Fps is (10 sec: 4512.1, 60 sec: 4027.6, 300 sec: 3901.6). Total num frames: 1601536. Throughput: 0: 1023.3. Samples: 399180. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:27:05,785][00408] Avg episode reward: [(0, '16.876')]
[2024-12-02 14:27:05,794][05219] Saving new best policy, reward=16.876!
[2024-12-02 14:27:10,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 1613824. Throughput: 0: 978.0. Samples: 403478. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:27:10,783][00408] Avg episode reward: [(0, '16.151')]
[2024-12-02 14:27:15,058][05232] Updated weights for policy 0, policy_version 400 (0.0030)
[2024-12-02 14:27:15,781][00408] Fps is (10 sec: 3686.8, 60 sec: 3959.4, 300 sec: 3901.6). Total num frames: 1638400. Throughput: 0: 972.2. Samples: 410202. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:27:15,783][00408] Avg episode reward: [(0, '16.748')]
[2024-12-02 14:27:20,781][00408] Fps is (10 sec: 4915.0, 60 sec: 4096.0, 300 sec: 3929.4). Total num frames: 1662976. Throughput: 0: 1004.4. Samples: 413726. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:27:20,784][00408] Avg episode reward: [(0, '16.497')]
[2024-12-02 14:27:25,781][00408] Fps is (10 sec: 3686.5, 60 sec: 3891.2, 300 sec: 3901.6). Total num frames: 1675264. Throughput: 0: 990.1. Samples: 418806. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:27:25,786][00408] Avg episode reward: [(0, '15.632')]
[2024-12-02 14:27:25,800][05219] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000409_1675264.pth...
[2024-12-02 14:27:25,977][05219] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000180_737280.pth
[2024-12-02 14:27:26,332][05232] Updated weights for policy 0, policy_version 410 (0.0027)
[2024-12-02 14:27:30,781][00408] Fps is (10 sec: 3276.9, 60 sec: 3891.2, 300 sec: 3901.6). Total num frames: 1695744. Throughput: 0: 963.4. Samples: 424664. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:27:30,783][00408] Avg episode reward: [(0, '17.408')]
[2024-12-02 14:27:30,847][05219] Saving new best policy, reward=17.408!
[2024-12-02 14:27:35,137][05232] Updated weights for policy 0, policy_version 420 (0.0028)
[2024-12-02 14:27:35,781][00408] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3929.4). Total num frames: 1720320. Throughput: 0: 982.2. Samples: 428194. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:27:35,784][00408] Avg episode reward: [(0, '16.772')]
[2024-12-02 14:27:40,781][00408] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3915.5). Total num frames: 1736704. Throughput: 0: 1012.0. Samples: 434124. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:27:40,784][00408] Avg episode reward: [(0, '16.341')]
[2024-12-02 14:27:45,783][00408] Fps is (10 sec: 3276.1, 60 sec: 3822.8, 300 sec: 3901.6). Total num frames: 1753088. Throughput: 0: 967.1. Samples: 439192. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:27:45,785][00408] Avg episode reward: [(0, '16.363')]
[2024-12-02 14:27:46,656][05232] Updated weights for policy 0, policy_version 430 (0.0021)
[2024-12-02 14:27:50,784][00408] Fps is (10 sec: 4094.7, 60 sec: 3959.3, 300 sec: 3929.3). Total num frames: 1777664. Throughput: 0: 969.5. Samples: 442808. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:27:50,790][00408] Avg episode reward: [(0, '16.445')]
[2024-12-02 14:27:55,781][00408] Fps is (10 sec: 4506.5, 60 sec: 4028.8, 300 sec: 3929.4). Total num frames: 1798144. Throughput: 0: 1023.3. Samples: 449526. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-12-02 14:27:55,785][00408] Avg episode reward: [(0, '15.759')]
[2024-12-02 14:27:56,383][05232] Updated weights for policy 0, policy_version 440 (0.0020)
[2024-12-02 14:28:00,781][00408] Fps is (10 sec: 3687.6, 60 sec: 3891.2, 300 sec: 3915.5). Total num frames: 1814528. Throughput: 0: 971.7. Samples: 453926. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:28:00,784][00408] Avg episode reward: [(0, '17.205')]
[2024-12-02 14:28:05,781][00408] Fps is (10 sec: 4096.2, 60 sec: 3959.6, 300 sec: 3943.3). Total num frames: 1839104. Throughput: 0: 967.3. Samples: 457256. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:28:05,787][00408] Avg episode reward: [(0, '17.361')]
[2024-12-02 14:28:06,540][05232] Updated weights for policy 0, policy_version 450 (0.0020)
[2024-12-02 14:28:10,781][00408] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 3957.2). Total num frames: 1859584. Throughput: 0: 1015.0. Samples: 464482. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:28:10,785][00408] Avg episode reward: [(0, '17.607')]
[2024-12-02 14:28:10,790][05219] Saving new best policy, reward=17.607!
[2024-12-02 14:28:15,782][00408] Fps is (10 sec: 3685.9, 60 sec: 3959.4, 300 sec: 3929.4). Total num frames: 1875968. Throughput: 0: 996.5. Samples: 469508. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-12-02 14:28:15,785][00408] Avg episode reward: [(0, '17.488')]
[2024-12-02 14:28:17,642][05232] Updated weights for policy 0, policy_version 460 (0.0024)
[2024-12-02 14:28:20,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3929.4). Total num frames: 1896448. Throughput: 0: 979.8. Samples: 472286. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:28:20,789][00408] Avg episode reward: [(0, '17.295')]
[2024-12-02 14:28:25,781][00408] Fps is (10 sec: 4506.2, 60 sec: 4096.0, 300 sec: 3971.0). Total num frames: 1921024. Throughput: 0: 1005.9. Samples: 479390. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:28:25,783][00408] Avg episode reward: [(0, '18.329')]
[2024-12-02 14:28:25,793][05219] Saving new best policy, reward=18.329!
[2024-12-02 14:28:26,213][05232] Updated weights for policy 0, policy_version 470 (0.0021)
[2024-12-02 14:28:30,781][00408] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3943.3). Total num frames: 1937408. Throughput: 0: 1022.9. Samples: 485220. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:28:30,787][00408] Avg episode reward: [(0, '17.483')]
[2024-12-02 14:28:35,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 1957888. Throughput: 0: 989.4. Samples: 487330. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:28:35,785][00408] Avg episode reward: [(0, '18.603')]
[2024-12-02 14:28:35,794][05219] Saving new best policy, reward=18.603!
[2024-12-02 14:28:37,446][05232] Updated weights for policy 0, policy_version 480 (0.0029)
[2024-12-02 14:28:40,781][00408] Fps is (10 sec: 4505.5, 60 sec: 4096.0, 300 sec: 3971.2). Total num frames: 1982464. Throughput: 0: 991.3. Samples: 494136. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:28:40,783][00408] Avg episode reward: [(0, '19.577')]
[2024-12-02 14:28:40,788][05219] Saving new best policy, reward=19.577!
[2024-12-02 14:28:45,788][00408] Fps is (10 sec: 4093.0, 60 sec: 4095.7, 300 sec: 3970.9). Total num frames: 1998848. Throughput: 0: 1040.2. Samples: 500744. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:28:45,791][00408] Avg episode reward: [(0, '20.509')]
[2024-12-02 14:28:45,806][05219] Saving new best policy, reward=20.509!
[2024-12-02 14:28:47,570][05232] Updated weights for policy 0, policy_version 490 (0.0031)
[2024-12-02 14:28:50,783][00408] Fps is (10 sec: 3276.3, 60 sec: 3959.6, 300 sec: 3943.2). Total num frames: 2015232. Throughput: 0: 1010.5. Samples: 502730. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:28:50,785][00408] Avg episode reward: [(0, '19.843')]
[2024-12-02 14:28:55,781][00408] Fps is (10 sec: 3689.1, 60 sec: 3959.5, 300 sec: 3957.2). Total num frames: 2035712. Throughput: 0: 976.1. Samples: 508408. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:28:55,786][00408] Avg episode reward: [(0, '20.218')]
[2024-12-02 14:28:58,192][05232] Updated weights for policy 0, policy_version 500 (0.0026)
[2024-12-02 14:29:00,781][00408] Fps is (10 sec: 4506.4, 60 sec: 4096.0, 300 sec: 3984.9). Total num frames: 2060288. Throughput: 0: 1010.7. Samples: 514990. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:29:00,785][00408] Avg episode reward: [(0, '19.255')]
[2024-12-02 14:29:05,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3943.3). Total num frames: 2072576. Throughput: 0: 1001.3. Samples: 517346. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:29:05,783][00408] Avg episode reward: [(0, '19.154')]
[2024-12-02 14:29:09,921][05232] Updated weights for policy 0, policy_version 510 (0.0019)
[2024-12-02 14:29:10,781][00408] Fps is (10 sec: 2867.2, 60 sec: 3822.9, 300 sec: 3929.4). Total num frames: 2088960. Throughput: 0: 947.2. Samples: 522014. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:29:10,783][00408] Avg episode reward: [(0, '18.953')]
[2024-12-02 14:29:15,781][00408] Fps is (10 sec: 4096.0, 60 sec: 3959.6, 300 sec: 3971.0). Total num frames: 2113536. Throughput: 0: 970.2. Samples: 528878. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:29:15,783][00408] Avg episode reward: [(0, '18.517')]
[2024-12-02 14:29:19,102][05232] Updated weights for policy 0, policy_version 520 (0.0028)
[2024-12-02 14:29:20,784][00408] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3957.2). Total num frames: 2134016. Throughput: 0: 997.7. Samples: 532226. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-12-02 14:29:20,786][00408] Avg episode reward: [(0, '19.169')]
[2024-12-02 14:29:25,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3915.5). Total num frames: 2146304. Throughput: 0: 939.4. Samples: 536408. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-12-02 14:29:25,793][00408] Avg episode reward: [(0, '19.480')]
[2024-12-02 14:29:25,807][05219] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000524_2146304.pth...
[2024-12-02 14:29:25,930][05219] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000293_1200128.pth
[2024-12-02 14:29:30,625][05232] Updated weights for policy 0, policy_version 530 (0.0015)
[2024-12-02 14:29:30,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3957.2). Total num frames: 2170880. Throughput: 0: 932.6. Samples: 542706. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-12-02 14:29:30,786][00408] Avg episode reward: [(0, '19.238')]
[2024-12-02 14:29:35,781][00408] Fps is (10 sec: 4505.7, 60 sec: 3891.2, 300 sec: 3957.2). Total num frames: 2191360. Throughput: 0: 962.5. Samples: 546042. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:29:35,783][00408] Avg episode reward: [(0, '19.326')]
[2024-12-02 14:29:40,784][00408] Fps is (10 sec: 3275.7, 60 sec: 3686.2, 300 sec: 3915.5). Total num frames: 2203648. Throughput: 0: 941.8. Samples: 550794. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:29:40,786][00408] Avg episode reward: [(0, '19.195')]
[2024-12-02 14:29:42,784][05232] Updated weights for policy 0, policy_version 540 (0.0026)
[2024-12-02 14:29:45,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3755.1, 300 sec: 3929.4). Total num frames: 2224128. Throughput: 0: 913.3. Samples: 556088. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:29:45,787][00408] Avg episode reward: [(0, '19.459')]
[2024-12-02 14:29:50,782][00408] Fps is (10 sec: 4097.1, 60 sec: 3823.0, 300 sec: 3943.3). Total num frames: 2244608. Throughput: 0: 933.1. Samples: 559334. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:29:50,784][00408] Avg episode reward: [(0, '19.700')]
[2024-12-02 14:29:52,514][05232] Updated weights for policy 0, policy_version 550 (0.0016)
[2024-12-02 14:29:55,784][00408] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3915.5). Total num frames: 2260992. Throughput: 0: 950.7. Samples: 564796. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:29:55,786][00408] Avg episode reward: [(0, '19.678')]
[2024-12-02 14:30:00,781][00408] Fps is (10 sec: 3277.0, 60 sec: 3618.1, 300 sec: 3901.6). Total num frames: 2277376. Throughput: 0: 901.6. Samples: 569450. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:30:00,784][00408] Avg episode reward: [(0, '19.730')]
[2024-12-02 14:30:04,176][05232] Updated weights for policy 0, policy_version 560 (0.0024)
[2024-12-02 14:30:05,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3929.4). Total num frames: 2297856. Throughput: 0: 903.9. Samples: 572900. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:30:05,784][00408] Avg episode reward: [(0, '17.793')]
[2024-12-02 14:30:10,781][00408] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3915.5). Total num frames: 2318336. Throughput: 0: 960.4. Samples: 579628. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:30:10,783][00408] Avg episode reward: [(0, '17.540')]
[2024-12-02 14:30:15,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3887.7). Total num frames: 2330624. Throughput: 0: 912.8. Samples: 583782. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-12-02 14:30:15,786][00408] Avg episode reward: [(0, '17.420')]
[2024-12-02 14:30:16,045][05232] Updated weights for policy 0, policy_version 570 (0.0017)
[2024-12-02 14:30:20,782][00408] Fps is (10 sec: 3685.9, 60 sec: 3686.3, 300 sec: 3915.5). Total num frames: 2355200. Throughput: 0: 903.8. Samples: 586714. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-12-02 14:30:20,788][00408] Avg episode reward: [(0, '16.983')]
[2024-12-02 14:30:24,996][05232] Updated weights for policy 0, policy_version 580 (0.0033)
[2024-12-02 14:30:25,781][00408] Fps is (10 sec: 4505.7, 60 sec: 3822.9, 300 sec: 3915.5). Total num frames: 2375680. Throughput: 0: 950.4. Samples: 593560. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-12-02 14:30:25,784][00408] Avg episode reward: [(0, '18.221')]
[2024-12-02 14:30:30,781][00408] Fps is (10 sec: 3686.9, 60 sec: 3686.4, 300 sec: 3901.6). Total num frames: 2392064. Throughput: 0: 942.5. Samples: 598500. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:30:30,792][00408] Avg episode reward: [(0, '19.063')]
[2024-12-02 14:30:35,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3887.8). Total num frames: 2412544. Throughput: 0: 918.5. Samples: 600668. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:30:35,785][00408] Avg episode reward: [(0, '18.357')]
[2024-12-02 14:30:36,651][05232] Updated weights for policy 0, policy_version 590 (0.0014)
[2024-12-02 14:30:40,781][00408] Fps is (10 sec: 4096.0, 60 sec: 3823.1, 300 sec: 3915.5). Total num frames: 2433024. Throughput: 0: 951.2. Samples: 607598. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-12-02 14:30:40,787][00408] Avg episode reward: [(0, '18.392')]
[2024-12-02 14:30:45,783][00408] Fps is (10 sec: 3685.5, 60 sec: 3754.5, 300 sec: 3887.9). Total num frames: 2449408. Throughput: 0: 977.2. Samples: 613428. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:30:45,786][00408] Avg episode reward: [(0, '19.524')]
[2024-12-02 14:30:47,428][05232] Updated weights for policy 0, policy_version 600 (0.0018)
[2024-12-02 14:30:50,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3860.0). Total num frames: 2465792. Throughput: 0: 945.8. Samples: 615462. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:30:50,787][00408] Avg episode reward: [(0, '19.390')]
[2024-12-02 14:30:55,781][00408] Fps is (10 sec: 3687.3, 60 sec: 3754.7, 300 sec: 3887.7). Total num frames: 2486272. Throughput: 0: 929.2. Samples: 621444. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-12-02 14:30:55,786][00408] Avg episode reward: [(0, '19.286')]
[2024-12-02 14:30:57,530][05232] Updated weights for policy 0, policy_version 610 (0.0015)
[2024-12-02 14:31:00,781][00408] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3901.6). Total num frames: 2510848. Throughput: 0: 986.9. Samples: 628194. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-12-02 14:31:00,786][00408] Avg episode reward: [(0, '21.202')]
[2024-12-02 14:31:00,788][05219] Saving new best policy, reward=21.202!
[2024-12-02 14:31:05,781][00408] Fps is (10 sec: 3686.2, 60 sec: 3754.6, 300 sec: 3860.0). Total num frames: 2523136. Throughput: 0: 964.7. Samples: 630126. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-12-02 14:31:05,786][00408] Avg episode reward: [(0, '21.847')]
[2024-12-02 14:31:05,809][05219] Saving new best policy, reward=21.847!
[2024-12-02 14:31:09,335][05232] Updated weights for policy 0, policy_version 620 (0.0015)
[2024-12-02 14:31:10,781][00408] Fps is (10 sec: 3276.7, 60 sec: 3754.7, 300 sec: 3873.8). Total num frames: 2543616. Throughput: 0: 927.1. Samples: 635278. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:31:10,786][00408] Avg episode reward: [(0, '22.398')]
[2024-12-02 14:31:10,792][05219] Saving new best policy, reward=22.398!
[2024-12-02 14:31:15,781][00408] Fps is (10 sec: 4505.7, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 2568192. Throughput: 0: 966.7. Samples: 642002. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-12-02 14:31:15,786][00408] Avg episode reward: [(0, '21.618')]
[2024-12-02 14:31:19,259][05232] Updated weights for policy 0, policy_version 630 (0.0018)
[2024-12-02 14:31:20,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3860.0). Total num frames: 2580480. Throughput: 0: 981.8. Samples: 644850. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:31:20,784][00408] Avg episode reward: [(0, '23.293')]
[2024-12-02 14:31:20,820][05219] Saving new best policy, reward=23.293!
[2024-12-02 14:31:25,782][00408] Fps is (10 sec: 3276.6, 60 sec: 3754.6, 300 sec: 3860.0). Total num frames: 2600960. Throughput: 0: 917.1. Samples: 648870. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-12-02 14:31:25,786][00408] Avg episode reward: [(0, '23.979')]
[2024-12-02 14:31:25,802][05219] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000635_2600960.pth...
[2024-12-02 14:31:25,934][05219] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000409_1675264.pth
[2024-12-02 14:31:25,952][05219] Saving new best policy, reward=23.979!
[2024-12-02 14:31:30,519][05232] Updated weights for policy 0, policy_version 640 (0.0033)
[2024-12-02 14:31:30,781][00408] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3873.8). Total num frames: 2621440. Throughput: 0: 935.9. Samples: 655540. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-12-02 14:31:30,783][00408] Avg episode reward: [(0, '22.099')]
[2024-12-02 14:31:35,782][00408] Fps is (10 sec: 4095.9, 60 sec: 3822.9, 300 sec: 3873.8). Total num frames: 2641920. Throughput: 0: 966.2. Samples: 658940. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:31:35,791][00408] Avg episode reward: [(0, '20.832')]
[2024-12-02 14:31:40,782][00408] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3832.2). Total num frames: 2654208. Throughput: 0: 933.0. Samples: 663428. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:31:40,784][00408] Avg episode reward: [(0, '21.502')]
[2024-12-02 14:31:42,267][05232] Updated weights for policy 0, policy_version 650 (0.0017)
[2024-12-02 14:31:45,781][00408] Fps is (10 sec: 3686.8, 60 sec: 3823.1, 300 sec: 3860.0). Total num frames: 2678784. Throughput: 0: 919.5. Samples: 669572. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-12-02 14:31:45,783][00408] Avg episode reward: [(0, '21.556')]
[2024-12-02 14:31:50,781][00408] Fps is (10 sec: 4505.9, 60 sec: 3891.2, 300 sec: 3874.1). Total num frames: 2699264. Throughput: 0: 953.9. Samples: 673050. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-12-02 14:31:50,788][00408] Avg episode reward: [(0, '21.463')]
[2024-12-02 14:31:51,369][05232] Updated weights for policy 0, policy_version 660 (0.0014)
[2024-12-02 14:31:55,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3832.2). Total num frames: 2711552. Throughput: 0: 958.4. Samples: 678404. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-12-02 14:31:55,788][00408] Avg episode reward: [(0, '21.492')]
[2024-12-02 14:32:00,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3832.2). Total num frames: 2732032. Throughput: 0: 923.5. Samples: 683558. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:32:00,790][00408] Avg episode reward: [(0, '21.390')]
[2024-12-02 14:32:03,014][05232] Updated weights for policy 0, policy_version 670 (0.0013)
[2024-12-02 14:32:05,781][00408] Fps is (10 sec: 4505.5, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 2756608. Throughput: 0: 936.3. Samples: 686982. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-12-02 14:32:05,785][00408] Avg episode reward: [(0, '20.620')]
[2024-12-02 14:32:10,785][00408] Fps is (10 sec: 4094.5, 60 sec: 3822.7, 300 sec: 3846.0). Total num frames: 2772992. Throughput: 0: 988.4. Samples: 693352. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:32:10,786][00408] Avg episode reward: [(0, '19.608')]
[2024-12-02 14:32:14,614][05232] Updated weights for policy 0, policy_version 680 (0.0027)
[2024-12-02 14:32:15,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3818.3). Total num frames: 2789376. Throughput: 0: 935.6. Samples: 697644. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:32:15,787][00408] Avg episode reward: [(0, '20.608')]
[2024-12-02 14:32:20,781][00408] Fps is (10 sec: 4097.5, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 2813952. Throughput: 0: 936.2. Samples: 701068. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:32:20,785][00408] Avg episode reward: [(0, '20.182')]
[2024-12-02 14:32:23,637][05232] Updated weights for policy 0, policy_version 690 (0.0017)
[2024-12-02 14:32:25,781][00408] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 3846.1). Total num frames: 2830336. Throughput: 0: 986.4. Samples: 707814. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:32:25,783][00408] Avg episode reward: [(0, '19.830')]
[2024-12-02 14:32:30,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 2846720. Throughput: 0: 946.8. Samples: 712176. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:32:30,783][00408] Avg episode reward: [(0, '20.173')]
[2024-12-02 14:32:35,545][05232] Updated weights for policy 0, policy_version 700 (0.0014)
[2024-12-02 14:32:35,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3832.2). Total num frames: 2867200. Throughput: 0: 926.8. Samples: 714758. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:32:35,787][00408] Avg episode reward: [(0, '20.859')]
[2024-12-02 14:32:40,781][00408] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 2887680. Throughput: 0: 958.9. Samples: 721554. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:32:40,788][00408] Avg episode reward: [(0, '20.941')]
[2024-12-02 14:32:45,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 2904064. Throughput: 0: 956.1. Samples: 726584. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:32:45,788][00408] Avg episode reward: [(0, '20.413')]
[2024-12-02 14:32:46,894][05232] Updated weights for policy 0, policy_version 710 (0.0028)
[2024-12-02 14:32:50,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3804.4). Total num frames: 2920448. Throughput: 0: 924.5. Samples: 728584. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:32:50,783][00408] Avg episode reward: [(0, '21.638')]
[2024-12-02 14:32:55,781][00408] Fps is (10 sec: 3686.3, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 2940928. Throughput: 0: 920.5. Samples: 734772. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:32:55,786][00408] Avg episode reward: [(0, '22.265')]
[2024-12-02 14:32:56,981][05232] Updated weights for policy 0, policy_version 720 (0.0021)
[2024-12-02 14:33:00,783][00408] Fps is (10 sec: 4095.0, 60 sec: 3822.8, 300 sec: 3804.4). Total num frames: 2961408. Throughput: 0: 956.7. Samples: 740700. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:33:00,786][00408] Avg episode reward: [(0, '21.935')]
[2024-12-02 14:33:05,781][00408] Fps is (10 sec: 3276.9, 60 sec: 3618.1, 300 sec: 3776.7). Total num frames: 2973696. Throughput: 0: 922.6. Samples: 742584. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:33:05,786][00408] Avg episode reward: [(0, '22.536')]
[2024-12-02 14:33:09,278][05232] Updated weights for policy 0, policy_version 730 (0.0027)
[2024-12-02 14:33:10,781][00408] Fps is (10 sec: 3277.6, 60 sec: 3686.6, 300 sec: 3790.6). Total num frames: 2994176. Throughput: 0: 891.7. Samples: 747940. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-12-02 14:33:10,786][00408] Avg episode reward: [(0, '23.033')]
[2024-12-02 14:33:15,782][00408] Fps is (10 sec: 4095.4, 60 sec: 3754.6, 300 sec: 3790.5). Total num frames: 3014656. Throughput: 0: 938.8. Samples: 754424. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:33:15,788][00408] Avg episode reward: [(0, '23.956')]
[2024-12-02 14:33:20,721][05232] Updated weights for policy 0, policy_version 740 (0.0030)
[2024-12-02 14:33:20,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3762.8). Total num frames: 3031040. Throughput: 0: 930.6. Samples: 756634. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:33:20,784][00408] Avg episode reward: [(0, '23.246')]
[2024-12-02 14:33:25,781][00408] Fps is (10 sec: 3277.3, 60 sec: 3618.1, 300 sec: 3762.8). Total num frames: 3047424. Throughput: 0: 882.3. Samples: 761258. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:33:25,783][00408] Avg episode reward: [(0, '23.635')]
[2024-12-02 14:33:25,795][05219] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000744_3047424.pth...
[2024-12-02 14:33:25,923][05219] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000524_2146304.pth
[2024-12-02 14:33:30,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3762.8). Total num frames: 3067904. Throughput: 0: 917.0. Samples: 767850. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:33:30,783][00408] Avg episode reward: [(0, '23.695')]
[2024-12-02 14:33:30,860][05232] Updated weights for policy 0, policy_version 750 (0.0015)
[2024-12-02 14:33:35,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3735.0). Total num frames: 3084288. Throughput: 0: 938.9. Samples: 770834. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:33:35,785][00408] Avg episode reward: [(0, '23.507')]
[2024-12-02 14:33:40,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3735.1). Total num frames: 3100672. Throughput: 0: 890.2. Samples: 774832. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:33:40,783][00408] Avg episode reward: [(0, '24.287')]
[2024-12-02 14:33:40,785][05219] Saving new best policy, reward=24.287!
[2024-12-02 14:33:43,009][05232] Updated weights for policy 0, policy_version 760 (0.0025)
[2024-12-02 14:33:45,781][00408] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3762.8). Total num frames: 3125248. Throughput: 0: 900.8. Samples: 781232. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:33:45,783][00408] Avg episode reward: [(0, '22.718')]
[2024-12-02 14:33:50,781][00408] Fps is (10 sec: 4505.4, 60 sec: 3754.6, 300 sec: 3762.8). Total num frames: 3145728. Throughput: 0: 934.1. Samples: 784618. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-12-02 14:33:50,786][00408] Avg episode reward: [(0, '23.233')]
[2024-12-02 14:33:53,939][05232] Updated weights for policy 0, policy_version 770 (0.0020)
[2024-12-02 14:33:55,781][00408] Fps is (10 sec: 3276.7, 60 sec: 3618.1, 300 sec: 3721.1). Total num frames: 3158016. Throughput: 0: 916.6. Samples: 789188. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-12-02 14:33:55,787][00408] Avg episode reward: [(0, '23.468')]
[2024-12-02 14:34:00,781][00408] Fps is (10 sec: 3276.9, 60 sec: 3618.3, 300 sec: 3748.9). Total num frames: 3178496. Throughput: 0: 897.0. Samples: 794788. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:34:00,788][00408] Avg episode reward: [(0, '24.125')]
[2024-12-02 14:34:04,237][05232] Updated weights for policy 0, policy_version 780 (0.0022)
[2024-12-02 14:34:05,781][00408] Fps is (10 sec: 4096.2, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 3198976. Throughput: 0: 920.8. Samples: 798068. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:34:05,783][00408] Avg episode reward: [(0, '22.920')]
[2024-12-02 14:34:10,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 3215360. Throughput: 0: 937.0. Samples: 803424. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-12-02 14:34:10,786][00408] Avg episode reward: [(0, '23.999')]
[2024-12-02 14:34:15,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3721.1). Total num frames: 3231744. Throughput: 0: 895.0. Samples: 808126. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:34:15,788][00408] Avg episode reward: [(0, '25.354')]
[2024-12-02 14:34:15,800][05219] Saving new best policy, reward=25.354!
[2024-12-02 14:34:16,565][05232] Updated weights for policy 0, policy_version 790 (0.0014)
[2024-12-02 14:34:20,781][00408] Fps is (10 sec: 3686.3, 60 sec: 3686.4, 300 sec: 3748.9). Total num frames: 3252224. Throughput: 0: 898.7. Samples: 811274. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:34:20,786][00408] Avg episode reward: [(0, '23.741')]
[2024-12-02 14:34:25,784][00408] Fps is (10 sec: 3685.1, 60 sec: 3686.2, 300 sec: 3721.1). Total num frames: 3268608. Throughput: 0: 946.9. Samples: 817448. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:34:25,788][00408] Avg episode reward: [(0, '24.187')]
[2024-12-02 14:34:27,797][05232] Updated weights for policy 0, policy_version 800 (0.0023)
[2024-12-02 14:34:30,781][00408] Fps is (10 sec: 2867.3, 60 sec: 3549.9, 300 sec: 3693.3). Total num frames: 3280896. Throughput: 0: 889.4. Samples: 821254. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:34:30,784][00408] Avg episode reward: [(0, '23.986')]
[2024-12-02 14:34:35,781][00408] Fps is (10 sec: 3687.7, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 3305472. Throughput: 0: 878.8. Samples: 824162. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-12-02 14:34:35,783][00408] Avg episode reward: [(0, '22.945')]
[2024-12-02 14:34:38,691][05232] Updated weights for policy 0, policy_version 810 (0.0016)
[2024-12-02 14:34:40,781][00408] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 3325952. Throughput: 0: 920.3. Samples: 830602. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-12-02 14:34:40,787][00408] Avg episode reward: [(0, '23.460')]
[2024-12-02 14:34:45,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3707.2). Total num frames: 3338240. Throughput: 0: 897.4. Samples: 835172. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:34:45,783][00408] Avg episode reward: [(0, '23.694')]
[2024-12-02 14:34:50,781][00408] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3707.2). Total num frames: 3354624. Throughput: 0: 875.3. Samples: 837458. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:34:50,783][00408] Avg episode reward: [(0, '23.708')]
[2024-12-02 14:34:50,801][05232] Updated weights for policy 0, policy_version 820 (0.0027)
[2024-12-02 14:34:55,781][00408] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 3379200. Throughput: 0: 900.8. Samples: 843960. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:34:55,788][00408] Avg episode reward: [(0, '23.543')]
[2024-12-02 14:35:00,783][00408] Fps is (10 sec: 4095.0, 60 sec: 3618.0, 300 sec: 3721.1). Total num frames: 3395584. Throughput: 0: 910.9. Samples: 849120. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:35:00,791][00408] Avg episode reward: [(0, '24.361')]
[2024-12-02 14:35:02,293][05232] Updated weights for policy 0, policy_version 830 (0.0029)
[2024-12-02 14:35:05,781][00408] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3693.3). Total num frames: 3407872. Throughput: 0: 883.1. Samples: 851012. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:35:05,783][00408] Avg episode reward: [(0, '24.606')]
[2024-12-02 14:35:10,781][00408] Fps is (10 sec: 3687.2, 60 sec: 3618.1, 300 sec: 3735.0). Total num frames: 3432448. Throughput: 0: 875.3. Samples: 856832. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:35:10,784][00408] Avg episode reward: [(0, '22.588')]
[2024-12-02 14:35:12,703][05232] Updated weights for policy 0, policy_version 840 (0.0013)
[2024-12-02 14:35:15,781][00408] Fps is (10 sec: 4095.9, 60 sec: 3618.1, 300 sec: 3707.2). Total num frames: 3448832. Throughput: 0: 928.7. Samples: 863044. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:35:15,799][00408] Avg episode reward: [(0, '22.576')]
[2024-12-02 14:35:20,781][00408] Fps is (10 sec: 2867.3, 60 sec: 3481.6, 300 sec: 3679.5). Total num frames: 3461120. Throughput: 0: 906.4. Samples: 864948. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:35:20,783][00408] Avg episode reward: [(0, '23.154')]
[2024-12-02 14:35:24,960][05232] Updated weights for policy 0, policy_version 850 (0.0027)
[2024-12-02 14:35:25,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3550.1, 300 sec: 3693.3). Total num frames: 3481600. Throughput: 0: 878.0. Samples: 870110. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:35:25,783][00408] Avg episode reward: [(0, '22.189')]
[2024-12-02 14:35:25,790][05219] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000850_3481600.pth...
[2024-12-02 14:35:25,944][05219] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000635_2600960.pth
[2024-12-02 14:35:30,781][00408] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 3502080. Throughput: 0: 914.5. Samples: 876326. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:35:30,785][00408] Avg episode reward: [(0, '23.324')]
[2024-12-02 14:35:35,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3679.5). Total num frames: 3518464. Throughput: 0: 918.0. Samples: 878770. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-12-02 14:35:35,785][00408] Avg episode reward: [(0, '23.021')]
[2024-12-02 14:35:36,885][05232] Updated weights for policy 0, policy_version 860 (0.0027)
[2024-12-02 14:35:40,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3679.5). Total num frames: 3534848. Throughput: 0: 865.9. Samples: 882926. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:35:40,786][00408] Avg episode reward: [(0, '23.425')]
[2024-12-02 14:35:45,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3693.3). Total num frames: 3555328. Throughput: 0: 895.4. Samples: 889410. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-12-02 14:35:45,789][00408] Avg episode reward: [(0, '23.467')]
[2024-12-02 14:35:47,022][05232] Updated weights for policy 0, policy_version 870 (0.0026)
[2024-12-02 14:35:50,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3679.5). Total num frames: 3571712. Throughput: 0: 924.8. Samples: 892630. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:35:50,785][00408] Avg episode reward: [(0, '23.567')]
[2024-12-02 14:35:55,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3651.7). Total num frames: 3588096. Throughput: 0: 885.2. Samples: 896664. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-12-02 14:35:55,784][00408] Avg episode reward: [(0, '23.856')]
[2024-12-02 14:35:59,416][05232] Updated weights for policy 0, policy_version 880 (0.0023)
[2024-12-02 14:36:00,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3550.0, 300 sec: 3679.5). Total num frames: 3608576. Throughput: 0: 877.8. Samples: 902544. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:36:00,783][00408] Avg episode reward: [(0, '25.074')]
[2024-12-02 14:36:05,790][00408] Fps is (10 sec: 4092.2, 60 sec: 3685.8, 300 sec: 3679.3). Total num frames: 3629056. Throughput: 0: 908.1. Samples: 905820. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:36:05,793][00408] Avg episode reward: [(0, '25.548')]
[2024-12-02 14:36:05,804][05219] Saving new best policy, reward=25.548!
[2024-12-02 14:36:10,786][00408] Fps is (10 sec: 3275.1, 60 sec: 3481.3, 300 sec: 3637.7). Total num frames: 3641344. Throughput: 0: 900.6. Samples: 910640. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-12-02 14:36:10,788][00408] Avg episode reward: [(0, '25.853')]
[2024-12-02 14:36:10,791][05219] Saving new best policy, reward=25.853!
[2024-12-02 14:36:11,169][05232] Updated weights for policy 0, policy_version 890 (0.0019)
[2024-12-02 14:36:15,781][00408] Fps is (10 sec: 3279.9, 60 sec: 3549.9, 300 sec: 3665.6). Total num frames: 3661824. Throughput: 0: 874.5. Samples: 915680. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
[2024-12-02 14:36:15,784][00408] Avg episode reward: [(0, '26.300')]
[2024-12-02 14:36:15,791][05219] Saving new best policy, reward=26.300!
[2024-12-02 14:36:20,781][00408] Fps is (10 sec: 4098.1, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3682304. Throughput: 0: 890.3. Samples: 918834. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:36:20,784][00408] Avg episode reward: [(0, '26.805')]
[2024-12-02 14:36:20,789][05219] Saving new best policy, reward=26.805!
[2024-12-02 14:36:21,353][05232] Updated weights for policy 0, policy_version 900 (0.0014)
[2024-12-02 14:36:25,783][00408] Fps is (10 sec: 3685.6, 60 sec: 3618.0, 300 sec: 3651.7). Total num frames: 3698688. Throughput: 0: 923.9. Samples: 924502. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:36:25,786][00408] Avg episode reward: [(0, '27.011')]
[2024-12-02 14:36:25,804][05219] Saving new best policy, reward=27.011!
[2024-12-02 14:36:30,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 3715072. Throughput: 0: 874.2. Samples: 928748. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-12-02 14:36:30,785][00408] Avg episode reward: [(0, '24.998')]
[2024-12-02 14:36:33,610][05232] Updated weights for policy 0, policy_version 910 (0.0029)
[2024-12-02 14:36:35,781][00408] Fps is (10 sec: 3687.1, 60 sec: 3618.1, 300 sec: 3665.6). Total num frames: 3735552. Throughput: 0: 874.4. Samples: 931976. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:36:35,788][00408] Avg episode reward: [(0, '24.624')]
[2024-12-02 14:36:40,784][00408] Fps is (10 sec: 4094.5, 60 sec: 3686.2, 300 sec: 3651.6). Total num frames: 3756032. Throughput: 0: 931.0. Samples: 938564. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:36:40,789][00408] Avg episode reward: [(0, '25.589')]
[2024-12-02 14:36:45,137][05232] Updated weights for policy 0, policy_version 920 (0.0014)
[2024-12-02 14:36:45,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3623.9). Total num frames: 3768320. Throughput: 0: 890.5. Samples: 942616. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:36:45,785][00408] Avg episode reward: [(0, '24.784')]
[2024-12-02 14:36:50,781][00408] Fps is (10 sec: 3278.0, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 3788800. Throughput: 0: 879.7. Samples: 945396. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:36:50,787][00408] Avg episode reward: [(0, '23.922')]
[2024-12-02 14:36:55,105][05232] Updated weights for policy 0, policy_version 930 (0.0018)
[2024-12-02 14:36:55,781][00408] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 3809280. Throughput: 0: 917.4. Samples: 951918. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-12-02 14:36:55,788][00408] Avg episode reward: [(0, '24.386')]
[2024-12-02 14:37:00,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 3825664. Throughput: 0: 911.2. Samples: 956684. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:37:00,784][00408] Avg episode reward: [(0, '24.777')]
[2024-12-02 14:37:05,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3550.4, 300 sec: 3624.0). Total num frames: 3842048. Throughput: 0: 885.8. Samples: 958694. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:37:05,788][00408] Avg episode reward: [(0, '26.646')]
[2024-12-02 14:37:07,423][05232] Updated weights for policy 0, policy_version 940 (0.0023)
[2024-12-02 14:37:10,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3686.7, 300 sec: 3637.8). Total num frames: 3862528. Throughput: 0: 898.1. Samples: 964916. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:37:10,787][00408] Avg episode reward: [(0, '25.771')]
[2024-12-02 14:37:15,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 3878912. Throughput: 0: 934.1. Samples: 970784. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:37:15,784][00408] Avg episode reward: [(0, '25.065')]
[2024-12-02 14:37:19,081][05232] Updated weights for policy 0, policy_version 950 (0.0030)
[2024-12-02 14:37:20,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 3895296. Throughput: 0: 904.7. Samples: 972686. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:37:20,788][00408] Avg episode reward: [(0, '26.192')]
[2024-12-02 14:37:25,781][00408] Fps is (10 sec: 3686.4, 60 sec: 3618.3, 300 sec: 3623.9). Total num frames: 3915776. Throughput: 0: 882.0. Samples: 978250. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-12-02 14:37:25,783][00408] Avg episode reward: [(0, '25.592')]
[2024-12-02 14:37:25,793][05219] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000956_3915776.pth...
[2024-12-02 14:37:25,918][05219] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000744_3047424.pth
[2024-12-02 14:37:29,493][05232] Updated weights for policy 0, policy_version 960 (0.0033)
[2024-12-02 14:37:30,781][00408] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 3936256. Throughput: 0: 930.4. Samples: 984482. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
[2024-12-02 14:37:30,789][00408] Avg episode reward: [(0, '26.031')]
[2024-12-02 14:37:35,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 3948544. Throughput: 0: 913.6. Samples: 986506. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-12-02 14:37:35,783][00408] Avg episode reward: [(0, '24.011')]
[2024-12-02 14:37:40,781][00408] Fps is (10 sec: 3276.8, 60 sec: 3550.1, 300 sec: 3610.0). Total num frames: 3969024. Throughput: 0: 875.7. Samples: 991326. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-12-02 14:37:40,783][00408] Avg episode reward: [(0, '24.704')]
[2024-12-02 14:37:41,498][05232] Updated weights for policy 0, policy_version 970 (0.0015)
[2024-12-02 14:37:45,781][00408] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 3989504. Throughput: 0: 914.0. Samples: 997816. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-12-02 14:37:45,784][00408] Avg episode reward: [(0, '24.803')]
[2024-12-02 14:37:49,963][05219] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2024-12-02 14:37:49,973][05219] Stopping Batcher_0...
[2024-12-02 14:37:49,973][05219] Loop batcher_evt_loop terminating...
[2024-12-02 14:37:49,973][00408] Component Batcher_0 stopped!
[2024-12-02 14:37:50,080][05232] Weights refcount: 2 0
[2024-12-02 14:37:50,082][00408] Component InferenceWorker_p0-w0 stopped!
[2024-12-02 14:37:50,085][05232] Stopping InferenceWorker_p0-w0...
[2024-12-02 14:37:50,086][05232] Loop inference_proc0-0_evt_loop terminating...
[2024-12-02 14:37:50,104][05219] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000850_3481600.pth
[2024-12-02 14:37:50,119][05219] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2024-12-02 14:37:50,391][00408] Component LearnerWorker_p0 stopped!
[2024-12-02 14:37:50,393][05219] Stopping LearnerWorker_p0...
[2024-12-02 14:37:50,400][05219] Loop learner_proc0_evt_loop terminating...
[2024-12-02 14:37:50,644][05237] Stopping RolloutWorker_w4...
[2024-12-02 14:37:50,651][00408] Component RolloutWorker_w4 stopped!
[2024-12-02 14:37:50,649][05233] Stopping RolloutWorker_w0...
[2024-12-02 14:37:50,653][00408] Component RolloutWorker_w0 stopped!
[2024-12-02 14:37:50,646][05237] Loop rollout_proc4_evt_loop terminating...
[2024-12-02 14:37:50,671][00408] Component RolloutWorker_w2 stopped!
[2024-12-02 14:37:50,671][05236] Stopping RolloutWorker_w2...
[2024-12-02 14:37:50,664][05233] Loop rollout_proc0_evt_loop terminating...
[2024-12-02 14:37:50,684][05238] Stopping RolloutWorker_w6...
[2024-12-02 14:37:50,687][05239] Stopping RolloutWorker_w5...
[2024-12-02 14:37:50,690][05238] Loop rollout_proc6_evt_loop terminating...
[2024-12-02 14:37:50,690][00408] Component RolloutWorker_w6 stopped!
[2024-12-02 14:37:50,701][00408] Component RolloutWorker_w5 stopped!
[2024-12-02 14:37:50,699][05239] Loop rollout_proc5_evt_loop terminating...
[2024-12-02 14:37:50,700][05234] Stopping RolloutWorker_w1...
[2024-12-02 14:37:50,705][05234] Loop rollout_proc1_evt_loop terminating...
[2024-12-02 14:37:50,682][05236] Loop rollout_proc2_evt_loop terminating...
[2024-12-02 14:37:50,704][00408] Component RolloutWorker_w1 stopped!
[2024-12-02 14:37:50,714][05235] Stopping RolloutWorker_w3...
[2024-12-02 14:37:50,715][05235] Loop rollout_proc3_evt_loop terminating...
[2024-12-02 14:37:50,714][00408] Component RolloutWorker_w3 stopped!
[2024-12-02 14:37:50,760][05240] Stopping RolloutWorker_w7...
[2024-12-02 14:37:50,761][05240] Loop rollout_proc7_evt_loop terminating...
[2024-12-02 14:37:50,760][00408] Component RolloutWorker_w7 stopped!
[2024-12-02 14:37:50,774][00408] Waiting for process learner_proc0 to stop...
[2024-12-02 14:37:52,785][00408] Waiting for process inference_proc0-0 to join...
[2024-12-02 14:37:52,895][00408] Waiting for process rollout_proc0 to join...
[2024-12-02 14:37:55,135][00408] Waiting for process rollout_proc1 to join...
[2024-12-02 14:37:55,139][00408] Waiting for process rollout_proc2 to join...
[2024-12-02 14:37:55,144][00408] Waiting for process rollout_proc3 to join...
[2024-12-02 14:37:55,148][00408] Waiting for process rollout_proc4 to join...
[2024-12-02 14:37:55,152][00408] Waiting for process rollout_proc5 to join...
[2024-12-02 14:37:55,155][00408] Waiting for process rollout_proc6 to join...
[2024-12-02 14:37:55,157][00408] Waiting for process rollout_proc7 to join...
[2024-12-02 14:37:55,163][00408] Batcher 0 profile tree view:
batching: 26.6184, releasing_batches: 0.0312
[2024-12-02 14:37:55,164][00408] InferenceWorker_p0-w0 profile tree view:
wait_policy: 0.0001
  wait_policy_total: 433.0231
update_model: 8.7533
  weight_update: 0.0030
one_step: 0.0100
  handle_policy_step: 584.1202
    deserialize: 14.8749, stack: 3.2133, obs_to_device_normalize: 123.0175, forward: 294.7832, send_messages: 29.0472
    prepare_outputs: 89.8354
      to_cpu: 53.7355
[2024-12-02 14:37:55,167][00408] Learner 0 profile tree view:
misc: 0.0085, prepare_batch: 13.4648
train: 73.4102
  epoch_init: 0.0174, minibatch_init: 0.0165, losses_postprocess: 0.6568, kl_divergence: 0.6849, after_optimizer: 33.6634
  calculate_losses: 25.8693
    losses_init: 0.0037, forward_head: 1.2502, bptt_initial: 17.1990, tail: 1.0272, advantages_returns: 0.2459, losses: 3.9098
    bptt: 1.8937
      bptt_forward_core: 1.8177
  update: 11.8033
    clip: 0.8598
[2024-12-02 14:37:55,170][00408] RolloutWorker_w0 profile tree view:
wait_for_trajectories: 0.3633, enqueue_policy_requests: 105.1592, env_step: 836.6398, overhead: 13.5901, complete_rollouts: 8.2049
save_policy_outputs: 20.8465
  split_output_tensors: 8.5305
[2024-12-02 14:37:55,171][00408] RolloutWorker_w7 profile tree view:
wait_for_trajectories: 0.4384, enqueue_policy_requests: 107.9246, env_step: 834.0598, overhead: 14.0801, complete_rollouts: 6.6816
save_policy_outputs: 20.5780
  split_output_tensors: 8.0255
[2024-12-02 14:37:55,172][00408] Loop Runner_EvtLoop terminating...
[2024-12-02 14:37:55,174][00408] Runner profile tree view:
main_loop: 1103.2292
[2024-12-02 14:37:55,175][00408] Collected {0: 4005888}, FPS: 3631.1
[2024-12-02 14:37:55,214][00408] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
[2024-12-02 14:37:55,216][00408] Overriding arg 'num_workers' with value 1 passed from command line
[2024-12-02 14:37:55,218][00408] Adding new argument 'no_render'=True that is not in the saved config file!
[2024-12-02 14:37:55,220][00408] Adding new argument 'save_video'=True that is not in the saved config file!
[2024-12-02 14:37:55,221][00408] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2024-12-02 14:37:55,222][00408] Adding new argument 'video_name'=None that is not in the saved config file!
[2024-12-02 14:37:55,224][00408] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
[2024-12-02 14:37:55,225][00408] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2024-12-02 14:37:55,226][00408] Adding new argument 'push_to_hub'=False that is not in the saved config file!
[2024-12-02 14:37:55,227][00408] Adding new argument 'hf_repository'=None that is not in the saved config file!
[2024-12-02 14:37:55,229][00408] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2024-12-02 14:37:55,230][00408] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2024-12-02 14:37:55,230][00408] Adding new argument 'train_script'=None that is not in the saved config file!
[2024-12-02 14:37:55,231][00408] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2024-12-02 14:37:55,232][00408] Using frameskip 1 and render_action_repeat=4 for evaluation
[2024-12-02 14:37:55,268][00408] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-12-02 14:37:55,272][00408] RunningMeanStd input shape: (3, 72, 128)
[2024-12-02 14:37:55,276][00408] RunningMeanStd input shape: (1,)
[2024-12-02 14:37:55,292][00408] ConvEncoder: input_channels=3
[2024-12-02 14:37:55,397][00408] Conv encoder output size: 512
[2024-12-02 14:37:55,399][00408] Policy head output size: 512
[2024-12-02 14:37:55,574][00408] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2024-12-02 14:37:56,374][00408] Num frames 100...
[2024-12-02 14:37:56,495][00408] Num frames 200...
[2024-12-02 14:37:56,614][00408] Num frames 300...
[2024-12-02 14:37:56,746][00408] Num frames 400...
[2024-12-02 14:37:56,870][00408] Num frames 500...
[2024-12-02 14:37:56,997][00408] Num frames 600...
[2024-12-02 14:37:57,088][00408] Avg episode rewards: #0: 13.290, true rewards: #0: 6.290
[2024-12-02 14:37:57,089][00408] Avg episode reward: 13.290, avg true_objective: 6.290
[2024-12-02 14:37:57,176][00408] Num frames 700...
[2024-12-02 14:37:57,302][00408] Num frames 800...
[2024-12-02 14:37:57,427][00408] Num frames 900...
[2024-12-02 14:37:57,554][00408] Num frames 1000...
[2024-12-02 14:37:57,693][00408] Num frames 1100...
[2024-12-02 14:37:57,815][00408] Num frames 1200...
[2024-12-02 14:37:57,880][00408] Avg episode rewards: #0: 12.025, true rewards: #0: 6.025
[2024-12-02 14:37:57,882][00408] Avg episode reward: 12.025, avg true_objective: 6.025
[2024-12-02 14:37:58,007][00408] Num frames 1300...
[2024-12-02 14:37:58,126][00408] Num frames 1400...
[2024-12-02 14:37:58,246][00408] Num frames 1500...
[2024-12-02 14:37:58,376][00408] Num frames 1600...
[2024-12-02 14:37:58,514][00408] Num frames 1700...
[2024-12-02 14:37:58,653][00408] Num frames 1800...
[2024-12-02 14:37:58,787][00408] Num frames 1900...
[2024-12-02 14:37:58,903][00408] Num frames 2000...
[2024-12-02 14:37:59,030][00408] Num frames 2100...
[2024-12-02 14:37:59,152][00408] Num frames 2200...
[2024-12-02 14:37:59,271][00408] Num frames 2300...
[2024-12-02 14:37:59,394][00408] Num frames 2400...
[2024-12-02 14:37:59,516][00408] Num frames 2500...
[2024-12-02 14:37:59,635][00408] Num frames 2600...
[2024-12-02 14:37:59,763][00408] Num frames 2700...
[2024-12-02 14:37:59,886][00408] Num frames 2800...
[2024-12-02 14:38:00,014][00408] Num frames 2900...
[2024-12-02 14:38:00,133][00408] Num frames 3000...
[2024-12-02 14:38:00,257][00408] Num frames 3100...
[2024-12-02 14:38:00,389][00408] Num frames 3200...
[2024-12-02 14:38:00,511][00408] Num frames 3300...
[2024-12-02 14:38:00,574][00408] Avg episode rewards: #0: 27.016, true rewards: #0: 11.017
[2024-12-02 14:38:00,575][00408] Avg episode reward: 27.016, avg true_objective: 11.017
[2024-12-02 14:38:00,692][00408] Num frames 3400...
[2024-12-02 14:38:00,816][00408] Num frames 3500...
[2024-12-02 14:38:00,936][00408] Num frames 3600...
[2024-12-02 14:38:01,059][00408] Num frames 3700...
[2024-12-02 14:38:01,177][00408] Num frames 3800...
[2024-12-02 14:38:01,300][00408] Num frames 3900...
[2024-12-02 14:38:01,423][00408] Num frames 4000...
[2024-12-02 14:38:01,548][00408] Num frames 4100...
[2024-12-02 14:38:01,667][00408] Num frames 4200...
[2024-12-02 14:38:01,792][00408] Num frames 4300...
[2024-12-02 14:38:01,917][00408] Num frames 4400...
[2024-12-02 14:38:02,044][00408] Num frames 4500...
[2024-12-02 14:38:02,168][00408] Num frames 4600...
[2024-12-02 14:38:02,291][00408] Num frames 4700...
[2024-12-02 14:38:02,414][00408] Num frames 4800...
[2024-12-02 14:38:02,536][00408] Num frames 4900...
[2024-12-02 14:38:02,660][00408] Num frames 5000...
[2024-12-02 14:38:02,851][00408] Avg episode rewards: #0: 31.492, true rewards: #0: 12.743
[2024-12-02 14:38:02,852][00408] Avg episode reward: 31.492, avg true_objective: 12.743
[2024-12-02 14:38:02,859][00408] Num frames 5100...
[2024-12-02 14:38:03,041][00408] Num frames 5200...
[2024-12-02 14:38:03,210][00408] Num frames 5300...
[2024-12-02 14:38:03,379][00408] Num frames 5400...
[2024-12-02 14:38:03,559][00408] Num frames 5500...
[2024-12-02 14:38:03,724][00408] Num frames 5600...
[2024-12-02 14:38:03,907][00408] Num frames 5700...
[2024-12-02 14:38:04,068][00408] Num frames 5800...
[2024-12-02 14:38:04,241][00408] Num frames 5900...
[2024-12-02 14:38:04,413][00408] Num frames 6000...
[2024-12-02 14:38:04,584][00408] Num frames 6100...
[2024-12-02 14:38:04,760][00408] Num frames 6200...
[2024-12-02 14:38:04,939][00408] Num frames 6300...
[2024-12-02 14:38:05,134][00408] Num frames 6400...
[2024-12-02 14:38:05,316][00408] Num frames 6500...
[2024-12-02 14:38:05,388][00408] Avg episode rewards: #0: 31.210, true rewards: #0: 13.010
[2024-12-02 14:38:05,389][00408] Avg episode reward: 31.210, avg true_objective: 13.010
[2024-12-02 14:38:05,514][00408] Num frames 6600...
[2024-12-02 14:38:05,636][00408] Num frames 6700...
[2024-12-02 14:38:05,758][00408] Num frames 6800...
[2024-12-02 14:38:05,881][00408] Avg episode rewards: #0: 26.761, true rewards: #0: 11.428
[2024-12-02 14:38:05,882][00408] Avg episode reward: 26.761, avg true_objective: 11.428
[2024-12-02 14:38:05,939][00408] Num frames 6900...
[2024-12-02 14:38:06,077][00408] Num frames 7000...
[2024-12-02 14:38:06,198][00408] Num frames 7100...
[2024-12-02 14:38:06,323][00408] Num frames 7200...
[2024-12-02 14:38:06,444][00408] Num frames 7300...
[2024-12-02 14:38:06,568][00408] Num frames 7400...
[2024-12-02 14:38:06,690][00408] Num frames 7500...
[2024-12-02 14:38:06,813][00408] Num frames 7600...
[2024-12-02 14:38:06,936][00408] Num frames 7700...
[2024-12-02 14:38:07,071][00408] Num frames 7800...
[2024-12-02 14:38:07,194][00408] Num frames 7900...
[2024-12-02 14:38:07,319][00408] Num frames 8000...
[2024-12-02 14:38:07,388][00408] Avg episode rewards: #0: 26.870, true rewards: #0: 11.441
[2024-12-02 14:38:07,390][00408] Avg episode reward: 26.870, avg true_objective: 11.441
[2024-12-02 14:38:07,503][00408] Num frames 8100...
[2024-12-02 14:38:07,627][00408] Num frames 8200...
[2024-12-02 14:38:07,745][00408] Num frames 8300...
[2024-12-02 14:38:07,864][00408] Num frames 8400...
[2024-12-02 14:38:07,995][00408] Num frames 8500...
[2024-12-02 14:38:08,122][00408] Avg episode rewards: #0: 25.066, true rewards: #0: 10.691
[2024-12-02 14:38:08,124][00408] Avg episode reward: 25.066, avg true_objective: 10.691
[2024-12-02 14:38:08,185][00408] Num frames 8600...
[2024-12-02 14:38:08,305][00408] Num frames 8700...
[2024-12-02 14:38:08,429][00408] Num frames 8800...
[2024-12-02 14:38:08,561][00408] Num frames 8900...
[2024-12-02 14:38:08,687][00408] Num frames 9000...
[2024-12-02 14:38:08,809][00408] Num frames 9100...
[2024-12-02 14:38:08,942][00408] Num frames 9200...
[2024-12-02 14:38:09,086][00408] Num frames 9300...
[2024-12-02 14:38:09,208][00408] Num frames 9400...
[2024-12-02 14:38:09,330][00408] Num frames 9500...
[2024-12-02 14:38:09,456][00408] Num frames 9600...
[2024-12-02 14:38:09,583][00408] Num frames 9700...
[2024-12-02 14:38:09,702][00408] Num frames 9800...
[2024-12-02 14:38:09,822][00408] Num frames 9900...
[2024-12-02 14:38:09,948][00408] Num frames 10000...
[2024-12-02 14:38:10,071][00408] Num frames 10100...
[2024-12-02 14:38:10,202][00408] Num frames 10200...
[2024-12-02 14:38:10,284][00408] Avg episode rewards: #0: 27.019, true rewards: #0: 11.352
[2024-12-02 14:38:10,286][00408] Avg episode reward: 27.019, avg true_objective: 11.352
[2024-12-02 14:38:10,393][00408] Num frames 10300...
[2024-12-02 14:38:10,516][00408] Num frames 10400...
[2024-12-02 14:38:10,634][00408] Num frames 10500...
[2024-12-02 14:38:10,753][00408] Num frames 10600...
[2024-12-02 14:38:10,875][00408] Num frames 10700...
[2024-12-02 14:38:11,000][00408] Num frames 10800...
[2024-12-02 14:38:11,160][00408] Avg episode rewards: #0: 25.589, true rewards: #0: 10.889
[2024-12-02 14:38:11,162][00408] Avg episode reward: 25.589, avg true_objective: 10.889
[2024-12-02 14:39:19,608][00408] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
[2024-12-02 14:39:19,642][00408] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
[2024-12-02 14:39:19,643][00408] Overriding arg 'num_workers' with value 1 passed from command line
[2024-12-02 14:39:19,645][00408] Adding new argument 'no_render'=True that is not in the saved config file!
[2024-12-02 14:39:19,646][00408] Adding new argument 'save_video'=True that is not in the saved config file!
[2024-12-02 14:39:19,648][00408] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2024-12-02 14:39:19,649][00408] Adding new argument 'video_name'=None that is not in the saved config file!
[2024-12-02 14:39:19,651][00408] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
[2024-12-02 14:39:19,653][00408] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2024-12-02 14:39:19,654][00408] Adding new argument 'push_to_hub'=True that is not in the saved config file!
[2024-12-02 14:39:19,658][00408] Adding new argument 'hf_repository'='peggia/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
[2024-12-02 14:39:19,659][00408] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2024-12-02 14:39:19,660][00408] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2024-12-02 14:39:19,661][00408] Adding new argument 'train_script'=None that is not in the saved config file!
[2024-12-02 14:39:19,662][00408] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2024-12-02 14:39:19,663][00408] Using frameskip 1 and render_action_repeat=4 for evaluation
[2024-12-02 14:39:19,692][00408] RunningMeanStd input shape: (3, 72, 128)
[2024-12-02 14:39:19,694][00408] RunningMeanStd input shape: (1,)
[2024-12-02 14:39:19,708][00408] ConvEncoder: input_channels=3
[2024-12-02 14:39:19,745][00408] Conv encoder output size: 512
[2024-12-02 14:39:19,746][00408] Policy head output size: 512
[2024-12-02 14:39:19,770][00408] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2024-12-02 14:39:20,205][00408] Num frames 100...
[2024-12-02 14:39:20,326][00408] Num frames 200...
[2024-12-02 14:39:20,457][00408] Num frames 300...
[2024-12-02 14:39:20,582][00408] Num frames 400...
[2024-12-02 14:39:20,705][00408] Num frames 500...
[2024-12-02 14:39:20,835][00408] Num frames 600...
[2024-12-02 14:39:20,962][00408] Num frames 700...
[2024-12-02 14:39:21,083][00408] Num frames 800...
[2024-12-02 14:39:21,205][00408] Num frames 900...
[2024-12-02 14:39:21,348][00408] Num frames 1000...
[2024-12-02 14:39:21,523][00408] Num frames 1100...
[2024-12-02 14:39:21,689][00408] Num frames 1200...
[2024-12-02 14:39:21,861][00408] Num frames 1300...
[2024-12-02 14:39:21,947][00408] Avg episode rewards: #0: 31.120, true rewards: #0: 13.120
[2024-12-02 14:39:21,949][00408] Avg episode reward: 31.120, avg true_objective: 13.120
[2024-12-02 14:39:22,101][00408] Num frames 1400...
[2024-12-02 14:39:22,272][00408] Num frames 1500...
[2024-12-02 14:39:22,440][00408] Num frames 1600...
[2024-12-02 14:39:22,656][00408] Avg episode rewards: #0: 18.980, true rewards: #0: 8.480
[2024-12-02 14:39:22,659][00408] Avg episode reward: 18.980, avg true_objective: 8.480
[2024-12-02 14:39:22,671][00408] Num frames 1700...
[2024-12-02 14:39:22,850][00408] Num frames 1800...
[2024-12-02 14:39:23,046][00408] Num frames 1900...
[2024-12-02 14:39:23,223][00408] Num frames 2000...
[2024-12-02 14:39:23,413][00408] Num frames 2100...
[2024-12-02 14:39:23,585][00408] Num frames 2200...
[2024-12-02 14:39:23,760][00408] Num frames 2300...
[2024-12-02 14:39:23,899][00408] Num frames 2400...
[2024-12-02 14:39:24,028][00408] Num frames 2500...
[2024-12-02 14:39:24,153][00408] Num frames 2600...
[2024-12-02 14:39:24,276][00408] Num frames 2700...
[2024-12-02 14:39:24,402][00408] Num frames 2800...
[2024-12-02 14:39:24,526][00408] Num frames 2900...
[2024-12-02 14:39:24,646][00408] Num frames 3000...
[2024-12-02 14:39:24,766][00408] Num frames 3100...
[2024-12-02 14:39:24,890][00408] Num frames 3200...
[2024-12-02 14:39:25,023][00408] Num frames 3300...
[2024-12-02 14:39:25,141][00408] Num frames 3400...
[2024-12-02 14:39:25,227][00408] Avg episode rewards: #0: 26.413, true rewards: #0: 11.413
[2024-12-02 14:39:25,228][00408] Avg episode reward: 26.413, avg true_objective: 11.413
[2024-12-02 14:39:25,327][00408] Num frames 3500...
[2024-12-02 14:39:25,450][00408] Num frames 3600...
[2024-12-02 14:39:25,570][00408] Num frames 3700...
[2024-12-02 14:39:25,694][00408] Num frames 3800...
[2024-12-02 14:39:25,813][00408] Num frames 3900...
[2024-12-02 14:39:25,938][00408] Num frames 4000...
[2024-12-02 14:39:26,083][00408] Num frames 4100...
[2024-12-02 14:39:26,206][00408] Num frames 4200...
[2024-12-02 14:39:26,329][00408] Num frames 4300...
[2024-12-02 14:39:26,458][00408] Num frames 4400...
[2024-12-02 14:39:26,582][00408] Num frames 4500...
[2024-12-02 14:39:26,707][00408] Num frames 4600...
[2024-12-02 14:39:26,839][00408] Num frames 4700...
[2024-12-02 14:39:26,967][00408] Num frames 4800...
[2024-12-02 14:39:27,096][00408] Num frames 4900...
[2024-12-02 14:39:27,222][00408] Num frames 5000...
[2024-12-02 14:39:27,387][00408] Avg episode rewards: #0: 31.220, true rewards: #0: 12.720
[2024-12-02 14:39:27,389][00408] Avg episode reward: 31.220, avg true_objective: 12.720
[2024-12-02 14:39:27,407][00408] Num frames 5100...
[2024-12-02 14:39:27,524][00408] Num frames 5200...
[2024-12-02 14:39:27,645][00408] Num frames 5300...
[2024-12-02 14:39:27,764][00408] Num frames 5400...
[2024-12-02 14:39:27,883][00408] Num frames 5500...
[2024-12-02 14:39:28,016][00408] Num frames 5600...
[2024-12-02 14:39:28,069][00408] Avg episode rewards: #0: 26.600, true rewards: #0: 11.200
[2024-12-02 14:39:28,071][00408] Avg episode reward: 26.600, avg true_objective: 11.200
[2024-12-02 14:39:28,194][00408] Num frames 5700...
[2024-12-02 14:39:28,315][00408] Num frames 5800...
[2024-12-02 14:39:28,434][00408] Num frames 5900...
[2024-12-02 14:39:28,563][00408] Num frames 6000...
[2024-12-02 14:39:28,680][00408] Num frames 6100...
[2024-12-02 14:39:28,788][00408] Avg episode rewards: #0: 23.573, true rewards: #0: 10.240
[2024-12-02 14:39:28,790][00408] Avg episode reward: 23.573, avg true_objective: 10.240
[2024-12-02 14:39:28,860][00408] Num frames 6200...
[2024-12-02 14:39:28,997][00408] Num frames 6300...
[2024-12-02 14:39:29,133][00408] Num frames 6400...
[2024-12-02 14:39:29,252][00408] Num frames 6500...
[2024-12-02 14:39:29,374][00408] Num frames 6600...
[2024-12-02 14:39:29,528][00408] Num frames 6700...
[2024-12-02 14:39:29,653][00408] Num frames 6800...
[2024-12-02 14:39:29,776][00408] Num frames 6900...
[2024-12-02 14:39:29,900][00408] Num frames 7000...
[2024-12-02 14:39:30,034][00408] Num frames 7100...
[2024-12-02 14:39:30,164][00408] Num frames 7200...
[2024-12-02 14:39:30,285][00408] Num frames 7300...
[2024-12-02 14:39:30,413][00408] Num frames 7400...
[2024-12-02 14:39:30,537][00408] Num frames 7500...
[2024-12-02 14:39:30,656][00408] Num frames 7600...
[2024-12-02 14:39:30,777][00408] Num frames 7700...
[2024-12-02 14:39:30,866][00408] Avg episode rewards: #0: 25.753, true rewards: #0: 11.039
[2024-12-02 14:39:30,868][00408] Avg episode reward: 25.753, avg true_objective: 11.039
[2024-12-02 14:39:30,968][00408] Num frames 7800...
[2024-12-02 14:39:31,088][00408] Num frames 7900...
[2024-12-02 14:39:31,223][00408] Num frames 8000...
[2024-12-02 14:39:31,352][00408] Num frames 8100...
[2024-12-02 14:39:31,473][00408] Num frames 8200...
[2024-12-02 14:39:31,595][00408] Num frames 8300...
[2024-12-02 14:39:31,715][00408] Num frames 8400...
[2024-12-02 14:39:31,835][00408] Num frames 8500...
[2024-12-02 14:39:31,991][00408] Avg episode rewards: #0: 25.225, true rewards: #0: 10.725
[2024-12-02 14:39:31,992][00408] Avg episode reward: 25.225, avg true_objective: 10.725
[2024-12-02 14:39:32,020][00408] Num frames 8600...
[2024-12-02 14:39:32,143][00408] Num frames 8700...
[2024-12-02 14:39:32,270][00408] Num frames 8800...
[2024-12-02 14:39:32,393][00408] Num frames 8900...
[2024-12-02 14:39:32,527][00408] Avg episode rewards: #0: 23.293, true rewards: #0: 9.960
[2024-12-02 14:39:32,529][00408] Avg episode reward: 23.293, avg true_objective: 9.960
[2024-12-02 14:39:32,577][00408] Num frames 9000...
[2024-12-02 14:39:32,695][00408] Num frames 9100...
[2024-12-02 14:39:32,813][00408] Num frames 9200...
[2024-12-02 14:39:32,937][00408] Num frames 9300...
[2024-12-02 14:39:33,050][00408] Avg episode rewards: #0: 21.439, true rewards: #0: 9.339
[2024-12-02 14:39:33,052][00408] Avg episode reward: 21.439, avg true_objective: 9.339
[2024-12-02 14:40:32,888][00408] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
[2024-12-02 14:40:41,662][00408] The model has been pushed to https://huggingface.co./peggia/rl_course_vizdoom_health_gathering_supreme
[2024-12-02 14:43:01,181][00408] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
[2024-12-02 14:43:01,184][00408] Overriding arg 'num_workers' with value 1 passed from command line
[2024-12-02 14:43:01,185][00408] Adding new argument 'no_render'=True that is not in the saved config file!
[2024-12-02 14:43:01,187][00408] Adding new argument 'save_video'=True that is not in the saved config file!
[2024-12-02 14:43:01,189][00408] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2024-12-02 14:43:01,193][00408] Adding new argument 'video_name'=None that is not in the saved config file!
[2024-12-02 14:43:01,194][00408] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
[2024-12-02 14:43:01,196][00408] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2024-12-02 14:43:01,202][00408] Adding new argument 'push_to_hub'=True that is not in the saved config file!
[2024-12-02 14:43:01,203][00408] Adding new argument 'hf_repository'='peggia/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
[2024-12-02 14:43:01,204][00408] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2024-12-02 14:43:01,204][00408] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2024-12-02 14:43:01,205][00408] Adding new argument 'train_script'=None that is not in the saved config file!
[2024-12-02 14:43:01,206][00408] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2024-12-02 14:43:01,208][00408] Using frameskip 1 and render_action_repeat=4 for evaluation
[2024-12-02 14:43:01,239][00408] RunningMeanStd input shape: (3, 72, 128)
[2024-12-02 14:43:01,242][00408] RunningMeanStd input shape: (1,)
[2024-12-02 14:43:01,256][00408] ConvEncoder: input_channels=3
[2024-12-02 14:43:01,294][00408] Conv encoder output size: 512
[2024-12-02 14:43:01,295][00408] Policy head output size: 512
[2024-12-02 14:43:01,317][00408] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2024-12-02 14:43:01,758][00408] Num frames 100...
[2024-12-02 14:43:01,877][00408] Num frames 200...
[2024-12-02 14:43:02,020][00408] Num frames 300...
[2024-12-02 14:43:02,147][00408] Num frames 400...
[2024-12-02 14:43:02,280][00408] Num frames 500...
[2024-12-02 14:43:02,432][00408] Avg episode rewards: #0: 8.760, true rewards: #0: 5.760
[2024-12-02 14:43:02,434][00408] Avg episode reward: 8.760, avg true_objective: 5.760
[2024-12-02 14:43:02,467][00408] Num frames 600...
[2024-12-02 14:43:02,588][00408] Num frames 700...
[2024-12-02 14:43:02,707][00408] Num frames 800...
[2024-12-02 14:43:02,830][00408] Num frames 900...
[2024-12-02 14:43:02,955][00408] Num frames 1000...
[2024-12-02 14:43:03,079][00408] Num frames 1100...
[2024-12-02 14:43:03,206][00408] Num frames 1200...
[2024-12-02 14:43:03,338][00408] Num frames 1300...
[2024-12-02 14:43:03,456][00408] Num frames 1400...
[2024-12-02 14:43:03,574][00408] Num frames 1500...
[2024-12-02 14:43:03,694][00408] Num frames 1600...
[2024-12-02 14:43:03,820][00408] Num frames 1700...
[2024-12-02 14:43:03,943][00408] Num frames 1800...
[2024-12-02 14:43:04,070][00408] Num frames 1900...
[2024-12-02 14:43:04,188][00408] Num frames 2000...
[2024-12-02 14:43:04,317][00408] Num frames 2100...
[2024-12-02 14:43:04,441][00408] Num frames 2200...
[2024-12-02 14:43:04,565][00408] Num frames 2300...
[2024-12-02 14:43:04,664][00408] Avg episode rewards: #0: 28.180, true rewards: #0: 11.680
[2024-12-02 14:43:04,666][00408] Avg episode reward: 28.180, avg true_objective: 11.680
[2024-12-02 14:43:04,744][00408] Num frames 2400...
[2024-12-02 14:43:04,861][00408] Num frames 2500...
[2024-12-02 14:43:04,988][00408] Num frames 2600...
[2024-12-02 14:43:05,105][00408] Num frames 2700...
[2024-12-02 14:43:05,223][00408] Num frames 2800...
[2024-12-02 14:43:05,352][00408] Num frames 2900...
[2024-12-02 14:43:05,477][00408] Num frames 3000...
[2024-12-02 14:43:05,601][00408] Num frames 3100...
[2024-12-02 14:43:05,666][00408] Avg episode rewards: #0: 24.350, true rewards: #0: 10.350
[2024-12-02 14:43:05,668][00408] Avg episode reward: 24.350, avg true_objective: 10.350
[2024-12-02 14:43:05,792][00408] Num frames 3200...
[2024-12-02 14:43:05,911][00408] Num frames 3300...
[2024-12-02 14:43:06,042][00408] Num frames 3400...
[2024-12-02 14:43:06,168][00408] Num frames 3500...
[2024-12-02 14:43:06,291][00408] Num frames 3600...
[2024-12-02 14:43:06,420][00408] Num frames 3700...
[2024-12-02 14:43:06,539][00408] Num frames 3800...
[2024-12-02 14:43:06,657][00408] Num frames 3900...
[2024-12-02 14:43:06,778][00408] Num frames 4000...
[2024-12-02 14:43:06,892][00408] Avg episode rewards: #0: 24.370, true rewards: #0: 10.120
[2024-12-02 14:43:06,894][00408] Avg episode reward: 24.370, avg true_objective: 10.120
[2024-12-02 14:43:06,968][00408] Num frames 4100...
[2024-12-02 14:43:07,090][00408] Num frames 4200...
[2024-12-02 14:43:07,210][00408] Num frames 4300...
[2024-12-02 14:43:07,332][00408] Num frames 4400...
[2024-12-02 14:43:07,466][00408] Num frames 4500...
[2024-12-02 14:43:07,591][00408] Num frames 4600...
[2024-12-02 14:43:07,710][00408] Num frames 4700...
[2024-12-02 14:43:07,831][00408] Num frames 4800...
[2024-12-02 14:43:07,960][00408] Num frames 4900...
[2024-12-02 14:43:08,109][00408] Avg episode rewards: #0: 23.952, true rewards: #0: 9.952
[2024-12-02 14:43:08,111][00408] Avg episode reward: 23.952, avg true_objective: 9.952
[2024-12-02 14:43:08,145][00408] Num frames 5000...
[2024-12-02 14:43:08,270][00408] Num frames 5100...
[2024-12-02 14:43:08,396][00408] Num frames 5200...
[2024-12-02 14:43:08,514][00408] Num frames 5300...
[2024-12-02 14:43:08,634][00408] Num frames 5400...
[2024-12-02 14:43:08,765][00408] Num frames 5500...
[2024-12-02 14:43:08,883][00408] Num frames 5600...
[2024-12-02 14:43:09,017][00408] Num frames 5700...
[2024-12-02 14:43:09,141][00408] Num frames 5800...
[2024-12-02 14:43:09,260][00408] Num frames 5900...
[2024-12-02 14:43:09,385][00408] Num frames 6000...
[2024-12-02 14:43:09,556][00408] Num frames 6100...
[2024-12-02 14:43:09,728][00408] Num frames 6200...
[2024-12-02 14:43:09,895][00408] Num frames 6300...
[2024-12-02 14:43:10,073][00408] Num frames 6400...
[2024-12-02 14:43:10,240][00408] Num frames 6500...
[2024-12-02 14:43:10,319][00408] Avg episode rewards: #0: 25.520, true rewards: #0: 10.853
[2024-12-02 14:43:10,321][00408] Avg episode reward: 25.520, avg true_objective: 10.853
[2024-12-02 14:43:10,494][00408] Num frames 6600...
[2024-12-02 14:43:10,662][00408] Num frames 6700...
[2024-12-02 14:43:10,829][00408] Num frames 6800...
[2024-12-02 14:43:11,001][00408] Num frames 6900...
[2024-12-02 14:43:11,171][00408] Num frames 7000...
[2024-12-02 14:43:11,362][00408] Num frames 7100...
[2024-12-02 14:43:11,545][00408] Num frames 7200...
[2024-12-02 14:43:11,717][00408] Num frames 7300...
[2024-12-02 14:43:11,913][00408] Num frames 7400...
[2024-12-02 14:43:12,089][00408] Num frames 7500...
[2024-12-02 14:43:12,212][00408] Num frames 7600...
[2024-12-02 14:43:12,336][00408] Num frames 7700...
[2024-12-02 14:43:12,455][00408] Num frames 7800...
[2024-12-02 14:43:12,586][00408] Num frames 7900...
[2024-12-02 14:43:12,707][00408] Num frames 8000...
[2024-12-02 14:43:12,831][00408] Num frames 8100...
[2024-12-02 14:43:12,958][00408] Num frames 8200...
[2024-12-02 14:43:13,080][00408] Num frames 8300...
[2024-12-02 14:43:13,206][00408] Num frames 8400...
[2024-12-02 14:43:13,330][00408] Num frames 8500...
[2024-12-02 14:43:13,453][00408] Num frames 8600...
[2024-12-02 14:43:13,527][00408] Avg episode rewards: #0: 30.445, true rewards: #0: 12.303
[2024-12-02 14:43:13,530][00408] Avg episode reward: 30.445, avg true_objective: 12.303
[2024-12-02 14:43:13,649][00408] Num frames 8700...
[2024-12-02 14:43:13,774][00408] Num frames 8800...
[2024-12-02 14:43:13,894][00408] Num frames 8900...
[2024-12-02 14:43:14,024][00408] Num frames 9000...
[2024-12-02 14:43:14,146][00408] Num frames 9100...
[2024-12-02 14:43:14,268][00408] Num frames 9200...
[2024-12-02 14:43:14,390][00408] Num frames 9300...
[2024-12-02 14:43:14,517][00408] Num frames 9400...
[2024-12-02 14:43:14,647][00408] Num frames 9500...
[2024-12-02 14:43:14,769][00408] Num frames 9600...
[2024-12-02 14:43:14,893][00408] Num frames 9700...
[2024-12-02 14:43:15,020][00408] Num frames 9800...
[2024-12-02 14:43:15,142][00408] Num frames 9900...
[2024-12-02 14:43:15,270][00408] Avg episode rewards: #0: 30.695, true rewards: #0: 12.445
[2024-12-02 14:43:15,271][00408] Avg episode reward: 30.695, avg true_objective: 12.445
[2024-12-02 14:43:15,331][00408] Num frames 10000...
[2024-12-02 14:43:15,451][00408] Num frames 10100...
[2024-12-02 14:43:15,576][00408] Num frames 10200...
[2024-12-02 14:43:15,655][00408] Avg episode rewards: #0: 27.902, true rewards: #0: 11.347
[2024-12-02 14:43:15,656][00408] Avg episode reward: 27.902, avg true_objective: 11.347
[2024-12-02 14:43:15,762][00408] Num frames 10300...
[2024-12-02 14:43:15,881][00408] Num frames 10400...
[2024-12-02 14:43:16,009][00408] Num frames 10500...
[2024-12-02 14:43:16,128][00408] Num frames 10600...
[2024-12-02 14:43:16,248][00408] Num frames 10700...
[2024-12-02 14:43:16,373][00408] Num frames 10800...
[2024-12-02 14:43:16,455][00408] Avg episode rewards: #0: 26.020, true rewards: #0: 10.820
[2024-12-02 14:43:16,457][00408] Avg episode reward: 26.020, avg true_objective: 10.820
[2024-12-02 14:44:23,342][00408] Replay video saved to /content/train_dir/default_experiment/replay.mp4!