[2024-10-23 03:11:23,004][00608] Saving configuration to /content/train_dir/default_experiment/config.json...
[2024-10-23 03:11:23,008][00608] Rollout worker 0 uses device cpu
[2024-10-23 03:11:23,010][00608] Rollout worker 1 uses device cpu
[2024-10-23 03:11:23,012][00608] Rollout worker 2 uses device cpu
[2024-10-23 03:11:23,013][00608] Rollout worker 3 uses device cpu
[2024-10-23 03:11:23,015][00608] Rollout worker 4 uses device cpu
[2024-10-23 03:11:23,016][00608] Rollout worker 5 uses device cpu
[2024-10-23 03:11:23,018][00608] Rollout worker 6 uses device cpu
[2024-10-23 03:11:23,020][00608] Rollout worker 7 uses device cpu
[2024-10-23 03:11:23,200][00608] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-10-23 03:11:23,204][00608] InferenceWorker_p0-w0: min num requests: 2
[2024-10-23 03:11:23,250][00608] Starting all processes...
[2024-10-23 03:11:23,254][00608] Starting process learner_proc0
[2024-10-23 03:11:25,375][00608] Starting all processes...
[2024-10-23 03:11:25,406][00608] Starting process inference_proc0-0
[2024-10-23 03:11:25,406][00608] Starting process rollout_proc0
[2024-10-23 03:11:25,407][00608] Starting process rollout_proc1
[2024-10-23 03:11:25,407][00608] Starting process rollout_proc3
[2024-10-23 03:11:25,407][00608] Starting process rollout_proc4
[2024-10-23 03:11:25,407][00608] Starting process rollout_proc5
[2024-10-23 03:11:25,407][00608] Starting process rollout_proc6
[2024-10-23 03:11:25,407][00608] Starting process rollout_proc7
[2024-10-23 03:11:25,407][00608] Starting process rollout_proc2
[2024-10-23 03:11:40,200][07347] Worker 4 uses CPU cores [0]
[2024-10-23 03:11:40,344][07329] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-10-23 03:11:40,346][07329] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
[2024-10-23 03:11:40,376][07329] Num visible devices: 1
[2024-10-23 03:11:40,399][07329] Starting seed is not provided
[2024-10-23 03:11:40,400][07329] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-10-23 03:11:40,401][07329] Initializing actor-critic model on device cuda:0
[2024-10-23 03:11:40,402][07329] RunningMeanStd input shape: (3, 72, 128)
[2024-10-23 03:11:40,405][07329] RunningMeanStd input shape: (1,)
[2024-10-23 03:11:40,451][07329] ConvEncoder: input_channels=3
[2024-10-23 03:11:40,779][07348] Worker 6 uses CPU cores [0]
[2024-10-23 03:11:40,785][07342] Worker 0 uses CPU cores [0]
[2024-10-23 03:11:40,951][07345] Worker 3 uses CPU cores [1]
[2024-10-23 03:11:41,018][07344] Worker 1 uses CPU cores [1]
[2024-10-23 03:11:41,028][07349] Worker 7 uses CPU cores [1]
[2024-10-23 03:11:41,074][07329] Conv encoder output size: 512
[2024-10-23 03:11:41,074][07329] Policy head output size: 512
[2024-10-23 03:11:41,108][07350] Worker 2 uses CPU cores [0]
[2024-10-23 03:11:41,138][07346] Worker 5 uses CPU cores [1]
[2024-10-23 03:11:41,161][07329] Created Actor Critic model with architecture:
[2024-10-23 03:11:41,161][07329] 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)
  )
)
[2024-10-23 03:11:41,177][07343] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-10-23 03:11:41,178][07343] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
[2024-10-23 03:11:41,196][07343] Num visible devices: 1
[2024-10-23 03:11:41,458][07329] Using optimizer <class 'torch.optim.adam.Adam'>
[2024-10-23 03:11:42,493][07329] No checkpoints found
[2024-10-23 03:11:42,493][07329] Did not load from checkpoint, starting from scratch!
[2024-10-23 03:11:42,493][07329] Initialized policy 0 weights for model version 0
[2024-10-23 03:11:42,499][07329] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-10-23 03:11:42,507][07329] LearnerWorker_p0 finished initialization!
[2024-10-23 03:11:42,592][07343] RunningMeanStd input shape: (3, 72, 128)
[2024-10-23 03:11:42,593][07343] RunningMeanStd input shape: (1,)
[2024-10-23 03:11:42,605][07343] ConvEncoder: input_channels=3
[2024-10-23 03:11:42,706][07343] Conv encoder output size: 512
[2024-10-23 03:11:42,706][07343] Policy head output size: 512
[2024-10-23 03:11:42,725][00608] 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)
[2024-10-23 03:11:42,760][00608] Inference worker 0-0 is ready!
[2024-10-23 03:11:42,761][00608] All inference workers are ready! Signal rollout workers to start!
[2024-10-23 03:11:42,960][07342] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-10-23 03:11:42,961][07347] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-10-23 03:11:42,962][07350] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-10-23 03:11:42,963][07348] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-10-23 03:11:42,963][07346] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-10-23 03:11:42,965][07344] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-10-23 03:11:42,967][07349] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-10-23 03:11:42,969][07345] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-10-23 03:11:43,188][00608] Heartbeat connected on Batcher_0
[2024-10-23 03:11:43,194][00608] Heartbeat connected on LearnerWorker_p0
[2024-10-23 03:11:43,235][00608] Heartbeat connected on InferenceWorker_p0-w0
[2024-10-23 03:11:44,337][07347] Decorrelating experience for 0 frames...
[2024-10-23 03:11:44,336][07350] Decorrelating experience for 0 frames...
[2024-10-23 03:11:44,338][07348] Decorrelating experience for 0 frames...
[2024-10-23 03:11:44,654][07349] Decorrelating experience for 0 frames...
[2024-10-23 03:11:44,650][07344] Decorrelating experience for 0 frames...
[2024-10-23 03:11:44,658][07346] Decorrelating experience for 0 frames...
[2024-10-23 03:11:44,664][07345] Decorrelating experience for 0 frames...
[2024-10-23 03:11:45,397][07344] Decorrelating experience for 32 frames...
[2024-10-23 03:11:45,399][07349] Decorrelating experience for 32 frames...
[2024-10-23 03:11:45,527][07350] Decorrelating experience for 32 frames...
[2024-10-23 03:11:45,547][07348] Decorrelating experience for 32 frames...
[2024-10-23 03:11:45,561][07342] Decorrelating experience for 0 frames...
[2024-10-23 03:11:46,353][07345] Decorrelating experience for 32 frames...
[2024-10-23 03:11:46,410][07346] Decorrelating experience for 32 frames...
[2024-10-23 03:11:46,730][07347] Decorrelating experience for 32 frames...
[2024-10-23 03:11:46,846][07342] Decorrelating experience for 32 frames...
[2024-10-23 03:11:47,234][07348] Decorrelating experience for 64 frames...
[2024-10-23 03:11:47,240][07345] Decorrelating experience for 64 frames...
[2024-10-23 03:11:47,713][07344] Decorrelating experience for 64 frames...
[2024-10-23 03:11:47,725][00608] 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)
[2024-10-23 03:11:48,605][07346] Decorrelating experience for 64 frames...
[2024-10-23 03:11:48,805][07345] Decorrelating experience for 96 frames...
[2024-10-23 03:11:48,821][07350] Decorrelating experience for 64 frames...
[2024-10-23 03:11:49,050][07347] Decorrelating experience for 64 frames...
[2024-10-23 03:11:49,177][07342] Decorrelating experience for 64 frames...
[2024-10-23 03:11:49,274][00608] Heartbeat connected on RolloutWorker_w3
[2024-10-23 03:11:49,296][07348] Decorrelating experience for 96 frames...
[2024-10-23 03:11:49,640][00608] Heartbeat connected on RolloutWorker_w6
[2024-10-23 03:11:50,800][07347] Decorrelating experience for 96 frames...
[2024-10-23 03:11:50,960][07349] Decorrelating experience for 64 frames...
[2024-10-23 03:11:50,952][07342] Decorrelating experience for 96 frames...
[2024-10-23 03:11:51,055][00608] Heartbeat connected on RolloutWorker_w4
[2024-10-23 03:11:51,192][07346] Decorrelating experience for 96 frames...
[2024-10-23 03:11:51,239][00608] Heartbeat connected on RolloutWorker_w0
[2024-10-23 03:11:51,609][00608] Heartbeat connected on RolloutWorker_w5
[2024-10-23 03:11:52,725][00608] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 10.8. Samples: 108. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2024-10-23 03:11:52,731][00608] Avg episode reward: [(0, '0.960')]
[2024-10-23 03:11:53,563][07350] Decorrelating experience for 96 frames...
[2024-10-23 03:11:54,324][00608] Heartbeat connected on RolloutWorker_w2
[2024-10-23 03:11:54,332][07344] Decorrelating experience for 96 frames...
[2024-10-23 03:11:54,691][07349] Decorrelating experience for 96 frames...
[2024-10-23 03:11:54,833][00608] Heartbeat connected on RolloutWorker_w1
[2024-10-23 03:11:55,268][00608] Heartbeat connected on RolloutWorker_w7
[2024-10-23 03:11:55,591][07329] Signal inference workers to stop experience collection...
[2024-10-23 03:11:55,606][07343] InferenceWorker_p0-w0: stopping experience collection
[2024-10-23 03:11:57,725][00608] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 118.0. Samples: 1770. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2024-10-23 03:11:57,727][00608] Avg episode reward: [(0, '3.048')]
[2024-10-23 03:11:59,105][07329] Signal inference workers to resume experience collection...
[2024-10-23 03:11:59,106][07343] InferenceWorker_p0-w0: resuming experience collection
[2024-10-23 03:12:02,725][00608] Fps is (10 sec: 2048.0, 60 sec: 1024.0, 300 sec: 1024.0). Total num frames: 20480. Throughput: 0: 201.6. Samples: 4032. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-10-23 03:12:02,729][00608] Avg episode reward: [(0, '3.645')]
[2024-10-23 03:12:07,725][00608] Fps is (10 sec: 3686.4, 60 sec: 1474.6, 300 sec: 1474.6). Total num frames: 36864. Throughput: 0: 389.6. Samples: 9740. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
[2024-10-23 03:12:07,729][00608] Avg episode reward: [(0, '3.915')]
[2024-10-23 03:12:07,948][07343] Updated weights for policy 0, policy_version 10 (0.0031)
[2024-10-23 03:12:12,725][00608] Fps is (10 sec: 3686.4, 60 sec: 1911.5, 300 sec: 1911.5). Total num frames: 57344. Throughput: 0: 399.3. Samples: 11980. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-10-23 03:12:12,732][00608] Avg episode reward: [(0, '4.394')]
[2024-10-23 03:12:17,489][07343] Updated weights for policy 0, policy_version 20 (0.0023)
[2024-10-23 03:12:17,725][00608] Fps is (10 sec: 4505.6, 60 sec: 2340.6, 300 sec: 2340.6). Total num frames: 81920. Throughput: 0: 542.0. Samples: 18970. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:12:17,728][00608] Avg episode reward: [(0, '4.310')]
[2024-10-23 03:12:22,725][00608] Fps is (10 sec: 4505.6, 60 sec: 2560.0, 300 sec: 2560.0). Total num frames: 102400. Throughput: 0: 642.4. Samples: 25696. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-10-23 03:12:22,734][00608] Avg episode reward: [(0, '4.140')]
[2024-10-23 03:12:22,737][07329] Saving new best policy, reward=4.140!
[2024-10-23 03:12:27,726][00608] Fps is (10 sec: 3686.2, 60 sec: 2639.6, 300 sec: 2639.6). Total num frames: 118784. Throughput: 0: 619.7. Samples: 27886. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:12:27,731][00608] Avg episode reward: [(0, '4.235')]
[2024-10-23 03:12:27,746][07329] Saving new best policy, reward=4.235!
[2024-10-23 03:12:28,680][07343] Updated weights for policy 0, policy_version 30 (0.0032)
[2024-10-23 03:12:32,725][00608] Fps is (10 sec: 3686.4, 60 sec: 2785.3, 300 sec: 2785.3). Total num frames: 139264. Throughput: 0: 755.4. Samples: 33994. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-10-23 03:12:32,732][00608] Avg episode reward: [(0, '4.308')]
[2024-10-23 03:12:32,783][07329] Saving new best policy, reward=4.308!
[2024-10-23 03:12:37,063][07343] Updated weights for policy 0, policy_version 40 (0.0038)
[2024-10-23 03:12:37,725][00608] Fps is (10 sec: 4505.9, 60 sec: 2978.9, 300 sec: 2978.9). Total num frames: 163840. Throughput: 0: 915.2. Samples: 41290. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:12:37,738][00608] Avg episode reward: [(0, '4.354')]
[2024-10-23 03:12:37,750][07329] Saving new best policy, reward=4.354!
[2024-10-23 03:12:42,725][00608] Fps is (10 sec: 4096.0, 60 sec: 3003.7, 300 sec: 3003.7). Total num frames: 180224. Throughput: 0: 928.3. Samples: 43542. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:12:42,730][00608] Avg episode reward: [(0, '4.340')]
[2024-10-23 03:12:47,725][00608] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3087.8). Total num frames: 200704. Throughput: 0: 998.4. Samples: 48958. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:12:47,730][00608] Avg episode reward: [(0, '4.294')]
[2024-10-23 03:12:48,040][07343] Updated weights for policy 0, policy_version 50 (0.0031)
[2024-10-23 03:12:52,725][00608] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3218.3). Total num frames: 225280. Throughput: 0: 1035.6. Samples: 56342. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-10-23 03:12:52,730][00608] Avg episode reward: [(0, '4.422')]
[2024-10-23 03:12:52,732][07329] Saving new best policy, reward=4.422!
[2024-10-23 03:12:57,725][00608] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3222.2). Total num frames: 241664. Throughput: 0: 1052.6. Samples: 59346. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-10-23 03:12:57,731][00608] Avg episode reward: [(0, '4.512')]
[2024-10-23 03:12:57,741][07329] Saving new best policy, reward=4.512!
[2024-10-23 03:12:58,469][07343] Updated weights for policy 0, policy_version 60 (0.0014)
[2024-10-23 03:13:02,726][00608] Fps is (10 sec: 3686.0, 60 sec: 4027.7, 300 sec: 3276.8). Total num frames: 262144. Throughput: 0: 995.7. Samples: 63778. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:13:02,730][00608] Avg episode reward: [(0, '4.498')]
[2024-10-23 03:13:07,725][00608] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 3325.0). Total num frames: 282624. Throughput: 0: 1008.1. Samples: 71062. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-10-23 03:13:07,731][00608] Avg episode reward: [(0, '4.254')]
[2024-10-23 03:13:07,768][07343] Updated weights for policy 0, policy_version 70 (0.0034)
[2024-10-23 03:13:12,735][00608] Fps is (10 sec: 4501.8, 60 sec: 4163.6, 300 sec: 3413.0). Total num frames: 307200. Throughput: 0: 1040.6. Samples: 74722. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:13:12,739][00608] Avg episode reward: [(0, '4.342')]
[2024-10-23 03:13:17,725][00608] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3363.0). Total num frames: 319488. Throughput: 0: 1013.0. Samples: 79578. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:13:17,728][00608] Avg episode reward: [(0, '4.434')]
[2024-10-23 03:13:17,737][07329] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000078_319488.pth...
[2024-10-23 03:13:18,826][07343] Updated weights for policy 0, policy_version 80 (0.0025)
[2024-10-23 03:13:22,725][00608] Fps is (10 sec: 3689.9, 60 sec: 4027.7, 300 sec: 3440.6). Total num frames: 344064. Throughput: 0: 996.4. Samples: 86128. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:13:22,732][00608] Avg episode reward: [(0, '4.235')]
[2024-10-23 03:13:27,238][07343] Updated weights for policy 0, policy_version 90 (0.0036)
[2024-10-23 03:13:27,725][00608] Fps is (10 sec: 4915.2, 60 sec: 4164.3, 300 sec: 3510.9). Total num frames: 368640. Throughput: 0: 1026.9. Samples: 89754. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:13:27,734][00608] Avg episode reward: [(0, '4.359')]
[2024-10-23 03:13:32,726][00608] Fps is (10 sec: 3686.3, 60 sec: 4027.7, 300 sec: 3463.0). Total num frames: 380928. Throughput: 0: 1030.0. Samples: 95310. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:13:32,728][00608] Avg episode reward: [(0, '4.361')]
[2024-10-23 03:13:37,725][00608] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3526.1). Total num frames: 405504. Throughput: 0: 991.2. Samples: 100946. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:13:37,727][00608] Avg episode reward: [(0, '4.502')]
[2024-10-23 03:13:38,404][07343] Updated weights for policy 0, policy_version 100 (0.0015)
[2024-10-23 03:13:42,725][00608] Fps is (10 sec: 4915.3, 60 sec: 4164.3, 300 sec: 3584.0). Total num frames: 430080. Throughput: 0: 1007.5. Samples: 104682. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:13:42,728][00608] Avg episode reward: [(0, '4.585')]
[2024-10-23 03:13:42,739][07329] Saving new best policy, reward=4.585!
[2024-10-23 03:13:47,725][00608] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 3571.7). Total num frames: 446464. Throughput: 0: 1050.4. Samples: 111044. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:13:47,730][00608] Avg episode reward: [(0, '4.423')]
[2024-10-23 03:13:48,646][07343] Updated weights for policy 0, policy_version 110 (0.0031)
[2024-10-23 03:13:52,725][00608] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3560.4). Total num frames: 462848. Throughput: 0: 998.7. Samples: 116002. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:13:52,731][00608] Avg episode reward: [(0, '4.259')]
[2024-10-23 03:13:57,726][00608] Fps is (10 sec: 4095.9, 60 sec: 4096.0, 300 sec: 3610.5). Total num frames: 487424. Throughput: 0: 998.7. Samples: 119654. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:13:57,727][00608] Avg episode reward: [(0, '4.464')]
[2024-10-23 03:13:58,004][07343] Updated weights for policy 0, policy_version 120 (0.0027)
[2024-10-23 03:14:02,725][00608] Fps is (10 sec: 4505.5, 60 sec: 4096.1, 300 sec: 3627.9). Total num frames: 507904. Throughput: 0: 1050.0. Samples: 126828. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:14:02,730][00608] Avg episode reward: [(0, '4.516')]
[2024-10-23 03:14:07,725][00608] Fps is (10 sec: 3686.5, 60 sec: 4027.7, 300 sec: 3615.8). Total num frames: 524288. Throughput: 0: 1003.0. Samples: 131262. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:14:07,730][00608] Avg episode reward: [(0, '4.547')]
[2024-10-23 03:14:09,004][07343] Updated weights for policy 0, policy_version 130 (0.0030)
[2024-10-23 03:14:12,725][00608] Fps is (10 sec: 4096.1, 60 sec: 4028.4, 300 sec: 3659.1). Total num frames: 548864. Throughput: 0: 996.2. Samples: 134584. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:14:12,731][00608] Avg episode reward: [(0, '4.356')]
[2024-10-23 03:14:17,725][00608] Fps is (10 sec: 4505.5, 60 sec: 4164.3, 300 sec: 3673.2). Total num frames: 569344. Throughput: 0: 1031.0. Samples: 141706. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:14:17,728][00608] Avg episode reward: [(0, '4.346')]
[2024-10-23 03:14:17,752][07343] Updated weights for policy 0, policy_version 140 (0.0030)
[2024-10-23 03:14:22,725][00608] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3660.8). Total num frames: 585728. Throughput: 0: 1020.8. Samples: 146884. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:14:22,728][00608] Avg episode reward: [(0, '4.273')]
[2024-10-23 03:14:27,725][00608] Fps is (10 sec: 3686.5, 60 sec: 3959.5, 300 sec: 3674.0). Total num frames: 606208. Throughput: 0: 992.1. Samples: 149326. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:14:27,735][00608] Avg episode reward: [(0, '4.276')]
[2024-10-23 03:14:28,760][07343] Updated weights for policy 0, policy_version 150 (0.0032)
[2024-10-23 03:14:32,725][00608] Fps is (10 sec: 4505.6, 60 sec: 4164.3, 300 sec: 3710.5). Total num frames: 630784. Throughput: 0: 1008.2. Samples: 156412. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:14:32,730][00608] Avg episode reward: [(0, '4.458')]
[2024-10-23 03:14:37,725][00608] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3698.1). Total num frames: 647168. Throughput: 0: 1032.6. Samples: 162470. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:14:37,730][00608] Avg episode reward: [(0, '4.435')]
[2024-10-23 03:14:39,338][07343] Updated weights for policy 0, policy_version 160 (0.0016)
[2024-10-23 03:14:42,725][00608] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3709.2). Total num frames: 667648. Throughput: 0: 999.7. Samples: 164642. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:14:42,730][00608] Avg episode reward: [(0, '4.436')]
[2024-10-23 03:14:47,725][00608] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 3741.8). Total num frames: 692224. Throughput: 0: 992.5. Samples: 171490. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:14:47,728][00608] Avg episode reward: [(0, '4.481')]
[2024-10-23 03:14:48,562][07343] Updated weights for policy 0, policy_version 170 (0.0031)
[2024-10-23 03:14:52,725][00608] Fps is (10 sec: 4505.6, 60 sec: 4164.3, 300 sec: 3751.1). Total num frames: 712704. Throughput: 0: 1044.5. Samples: 178266. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:14:52,728][00608] Avg episode reward: [(0, '4.506')]
[2024-10-23 03:14:57,726][00608] Fps is (10 sec: 3276.7, 60 sec: 3959.5, 300 sec: 3717.9). Total num frames: 724992. Throughput: 0: 1017.8. Samples: 180386. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:14:57,730][00608] Avg episode reward: [(0, '4.509')]
[2024-10-23 03:14:59,746][07343] Updated weights for policy 0, policy_version 180 (0.0022)
[2024-10-23 03:15:02,725][00608] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3747.8). Total num frames: 749568. Throughput: 0: 989.0. Samples: 186212. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:15:02,731][00608] Avg episode reward: [(0, '4.640')]
[2024-10-23 03:15:02,733][07329] Saving new best policy, reward=4.640!
[2024-10-23 03:15:07,725][00608] Fps is (10 sec: 4915.3, 60 sec: 4164.3, 300 sec: 3776.3). Total num frames: 774144. Throughput: 0: 1033.3. Samples: 193384. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
[2024-10-23 03:15:07,728][00608] Avg episode reward: [(0, '4.742')]
[2024-10-23 03:15:07,739][07329] Saving new best policy, reward=4.742!
[2024-10-23 03:15:08,847][07343] Updated weights for policy 0, policy_version 190 (0.0052)
[2024-10-23 03:15:12,725][00608] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3744.9). Total num frames: 786432. Throughput: 0: 1034.8. Samples: 195892. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:15:12,731][00608] Avg episode reward: [(0, '4.722')]
[2024-10-23 03:15:17,725][00608] Fps is (10 sec: 3686.5, 60 sec: 4027.7, 300 sec: 3772.1). Total num frames: 811008. Throughput: 0: 992.4. Samples: 201070. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:15:17,728][00608] Avg episode reward: [(0, '4.597')]
[2024-10-23 03:15:17,738][07329] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000198_811008.pth...
[2024-10-23 03:15:19,505][07343] Updated weights for policy 0, policy_version 200 (0.0023)
[2024-10-23 03:15:22,725][00608] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 3779.5). Total num frames: 831488. Throughput: 0: 1015.0. Samples: 208144. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:15:22,730][00608] Avg episode reward: [(0, '4.385')]
[2024-10-23 03:15:27,725][00608] Fps is (10 sec: 4095.9, 60 sec: 4096.0, 300 sec: 3786.5). Total num frames: 851968. Throughput: 0: 1039.8. Samples: 211432. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
[2024-10-23 03:15:27,732][00608] Avg episode reward: [(0, '4.394')]
[2024-10-23 03:15:30,727][07343] Updated weights for policy 0, policy_version 210 (0.0050)
[2024-10-23 03:15:32,725][00608] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3757.6). Total num frames: 864256. Throughput: 0: 976.0. Samples: 215412. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
[2024-10-23 03:15:32,730][00608] Avg episode reward: [(0, '4.490')]
[2024-10-23 03:15:37,725][00608] Fps is (10 sec: 2867.2, 60 sec: 3891.2, 300 sec: 3747.4). Total num frames: 880640. Throughput: 0: 926.1. Samples: 219940. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:15:37,731][00608] Avg episode reward: [(0, '4.669')]
[2024-10-23 03:15:41,766][07343] Updated weights for policy 0, policy_version 220 (0.0034)
[2024-10-23 03:15:42,725][00608] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3771.7). Total num frames: 905216. Throughput: 0: 959.0. Samples: 223540. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:15:42,728][00608] Avg episode reward: [(0, '4.591')]
[2024-10-23 03:15:47,725][00608] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3744.9). Total num frames: 917504. Throughput: 0: 955.4. Samples: 229206. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:15:47,727][00608] Avg episode reward: [(0, '4.409')]
[2024-10-23 03:15:52,725][00608] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3751.9). Total num frames: 937984. Throughput: 0: 925.5. Samples: 235032. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-10-23 03:15:52,728][00608] Avg episode reward: [(0, '4.439')]
[2024-10-23 03:15:52,786][07343] Updated weights for policy 0, policy_version 230 (0.0033)
[2024-10-23 03:15:57,725][00608] Fps is (10 sec: 4505.5, 60 sec: 3959.5, 300 sec: 3774.7). Total num frames: 962560. Throughput: 0: 949.1. Samples: 238600. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-10-23 03:15:57,733][00608] Avg episode reward: [(0, '4.721')]
[2024-10-23 03:16:02,725][00608] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3765.2). Total num frames: 978944. Throughput: 0: 973.8. Samples: 244892. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:16:02,729][00608] Avg episode reward: [(0, '4.743')]
[2024-10-23 03:16:02,746][07329] Saving new best policy, reward=4.743!
[2024-10-23 03:16:02,754][07343] Updated weights for policy 0, policy_version 240 (0.0046)
[2024-10-23 03:16:07,725][00608] Fps is (10 sec: 3686.5, 60 sec: 3754.7, 300 sec: 3771.4). Total num frames: 999424. Throughput: 0: 925.1. Samples: 249774. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:16:07,729][00608] Avg episode reward: [(0, '4.570')]
[2024-10-23 03:16:12,498][07343] Updated weights for policy 0, policy_version 250 (0.0022)
[2024-10-23 03:16:12,725][00608] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3792.6). Total num frames: 1024000. Throughput: 0: 933.8. Samples: 253454. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-10-23 03:16:12,728][00608] Avg episode reward: [(0, '4.458')]
[2024-10-23 03:16:17,725][00608] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3798.1). Total num frames: 1044480. Throughput: 0: 1002.4. Samples: 260520. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:16:17,731][00608] Avg episode reward: [(0, '4.494')]
[2024-10-23 03:16:22,725][00608] Fps is (10 sec: 3276.7, 60 sec: 3754.7, 300 sec: 3774.2). Total num frames: 1056768. Throughput: 0: 1000.0. Samples: 264942. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-10-23 03:16:22,728][00608] Avg episode reward: [(0, '4.563')]
[2024-10-23 03:16:23,563][07343] Updated weights for policy 0, policy_version 260 (0.0044)
[2024-10-23 03:16:27,725][00608] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3794.2). Total num frames: 1081344. Throughput: 0: 996.4. Samples: 268376. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:16:27,728][00608] Avg episode reward: [(0, '4.730')]
[2024-10-23 03:16:32,045][07343] Updated weights for policy 0, policy_version 270 (0.0026)
[2024-10-23 03:16:32,725][00608] Fps is (10 sec: 4915.3, 60 sec: 4027.7, 300 sec: 3813.5). Total num frames: 1105920. Throughput: 0: 1030.9. Samples: 275598. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:16:32,728][00608] Avg episode reward: [(0, '4.617')]
[2024-10-23 03:16:37,725][00608] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3804.4). Total num frames: 1122304. Throughput: 0: 1016.4. Samples: 280768. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-10-23 03:16:37,728][00608] Avg episode reward: [(0, '4.720')]
[2024-10-23 03:16:42,725][00608] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3873.8). Total num frames: 1142784. Throughput: 0: 996.7. Samples: 283452. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:16:42,731][00608] Avg episode reward: [(0, '4.874')]
[2024-10-23 03:16:42,735][07329] Saving new best policy, reward=4.874!
[2024-10-23 03:16:43,106][07343] Updated weights for policy 0, policy_version 280 (0.0020)
[2024-10-23 03:16:47,725][00608] Fps is (10 sec: 4505.6, 60 sec: 4164.3, 300 sec: 3957.2). Total num frames: 1167360. Throughput: 0: 1018.6. Samples: 290728. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:16:47,728][00608] Avg episode reward: [(0, '4.934')]
[2024-10-23 03:16:47,739][07329] Saving new best policy, reward=4.934!
[2024-10-23 03:16:52,725][00608] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 1183744. Throughput: 0: 1039.9. Samples: 296570. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:16:52,731][00608] Avg episode reward: [(0, '4.987')]
[2024-10-23 03:16:52,735][07329] Saving new best policy, reward=4.987!
[2024-10-23 03:16:53,143][07343] Updated weights for policy 0, policy_version 290 (0.0035)
[2024-10-23 03:16:57,725][00608] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4012.7). Total num frames: 1204224. Throughput: 0: 1006.4. Samples: 298742. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-10-23 03:16:57,729][00608] Avg episode reward: [(0, '5.054')]
[2024-10-23 03:16:57,742][07329] Saving new best policy, reward=5.054!
[2024-10-23 03:17:02,641][07343] Updated weights for policy 0, policy_version 300 (0.0041)
[2024-10-23 03:17:02,725][00608] Fps is (10 sec: 4505.6, 60 sec: 4164.3, 300 sec: 4040.5). Total num frames: 1228800. Throughput: 0: 1004.4. Samples: 305718. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-10-23 03:17:02,731][00608] Avg episode reward: [(0, '5.200')]
[2024-10-23 03:17:02,736][07329] Saving new best policy, reward=5.200!
[2024-10-23 03:17:07,725][00608] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4026.6). Total num frames: 1245184. Throughput: 0: 1046.9. Samples: 312054. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-10-23 03:17:07,732][00608] Avg episode reward: [(0, '5.480')]
[2024-10-23 03:17:07,746][07329] Saving new best policy, reward=5.480!
[2024-10-23 03:17:12,725][00608] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3998.8). Total num frames: 1261568. Throughput: 0: 1017.2. Samples: 314148. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-10-23 03:17:12,728][00608] Avg episode reward: [(0, '5.517')]
[2024-10-23 03:17:12,734][07329] Saving new best policy, reward=5.517!
[2024-10-23 03:17:13,877][07343] Updated weights for policy 0, policy_version 310 (0.0036)
[2024-10-23 03:17:17,725][00608] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 4012.7). Total num frames: 1286144. Throughput: 0: 995.8. Samples: 320410. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:17:17,730][00608] Avg episode reward: [(0, '5.688')]
[2024-10-23 03:17:17,740][07329] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000314_1286144.pth...
[2024-10-23 03:17:17,879][07329] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000078_319488.pth
[2024-10-23 03:17:17,896][07329] Saving new best policy, reward=5.688!
[2024-10-23 03:17:22,608][07343] Updated weights for policy 0, policy_version 320 (0.0025)
[2024-10-23 03:17:22,725][00608] Fps is (10 sec: 4915.2, 60 sec: 4232.5, 300 sec: 4040.5). Total num frames: 1310720. Throughput: 0: 1039.2. Samples: 327532. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:17:22,727][00608] Avg episode reward: [(0, '5.891')]
[2024-10-23 03:17:22,735][07329] Saving new best policy, reward=5.891!
[2024-10-23 03:17:27,726][00608] Fps is (10 sec: 3686.3, 60 sec: 4027.7, 300 sec: 4012.7). Total num frames: 1323008. Throughput: 0: 1029.3. Samples: 329772. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:17:27,733][00608] Avg episode reward: [(0, '5.723')]
[2024-10-23 03:17:32,725][00608] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4012.7). Total num frames: 1347584. Throughput: 0: 992.8. Samples: 335404. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:17:32,727][00608] Avg episode reward: [(0, '5.353')]
[2024-10-23 03:17:33,345][07343] Updated weights for policy 0, policy_version 330 (0.0027)
[2024-10-23 03:17:37,725][00608] Fps is (10 sec: 4915.4, 60 sec: 4164.3, 300 sec: 4040.5). Total num frames: 1372160. Throughput: 0: 1023.1. Samples: 342610. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:17:37,728][00608] Avg episode reward: [(0, '5.141')]
[2024-10-23 03:17:42,725][00608] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4026.6). Total num frames: 1388544. Throughput: 0: 1041.8. Samples: 345624. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:17:42,728][00608] Avg episode reward: [(0, '5.185')]
[2024-10-23 03:17:43,985][07343] Updated weights for policy 0, policy_version 340 (0.0033)
[2024-10-23 03:17:47,725][00608] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4012.7). Total num frames: 1409024. Throughput: 0: 994.9. Samples: 350490. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:17:47,733][00608] Avg episode reward: [(0, '5.072')]
[2024-10-23 03:17:52,682][07343] Updated weights for policy 0, policy_version 350 (0.0035)
[2024-10-23 03:17:52,726][00608] Fps is (10 sec: 4505.5, 60 sec: 4164.2, 300 sec: 4040.5). Total num frames: 1433600. Throughput: 0: 1018.8. Samples: 357898. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
[2024-10-23 03:17:52,728][00608] Avg episode reward: [(0, '5.424')]
[2024-10-23 03:17:57,727][00608] Fps is (10 sec: 4095.2, 60 sec: 4095.9, 300 sec: 4026.6). Total num frames: 1449984. Throughput: 0: 1054.0. Samples: 361582. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-10-23 03:17:57,732][00608] Avg episode reward: [(0, '5.560')]
[2024-10-23 03:18:02,725][00608] Fps is (10 sec: 3276.9, 60 sec: 3959.5, 300 sec: 4012.7). Total num frames: 1466368. Throughput: 0: 1016.3. Samples: 366144. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:18:02,730][00608] Avg episode reward: [(0, '5.546')]
[2024-10-23 03:18:03,758][07343] Updated weights for policy 0, policy_version 360 (0.0026)
[2024-10-23 03:18:07,725][00608] Fps is (10 sec: 4096.8, 60 sec: 4096.0, 300 sec: 4012.8). Total num frames: 1490944. Throughput: 0: 1010.4. Samples: 372998. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-10-23 03:18:07,730][00608] Avg episode reward: [(0, '5.893')]
[2024-10-23 03:18:07,744][07329] Saving new best policy, reward=5.893!
[2024-10-23 03:18:12,187][07343] Updated weights for policy 0, policy_version 370 (0.0040)
[2024-10-23 03:18:12,732][00608] Fps is (10 sec: 4912.2, 60 sec: 4232.1, 300 sec: 4054.3). Total num frames: 1515520. Throughput: 0: 1042.1. Samples: 376672. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:18:12,734][00608] Avg episode reward: [(0, '6.037')]
[2024-10-23 03:18:12,736][07329] Saving new best policy, reward=6.037!
[2024-10-23 03:18:17,729][00608] Fps is (10 sec: 3685.2, 60 sec: 4027.5, 300 sec: 4012.6). Total num frames: 1527808. Throughput: 0: 1036.3. Samples: 382040. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:18:17,730][00608] Avg episode reward: [(0, '5.742')]
[2024-10-23 03:18:22,725][00608] Fps is (10 sec: 3688.7, 60 sec: 4027.7, 300 sec: 4012.7). Total num frames: 1552384. Throughput: 0: 1014.5. Samples: 388262. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-10-23 03:18:22,728][00608] Avg episode reward: [(0, '5.774')]
[2024-10-23 03:18:22,933][07343] Updated weights for policy 0, policy_version 380 (0.0039)
[2024-10-23 03:18:27,725][00608] Fps is (10 sec: 4916.8, 60 sec: 4232.6, 300 sec: 4054.3). Total num frames: 1576960. Throughput: 0: 1030.4. Samples: 391992. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:18:27,728][00608] Avg episode reward: [(0, '5.984')]
[2024-10-23 03:18:32,726][00608] Fps is (10 sec: 4095.9, 60 sec: 4096.0, 300 sec: 4026.6). Total num frames: 1593344. Throughput: 0: 1058.9. Samples: 398140. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:18:32,732][00608] Avg episode reward: [(0, '6.096')]
[2024-10-23 03:18:32,734][07329] Saving new best policy, reward=6.096!
[2024-10-23 03:18:33,314][07343] Updated weights for policy 0, policy_version 390 (0.0029)
[2024-10-23 03:18:37,725][00608] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4012.7). Total num frames: 1613824. Throughput: 0: 1012.7. Samples: 403468. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:18:37,732][00608] Avg episode reward: [(0, '6.123')]
[2024-10-23 03:18:37,742][07329] Saving new best policy, reward=6.123!
[2024-10-23 03:18:42,321][07343] Updated weights for policy 0, policy_version 400 (0.0028)
[2024-10-23 03:18:42,725][00608] Fps is (10 sec: 4505.7, 60 sec: 4164.3, 300 sec: 4040.5). Total num frames: 1638400. Throughput: 0: 1010.9. Samples: 407070. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:18:42,728][00608] Avg episode reward: [(0, '6.178')]
[2024-10-23 03:18:42,730][07329] Saving new best policy, reward=6.178!
[2024-10-23 03:18:47,726][00608] Fps is (10 sec: 4505.4, 60 sec: 4164.2, 300 sec: 4054.3). Total num frames: 1658880. Throughput: 0: 1063.6. Samples: 414008. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:18:47,728][00608] Avg episode reward: [(0, '5.710')]
[2024-10-23 03:18:52,725][00608] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4026.6). Total num frames: 1675264. Throughput: 0: 1012.3. Samples: 418550. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:18:52,732][00608] Avg episode reward: [(0, '6.386')]
[2024-10-23 03:18:52,734][07329] Saving new best policy, reward=6.386!
[2024-10-23 03:18:53,359][07343] Updated weights for policy 0, policy_version 410 (0.0026)
[2024-10-23 03:18:57,725][00608] Fps is (10 sec: 4096.2, 60 sec: 4164.4, 300 sec: 4040.5). Total num frames: 1699840. Throughput: 0: 1012.7. Samples: 422236. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:18:57,730][00608] Avg episode reward: [(0, '7.316')]
[2024-10-23 03:18:57,738][07329] Saving new best policy, reward=7.316!
[2024-10-23 03:19:01,707][07343] Updated weights for policy 0, policy_version 420 (0.0032)
[2024-10-23 03:19:02,729][00608] Fps is (10 sec: 4504.2, 60 sec: 4232.3, 300 sec: 4054.3). Total num frames: 1720320. Throughput: 0: 1056.6. Samples: 429588. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:19:02,731][00608] Avg episode reward: [(0, '7.423')]
[2024-10-23 03:19:02,733][07329] Saving new best policy, reward=7.423!
[2024-10-23 03:19:07,725][00608] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4026.6). Total num frames: 1736704. Throughput: 0: 1021.6. Samples: 434234. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-10-23 03:19:07,730][00608] Avg episode reward: [(0, '7.525')]
[2024-10-23 03:19:07,743][07329] Saving new best policy, reward=7.525!
[2024-10-23 03:19:12,725][00608] Fps is (10 sec: 3687.6, 60 sec: 4028.2, 300 sec: 4026.6). Total num frames: 1757184. Throughput: 0: 1002.4. Samples: 437102. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:19:12,727][00608] Avg episode reward: [(0, '7.451')]
[2024-10-23 03:19:12,803][07343] Updated weights for policy 0, policy_version 430 (0.0034)
[2024-10-23 03:19:17,725][00608] Fps is (10 sec: 4505.6, 60 sec: 4232.8, 300 sec: 4054.3). Total num frames: 1781760. Throughput: 0: 1028.3. Samples: 444412. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-10-23 03:19:17,730][00608] Avg episode reward: [(0, '8.165')]
[2024-10-23 03:19:17,740][07329] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000435_1781760.pth...
[2024-10-23 03:19:17,859][07329] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000198_811008.pth
[2024-10-23 03:19:17,872][07329] Saving new best policy, reward=8.165!
[2024-10-23 03:19:22,725][00608] Fps is (10 sec: 4095.9, 60 sec: 4096.0, 300 sec: 4040.5). Total num frames: 1798144. Throughput: 0: 1032.4. Samples: 449928. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:19:22,727][00608] Avg episode reward: [(0, '8.719')]
[2024-10-23 03:19:22,729][07329] Saving new best policy, reward=8.719!
[2024-10-23 03:19:23,515][07343] Updated weights for policy 0, policy_version 440 (0.0027)
[2024-10-23 03:19:27,725][00608] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4026.6). Total num frames: 1818624. Throughput: 0: 1000.4. Samples: 452090. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-10-23 03:19:27,732][00608] Avg episode reward: [(0, '9.536')]
[2024-10-23 03:19:27,741][07329] Saving new best policy, reward=9.536!
[2024-10-23 03:19:32,336][07343] Updated weights for policy 0, policy_version 450 (0.0029)
[2024-10-23 03:19:32,725][00608] Fps is (10 sec: 4505.7, 60 sec: 4164.3, 300 sec: 4054.3). Total num frames: 1843200. Throughput: 0: 1009.9. Samples: 459454. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:19:32,731][00608] Avg episode reward: [(0, '9.832')]
[2024-10-23 03:19:32,733][07329] Saving new best policy, reward=9.832!
[2024-10-23 03:19:37,728][00608] Fps is (10 sec: 4095.1, 60 sec: 4095.9, 300 sec: 4040.4). Total num frames: 1859584. Throughput: 0: 1045.9. Samples: 465616. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-10-23 03:19:37,732][00608] Avg episode reward: [(0, '10.489')]
[2024-10-23 03:19:37,814][07329] Saving new best policy, reward=10.489!
[2024-10-23 03:19:42,725][00608] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4026.6). Total num frames: 1880064. Throughput: 0: 1012.5. Samples: 467800. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-10-23 03:19:42,729][00608] Avg episode reward: [(0, '10.604')]
[2024-10-23 03:19:42,731][07329] Saving new best policy, reward=10.604!
[2024-10-23 03:19:43,607][07343] Updated weights for policy 0, policy_version 460 (0.0030)
[2024-10-23 03:19:47,725][00608] Fps is (10 sec: 4096.9, 60 sec: 4027.8, 300 sec: 4026.6). Total num frames: 1900544. Throughput: 0: 994.3. Samples: 474328. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:19:47,731][00608] Avg episode reward: [(0, '10.808')]
[2024-10-23 03:19:47,755][07329] Saving new best policy, reward=10.808!
[2024-10-23 03:19:52,171][07343] Updated weights for policy 0, policy_version 470 (0.0016)
[2024-10-23 03:19:52,725][00608] Fps is (10 sec: 4505.5, 60 sec: 4164.3, 300 sec: 4068.2). Total num frames: 1925120. Throughput: 0: 1047.9. Samples: 481390. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-10-23 03:19:52,732][00608] Avg episode reward: [(0, '10.105')]
[2024-10-23 03:19:57,725][00608] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 4026.6). Total num frames: 1937408. Throughput: 0: 1033.4. Samples: 483606. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:19:57,728][00608] Avg episode reward: [(0, '9.222')]
[2024-10-23 03:20:02,726][00608] Fps is (10 sec: 2457.6, 60 sec: 3823.1, 300 sec: 3984.9). Total num frames: 1949696. Throughput: 0: 956.7. Samples: 487464. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-10-23 03:20:02,728][00608] Avg episode reward: [(0, '8.499')]
[2024-10-23 03:20:05,569][07343] Updated weights for policy 0, policy_version 480 (0.0046)
[2024-10-23 03:20:07,725][00608] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 4026.6). Total num frames: 1974272. Throughput: 0: 970.0. Samples: 493576. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:20:07,729][00608] Avg episode reward: [(0, '9.296')]
[2024-10-23 03:20:12,725][00608] Fps is (10 sec: 4505.7, 60 sec: 3959.5, 300 sec: 4012.7). Total num frames: 1994752. Throughput: 0: 1002.2. Samples: 497188. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:20:12,730][00608] Avg episode reward: [(0, '10.035')]
[2024-10-23 03:20:16,392][07343] Updated weights for policy 0, policy_version 490 (0.0046)
[2024-10-23 03:20:17,725][00608] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3998.8). Total num frames: 2011136. Throughput: 0: 937.5. Samples: 501642. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-10-23 03:20:17,730][00608] Avg episode reward: [(0, '11.266')]
[2024-10-23 03:20:17,739][07329] Saving new best policy, reward=11.266!
[2024-10-23 03:20:22,725][00608] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 4012.7). Total num frames: 2035712. Throughput: 0: 958.7. Samples: 508756. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:20:22,728][00608] Avg episode reward: [(0, '11.718')]
[2024-10-23 03:20:22,734][07329] Saving new best policy, reward=11.718!
[2024-10-23 03:20:24,994][07343] Updated weights for policy 0, policy_version 500 (0.0024)
[2024-10-23 03:20:27,727][00608] Fps is (10 sec: 4504.8, 60 sec: 3959.4, 300 sec: 4040.4). Total num frames: 2056192. Throughput: 0: 989.7. Samples: 512340. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
[2024-10-23 03:20:27,735][00608] Avg episode reward: [(0, '11.415')]
[2024-10-23 03:20:32,725][00608] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 4040.5). Total num frames: 2072576. Throughput: 0: 955.5. Samples: 517324. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-10-23 03:20:32,733][00608] Avg episode reward: [(0, '11.730')]
[2024-10-23 03:20:32,739][07329] Saving new best policy, reward=11.730!
[2024-10-23 03:20:36,102][07343] Updated weights for policy 0, policy_version 510 (0.0031)
[2024-10-23 03:20:37,725][00608] Fps is (10 sec: 4096.7, 60 sec: 3959.6, 300 sec: 4040.5). Total num frames: 2097152. Throughput: 0: 939.1. Samples: 523648. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:20:37,728][00608] Avg episode reward: [(0, '12.472')]
[2024-10-23 03:20:37,741][07329] Saving new best policy, reward=12.472!
[2024-10-23 03:20:42,725][00608] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 4068.2). Total num frames: 2117632. Throughput: 0: 969.2. Samples: 527218. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:20:42,727][00608] Avg episode reward: [(0, '13.131')]
[2024-10-23 03:20:42,729][07329] Saving new best policy, reward=13.131!
[2024-10-23 03:20:45,808][07343] Updated weights for policy 0, policy_version 520 (0.0034)
[2024-10-23 03:20:47,728][00608] Fps is (10 sec: 3685.4, 60 sec: 3891.0, 300 sec: 4054.3). Total num frames: 2134016. Throughput: 0: 1011.1. Samples: 532964. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:20:47,736][00608] Avg episode reward: [(0, '13.824')]
[2024-10-23 03:20:47,750][07329] Saving new best policy, reward=13.824!
[2024-10-23 03:20:52,725][00608] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 4040.5). Total num frames: 2154496. Throughput: 0: 998.1. Samples: 538490. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-10-23 03:20:52,733][00608] Avg episode reward: [(0, '14.605')]
[2024-10-23 03:20:52,738][07329] Saving new best policy, reward=14.605!
[2024-10-23 03:20:55,599][07343] Updated weights for policy 0, policy_version 530 (0.0050)
[2024-10-23 03:20:57,725][00608] Fps is (10 sec: 4506.7, 60 sec: 4027.7, 300 sec: 4068.2). Total num frames: 2179072. Throughput: 0: 997.1. Samples: 542058. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-10-23 03:20:57,733][00608] Avg episode reward: [(0, '14.801')]
[2024-10-23 03:20:57,742][07329] Saving new best policy, reward=14.801!
[2024-10-23 03:21:02,725][00608] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4054.3). Total num frames: 2195456. Throughput: 0: 1047.0. Samples: 548758. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-10-23 03:21:02,731][00608] Avg episode reward: [(0, '14.303')]
[2024-10-23 03:21:06,951][07343] Updated weights for policy 0, policy_version 540 (0.0033)
[2024-10-23 03:21:07,725][00608] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 4026.6). Total num frames: 2211840. Throughput: 0: 992.4. Samples: 553416. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:21:07,727][00608] Avg episode reward: [(0, '14.916')]
[2024-10-23 03:21:07,817][07329] Saving new best policy, reward=14.916!
[2024-10-23 03:21:12,725][00608] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 4040.5). Total num frames: 2236416. Throughput: 0: 993.1. Samples: 557026. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:21:12,728][00608] Avg episode reward: [(0, '14.244')]
[2024-10-23 03:21:15,332][07343] Updated weights for policy 0, policy_version 550 (0.0028)
[2024-10-23 03:21:17,725][00608] Fps is (10 sec: 4915.2, 60 sec: 4164.3, 300 sec: 4082.1). Total num frames: 2260992. Throughput: 0: 1044.4. Samples: 564322. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:21:17,730][00608] Avg episode reward: [(0, '15.500')]
[2024-10-23 03:21:17,743][07329] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000552_2260992.pth...
[2024-10-23 03:21:17,933][07329] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000314_1286144.pth
[2024-10-23 03:21:17,955][07329] Saving new best policy, reward=15.500!
[2024-10-23 03:21:22,725][00608] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 4040.5). Total num frames: 2273280. Throughput: 0: 1004.7. Samples: 568858. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:21:22,730][00608] Avg episode reward: [(0, '15.990')]
[2024-10-23 03:21:22,737][07329] Saving new best policy, reward=15.990!
[2024-10-23 03:21:26,404][07343] Updated weights for policy 0, policy_version 560 (0.0053)
[2024-10-23 03:21:27,725][00608] Fps is (10 sec: 3686.3, 60 sec: 4027.8, 300 sec: 4040.5). Total num frames: 2297856. Throughput: 0: 994.1. Samples: 571954. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:21:27,732][00608] Avg episode reward: [(0, '16.608')]
[2024-10-23 03:21:27,742][07329] Saving new best policy, reward=16.608!
[2024-10-23 03:21:32,725][00608] Fps is (10 sec: 4915.2, 60 sec: 4164.3, 300 sec: 4068.2). Total num frames: 2322432. Throughput: 0: 1029.9. Samples: 579306. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-10-23 03:21:32,730][00608] Avg episode reward: [(0, '17.059')]
[2024-10-23 03:21:32,733][07329] Saving new best policy, reward=17.059!
[2024-10-23 03:21:36,118][07343] Updated weights for policy 0, policy_version 570 (0.0018)
[2024-10-23 03:21:37,725][00608] Fps is (10 sec: 4096.1, 60 sec: 4027.7, 300 sec: 4054.3). Total num frames: 2338816. Throughput: 0: 1026.2. Samples: 584670. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:21:37,734][00608] Avg episode reward: [(0, '16.284')]
[2024-10-23 03:21:42,725][00608] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4040.5). Total num frames: 2359296. Throughput: 0: 1000.0. Samples: 587056. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:21:42,732][00608] Avg episode reward: [(0, '17.959')]
[2024-10-23 03:21:42,736][07329] Saving new best policy, reward=17.959!
[2024-10-23 03:21:45,885][07343] Updated weights for policy 0, policy_version 580 (0.0035)
[2024-10-23 03:21:47,725][00608] Fps is (10 sec: 4505.6, 60 sec: 4164.4, 300 sec: 4068.2). Total num frames: 2383872. Throughput: 0: 1014.8. Samples: 594422. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:21:47,729][00608] Avg episode reward: [(0, '17.987')]
[2024-10-23 03:21:47,745][07329] Saving new best policy, reward=17.987!
[2024-10-23 03:21:52,725][00608] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4054.3). Total num frames: 2400256. Throughput: 0: 1048.3. Samples: 600588. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:21:52,731][00608] Avg episode reward: [(0, '17.765')]
[2024-10-23 03:21:56,804][07343] Updated weights for policy 0, policy_version 590 (0.0028)
[2024-10-23 03:21:57,725][00608] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4040.5). Total num frames: 2420736. Throughput: 0: 1017.3. Samples: 602806. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:21:57,730][00608] Avg episode reward: [(0, '17.620')]
[2024-10-23 03:22:02,725][00608] Fps is (10 sec: 4505.6, 60 sec: 4164.3, 300 sec: 4068.2). Total num frames: 2445312. Throughput: 0: 1006.4. Samples: 609610. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:22:02,732][00608] Avg episode reward: [(0, '15.420')]
[2024-10-23 03:22:05,228][07343] Updated weights for policy 0, policy_version 600 (0.0028)
[2024-10-23 03:22:07,725][00608] Fps is (10 sec: 4505.6, 60 sec: 4232.5, 300 sec: 4082.1). Total num frames: 2465792. Throughput: 0: 1058.2. Samples: 616476. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:22:07,730][00608] Avg episode reward: [(0, '15.690')]
[2024-10-23 03:22:12,725][00608] Fps is (10 sec: 3276.8, 60 sec: 4027.7, 300 sec: 4040.5). Total num frames: 2478080. Throughput: 0: 1037.8. Samples: 618656. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:22:12,732][00608] Avg episode reward: [(0, '16.441')]
[2024-10-23 03:22:16,315][07343] Updated weights for policy 0, policy_version 610 (0.0033)
[2024-10-23 03:22:17,725][00608] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4040.5). Total num frames: 2502656. Throughput: 0: 1010.1. Samples: 624762. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-10-23 03:22:17,733][00608] Avg episode reward: [(0, '18.246')]
[2024-10-23 03:22:17,763][07329] Saving new best policy, reward=18.246!
[2024-10-23 03:22:22,725][00608] Fps is (10 sec: 4915.2, 60 sec: 4232.5, 300 sec: 4082.1). Total num frames: 2527232. Throughput: 0: 1054.8. Samples: 632136. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:22:22,728][00608] Avg episode reward: [(0, '19.513')]
[2024-10-23 03:22:22,737][07329] Saving new best policy, reward=19.513!
[2024-10-23 03:22:25,989][07343] Updated weights for policy 0, policy_version 620 (0.0041)
[2024-10-23 03:22:27,725][00608] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4054.3). Total num frames: 2543616. Throughput: 0: 1055.1. Samples: 634536. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:22:27,730][00608] Avg episode reward: [(0, '20.699')]
[2024-10-23 03:22:27,745][07329] Saving new best policy, reward=20.699!
[2024-10-23 03:22:32,725][00608] Fps is (10 sec: 3686.3, 60 sec: 4027.7, 300 sec: 4040.5). Total num frames: 2564096. Throughput: 0: 1011.4. Samples: 639934. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:22:32,729][00608] Avg episode reward: [(0, '21.383')]
[2024-10-23 03:22:32,738][07329] Saving new best policy, reward=21.383!
[2024-10-23 03:22:35,734][07343] Updated weights for policy 0, policy_version 630 (0.0042)
[2024-10-23 03:22:37,725][00608] Fps is (10 sec: 4505.6, 60 sec: 4164.3, 300 sec: 4068.2). Total num frames: 2588672. Throughput: 0: 1032.9. Samples: 647070. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:22:37,733][00608] Avg episode reward: [(0, '21.381')]
[2024-10-23 03:22:42,725][00608] Fps is (10 sec: 4096.1, 60 sec: 4096.0, 300 sec: 4054.3). Total num frames: 2605056. Throughput: 0: 1056.8. Samples: 650360. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-10-23 03:22:42,728][00608] Avg episode reward: [(0, '20.358')]
[2024-10-23 03:22:46,451][07343] Updated weights for policy 0, policy_version 640 (0.0039)
[2024-10-23 03:22:47,725][00608] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4040.5). Total num frames: 2625536. Throughput: 0: 1006.6. Samples: 654906. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-10-23 03:22:47,727][00608] Avg episode reward: [(0, '20.757')]
[2024-10-23 03:22:52,725][00608] Fps is (10 sec: 4505.5, 60 sec: 4164.3, 300 sec: 4068.3). Total num frames: 2650112. Throughput: 0: 1019.5. Samples: 662352. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-10-23 03:22:52,729][00608] Avg episode reward: [(0, '21.465')]
[2024-10-23 03:22:52,732][07329] Saving new best policy, reward=21.465!
[2024-10-23 03:22:55,030][07343] Updated weights for policy 0, policy_version 650 (0.0033)
[2024-10-23 03:22:57,725][00608] Fps is (10 sec: 4505.6, 60 sec: 4164.3, 300 sec: 4082.1). Total num frames: 2670592. Throughput: 0: 1051.1. Samples: 665956. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-10-23 03:22:57,733][00608] Avg episode reward: [(0, '21.828')]
[2024-10-23 03:22:57,742][07329] Saving new best policy, reward=21.828!
[2024-10-23 03:23:02,725][00608] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 4040.5). Total num frames: 2682880. Throughput: 0: 1019.1. Samples: 670622. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-10-23 03:23:02,733][00608] Avg episode reward: [(0, '22.297')]
[2024-10-23 03:23:02,798][07329] Saving new best policy, reward=22.297!
[2024-10-23 03:23:06,331][07343] Updated weights for policy 0, policy_version 660 (0.0026)
[2024-10-23 03:23:07,727][00608] Fps is (10 sec: 3685.9, 60 sec: 4027.6, 300 sec: 4040.5). Total num frames: 2707456. Throughput: 0: 997.2. Samples: 677010. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:23:07,729][00608] Avg episode reward: [(0, '23.139')]
[2024-10-23 03:23:07,742][07329] Saving new best policy, reward=23.139!
[2024-10-23 03:23:12,725][00608] Fps is (10 sec: 4915.2, 60 sec: 4232.5, 300 sec: 4082.2). Total num frames: 2732032. Throughput: 0: 1023.1. Samples: 680576. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-10-23 03:23:12,730][00608] Avg episode reward: [(0, '22.773')]
[2024-10-23 03:23:16,677][07343] Updated weights for policy 0, policy_version 670 (0.0024)
[2024-10-23 03:23:17,725][00608] Fps is (10 sec: 3686.9, 60 sec: 4027.7, 300 sec: 4040.5). Total num frames: 2744320. Throughput: 0: 1026.1. Samples: 686108. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:23:17,734][00608] Avg episode reward: [(0, '22.526')]
[2024-10-23 03:23:17,748][07329] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000670_2744320.pth...
[2024-10-23 03:23:17,918][07329] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000435_1781760.pth
[2024-10-23 03:23:22,725][00608] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4040.5). Total num frames: 2768896. Throughput: 0: 997.7. Samples: 691968. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-10-23 03:23:22,733][00608] Avg episode reward: [(0, '22.699')]
[2024-10-23 03:23:25,861][07343] Updated weights for policy 0, policy_version 680 (0.0040)
[2024-10-23 03:23:27,725][00608] Fps is (10 sec: 4915.2, 60 sec: 4164.3, 300 sec: 4068.2). Total num frames: 2793472. Throughput: 0: 1006.6. Samples: 695658. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:23:27,732][00608] Avg episode reward: [(0, '22.478')]
[2024-10-23 03:23:32,725][00608] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4054.3). Total num frames: 2809856. Throughput: 0: 1045.9. Samples: 701970. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-10-23 03:23:32,732][00608] Avg episode reward: [(0, '21.853')]
[2024-10-23 03:23:36,806][07343] Updated weights for policy 0, policy_version 690 (0.0028)
[2024-10-23 03:23:37,725][00608] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 4026.6). Total num frames: 2826240. Throughput: 0: 993.9. Samples: 707076. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-10-23 03:23:37,731][00608] Avg episode reward: [(0, '22.971')]
[2024-10-23 03:23:42,725][00608] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4040.5). Total num frames: 2850816. Throughput: 0: 996.1. Samples: 710780. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-10-23 03:23:42,728][00608] Avg episode reward: [(0, '23.278')]
[2024-10-23 03:23:42,787][07329] Saving new best policy, reward=23.278!
[2024-10-23 03:23:45,378][07343] Updated weights for policy 0, policy_version 700 (0.0023)
[2024-10-23 03:23:47,727][00608] Fps is (10 sec: 4505.0, 60 sec: 4095.9, 300 sec: 4054.3). Total num frames: 2871296. Throughput: 0: 1049.3. Samples: 717842. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-10-23 03:23:47,738][00608] Avg episode reward: [(0, '22.235')]
[2024-10-23 03:23:52,725][00608] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 4026.6). Total num frames: 2887680. Throughput: 0: 1006.5. Samples: 722302. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:23:52,728][00608] Avg episode reward: [(0, '23.564')]
[2024-10-23 03:23:52,731][07329] Saving new best policy, reward=23.564!
[2024-10-23 03:23:56,423][07343] Updated weights for policy 0, policy_version 710 (0.0031)
[2024-10-23 03:23:57,725][00608] Fps is (10 sec: 4096.5, 60 sec: 4027.7, 300 sec: 4040.5). Total num frames: 2912256. Throughput: 0: 1003.8. Samples: 725746. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-10-23 03:23:57,730][00608] Avg episode reward: [(0, '23.699')]
[2024-10-23 03:23:57,741][07329] Saving new best policy, reward=23.699!
[2024-10-23 03:24:02,728][00608] Fps is (10 sec: 4914.1, 60 sec: 4232.4, 300 sec: 4068.2). Total num frames: 2936832. Throughput: 0: 1041.9. Samples: 732996. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-10-23 03:24:02,731][00608] Avg episode reward: [(0, '21.644')]
[2024-10-23 03:24:06,780][07343] Updated weights for policy 0, policy_version 720 (0.0020)
[2024-10-23 03:24:07,725][00608] Fps is (10 sec: 3686.4, 60 sec: 4027.8, 300 sec: 4040.5). Total num frames: 2949120. Throughput: 0: 1017.8. Samples: 737770. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-10-23 03:24:07,732][00608] Avg episode reward: [(0, '21.429')]
[2024-10-23 03:24:12,725][00608] Fps is (10 sec: 3687.2, 60 sec: 4027.7, 300 sec: 4040.5). Total num frames: 2973696. Throughput: 0: 996.5. Samples: 740500. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-10-23 03:24:12,728][00608] Avg episode reward: [(0, '22.503')]
[2024-10-23 03:24:15,886][07343] Updated weights for policy 0, policy_version 730 (0.0057)
[2024-10-23 03:24:17,728][00608] Fps is (10 sec: 4913.8, 60 sec: 4232.3, 300 sec: 4068.2). Total num frames: 2998272. Throughput: 0: 1022.1. Samples: 747966. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-10-23 03:24:17,731][00608] Avg episode reward: [(0, '21.622')]
[2024-10-23 03:24:22,725][00608] Fps is (10 sec: 3686.5, 60 sec: 4027.7, 300 sec: 4040.5). Total num frames: 3010560. Throughput: 0: 1015.2. Samples: 752758. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-10-23 03:24:22,728][00608] Avg episode reward: [(0, '21.629')]
[2024-10-23 03:24:27,725][00608] Fps is (10 sec: 2458.3, 60 sec: 3822.9, 300 sec: 3998.8). Total num frames: 3022848. Throughput: 0: 971.5. Samples: 754496. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:24:27,728][00608] Avg episode reward: [(0, '21.609')]
[2024-10-23 03:24:29,806][07343] Updated weights for policy 0, policy_version 740 (0.0030)
[2024-10-23 03:24:32,725][00608] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 4012.7). Total num frames: 3043328. Throughput: 0: 927.0. Samples: 759554. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-10-23 03:24:32,728][00608] Avg episode reward: [(0, '24.422')]
[2024-10-23 03:24:32,735][07329] Saving new best policy, reward=24.422!
[2024-10-23 03:24:37,725][00608] Fps is (10 sec: 4505.7, 60 sec: 4027.7, 300 sec: 4026.6). Total num frames: 3067904. Throughput: 0: 981.0. Samples: 766448. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:24:37,732][00608] Avg episode reward: [(0, '24.331')]
[2024-10-23 03:24:38,511][07343] Updated weights for policy 0, policy_version 750 (0.0015)
[2024-10-23 03:24:42,726][00608] Fps is (10 sec: 4095.6, 60 sec: 3891.1, 300 sec: 4012.7). Total num frames: 3084288. Throughput: 0: 975.0. Samples: 769624. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:24:42,733][00608] Avg episode reward: [(0, '24.147')]
[2024-10-23 03:24:47,725][00608] Fps is (10 sec: 3276.8, 60 sec: 3823.0, 300 sec: 3984.9). Total num frames: 3100672. Throughput: 0: 919.3. Samples: 774364. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:24:47,729][00608] Avg episode reward: [(0, '24.170')]
[2024-10-23 03:24:49,519][07343] Updated weights for policy 0, policy_version 760 (0.0043)
[2024-10-23 03:24:52,725][00608] Fps is (10 sec: 4506.1, 60 sec: 4027.7, 300 sec: 4040.5). Total num frames: 3129344. Throughput: 0: 977.0. Samples: 781734. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:24:52,729][00608] Avg episode reward: [(0, '23.576')]
[2024-10-23 03:24:57,729][00608] Fps is (10 sec: 4503.8, 60 sec: 3890.9, 300 sec: 4054.3). Total num frames: 3145728. Throughput: 0: 999.1. Samples: 785462. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:24:57,732][00608] Avg episode reward: [(0, '21.638')]
[2024-10-23 03:24:59,412][07343] Updated weights for policy 0, policy_version 770 (0.0024)
[2024-10-23 03:25:02,725][00608] Fps is (10 sec: 3276.8, 60 sec: 3754.8, 300 sec: 4026.6). Total num frames: 3162112. Throughput: 0: 935.0. Samples: 790040. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:25:02,732][00608] Avg episode reward: [(0, '21.610')]
[2024-10-23 03:25:07,725][00608] Fps is (10 sec: 4097.7, 60 sec: 3959.5, 300 sec: 4040.5). Total num frames: 3186688. Throughput: 0: 970.5. Samples: 796432. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:25:07,733][00608] Avg episode reward: [(0, '21.566')]
[2024-10-23 03:25:09,147][07343] Updated weights for policy 0, policy_version 780 (0.0036)
[2024-10-23 03:25:12,727][00608] Fps is (10 sec: 4504.6, 60 sec: 3891.1, 300 sec: 4054.3). Total num frames: 3207168. Throughput: 0: 1010.6. Samples: 799974. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-10-23 03:25:12,730][00608] Avg episode reward: [(0, '22.606')]
[2024-10-23 03:25:17,725][00608] Fps is (10 sec: 3686.4, 60 sec: 3754.8, 300 sec: 4026.6). Total num frames: 3223552. Throughput: 0: 1022.5. Samples: 805566. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:25:17,730][00608] Avg episode reward: [(0, '23.778')]
[2024-10-23 03:25:17,742][07329] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000787_3223552.pth...
[2024-10-23 03:25:17,944][07329] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000552_2260992.pth
[2024-10-23 03:25:20,234][07343] Updated weights for policy 0, policy_version 790 (0.0013)
[2024-10-23 03:25:22,725][00608] Fps is (10 sec: 4096.9, 60 sec: 3959.5, 300 sec: 4040.5). Total num frames: 3248128. Throughput: 0: 998.5. Samples: 811382. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:25:22,731][00608] Avg episode reward: [(0, '25.015')]
[2024-10-23 03:25:22,734][07329] Saving new best policy, reward=25.015!
[2024-10-23 03:25:27,725][00608] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 4054.3). Total num frames: 3268608. Throughput: 0: 1005.2. Samples: 814858. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:25:27,728][00608] Avg episode reward: [(0, '23.860')]
[2024-10-23 03:25:28,869][07343] Updated weights for policy 0, policy_version 800 (0.0030)
[2024-10-23 03:25:32,728][00608] Fps is (10 sec: 3685.6, 60 sec: 4027.6, 300 sec: 4026.5). Total num frames: 3284992. Throughput: 0: 1042.2. Samples: 821264. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:25:32,730][00608] Avg episode reward: [(0, '23.900')]
[2024-10-23 03:25:37,725][00608] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 4026.6). Total num frames: 3305472. Throughput: 0: 990.8. Samples: 826322. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:25:37,728][00608] Avg episode reward: [(0, '23.508')]
[2024-10-23 03:25:39,726][07343] Updated weights for policy 0, policy_version 810 (0.0023)
[2024-10-23 03:25:42,725][00608] Fps is (10 sec: 4506.6, 60 sec: 4096.1, 300 sec: 4054.4). Total num frames: 3330048. Throughput: 0: 990.2. Samples: 830016. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:25:42,732][00608] Avg episode reward: [(0, '23.587')]
[2024-10-23 03:25:47,726][00608] Fps is (10 sec: 4505.5, 60 sec: 4164.3, 300 sec: 4054.3). Total num frames: 3350528. Throughput: 0: 1043.3. Samples: 836988. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:25:47,728][00608] Avg episode reward: [(0, '23.690')]
[2024-10-23 03:25:50,389][07343] Updated weights for policy 0, policy_version 820 (0.0020)
[2024-10-23 03:25:52,725][00608] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 4012.7). Total num frames: 3362816. Throughput: 0: 999.1. Samples: 841392. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:25:52,729][00608] Avg episode reward: [(0, '25.313')]
[2024-10-23 03:25:52,743][07329] Saving new best policy, reward=25.313!
[2024-10-23 03:25:57,725][00608] Fps is (10 sec: 3686.5, 60 sec: 4028.0, 300 sec: 4040.5). Total num frames: 3387392. Throughput: 0: 995.7. Samples: 844778. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:25:57,730][00608] Avg episode reward: [(0, '26.026')]
[2024-10-23 03:25:57,747][07329] Saving new best policy, reward=26.026!
[2024-10-23 03:25:59,782][07343] Updated weights for policy 0, policy_version 830 (0.0066)
[2024-10-23 03:26:02,725][00608] Fps is (10 sec: 4915.2, 60 sec: 4164.3, 300 sec: 4068.2). Total num frames: 3411968. Throughput: 0: 1026.6. Samples: 851762. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
[2024-10-23 03:26:02,727][00608] Avg episode reward: [(0, '26.337')]
[2024-10-23 03:26:02,733][07329] Saving new best policy, reward=26.337!
[2024-10-23 03:26:07,725][00608] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 4026.6). Total num frames: 3424256. Throughput: 0: 1005.5. Samples: 856628. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:26:07,729][00608] Avg episode reward: [(0, '26.611')]
[2024-10-23 03:26:07,738][07329] Saving new best policy, reward=26.611!
[2024-10-23 03:26:11,258][07343] Updated weights for policy 0, policy_version 840 (0.0050)
[2024-10-23 03:26:12,725][00608] Fps is (10 sec: 3276.8, 60 sec: 3959.6, 300 sec: 4012.7). Total num frames: 3444736. Throughput: 0: 981.9. Samples: 859042. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:26:12,728][00608] Avg episode reward: [(0, '25.247')]
[2024-10-23 03:26:17,725][00608] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 4054.3). Total num frames: 3469312. Throughput: 0: 999.0. Samples: 866218. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:26:17,730][00608] Avg episode reward: [(0, '23.874')]
[2024-10-23 03:26:20,289][07343] Updated weights for policy 0, policy_version 850 (0.0038)
[2024-10-23 03:26:22,725][00608] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 4026.6). Total num frames: 3485696. Throughput: 0: 1013.3. Samples: 871920. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:26:22,732][00608] Avg episode reward: [(0, '24.266')]
[2024-10-23 03:26:27,725][00608] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 4012.7). Total num frames: 3506176. Throughput: 0: 976.7. Samples: 873966. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:26:27,731][00608] Avg episode reward: [(0, '24.260')]
[2024-10-23 03:26:31,296][07343] Updated weights for policy 0, policy_version 860 (0.0017)
[2024-10-23 03:26:32,725][00608] Fps is (10 sec: 4096.0, 60 sec: 4027.9, 300 sec: 4026.6). Total num frames: 3526656. Throughput: 0: 968.2. Samples: 880556. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-10-23 03:26:32,733][00608] Avg episode reward: [(0, '24.036')]
[2024-10-23 03:26:37,731][00608] Fps is (10 sec: 4093.6, 60 sec: 4027.3, 300 sec: 4026.5). Total num frames: 3547136. Throughput: 0: 1014.1. Samples: 887034. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:26:37,734][00608] Avg episode reward: [(0, '25.411')]
[2024-10-23 03:26:42,725][00608] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3984.9). Total num frames: 3559424. Throughput: 0: 981.2. Samples: 888930. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:26:42,728][00608] Avg episode reward: [(0, '26.931')]
[2024-10-23 03:26:42,732][07329] Saving new best policy, reward=26.931!
[2024-10-23 03:26:42,994][07343] Updated weights for policy 0, policy_version 870 (0.0050)
[2024-10-23 03:26:47,726][00608] Fps is (10 sec: 3688.4, 60 sec: 3891.2, 300 sec: 4012.7). Total num frames: 3584000. Throughput: 0: 954.0. Samples: 894692. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:26:47,733][00608] Avg episode reward: [(0, '27.522')]
[2024-10-23 03:26:47,748][07329] Saving new best policy, reward=27.522!
[2024-10-23 03:26:51,857][07343] Updated weights for policy 0, policy_version 880 (0.0023)
[2024-10-23 03:26:52,725][00608] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 4012.7). Total num frames: 3604480. Throughput: 0: 998.7. Samples: 901570. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:26:52,730][00608] Avg episode reward: [(0, '27.482')]
[2024-10-23 03:26:57,727][00608] Fps is (10 sec: 3686.1, 60 sec: 3891.1, 300 sec: 3984.9). Total num frames: 3620864. Throughput: 0: 997.9. Samples: 903950. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:26:57,729][00608] Avg episode reward: [(0, '27.313')]
[2024-10-23 03:27:02,728][00608] Fps is (10 sec: 3685.6, 60 sec: 3822.8, 300 sec: 3984.9). Total num frames: 3641344. Throughput: 0: 952.0. Samples: 909062. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:27:02,730][00608] Avg episode reward: [(0, '26.628')]
[2024-10-23 03:27:03,284][07343] Updated weights for policy 0, policy_version 890 (0.0023)
[2024-10-23 03:27:07,725][00608] Fps is (10 sec: 4506.2, 60 sec: 4027.7, 300 sec: 4026.6). Total num frames: 3665920. Throughput: 0: 980.6. Samples: 916048. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:27:07,732][00608] Avg episode reward: [(0, '23.368')]
[2024-10-23 03:27:12,725][00608] Fps is (10 sec: 4096.9, 60 sec: 3959.5, 300 sec: 3998.8). Total num frames: 3682304. Throughput: 0: 1002.4. Samples: 919076. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-10-23 03:27:12,731][00608] Avg episode reward: [(0, '22.199')]
[2024-10-23 03:27:14,139][07343] Updated weights for policy 0, policy_version 900 (0.0024)
[2024-10-23 03:27:17,725][00608] Fps is (10 sec: 3276.7, 60 sec: 3822.9, 300 sec: 3971.0). Total num frames: 3698688. Throughput: 0: 951.9. Samples: 923390. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:27:17,727][00608] Avg episode reward: [(0, '21.409')]
[2024-10-23 03:27:17,743][07329] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000903_3698688.pth...
[2024-10-23 03:27:17,870][07329] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000670_2744320.pth
[2024-10-23 03:27:22,725][00608] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3998.8). Total num frames: 3723264. Throughput: 0: 961.7. Samples: 930306. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:27:22,728][00608] Avg episode reward: [(0, '21.004')]
[2024-10-23 03:27:23,684][07343] Updated weights for policy 0, policy_version 910 (0.0022)
[2024-10-23 03:27:27,727][00608] Fps is (10 sec: 4095.4, 60 sec: 3891.1, 300 sec: 3984.9). Total num frames: 3739648. Throughput: 0: 997.3. Samples: 933812. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-10-23 03:27:27,733][00608] Avg episode reward: [(0, '21.194')]
[2024-10-23 03:27:32,725][00608] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3957.2). Total num frames: 3756032. Throughput: 0: 973.6. Samples: 938502. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:27:32,728][00608] Avg episode reward: [(0, '22.367')]
[2024-10-23 03:27:34,931][07343] Updated weights for policy 0, policy_version 920 (0.0033)
[2024-10-23 03:27:37,728][00608] Fps is (10 sec: 4095.7, 60 sec: 3891.4, 300 sec: 3984.9). Total num frames: 3780608. Throughput: 0: 958.6. Samples: 944708. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:27:37,731][00608] Avg episode reward: [(0, '21.220')]
[2024-10-23 03:27:42,729][00608] Fps is (10 sec: 4503.9, 60 sec: 4027.5, 300 sec: 3984.9). Total num frames: 3801088. Throughput: 0: 978.2. Samples: 947972. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:27:42,732][00608] Avg episode reward: [(0, '21.197')]
[2024-10-23 03:27:45,035][07343] Updated weights for policy 0, policy_version 930 (0.0027)
[2024-10-23 03:27:47,725][00608] Fps is (10 sec: 3277.6, 60 sec: 3823.0, 300 sec: 3943.3). Total num frames: 3813376. Throughput: 0: 985.8. Samples: 953422. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:27:47,729][00608] Avg episode reward: [(0, '20.879')]
[2024-10-23 03:27:52,725][00608] Fps is (10 sec: 3278.1, 60 sec: 3822.9, 300 sec: 3943.3). Total num frames: 3833856. Throughput: 0: 951.6. Samples: 958870. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:27:52,732][00608] Avg episode reward: [(0, '21.359')]
[2024-10-23 03:27:55,312][07343] Updated weights for policy 0, policy_version 940 (0.0034)
[2024-10-23 03:27:57,726][00608] Fps is (10 sec: 4505.5, 60 sec: 3959.5, 300 sec: 3984.9). Total num frames: 3858432. Throughput: 0: 961.7. Samples: 962354. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-10-23 03:27:57,730][00608] Avg episode reward: [(0, '22.860')]
[2024-10-23 03:28:02,725][00608] Fps is (10 sec: 4505.6, 60 sec: 3959.6, 300 sec: 3971.1). Total num frames: 3878912. Throughput: 0: 1010.8. Samples: 968878. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:28:02,734][00608] Avg episode reward: [(0, '23.418')]
[2024-10-23 03:28:06,451][07343] Updated weights for policy 0, policy_version 950 (0.0032)
[2024-10-23 03:28:07,726][00608] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3943.3). Total num frames: 3895296. Throughput: 0: 964.1. Samples: 973690. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-10-23 03:28:07,732][00608] Avg episode reward: [(0, '24.786')]
[2024-10-23 03:28:12,725][00608] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3984.9). Total num frames: 3919872. Throughput: 0: 964.8. Samples: 977228. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:28:12,728][00608] Avg episode reward: [(0, '24.569')]
[2024-10-23 03:28:14,952][07343] Updated weights for policy 0, policy_version 960 (0.0025)
[2024-10-23 03:28:17,727][00608] Fps is (10 sec: 4505.0, 60 sec: 4027.6, 300 sec: 3971.0). Total num frames: 3940352. Throughput: 0: 1021.9. Samples: 984488. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-10-23 03:28:17,733][00608] Avg episode reward: [(0, '24.099')]
[2024-10-23 03:28:22,725][00608] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3943.3). Total num frames: 3956736. Throughput: 0: 982.5. Samples: 988918. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-10-23 03:28:22,730][00608] Avg episode reward: [(0, '24.781')]
[2024-10-23 03:28:26,099][07343] Updated weights for policy 0, policy_version 970 (0.0048)
[2024-10-23 03:28:27,725][00608] Fps is (10 sec: 3687.0, 60 sec: 3959.6, 300 sec: 3957.2). Total num frames: 3977216. Throughput: 0: 982.4. Samples: 992174. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-10-23 03:28:27,732][00608] Avg episode reward: [(0, '26.359')]
[2024-10-23 03:28:32,726][00608] Fps is (10 sec: 4505.5, 60 sec: 4096.0, 300 sec: 3984.9). Total num frames: 4001792. Throughput: 0: 1025.2. Samples: 999556. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-10-23 03:28:32,731][00608] Avg episode reward: [(0, '24.991')]
[2024-10-23 03:28:32,933][07329] Stopping Batcher_0...
[2024-10-23 03:28:32,933][07329] Loop batcher_evt_loop terminating...
[2024-10-23 03:28:32,936][07329] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2024-10-23 03:28:32,933][00608] Component Batcher_0 stopped!
[2024-10-23 03:28:33,014][07343] Weights refcount: 2 0
[2024-10-23 03:28:33,017][07343] Stopping InferenceWorker_p0-w0...
[2024-10-23 03:28:33,017][07343] Loop inference_proc0-0_evt_loop terminating...
[2024-10-23 03:28:33,020][00608] Component InferenceWorker_p0-w0 stopped!
[2024-10-23 03:28:33,113][07329] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000787_3223552.pth
[2024-10-23 03:28:33,137][07329] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2024-10-23 03:28:33,423][00608] Component LearnerWorker_p0 stopped!
[2024-10-23 03:28:33,426][07329] Stopping LearnerWorker_p0...
[2024-10-23 03:28:33,426][07329] Loop learner_proc0_evt_loop terminating...
[2024-10-23 03:28:33,500][00608] Component RolloutWorker_w4 stopped!
[2024-10-23 03:28:33,506][07347] Stopping RolloutWorker_w4...
[2024-10-23 03:28:33,506][07347] Loop rollout_proc4_evt_loop terminating...
[2024-10-23 03:28:33,523][00608] Component RolloutWorker_w2 stopped!
[2024-10-23 03:28:33,529][07350] Stopping RolloutWorker_w2...
[2024-10-23 03:28:33,529][07350] Loop rollout_proc2_evt_loop terminating...
[2024-10-23 03:28:33,564][00608] Component RolloutWorker_w6 stopped!
[2024-10-23 03:28:33,569][07348] Stopping RolloutWorker_w6...
[2024-10-23 03:28:33,570][07348] Loop rollout_proc6_evt_loop terminating...
[2024-10-23 03:28:33,574][00608] Component RolloutWorker_w0 stopped!
[2024-10-23 03:28:33,579][07342] Stopping RolloutWorker_w0...
[2024-10-23 03:28:33,579][07342] Loop rollout_proc0_evt_loop terminating...
[2024-10-23 03:28:33,607][00608] Component RolloutWorker_w1 stopped!
[2024-10-23 03:28:33,607][07344] Stopping RolloutWorker_w1...
[2024-10-23 03:28:33,611][07344] Loop rollout_proc1_evt_loop terminating...
[2024-10-23 03:28:33,659][07349] Stopping RolloutWorker_w7...
[2024-10-23 03:28:33,659][07349] Loop rollout_proc7_evt_loop terminating...
[2024-10-23 03:28:33,659][00608] Component RolloutWorker_w7 stopped!
[2024-10-23 03:28:33,682][07346] Stopping RolloutWorker_w5...
[2024-10-23 03:28:33,683][07346] Loop rollout_proc5_evt_loop terminating...
[2024-10-23 03:28:33,682][00608] Component RolloutWorker_w5 stopped!
[2024-10-23 03:28:33,766][07345] Stopping RolloutWorker_w3...
[2024-10-23 03:28:33,766][07345] Loop rollout_proc3_evt_loop terminating...
[2024-10-23 03:28:33,766][00608] Component RolloutWorker_w3 stopped!
[2024-10-23 03:28:33,769][00608] Waiting for process learner_proc0 to stop...
[2024-10-23 03:28:35,290][00608] Waiting for process inference_proc0-0 to join...
[2024-10-23 03:28:35,572][00608] Waiting for process rollout_proc0 to join...
[2024-10-23 03:28:37,822][00608] Waiting for process rollout_proc1 to join...
[2024-10-23 03:28:38,011][00608] Waiting for process rollout_proc2 to join...
[2024-10-23 03:28:38,014][00608] Waiting for process rollout_proc3 to join...
[2024-10-23 03:28:38,019][00608] Waiting for process rollout_proc4 to join...
[2024-10-23 03:28:38,023][00608] Waiting for process rollout_proc5 to join...
[2024-10-23 03:28:38,026][00608] Waiting for process rollout_proc6 to join...
[2024-10-23 03:28:38,030][00608] Waiting for process rollout_proc7 to join...
[2024-10-23 03:28:38,034][00608] Batcher 0 profile tree view:
batching: 26.2510, releasing_batches: 0.0252
[2024-10-23 03:28:38,037][00608] InferenceWorker_p0-w0 profile tree view:
wait_policy: 0.0000
  wait_policy_total: 377.9962
update_model: 8.8957
  weight_update: 0.0020
one_step: 0.0085
  handle_policy_step: 579.3976
    deserialize: 14.2673, stack: 3.0937, obs_to_device_normalize: 118.7638, forward: 306.6277, send_messages: 28.3279
    prepare_outputs: 80.3398
      to_cpu: 46.3522
[2024-10-23 03:28:38,039][00608] Learner 0 profile tree view:
misc: 0.0048, prepare_batch: 13.5779
train: 73.5504
  epoch_init: 0.0106, minibatch_init: 0.0235, losses_postprocess: 0.6749, kl_divergence: 0.5684, after_optimizer: 33.5009
  calculate_losses: 26.3616
    losses_init: 0.0035, forward_head: 1.2203, bptt_initial: 17.7526, tail: 1.0479, advantages_returns: 0.3036, losses: 3.9103
    bptt: 1.8405
      bptt_forward_core: 1.7344
  update: 11.7799
    clip: 0.8731
[2024-10-23 03:28:38,040][00608] RolloutWorker_w0 profile tree view:
wait_for_trajectories: 0.3307, enqueue_policy_requests: 84.3400, env_step: 791.3702, overhead: 12.4609, complete_rollouts: 7.0077
save_policy_outputs: 19.8606
  split_output_tensors: 7.7300
[2024-10-23 03:28:38,042][00608] RolloutWorker_w7 profile tree view:
wait_for_trajectories: 0.2959, enqueue_policy_requests: 89.5735, env_step: 781.1690, overhead: 11.5479, complete_rollouts: 7.0222
save_policy_outputs: 19.3218
  split_output_tensors: 7.9793
[2024-10-23 03:28:38,046][00608] Loop Runner_EvtLoop terminating...
[2024-10-23 03:28:38,048][00608] Runner profile tree view:
main_loop: 1034.7978
[2024-10-23 03:28:38,049][00608] Collected {0: 4005888}, FPS: 3871.2
[2024-10-23 03:30:12,850][00608] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
[2024-10-23 03:30:12,852][00608] Overriding arg 'num_workers' with value 1 passed from command line
[2024-10-23 03:30:12,854][00608] Adding new argument 'no_render'=True that is not in the saved config file!
[2024-10-23 03:30:12,857][00608] Adding new argument 'save_video'=True that is not in the saved config file!
[2024-10-23 03:30:12,858][00608] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2024-10-23 03:30:12,861][00608] Adding new argument 'video_name'=None that is not in the saved config file!
[2024-10-23 03:30:12,862][00608] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
[2024-10-23 03:30:12,865][00608] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2024-10-23 03:30:12,867][00608] Adding new argument 'push_to_hub'=False that is not in the saved config file!
[2024-10-23 03:30:12,869][00608] Adding new argument 'hf_repository'=None that is not in the saved config file!
[2024-10-23 03:30:12,870][00608] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2024-10-23 03:30:12,871][00608] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2024-10-23 03:30:12,872][00608] Adding new argument 'train_script'=None that is not in the saved config file!
[2024-10-23 03:30:12,873][00608] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2024-10-23 03:30:12,874][00608] Using frameskip 1 and render_action_repeat=4 for evaluation
[2024-10-23 03:30:12,906][00608] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-10-23 03:30:12,909][00608] RunningMeanStd input shape: (3, 72, 128)
[2024-10-23 03:30:12,913][00608] RunningMeanStd input shape: (1,)
[2024-10-23 03:30:12,929][00608] ConvEncoder: input_channels=3
[2024-10-23 03:30:13,032][00608] Conv encoder output size: 512
[2024-10-23 03:30:13,034][00608] Policy head output size: 512
[2024-10-23 03:30:13,202][00608] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2024-10-23 03:30:14,004][00608] Num frames 100...
[2024-10-23 03:30:14,125][00608] Num frames 200...
[2024-10-23 03:30:14,249][00608] Num frames 300...
[2024-10-23 03:30:14,384][00608] Num frames 400...
[2024-10-23 03:30:14,505][00608] Num frames 500...
[2024-10-23 03:30:14,624][00608] Num frames 600...
[2024-10-23 03:30:14,743][00608] Num frames 700...
[2024-10-23 03:30:14,869][00608] Num frames 800...
[2024-10-23 03:30:14,988][00608] Num frames 900...
[2024-10-23 03:30:15,110][00608] Num frames 1000...
[2024-10-23 03:30:15,229][00608] Num frames 1100...
[2024-10-23 03:30:15,360][00608] Num frames 1200...
[2024-10-23 03:30:15,484][00608] Num frames 1300...
[2024-10-23 03:30:15,603][00608] Num frames 1400...
[2024-10-23 03:30:15,727][00608] Num frames 1500...
[2024-10-23 03:30:15,855][00608] Num frames 1600...
[2024-10-23 03:30:15,975][00608] Num frames 1700...
[2024-10-23 03:30:16,034][00608] Avg episode rewards: #0: 43.010, true rewards: #0: 17.010
[2024-10-23 03:30:16,035][00608] Avg episode reward: 43.010, avg true_objective: 17.010
[2024-10-23 03:30:16,154][00608] Num frames 1800...
[2024-10-23 03:30:16,278][00608] Num frames 1900...
[2024-10-23 03:30:16,403][00608] Num frames 2000...
[2024-10-23 03:30:16,520][00608] Num frames 2100...
[2024-10-23 03:30:16,607][00608] Avg episode rewards: #0: 24.620, true rewards: #0: 10.620
[2024-10-23 03:30:16,609][00608] Avg episode reward: 24.620, avg true_objective: 10.620
[2024-10-23 03:30:16,701][00608] Num frames 2200...
[2024-10-23 03:30:16,823][00608] Num frames 2300...
[2024-10-23 03:30:16,950][00608] Num frames 2400...
[2024-10-23 03:30:17,070][00608] Num frames 2500...
[2024-10-23 03:30:17,191][00608] Num frames 2600...
[2024-10-23 03:30:17,312][00608] Num frames 2700...
[2024-10-23 03:30:17,408][00608] Avg episode rewards: #0: 20.440, true rewards: #0: 9.107
[2024-10-23 03:30:17,410][00608] Avg episode reward: 20.440, avg true_objective: 9.107
[2024-10-23 03:30:17,493][00608] Num frames 2800...
[2024-10-23 03:30:17,612][00608] Num frames 2900...
[2024-10-23 03:30:17,741][00608] Num frames 3000...
[2024-10-23 03:30:17,915][00608] Num frames 3100...
[2024-10-23 03:30:18,091][00608] Num frames 3200...
[2024-10-23 03:30:18,259][00608] Num frames 3300...
[2024-10-23 03:30:18,442][00608] Num frames 3400...
[2024-10-23 03:30:18,611][00608] Num frames 3500...
[2024-10-23 03:30:18,777][00608] Num frames 3600...
[2024-10-23 03:30:18,945][00608] Num frames 3700...
[2024-10-23 03:30:19,125][00608] Num frames 3800...
[2024-10-23 03:30:19,294][00608] Num frames 3900...
[2024-10-23 03:30:19,518][00608] Avg episode rewards: #0: 23.485, true rewards: #0: 9.985
[2024-10-23 03:30:19,520][00608] Avg episode reward: 23.485, avg true_objective: 9.985
[2024-10-23 03:30:19,533][00608] Num frames 4000...
[2024-10-23 03:30:19,711][00608] Num frames 4100...
[2024-10-23 03:30:19,881][00608] Num frames 4200...
[2024-10-23 03:30:20,054][00608] Num frames 4300...
[2024-10-23 03:30:20,192][00608] Num frames 4400...
[2024-10-23 03:30:20,311][00608] Num frames 4500...
[2024-10-23 03:30:20,439][00608] Num frames 4600...
[2024-10-23 03:30:20,568][00608] Num frames 4700...
[2024-10-23 03:30:20,688][00608] Num frames 4800...
[2024-10-23 03:30:20,809][00608] Num frames 4900...
[2024-10-23 03:30:20,938][00608] Num frames 5000...
[2024-10-23 03:30:21,057][00608] Num frames 5100...
[2024-10-23 03:30:21,179][00608] Num frames 5200...
[2024-10-23 03:30:21,301][00608] Num frames 5300...
[2024-10-23 03:30:21,423][00608] Num frames 5400...
[2024-10-23 03:30:21,552][00608] Num frames 5500...
[2024-10-23 03:30:21,678][00608] Num frames 5600...
[2024-10-23 03:30:21,809][00608] Num frames 5700...
[2024-10-23 03:30:21,935][00608] Num frames 5800...
[2024-10-23 03:30:22,058][00608] Num frames 5900...
[2024-10-23 03:30:22,183][00608] Num frames 6000...
[2024-10-23 03:30:22,350][00608] Avg episode rewards: #0: 30.188, true rewards: #0: 12.188
[2024-10-23 03:30:22,351][00608] Avg episode reward: 30.188, avg true_objective: 12.188
[2024-10-23 03:30:22,362][00608] Num frames 6100...
[2024-10-23 03:30:22,479][00608] Num frames 6200...
[2024-10-23 03:30:22,611][00608] Num frames 6300...
[2024-10-23 03:30:22,734][00608] Num frames 6400...
[2024-10-23 03:30:22,862][00608] Num frames 6500...
[2024-10-23 03:30:22,985][00608] Num frames 6600...
[2024-10-23 03:30:23,111][00608] Num frames 6700...
[2024-10-23 03:30:23,231][00608] Num frames 6800...
[2024-10-23 03:30:23,350][00608] Num frames 6900...
[2024-10-23 03:30:23,468][00608] Num frames 7000...
[2024-10-23 03:30:23,599][00608] Num frames 7100...
[2024-10-23 03:30:23,720][00608] Num frames 7200...
[2024-10-23 03:30:23,845][00608] Num frames 7300...
[2024-10-23 03:30:23,971][00608] Num frames 7400...
[2024-10-23 03:30:24,093][00608] Num frames 7500...
[2024-10-23 03:30:24,214][00608] Num frames 7600...
[2024-10-23 03:30:24,335][00608] Num frames 7700...
[2024-10-23 03:30:24,455][00608] Num frames 7800...
[2024-10-23 03:30:24,576][00608] Num frames 7900...
[2024-10-23 03:30:24,703][00608] Avg episode rewards: #0: 32.583, true rewards: #0: 13.250
[2024-10-23 03:30:24,707][00608] Avg episode reward: 32.583, avg true_objective: 13.250
[2024-10-23 03:30:24,769][00608] Num frames 8000...
[2024-10-23 03:30:24,896][00608] Num frames 8100...
[2024-10-23 03:30:25,021][00608] Num frames 8200...
[2024-10-23 03:30:25,145][00608] Num frames 8300...
[2024-10-23 03:30:25,266][00608] Num frames 8400...
[2024-10-23 03:30:25,387][00608] Num frames 8500...
[2024-10-23 03:30:25,508][00608] Num frames 8600...
[2024-10-23 03:30:25,639][00608] Num frames 8700...
[2024-10-23 03:30:25,760][00608] Num frames 8800...
[2024-10-23 03:30:25,885][00608] Num frames 8900...
[2024-10-23 03:30:26,002][00608] Num frames 9000...
[2024-10-23 03:30:26,124][00608] Num frames 9100...
[2024-10-23 03:30:26,245][00608] Num frames 9200...
[2024-10-23 03:30:26,352][00608] Avg episode rewards: #0: 32.488, true rewards: #0: 13.203
[2024-10-23 03:30:26,354][00608] Avg episode reward: 32.488, avg true_objective: 13.203
[2024-10-23 03:30:26,425][00608] Num frames 9300...
[2024-10-23 03:30:26,545][00608] Num frames 9400...
[2024-10-23 03:30:26,672][00608] Num frames 9500...
[2024-10-23 03:30:26,796][00608] Num frames 9600...
[2024-10-23 03:30:26,923][00608] Num frames 9700...
[2024-10-23 03:30:27,044][00608] Num frames 9800...
[2024-10-23 03:30:27,169][00608] Num frames 9900...
[2024-10-23 03:30:27,315][00608] Avg episode rewards: #0: 29.972, true rewards: #0: 12.472
[2024-10-23 03:30:27,317][00608] Avg episode reward: 29.972, avg true_objective: 12.472
[2024-10-23 03:30:27,348][00608] Num frames 10000...
[2024-10-23 03:30:27,468][00608] Num frames 10100...
[2024-10-23 03:30:27,589][00608] Num frames 10200...
[2024-10-23 03:30:27,718][00608] Num frames 10300...
[2024-10-23 03:30:27,846][00608] Num frames 10400...
[2024-10-23 03:30:27,970][00608] Num frames 10500...
[2024-10-23 03:30:28,092][00608] Num frames 10600...
[2024-10-23 03:30:28,212][00608] Num frames 10700...
[2024-10-23 03:30:28,335][00608] Num frames 10800...
[2024-10-23 03:30:28,454][00608] Num frames 10900...
[2024-10-23 03:30:28,528][00608] Avg episode rewards: #0: 28.794, true rewards: #0: 12.128
[2024-10-23 03:30:28,529][00608] Avg episode reward: 28.794, avg true_objective: 12.128
[2024-10-23 03:30:28,636][00608] Num frames 11000...
[2024-10-23 03:30:28,767][00608] Num frames 11100...
[2024-10-23 03:30:28,892][00608] Num frames 11200...
[2024-10-23 03:30:29,016][00608] Num frames 11300...
[2024-10-23 03:30:29,137][00608] Num frames 11400...
[2024-10-23 03:30:29,258][00608] Num frames 11500...
[2024-10-23 03:30:29,384][00608] Num frames 11600...
[2024-10-23 03:30:29,507][00608] Num frames 11700...
[2024-10-23 03:30:29,633][00608] Num frames 11800...
[2024-10-23 03:30:29,702][00608] Avg episode rewards: #0: 28.311, true rewards: #0: 11.811
[2024-10-23 03:30:29,705][00608] Avg episode reward: 28.311, avg true_objective: 11.811
[2024-10-23 03:31:39,722][00608] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
[2024-10-23 03:33:55,175][00608] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
[2024-10-23 03:33:55,176][00608] Overriding arg 'num_workers' with value 1 passed from command line
[2024-10-23 03:33:55,177][00608] Adding new argument 'no_render'=True that is not in the saved config file!
[2024-10-23 03:33:55,178][00608] Adding new argument 'save_video'=True that is not in the saved config file!
[2024-10-23 03:33:55,180][00608] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2024-10-23 03:33:55,181][00608] Adding new argument 'video_name'=None that is not in the saved config file!
[2024-10-23 03:33:55,184][00608] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
[2024-10-23 03:33:55,185][00608] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2024-10-23 03:33:55,186][00608] Adding new argument 'push_to_hub'=True that is not in the saved config file!
[2024-10-23 03:33:55,187][00608] Adding new argument 'hf_repository'='ThomasSimonini/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
[2024-10-23 03:33:55,189][00608] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2024-10-23 03:33:55,191][00608] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2024-10-23 03:33:55,192][00608] Adding new argument 'train_script'=None that is not in the saved config file!
[2024-10-23 03:33:55,194][00608] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2024-10-23 03:33:55,195][00608] Using frameskip 1 and render_action_repeat=4 for evaluation
[2024-10-23 03:33:55,227][00608] RunningMeanStd input shape: (3, 72, 128)
[2024-10-23 03:33:55,229][00608] RunningMeanStd input shape: (1,)
[2024-10-23 03:33:55,242][00608] ConvEncoder: input_channels=3
[2024-10-23 03:33:55,278][00608] Conv encoder output size: 512
[2024-10-23 03:33:55,280][00608] Policy head output size: 512
[2024-10-23 03:33:55,298][00608] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2024-10-23 03:33:55,714][00608] Num frames 100...
[2024-10-23 03:33:55,852][00608] Num frames 200...
[2024-10-23 03:33:55,986][00608] Num frames 300...
[2024-10-23 03:33:56,101][00608] Num frames 400...
[2024-10-23 03:33:56,219][00608] Num frames 500...
[2024-10-23 03:33:56,342][00608] Num frames 600...
[2024-10-23 03:33:56,502][00608] Avg episode rewards: #0: 13.870, true rewards: #0: 6.870
[2024-10-23 03:33:56,503][00608] Avg episode reward: 13.870, avg true_objective: 6.870
[2024-10-23 03:33:56,522][00608] Num frames 700...
[2024-10-23 03:33:56,643][00608] Num frames 800...
[2024-10-23 03:33:56,765][00608] Num frames 900...
[2024-10-23 03:33:56,902][00608] Num frames 1000...
[2024-10-23 03:33:57,027][00608] Num frames 1100...
[2024-10-23 03:33:57,145][00608] Num frames 1200...
[2024-10-23 03:33:57,268][00608] Num frames 1300...
[2024-10-23 03:33:57,388][00608] Num frames 1400...
[2024-10-23 03:33:57,506][00608] Num frames 1500...
[2024-10-23 03:33:57,628][00608] Num frames 1600...
[2024-10-23 03:33:57,703][00608] Avg episode rewards: #0: 15.075, true rewards: #0: 8.075
[2024-10-23 03:33:57,704][00608] Avg episode reward: 15.075, avg true_objective: 8.075
[2024-10-23 03:33:57,804][00608] Num frames 1700...
[2024-10-23 03:33:57,942][00608] Num frames 1800...
[2024-10-23 03:33:58,066][00608] Num frames 1900...
[2024-10-23 03:33:58,185][00608] Num frames 2000...
[2024-10-23 03:33:58,333][00608] Avg episode rewards: #0: 12.597, true rewards: #0: 6.930
[2024-10-23 03:33:58,334][00608] Avg episode reward: 12.597, avg true_objective: 6.930
[2024-10-23 03:33:58,362][00608] Num frames 2100...
[2024-10-23 03:33:58,481][00608] Num frames 2200...
[2024-10-23 03:33:58,599][00608] Num frames 2300...
[2024-10-23 03:33:58,718][00608] Num frames 2400...
[2024-10-23 03:33:58,842][00608] Num frames 2500...
[2024-10-23 03:33:58,969][00608] Num frames 2600...
[2024-10-23 03:33:59,089][00608] Num frames 2700...
[2024-10-23 03:33:59,209][00608] Num frames 2800...
[2024-10-23 03:33:59,328][00608] Num frames 2900...
[2024-10-23 03:33:59,450][00608] Num frames 3000...
[2024-10-23 03:33:59,571][00608] Num frames 3100...
[2024-10-23 03:33:59,694][00608] Num frames 3200...
[2024-10-23 03:33:59,817][00608] Num frames 3300...
[2024-10-23 03:33:59,951][00608] Num frames 3400...
[2024-10-23 03:34:00,074][00608] Num frames 3500...
[2024-10-23 03:34:00,199][00608] Num frames 3600...
[2024-10-23 03:34:00,320][00608] Num frames 3700...
[2024-10-23 03:34:00,439][00608] Num frames 3800...
[2024-10-23 03:34:00,566][00608] Num frames 3900...
[2024-10-23 03:34:00,689][00608] Num frames 4000...
[2024-10-23 03:34:00,814][00608] Num frames 4100...
[2024-10-23 03:34:00,975][00608] Avg episode rewards: #0: 23.197, true rewards: #0: 10.448
[2024-10-23 03:34:00,977][00608] Avg episode reward: 23.197, avg true_objective: 10.448
[2024-10-23 03:34:01,006][00608] Num frames 4200...
[2024-10-23 03:34:01,122][00608] Num frames 4300...
[2024-10-23 03:34:01,246][00608] Num frames 4400...
[2024-10-23 03:34:01,364][00608] Num frames 4500...
[2024-10-23 03:34:01,489][00608] Num frames 4600...
[2024-10-23 03:34:01,617][00608] Num frames 4700...
[2024-10-23 03:34:01,735][00608] Num frames 4800...
[2024-10-23 03:34:01,862][00608] Num frames 4900...
[2024-10-23 03:34:01,993][00608] Num frames 5000...
[2024-10-23 03:34:02,113][00608] Num frames 5100...
[2024-10-23 03:34:02,216][00608] Avg episode rewards: #0: 22.278, true rewards: #0: 10.278
[2024-10-23 03:34:02,218][00608] Avg episode reward: 22.278, avg true_objective: 10.278
[2024-10-23 03:34:02,299][00608] Num frames 5200...
[2024-10-23 03:34:02,421][00608] Num frames 5300...
[2024-10-23 03:34:02,537][00608] Num frames 5400...
[2024-10-23 03:34:02,654][00608] Num frames 5500...
[2024-10-23 03:34:02,776][00608] Num frames 5600...
[2024-10-23 03:34:02,910][00608] Num frames 5700...
[2024-10-23 03:34:03,041][00608] Num frames 5800...
[2024-10-23 03:34:03,165][00608] Num frames 5900...
[2024-10-23 03:34:03,287][00608] Num frames 6000...
[2024-10-23 03:34:03,460][00608] Avg episode rewards: #0: 21.998, true rewards: #0: 10.165
[2024-10-23 03:34:03,462][00608] Avg episode reward: 21.998, avg true_objective: 10.165
[2024-10-23 03:34:03,466][00608] Num frames 6100...
[2024-10-23 03:34:03,590][00608] Num frames 6200...
[2024-10-23 03:34:03,710][00608] Num frames 6300...
[2024-10-23 03:34:03,837][00608] Num frames 6400...
[2024-10-23 03:34:03,962][00608] Num frames 6500...
[2024-10-23 03:34:04,091][00608] Num frames 6600...
[2024-10-23 03:34:04,211][00608] Num frames 6700...
[2024-10-23 03:34:04,352][00608] Avg episode rewards: #0: 21.101, true rewards: #0: 9.673
[2024-10-23 03:34:04,354][00608] Avg episode reward: 21.101, avg true_objective: 9.673
[2024-10-23 03:34:04,392][00608] Num frames 6800...
[2024-10-23 03:34:04,511][00608] Num frames 6900...
[2024-10-23 03:34:04,646][00608] Num frames 7000...
[2024-10-23 03:34:04,767][00608] Num frames 7100...
[2024-10-23 03:34:04,891][00608] Num frames 7200...
[2024-10-23 03:34:05,052][00608] Num frames 7300...
[2024-10-23 03:34:05,220][00608] Num frames 7400...
[2024-10-23 03:34:05,387][00608] Num frames 7500...
[2024-10-23 03:34:05,550][00608] Num frames 7600...
[2024-10-23 03:34:05,719][00608] Num frames 7700...
[2024-10-23 03:34:05,945][00608] Avg episode rewards: #0: 21.119, true rewards: #0: 9.744
[2024-10-23 03:34:05,946][00608] Avg episode reward: 21.119, avg true_objective: 9.744
[2024-10-23 03:34:05,957][00608] Num frames 7800...
[2024-10-23 03:34:06,132][00608] Num frames 7900...
[2024-10-23 03:34:06,297][00608] Num frames 8000...
[2024-10-23 03:34:06,464][00608] Num frames 8100...
[2024-10-23 03:34:06,643][00608] Num frames 8200...
[2024-10-23 03:34:06,813][00608] Num frames 8300...
[2024-10-23 03:34:06,991][00608] Num frames 8400...
[2024-10-23 03:34:07,178][00608] Num frames 8500...
[2024-10-23 03:34:07,353][00608] Num frames 8600...
[2024-10-23 03:34:07,488][00608] Num frames 8700...
[2024-10-23 03:34:07,612][00608] Num frames 8800...
[2024-10-23 03:34:07,732][00608] Num frames 8900...
[2024-10-23 03:34:07,840][00608] Avg episode rewards: #0: 21.827, true rewards: #0: 9.938
[2024-10-23 03:34:07,841][00608] Avg episode reward: 21.827, avg true_objective: 9.938
[2024-10-23 03:34:07,913][00608] Num frames 9000...
[2024-10-23 03:34:08,035][00608] Num frames 9100...
[2024-10-23 03:34:08,154][00608] Num frames 9200...
[2024-10-23 03:34:08,287][00608] Num frames 9300...
[2024-10-23 03:34:08,408][00608] Num frames 9400...
[2024-10-23 03:34:08,528][00608] Num frames 9500...
[2024-10-23 03:34:08,651][00608] Num frames 9600...
[2024-10-23 03:34:08,776][00608] Num frames 9700...
[2024-10-23 03:34:08,911][00608] Num frames 9800...
[2024-10-23 03:34:09,030][00608] Num frames 9900...
[2024-10-23 03:34:09,155][00608] Num frames 10000...
[2024-10-23 03:34:09,285][00608] Num frames 10100...
[2024-10-23 03:34:09,405][00608] Num frames 10200...
[2024-10-23 03:34:09,558][00608] Num frames 10300...
[2024-10-23 03:34:09,690][00608] Num frames 10400...
[2024-10-23 03:34:09,815][00608] Num frames 10500...
[2024-10-23 03:34:09,943][00608] Num frames 10600...
[2024-10-23 03:34:10,063][00608] Num frames 10700...
[2024-10-23 03:34:10,188][00608] Num frames 10800...
[2024-10-23 03:34:10,317][00608] Num frames 10900...
[2024-10-23 03:34:10,440][00608] Num frames 11000...
[2024-10-23 03:34:10,550][00608] Avg episode rewards: #0: 25.444, true rewards: #0: 11.044
[2024-10-23 03:34:10,552][00608] Avg episode reward: 25.444, avg true_objective: 11.044
[2024-10-23 03:35:15,463][00608] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
[2024-10-23 03:51:25,030][00608] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
[2024-10-23 03:51:25,032][00608] Overriding arg 'num_workers' with value 1 passed from command line
[2024-10-23 03:51:25,034][00608] Adding new argument 'no_render'=True that is not in the saved config file!
[2024-10-23 03:51:25,036][00608] Adding new argument 'save_video'=True that is not in the saved config file!
[2024-10-23 03:51:25,038][00608] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2024-10-23 03:51:25,040][00608] Adding new argument 'video_name'=None that is not in the saved config file!
[2024-10-23 03:51:25,041][00608] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
[2024-10-23 03:51:25,043][00608] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2024-10-23 03:51:25,044][00608] Adding new argument 'push_to_hub'=True that is not in the saved config file!
[2024-10-23 03:51:25,045][00608] Adding new argument 'hf_repository'='Joseph2142/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
[2024-10-23 03:51:25,046][00608] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2024-10-23 03:51:25,047][00608] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2024-10-23 03:51:25,048][00608] Adding new argument 'train_script'=None that is not in the saved config file!
[2024-10-23 03:51:25,049][00608] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2024-10-23 03:51:25,050][00608] Using frameskip 1 and render_action_repeat=4 for evaluation
[2024-10-23 03:51:25,085][00608] RunningMeanStd input shape: (3, 72, 128)
[2024-10-23 03:51:25,088][00608] RunningMeanStd input shape: (1,)
[2024-10-23 03:51:25,101][00608] ConvEncoder: input_channels=3
[2024-10-23 03:51:25,136][00608] Conv encoder output size: 512
[2024-10-23 03:51:25,138][00608] Policy head output size: 512
[2024-10-23 03:51:25,156][00608] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2024-10-23 03:51:25,554][00608] Num frames 100...
[2024-10-23 03:51:25,671][00608] Num frames 200...
[2024-10-23 03:51:25,791][00608] Num frames 300...
[2024-10-23 03:51:25,930][00608] Num frames 400...
[2024-10-23 03:51:26,050][00608] Avg episode rewards: #0: 5.480, true rewards: #0: 4.480
[2024-10-23 03:51:26,052][00608] Avg episode reward: 5.480, avg true_objective: 4.480
[2024-10-23 03:51:26,114][00608] Num frames 500...
[2024-10-23 03:51:26,229][00608] Num frames 600...
[2024-10-23 03:51:26,351][00608] Num frames 700...
[2024-10-23 03:51:26,471][00608] Num frames 800...
[2024-10-23 03:51:26,591][00608] Num frames 900...
[2024-10-23 03:51:26,712][00608] Num frames 1000...
[2024-10-23 03:51:26,840][00608] Num frames 1100...
[2024-10-23 03:51:26,997][00608] Avg episode rewards: #0: 9.420, true rewards: #0: 5.920
[2024-10-23 03:51:26,999][00608] Avg episode reward: 9.420, avg true_objective: 5.920
[2024-10-23 03:51:27,021][00608] Num frames 1200...
[2024-10-23 03:51:27,141][00608] Num frames 1300...
[2024-10-23 03:51:27,263][00608] Num frames 1400...
[2024-10-23 03:51:27,384][00608] Num frames 1500...
[2024-10-23 03:51:27,503][00608] Num frames 1600...
[2024-10-23 03:51:27,622][00608] Num frames 1700...
[2024-10-23 03:51:27,746][00608] Num frames 1800...
[2024-10-23 03:51:27,875][00608] Num frames 1900...
[2024-10-23 03:51:27,997][00608] Num frames 2000...
[2024-10-23 03:51:28,130][00608] Num frames 2100...
[2024-10-23 03:51:28,253][00608] Num frames 2200...
[2024-10-23 03:51:28,376][00608] Num frames 2300...
[2024-10-23 03:51:28,496][00608] Num frames 2400...
[2024-10-23 03:51:28,618][00608] Num frames 2500...
[2024-10-23 03:51:28,746][00608] Num frames 2600...
[2024-10-23 03:51:28,876][00608] Num frames 2700...
[2024-10-23 03:51:28,945][00608] Avg episode rewards: #0: 18.370, true rewards: #0: 9.037
[2024-10-23 03:51:28,947][00608] Avg episode reward: 18.370, avg true_objective: 9.037
[2024-10-23 03:51:29,062][00608] Num frames 2800...
[2024-10-23 03:51:29,184][00608] Num frames 2900...
[2024-10-23 03:51:29,301][00608] Num frames 3000...
[2024-10-23 03:51:29,420][00608] Num frames 3100...
[2024-10-23 03:51:29,541][00608] Num frames 3200...
[2024-10-23 03:51:29,667][00608] Num frames 3300...
[2024-10-23 03:51:29,788][00608] Num frames 3400...
[2024-10-23 03:51:29,917][00608] Num frames 3500...
[2024-10-23 03:51:30,039][00608] Num frames 3600...
[2024-10-23 03:51:30,166][00608] Num frames 3700...
[2024-10-23 03:51:30,302][00608] Avg episode rewards: #0: 19.168, true rewards: #0: 9.417
[2024-10-23 03:51:30,304][00608] Avg episode reward: 19.168, avg true_objective: 9.417
[2024-10-23 03:51:30,344][00608] Num frames 3800...
[2024-10-23 03:51:30,462][00608] Num frames 3900...
[2024-10-23 03:51:30,588][00608] Num frames 4000...
[2024-10-23 03:51:30,709][00608] Num frames 4100...
[2024-10-23 03:51:30,835][00608] Num frames 4200...
[2024-10-23 03:51:30,962][00608] Num frames 4300...
[2024-10-23 03:51:31,031][00608] Avg episode rewards: #0: 16.822, true rewards: #0: 8.622
[2024-10-23 03:51:31,033][00608] Avg episode reward: 16.822, avg true_objective: 8.622
[2024-10-23 03:51:31,145][00608] Num frames 4400...
[2024-10-23 03:51:31,308][00608] Num frames 4500...
[2024-10-23 03:51:31,475][00608] Num frames 4600...
[2024-10-23 03:51:31,636][00608] Num frames 4700...
[2024-10-23 03:51:31,805][00608] Num frames 4800...
[2024-10-23 03:51:31,977][00608] Num frames 4900...
[2024-10-23 03:51:32,154][00608] Num frames 5000...
[2024-10-23 03:51:32,321][00608] Num frames 5100...
[2024-10-23 03:51:32,485][00608] Num frames 5200...
[2024-10-23 03:51:32,668][00608] Num frames 5300...
[2024-10-23 03:51:32,838][00608] Num frames 5400...
[2024-10-23 03:51:33,017][00608] Num frames 5500...
[2024-10-23 03:51:33,202][00608] Num frames 5600...
[2024-10-23 03:51:33,375][00608] Num frames 5700...
[2024-10-23 03:51:33,554][00608] Num frames 5800...
[2024-10-23 03:51:33,689][00608] Num frames 5900...
[2024-10-23 03:51:33,815][00608] Num frames 6000...
[2024-10-23 03:51:33,946][00608] Num frames 6100...
[2024-10-23 03:51:34,072][00608] Num frames 6200...
[2024-10-23 03:51:34,195][00608] Num frames 6300...
[2024-10-23 03:51:34,324][00608] Num frames 6400...
[2024-10-23 03:51:34,394][00608] Avg episode rewards: #0: 23.351, true rewards: #0: 10.685
[2024-10-23 03:51:34,395][00608] Avg episode reward: 23.351, avg true_objective: 10.685
[2024-10-23 03:51:34,503][00608] Num frames 6500...
[2024-10-23 03:51:34,626][00608] Num frames 6600...
[2024-10-23 03:51:34,751][00608] Num frames 6700...
[2024-10-23 03:51:34,879][00608] Num frames 6800...
[2024-10-23 03:51:35,003][00608] Num frames 6900...
[2024-10-23 03:51:35,128][00608] Num frames 7000...
[2024-10-23 03:51:35,255][00608] Num frames 7100...
[2024-10-23 03:51:35,381][00608] Num frames 7200...
[2024-10-23 03:51:35,503][00608] Num frames 7300...
[2024-10-23 03:51:35,628][00608] Num frames 7400...
[2024-10-23 03:51:35,756][00608] Num frames 7500...
[2024-10-23 03:51:35,817][00608] Avg episode rewards: #0: 24.006, true rewards: #0: 10.720
[2024-10-23 03:51:35,819][00608] Avg episode reward: 24.006, avg true_objective: 10.720
[2024-10-23 03:51:35,943][00608] Num frames 7600...
[2024-10-23 03:51:36,063][00608] Num frames 7700...
[2024-10-23 03:51:36,186][00608] Num frames 7800...
[2024-10-23 03:51:36,316][00608] Num frames 7900...
[2024-10-23 03:51:36,439][00608] Num frames 8000...
[2024-10-23 03:51:36,563][00608] Num frames 8100...
[2024-10-23 03:51:36,683][00608] Num frames 8200...
[2024-10-23 03:51:36,802][00608] Num frames 8300...
[2024-10-23 03:51:36,932][00608] Num frames 8400...
[2024-10-23 03:51:37,054][00608] Num frames 8500...
[2024-10-23 03:51:37,221][00608] Avg episode rewards: #0: 24.615, true rewards: #0: 10.740
[2024-10-23 03:51:37,222][00608] Avg episode reward: 24.615, avg true_objective: 10.740
[2024-10-23 03:51:37,235][00608] Num frames 8600...
[2024-10-23 03:51:37,363][00608] Num frames 8700...
[2024-10-23 03:51:37,484][00608] Num frames 8800...
[2024-10-23 03:51:37,604][00608] Num frames 8900...
[2024-10-23 03:51:37,727][00608] Num frames 9000...
[2024-10-23 03:51:37,859][00608] Num frames 9100...
[2024-10-23 03:51:37,958][00608] Avg episode rewards: #0: 22.818, true rewards: #0: 10.151
[2024-10-23 03:51:37,959][00608] Avg episode reward: 22.818, avg true_objective: 10.151
[2024-10-23 03:51:38,039][00608] Num frames 9200...
[2024-10-23 03:51:38,160][00608] Num frames 9300...
[2024-10-23 03:51:38,282][00608] Num frames 9400...
[2024-10-23 03:51:38,412][00608] Num frames 9500...
[2024-10-23 03:51:38,534][00608] Num frames 9600...
[2024-10-23 03:51:38,656][00608] Num frames 9700...
[2024-10-23 03:51:38,775][00608] Num frames 9800...
[2024-10-23 03:51:38,904][00608] Num frames 9900...
[2024-10-23 03:51:39,024][00608] Num frames 10000...
[2024-10-23 03:51:39,144][00608] Num frames 10100...
[2024-10-23 03:51:39,267][00608] Num frames 10200...
[2024-10-23 03:51:39,436][00608] Avg episode rewards: #0: 22.988, true rewards: #0: 10.288
[2024-10-23 03:51:39,437][00608] Avg episode reward: 22.988, avg true_objective: 10.288
[2024-10-23 03:52:40,139][00608] Replay video saved to /content/train_dir/default_experiment/replay.mp4!