[2023-02-22 16:49:30,971][07386] Saving configuration to /content/train_dir/default_experiment/config.json...
[2023-02-22 16:49:30,975][07386] Rollout worker 0 uses device cpu
[2023-02-22 16:49:30,977][07386] Rollout worker 1 uses device cpu
[2023-02-22 16:49:30,979][07386] Rollout worker 2 uses device cpu
[2023-02-22 16:49:30,982][07386] Rollout worker 3 uses device cpu
[2023-02-22 16:49:30,984][07386] Rollout worker 4 uses device cpu
[2023-02-22 16:49:30,991][07386] Rollout worker 5 uses device cpu
[2023-02-22 16:49:30,992][07386] Rollout worker 6 uses device cpu
[2023-02-22 16:49:30,993][07386] Rollout worker 7 uses device cpu
[2023-02-22 16:49:31,283][07386] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-22 16:49:31,286][07386] InferenceWorker_p0-w0: min num requests: 2
[2023-02-22 16:49:31,339][07386] Starting all processes...
[2023-02-22 16:49:31,344][07386] Starting process learner_proc0
[2023-02-22 16:49:31,419][07386] Starting all processes...
[2023-02-22 16:49:31,510][07386] Starting process inference_proc0-0
[2023-02-22 16:49:31,514][07386] Starting process rollout_proc0
[2023-02-22 16:49:31,514][07386] Starting process rollout_proc1
[2023-02-22 16:49:31,516][07386] Starting process rollout_proc2
[2023-02-22 16:49:31,516][07386] Starting process rollout_proc3
[2023-02-22 16:49:31,518][07386] Starting process rollout_proc4
[2023-02-22 16:49:31,518][07386] Starting process rollout_proc5
[2023-02-22 16:49:31,518][07386] Starting process rollout_proc6
[2023-02-22 16:49:31,519][07386] Starting process rollout_proc7
[2023-02-22 16:49:42,519][12864] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-22 16:49:42,519][12864] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
[2023-02-22 16:49:42,680][12890] Worker 7 uses CPU cores [1]
[2023-02-22 16:49:43,129][12879] Worker 0 uses CPU cores [0]
[2023-02-22 16:49:43,270][12878] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-22 16:49:43,270][12878] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
[2023-02-22 16:49:43,420][12881] Worker 2 uses CPU cores [0]
[2023-02-22 16:49:43,460][12880] Worker 1 uses CPU cores [1]
[2023-02-22 16:49:43,509][12889] Worker 6 uses CPU cores [0]
[2023-02-22 16:49:43,635][12882] Worker 3 uses CPU cores [1]
[2023-02-22 16:49:43,743][12888] Worker 5 uses CPU cores [1]
[2023-02-22 16:49:43,992][12883] Worker 4 uses CPU cores [0]
[2023-02-22 16:49:44,134][12878] Num visible devices: 1
[2023-02-22 16:49:44,139][12864] Num visible devices: 1
[2023-02-22 16:49:44,154][12864] Starting seed is not provided
[2023-02-22 16:49:44,155][12864] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-22 16:49:44,156][12864] Initializing actor-critic model on device cuda:0
[2023-02-22 16:49:44,156][12864] RunningMeanStd input shape: (3, 72, 128)
[2023-02-22 16:49:44,159][12864] RunningMeanStd input shape: (1,)
[2023-02-22 16:49:44,187][12864] ConvEncoder: input_channels=3
[2023-02-22 16:49:44,757][12864] Conv encoder output size: 512
[2023-02-22 16:49:44,757][12864] Policy head output size: 512
[2023-02-22 16:49:44,856][12864] Created Actor Critic model with architecture:
[2023-02-22 16:49:44,856][12864] ActorCriticSharedWeights(
  (obs_normalizer): ObservationNormalizer(
    (running_mean_std): RunningMeanStdDictInPlace(
      (running_mean_std): ModuleDict(
        (obs): RunningMeanStdInPlace()
      )
    )
  )
  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
  (encoder): VizdoomEncoder(
    (basic_encoder): ConvEncoder(
      (enc): RecursiveScriptModule(
        original_name=ConvEncoderImpl
        (conv_head): RecursiveScriptModule(
          original_name=Sequential
          (0): RecursiveScriptModule(original_name=Conv2d)
          (1): RecursiveScriptModule(original_name=ELU)
          (2): RecursiveScriptModule(original_name=Conv2d)
          (3): RecursiveScriptModule(original_name=ELU)
          (4): RecursiveScriptModule(original_name=Conv2d)
          (5): RecursiveScriptModule(original_name=ELU)
        )
        (mlp_layers): RecursiveScriptModule(
          original_name=Sequential
          (0): RecursiveScriptModule(original_name=Linear)
          (1): RecursiveScriptModule(original_name=ELU)
        )
      )
    )
  )
  (core): ModelCoreRNN(
    (core): GRU(512, 512)
  )
  (decoder): MlpDecoder(
    (mlp): Identity()
  )
  (critic_linear): Linear(in_features=512, out_features=1, bias=True)
  (action_parameterization): ActionParameterizationDefault(
    (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
  )
)
[2023-02-22 16:49:51,274][07386] Heartbeat connected on Batcher_0
[2023-02-22 16:49:51,283][07386] Heartbeat connected on InferenceWorker_p0-w0
[2023-02-22 16:49:51,293][07386] Heartbeat connected on RolloutWorker_w0
[2023-02-22 16:49:51,306][07386] Heartbeat connected on RolloutWorker_w1
[2023-02-22 16:49:51,310][07386] Heartbeat connected on RolloutWorker_w2
[2023-02-22 16:49:51,314][07386] Heartbeat connected on RolloutWorker_w3
[2023-02-22 16:49:51,321][07386] Heartbeat connected on RolloutWorker_w4
[2023-02-22 16:49:51,325][07386] Heartbeat connected on RolloutWorker_w5
[2023-02-22 16:49:51,334][07386] Heartbeat connected on RolloutWorker_w6
[2023-02-22 16:49:51,343][07386] Heartbeat connected on RolloutWorker_w7
[2023-02-22 16:49:53,616][12864] Using optimizer <class 'torch.optim.adam.Adam'>
[2023-02-22 16:49:53,618][12864] No checkpoints found
[2023-02-22 16:49:53,618][12864] Did not load from checkpoint, starting from scratch!
[2023-02-22 16:49:53,619][12864] Initialized policy 0 weights for model version 0
[2023-02-22 16:49:53,623][12864] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-22 16:49:53,629][12864] LearnerWorker_p0 finished initialization!
[2023-02-22 16:49:53,631][07386] Heartbeat connected on LearnerWorker_p0
[2023-02-22 16:49:53,831][12878] RunningMeanStd input shape: (3, 72, 128)
[2023-02-22 16:49:53,833][12878] RunningMeanStd input shape: (1,)
[2023-02-22 16:49:53,845][12878] ConvEncoder: input_channels=3
[2023-02-22 16:49:53,942][12878] Conv encoder output size: 512
[2023-02-22 16:49:53,943][12878] Policy head output size: 512
[2023-02-22 16:49:55,841][07386] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2023-02-22 16:49:56,272][07386] Inference worker 0-0 is ready!
[2023-02-22 16:49:56,274][07386] All inference workers are ready! Signal rollout workers to start!
[2023-02-22 16:49:56,415][12880] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-22 16:49:56,481][12881] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-22 16:49:56,489][12883] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-22 16:49:56,468][12890] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-22 16:49:56,493][12889] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-22 16:49:56,513][12879] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-22 16:49:56,495][12882] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-22 16:49:56,578][12888] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-22 16:49:58,409][12883] Decorrelating experience for 0 frames...
[2023-02-22 16:49:58,411][12881] Decorrelating experience for 0 frames...
[2023-02-22 16:49:58,411][12880] Decorrelating experience for 0 frames...
[2023-02-22 16:49:58,412][12890] Decorrelating experience for 0 frames...
[2023-02-22 16:49:58,418][12889] Decorrelating experience for 0 frames...
[2023-02-22 16:49:58,420][12882] Decorrelating experience for 0 frames...
[2023-02-22 16:49:58,430][12888] Decorrelating experience for 0 frames...
[2023-02-22 16:49:59,371][12890] Decorrelating experience for 32 frames...
[2023-02-22 16:49:59,518][12880] Decorrelating experience for 32 frames...
[2023-02-22 16:49:59,875][12881] Decorrelating experience for 32 frames...
[2023-02-22 16:49:59,883][12889] Decorrelating experience for 32 frames...
[2023-02-22 16:49:59,881][12883] Decorrelating experience for 32 frames...
[2023-02-22 16:50:00,840][07386] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2023-02-22 16:50:00,865][12880] Decorrelating experience for 64 frames...
[2023-02-22 16:50:01,169][12882] Decorrelating experience for 32 frames...
[2023-02-22 16:50:01,172][12888] Decorrelating experience for 32 frames...
[2023-02-22 16:50:01,462][12879] Decorrelating experience for 0 frames...
[2023-02-22 16:50:01,573][12889] Decorrelating experience for 64 frames...
[2023-02-22 16:50:01,614][12883] Decorrelating experience for 64 frames...
[2023-02-22 16:50:02,644][12890] Decorrelating experience for 64 frames...
[2023-02-22 16:50:02,807][12888] Decorrelating experience for 64 frames...
[2023-02-22 16:50:02,809][12882] Decorrelating experience for 64 frames...
[2023-02-22 16:50:03,125][12879] Decorrelating experience for 32 frames...
[2023-02-22 16:50:03,204][12889] Decorrelating experience for 96 frames...
[2023-02-22 16:50:03,243][12883] Decorrelating experience for 96 frames...
[2023-02-22 16:50:03,783][12881] Decorrelating experience for 64 frames...
[2023-02-22 16:50:04,140][12879] Decorrelating experience for 64 frames...
[2023-02-22 16:50:04,482][12890] Decorrelating experience for 96 frames...
[2023-02-22 16:50:04,549][12888] Decorrelating experience for 96 frames...
[2023-02-22 16:50:04,552][12882] Decorrelating experience for 96 frames...
[2023-02-22 16:50:04,806][12881] Decorrelating experience for 96 frames...
[2023-02-22 16:50:04,902][12880] Decorrelating experience for 96 frames...
[2023-02-22 16:50:05,102][12879] Decorrelating experience for 96 frames...
[2023-02-22 16:50:05,840][07386] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2023-02-22 16:50:10,027][12864] Signal inference workers to stop experience collection...
[2023-02-22 16:50:10,040][12878] InferenceWorker_p0-w0: stopping experience collection
[2023-02-22 16:50:10,840][07386] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 56.7. Samples: 850. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2023-02-22 16:50:10,845][07386] Avg episode reward: [(0, '1.956')]
[2023-02-22 16:50:12,665][12864] Signal inference workers to resume experience collection...
[2023-02-22 16:50:12,667][12878] InferenceWorker_p0-w0: resuming experience collection
[2023-02-22 16:50:15,840][07386] Fps is (10 sec: 1228.8, 60 sec: 614.4, 300 sec: 614.4). Total num frames: 12288. Throughput: 0: 154.5. Samples: 3090. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-02-22 16:50:15,843][07386] Avg episode reward: [(0, '2.856')]
[2023-02-22 16:50:20,840][07386] Fps is (10 sec: 2867.2, 60 sec: 1146.9, 300 sec: 1146.9). Total num frames: 28672. Throughput: 0: 289.6. Samples: 7240. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0)
[2023-02-22 16:50:20,847][07386] Avg episode reward: [(0, '3.557')]
[2023-02-22 16:50:23,451][12878] Updated weights for policy 0, policy_version 10 (0.0027)
[2023-02-22 16:50:25,840][07386] Fps is (10 sec: 3686.5, 60 sec: 1638.5, 300 sec: 1638.5). Total num frames: 49152. Throughput: 0: 342.4. Samples: 10272. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0)
[2023-02-22 16:50:25,843][07386] Avg episode reward: [(0, '4.235')]
[2023-02-22 16:50:30,840][07386] Fps is (10 sec: 4505.6, 60 sec: 2106.6, 300 sec: 2106.6). Total num frames: 73728. Throughput: 0: 506.5. Samples: 17728. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0)
[2023-02-22 16:50:30,842][07386] Avg episode reward: [(0, '4.258')]
[2023-02-22 16:50:31,885][12878] Updated weights for policy 0, policy_version 20 (0.0020)
[2023-02-22 16:50:35,840][07386] Fps is (10 sec: 4096.0, 60 sec: 2252.9, 300 sec: 2252.9). Total num frames: 90112. Throughput: 0: 591.3. Samples: 23652. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 16:50:35,847][07386] Avg episode reward: [(0, '4.394')]
[2023-02-22 16:50:40,840][07386] Fps is (10 sec: 3276.7, 60 sec: 2366.6, 300 sec: 2366.6). Total num frames: 106496. Throughput: 0: 563.1. Samples: 25338. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:50:40,846][07386] Avg episode reward: [(0, '4.253')]
[2023-02-22 16:50:40,852][12864] Saving new best policy, reward=4.253!
[2023-02-22 16:50:44,403][12878] Updated weights for policy 0, policy_version 30 (0.0012)
[2023-02-22 16:50:45,840][07386] Fps is (10 sec: 3686.4, 60 sec: 2539.6, 300 sec: 2539.6). Total num frames: 126976. Throughput: 0: 693.1. Samples: 31188. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:50:45,843][07386] Avg episode reward: [(0, '4.338')]
[2023-02-22 16:50:45,852][12864] Saving new best policy, reward=4.338!
[2023-02-22 16:50:50,840][07386] Fps is (10 sec: 4505.8, 60 sec: 2755.6, 300 sec: 2755.6). Total num frames: 151552. Throughput: 0: 854.8. Samples: 38464. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 16:50:50,843][07386] Avg episode reward: [(0, '4.250')]
[2023-02-22 16:50:53,360][12878] Updated weights for policy 0, policy_version 40 (0.0015)
[2023-02-22 16:50:55,842][07386] Fps is (10 sec: 4095.3, 60 sec: 2798.9, 300 sec: 2798.9). Total num frames: 167936. Throughput: 0: 902.6. Samples: 41470. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:50:55,846][07386] Avg episode reward: [(0, '4.462')]
[2023-02-22 16:50:55,860][12864] Saving new best policy, reward=4.462!
[2023-02-22 16:51:00,841][07386] Fps is (10 sec: 3276.6, 60 sec: 3072.0, 300 sec: 2835.7). Total num frames: 184320. Throughput: 0: 955.5. Samples: 46086. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:51:00,845][07386] Avg episode reward: [(0, '4.553')]
[2023-02-22 16:51:00,854][12864] Saving new best policy, reward=4.553!
[2023-02-22 16:51:04,687][12878] Updated weights for policy 0, policy_version 50 (0.0028)
[2023-02-22 16:51:05,840][07386] Fps is (10 sec: 4096.7, 60 sec: 3481.6, 300 sec: 2984.3). Total num frames: 208896. Throughput: 0: 1006.8. Samples: 52544. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:51:05,843][07386] Avg episode reward: [(0, '4.734')]
[2023-02-22 16:51:05,852][12864] Saving new best policy, reward=4.734!
[2023-02-22 16:51:10,840][07386] Fps is (10 sec: 4915.5, 60 sec: 3891.2, 300 sec: 3113.0). Total num frames: 233472. Throughput: 0: 1018.8. Samples: 56118. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 16:51:10,847][07386] Avg episode reward: [(0, '4.446')]
[2023-02-22 16:51:13,960][12878] Updated weights for policy 0, policy_version 60 (0.0041)
[2023-02-22 16:51:15,842][07386] Fps is (10 sec: 4095.0, 60 sec: 3959.3, 300 sec: 3123.2). Total num frames: 249856. Throughput: 0: 986.7. Samples: 62134. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-22 16:51:15,844][07386] Avg episode reward: [(0, '4.273')]
[2023-02-22 16:51:20,841][07386] Fps is (10 sec: 3276.7, 60 sec: 3959.5, 300 sec: 3132.3). Total num frames: 266240. Throughput: 0: 959.9. Samples: 66846. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:51:20,846][07386] Avg episode reward: [(0, '4.330')]
[2023-02-22 16:51:24,881][12878] Updated weights for policy 0, policy_version 70 (0.0014)
[2023-02-22 16:51:25,840][07386] Fps is (10 sec: 4097.0, 60 sec: 4027.7, 300 sec: 3231.3). Total num frames: 290816. Throughput: 0: 997.6. Samples: 70230. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:51:25,842][07386] Avg episode reward: [(0, '4.481')]
[2023-02-22 16:51:25,857][12864] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000071_290816.pth...
[2023-02-22 16:51:30,847][07386] Fps is (10 sec: 4502.4, 60 sec: 3959.0, 300 sec: 3276.6). Total num frames: 311296. Throughput: 0: 1033.7. Samples: 77714. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 16:51:30,852][07386] Avg episode reward: [(0, '4.518')]
[2023-02-22 16:51:35,843][07386] Fps is (10 sec: 3275.7, 60 sec: 3891.0, 300 sec: 3235.8). Total num frames: 323584. Throughput: 0: 965.5. Samples: 81916. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
[2023-02-22 16:51:35,846][07386] Avg episode reward: [(0, '4.392')]
[2023-02-22 16:51:36,085][12878] Updated weights for policy 0, policy_version 80 (0.0030)
[2023-02-22 16:51:40,840][07386] Fps is (10 sec: 2459.4, 60 sec: 3823.0, 300 sec: 3198.8). Total num frames: 335872. Throughput: 0: 940.9. Samples: 83810. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 16:51:40,843][07386] Avg episode reward: [(0, '4.393')]
[2023-02-22 16:51:45,840][07386] Fps is (10 sec: 2868.2, 60 sec: 3754.7, 300 sec: 3202.4). Total num frames: 352256. Throughput: 0: 925.7. Samples: 87744. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:51:45,847][07386] Avg episode reward: [(0, '4.328')]
[2023-02-22 16:51:48,666][12878] Updated weights for policy 0, policy_version 90 (0.0021)
[2023-02-22 16:51:50,840][07386] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3276.8). Total num frames: 376832. Throughput: 0: 939.1. Samples: 94802. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 16:51:50,848][07386] Avg episode reward: [(0, '4.536')]
[2023-02-22 16:51:55,841][07386] Fps is (10 sec: 4914.6, 60 sec: 3891.2, 300 sec: 3345.1). Total num frames: 401408. Throughput: 0: 943.3. Samples: 98566. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 16:51:55,846][07386] Avg episode reward: [(0, '4.755')]
[2023-02-22 16:51:55,857][12864] Saving new best policy, reward=4.755!
[2023-02-22 16:51:57,873][12878] Updated weights for policy 0, policy_version 100 (0.0018)
[2023-02-22 16:52:00,841][07386] Fps is (10 sec: 4095.7, 60 sec: 3891.2, 300 sec: 3342.4). Total num frames: 417792. Throughput: 0: 930.2. Samples: 103992. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:52:00,847][07386] Avg episode reward: [(0, '4.691')]
[2023-02-22 16:52:05,840][07386] Fps is (10 sec: 3277.2, 60 sec: 3754.7, 300 sec: 3339.9). Total num frames: 434176. Throughput: 0: 934.0. Samples: 108874. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-22 16:52:05,846][07386] Avg episode reward: [(0, '4.565')]
[2023-02-22 16:52:08,926][12878] Updated weights for policy 0, policy_version 110 (0.0013)
[2023-02-22 16:52:10,840][07386] Fps is (10 sec: 4096.3, 60 sec: 3754.7, 300 sec: 3398.2). Total num frames: 458752. Throughput: 0: 940.9. Samples: 112572. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 16:52:10,845][07386] Avg episode reward: [(0, '4.487')]
[2023-02-22 16:52:15,842][07386] Fps is (10 sec: 4504.5, 60 sec: 3822.9, 300 sec: 3423.1). Total num frames: 479232. Throughput: 0: 937.8. Samples: 119910. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 16:52:15,847][07386] Avg episode reward: [(0, '4.587')]
[2023-02-22 16:52:18,457][12878] Updated weights for policy 0, policy_version 120 (0.0014)
[2023-02-22 16:52:20,840][07386] Fps is (10 sec: 3686.3, 60 sec: 3822.9, 300 sec: 3418.1). Total num frames: 495616. Throughput: 0: 954.0. Samples: 124842. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 16:52:20,845][07386] Avg episode reward: [(0, '4.765')]
[2023-02-22 16:52:20,917][12864] Saving new best policy, reward=4.765!
[2023-02-22 16:52:25,840][07386] Fps is (10 sec: 3687.3, 60 sec: 3754.7, 300 sec: 3440.7). Total num frames: 516096. Throughput: 0: 964.0. Samples: 127192. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
[2023-02-22 16:52:25,846][07386] Avg episode reward: [(0, '4.512')]
[2023-02-22 16:52:29,130][12878] Updated weights for policy 0, policy_version 130 (0.0039)
[2023-02-22 16:52:30,840][07386] Fps is (10 sec: 4505.7, 60 sec: 3823.4, 300 sec: 3488.2). Total num frames: 540672. Throughput: 0: 1029.9. Samples: 134090. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 16:52:30,842][07386] Avg episode reward: [(0, '4.477')]
[2023-02-22 16:52:35,840][07386] Fps is (10 sec: 4505.6, 60 sec: 3959.7, 300 sec: 3507.2). Total num frames: 561152. Throughput: 0: 1029.9. Samples: 141148. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 16:52:35,846][07386] Avg episode reward: [(0, '4.635')]
[2023-02-22 16:52:38,770][12878] Updated weights for policy 0, policy_version 140 (0.0017)
[2023-02-22 16:52:40,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3500.2). Total num frames: 577536. Throughput: 0: 997.5. Samples: 143452. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 16:52:40,846][07386] Avg episode reward: [(0, '4.578')]
[2023-02-22 16:52:45,840][07386] Fps is (10 sec: 3686.3, 60 sec: 4096.0, 300 sec: 3517.8). Total num frames: 598016. Throughput: 0: 981.3. Samples: 148150. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:52:45,848][07386] Avg episode reward: [(0, '4.728')]
[2023-02-22 16:52:49,206][12878] Updated weights for policy 0, policy_version 150 (0.0017)
[2023-02-22 16:52:50,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3534.3). Total num frames: 618496. Throughput: 0: 1038.5. Samples: 155606. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 16:52:50,846][07386] Avg episode reward: [(0, '4.704')]
[2023-02-22 16:52:55,840][07386] Fps is (10 sec: 4505.5, 60 sec: 4027.8, 300 sec: 3572.6). Total num frames: 643072. Throughput: 0: 1038.8. Samples: 159320. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
[2023-02-22 16:52:55,847][07386] Avg episode reward: [(0, '4.839')]
[2023-02-22 16:52:55,857][12864] Saving new best policy, reward=4.839!
[2023-02-22 16:52:59,237][12878] Updated weights for policy 0, policy_version 160 (0.0013)
[2023-02-22 16:53:00,842][07386] Fps is (10 sec: 4095.3, 60 sec: 4027.7, 300 sec: 3564.6). Total num frames: 659456. Throughput: 0: 988.9. Samples: 164410. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:53:00,846][07386] Avg episode reward: [(0, '4.727')]
[2023-02-22 16:53:05,840][07386] Fps is (10 sec: 3276.9, 60 sec: 4027.7, 300 sec: 3557.1). Total num frames: 675840. Throughput: 0: 997.2. Samples: 169714. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 16:53:05,842][07386] Avg episode reward: [(0, '4.672')]
[2023-02-22 16:53:09,255][12878] Updated weights for policy 0, policy_version 170 (0.0019)
[2023-02-22 16:53:10,841][07386] Fps is (10 sec: 4096.3, 60 sec: 4027.7, 300 sec: 3591.9). Total num frames: 700416. Throughput: 0: 1028.5. Samples: 173476. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 16:53:10,844][07386] Avg episode reward: [(0, '4.790')]
[2023-02-22 16:53:15,847][07386] Fps is (10 sec: 4911.6, 60 sec: 4095.7, 300 sec: 3624.9). Total num frames: 724992. Throughput: 0: 1037.1. Samples: 180766. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:53:15,859][07386] Avg episode reward: [(0, '4.823')]
[2023-02-22 16:53:19,712][12878] Updated weights for policy 0, policy_version 180 (0.0020)
[2023-02-22 16:53:20,840][07386] Fps is (10 sec: 4096.5, 60 sec: 4096.0, 300 sec: 3616.5). Total num frames: 741376. Throughput: 0: 985.0. Samples: 185474. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 16:53:20,844][07386] Avg episode reward: [(0, '4.830')]
[2023-02-22 16:53:25,840][07386] Fps is (10 sec: 3279.2, 60 sec: 4027.7, 300 sec: 3608.4). Total num frames: 757760. Throughput: 0: 987.5. Samples: 187888. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:53:25,843][07386] Avg episode reward: [(0, '4.805')]
[2023-02-22 16:53:25,858][12864] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000185_757760.pth...
[2023-02-22 16:53:29,396][12878] Updated weights for policy 0, policy_version 190 (0.0018)
[2023-02-22 16:53:30,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3638.8). Total num frames: 782336. Throughput: 0: 1040.8. Samples: 194986. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:53:30,843][07386] Avg episode reward: [(0, '5.176')]
[2023-02-22 16:53:30,845][12864] Saving new best policy, reward=5.176!
[2023-02-22 16:53:35,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3649.2). Total num frames: 802816. Throughput: 0: 1023.9. Samples: 201682. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-22 16:53:35,847][07386] Avg episode reward: [(0, '5.289')]
[2023-02-22 16:53:35,863][12864] Saving new best policy, reward=5.289!
[2023-02-22 16:53:40,217][12878] Updated weights for policy 0, policy_version 200 (0.0012)
[2023-02-22 16:53:40,840][07386] Fps is (10 sec: 3686.5, 60 sec: 4027.7, 300 sec: 3640.9). Total num frames: 819200. Throughput: 0: 990.0. Samples: 203868. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:53:40,845][07386] Avg episode reward: [(0, '5.038')]
[2023-02-22 16:53:45,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4027.8, 300 sec: 3650.8). Total num frames: 839680. Throughput: 0: 988.0. Samples: 208868. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:53:45,842][07386] Avg episode reward: [(0, '5.004')]
[2023-02-22 16:53:49,673][12878] Updated weights for policy 0, policy_version 210 (0.0021)
[2023-02-22 16:53:50,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 3677.7). Total num frames: 864256. Throughput: 0: 1033.9. Samples: 216238. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 16:53:50,843][07386] Avg episode reward: [(0, '5.258')]
[2023-02-22 16:53:55,842][07386] Fps is (10 sec: 4504.5, 60 sec: 4027.6, 300 sec: 3686.4). Total num frames: 884736. Throughput: 0: 1033.7. Samples: 219992. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 16:53:55,849][07386] Avg episode reward: [(0, '5.417')]
[2023-02-22 16:53:55,861][12864] Saving new best policy, reward=5.417!
[2023-02-22 16:54:00,558][12878] Updated weights for policy 0, policy_version 220 (0.0034)
[2023-02-22 16:54:00,845][07386] Fps is (10 sec: 3684.4, 60 sec: 4027.5, 300 sec: 3678.0). Total num frames: 901120. Throughput: 0: 981.5. Samples: 224930. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 16:54:00,848][07386] Avg episode reward: [(0, '5.487')]
[2023-02-22 16:54:00,856][12864] Saving new best policy, reward=5.487!
[2023-02-22 16:54:05,840][07386] Fps is (10 sec: 3687.3, 60 sec: 4096.0, 300 sec: 3686.4). Total num frames: 921600. Throughput: 0: 998.8. Samples: 230422. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:54:05,847][07386] Avg episode reward: [(0, '5.543')]
[2023-02-22 16:54:05,861][12864] Saving new best policy, reward=5.543!
[2023-02-22 16:54:09,959][12878] Updated weights for policy 0, policy_version 230 (0.0017)
[2023-02-22 16:54:10,840][07386] Fps is (10 sec: 4508.1, 60 sec: 4096.1, 300 sec: 3710.5). Total num frames: 946176. Throughput: 0: 1027.9. Samples: 234142. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 16:54:10,848][07386] Avg episode reward: [(0, '5.501')]
[2023-02-22 16:54:15,840][07386] Fps is (10 sec: 4505.5, 60 sec: 4028.2, 300 sec: 3717.9). Total num frames: 966656. Throughput: 0: 1028.9. Samples: 241286. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 16:54:15,843][07386] Avg episode reward: [(0, '5.770')]
[2023-02-22 16:54:15,856][12864] Saving new best policy, reward=5.770!
[2023-02-22 16:54:20,772][12878] Updated weights for policy 0, policy_version 240 (0.0016)
[2023-02-22 16:54:20,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3709.6). Total num frames: 983040. Throughput: 0: 985.9. Samples: 246046. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 16:54:20,845][07386] Avg episode reward: [(0, '5.999')]
[2023-02-22 16:54:20,850][12864] Saving new best policy, reward=5.999!
[2023-02-22 16:54:25,840][07386] Fps is (10 sec: 3276.8, 60 sec: 4027.7, 300 sec: 3701.6). Total num frames: 999424. Throughput: 0: 990.4. Samples: 248434. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 16:54:25,842][07386] Avg episode reward: [(0, '5.747')]
[2023-02-22 16:54:29,985][12878] Updated weights for policy 0, policy_version 250 (0.0024)
[2023-02-22 16:54:30,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 3738.6). Total num frames: 1028096. Throughput: 0: 1043.3. Samples: 255816. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 16:54:30,843][07386] Avg episode reward: [(0, '6.098')]
[2023-02-22 16:54:30,849][12864] Saving new best policy, reward=6.098!
[2023-02-22 16:54:35,840][07386] Fps is (10 sec: 4915.2, 60 sec: 4096.0, 300 sec: 3744.9). Total num frames: 1048576. Throughput: 0: 1027.1. Samples: 262456. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 16:54:35,842][07386] Avg episode reward: [(0, '6.581')]
[2023-02-22 16:54:35,854][12864] Saving new best policy, reward=6.581!
[2023-02-22 16:54:40,847][07386] Fps is (10 sec: 3274.4, 60 sec: 4027.2, 300 sec: 3722.3). Total num frames: 1060864. Throughput: 0: 995.8. Samples: 264810. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 16:54:40,850][07386] Avg episode reward: [(0, '6.335')]
[2023-02-22 16:54:41,087][12878] Updated weights for policy 0, policy_version 260 (0.0015)
[2023-02-22 16:54:45,840][07386] Fps is (10 sec: 3276.8, 60 sec: 4027.7, 300 sec: 3728.8). Total num frames: 1081344. Throughput: 0: 997.4. Samples: 269806. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
[2023-02-22 16:54:45,848][07386] Avg episode reward: [(0, '5.840')]
[2023-02-22 16:54:50,170][12878] Updated weights for policy 0, policy_version 270 (0.0014)
[2023-02-22 16:54:50,840][07386] Fps is (10 sec: 4508.9, 60 sec: 4027.7, 300 sec: 3748.9). Total num frames: 1105920. Throughput: 0: 1040.4. Samples: 277240. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:54:50,842][07386] Avg episode reward: [(0, '6.036')]
[2023-02-22 16:54:55,841][07386] Fps is (10 sec: 4505.0, 60 sec: 4027.8, 300 sec: 3818.3). Total num frames: 1126400. Throughput: 0: 1041.1. Samples: 280992. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 16:54:55,850][07386] Avg episode reward: [(0, '6.786')]
[2023-02-22 16:54:55,893][12864] Saving new best policy, reward=6.786!
[2023-02-22 16:55:00,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4028.1, 300 sec: 3873.8). Total num frames: 1142784. Throughput: 0: 988.4. Samples: 285762. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 16:55:00,843][07386] Avg episode reward: [(0, '7.264')]
[2023-02-22 16:55:00,845][12864] Saving new best policy, reward=7.264!
[2023-02-22 16:55:01,415][12878] Updated weights for policy 0, policy_version 280 (0.0016)
[2023-02-22 16:55:05,840][07386] Fps is (10 sec: 3686.9, 60 sec: 4027.7, 300 sec: 3943.3). Total num frames: 1163264. Throughput: 0: 1005.4. Samples: 291288. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 16:55:05,843][07386] Avg episode reward: [(0, '7.888')]
[2023-02-22 16:55:05,855][12864] Saving new best policy, reward=7.888!
[2023-02-22 16:55:10,329][12878] Updated weights for policy 0, policy_version 290 (0.0012)
[2023-02-22 16:55:10,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3984.9). Total num frames: 1187840. Throughput: 0: 1033.3. Samples: 294934. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:55:10,848][07386] Avg episode reward: [(0, '7.761')]
[2023-02-22 16:55:15,840][07386] Fps is (10 sec: 4505.7, 60 sec: 4027.7, 300 sec: 3998.8). Total num frames: 1208320. Throughput: 0: 1025.2. Samples: 301950. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 16:55:15,842][07386] Avg episode reward: [(0, '7.594')]
[2023-02-22 16:55:20,840][07386] Fps is (10 sec: 3686.3, 60 sec: 4027.7, 300 sec: 3984.9). Total num frames: 1224704. Throughput: 0: 981.9. Samples: 306642. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:55:20,844][07386] Avg episode reward: [(0, '8.471')]
[2023-02-22 16:55:20,849][12864] Saving new best policy, reward=8.471!
[2023-02-22 16:55:21,626][12878] Updated weights for policy 0, policy_version 300 (0.0013)
[2023-02-22 16:55:25,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 3971.0). Total num frames: 1245184. Throughput: 0: 985.7. Samples: 309160. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:55:25,847][07386] Avg episode reward: [(0, '8.453')]
[2023-02-22 16:55:25,862][12864] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000304_1245184.pth...
[2023-02-22 16:55:25,997][12864] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000071_290816.pth
[2023-02-22 16:55:30,466][12878] Updated weights for policy 0, policy_version 310 (0.0026)
[2023-02-22 16:55:30,840][07386] Fps is (10 sec: 4505.7, 60 sec: 4027.7, 300 sec: 3998.8). Total num frames: 1269760. Throughput: 0: 1041.0. Samples: 316650. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:55:30,842][07386] Avg episode reward: [(0, '9.027')]
[2023-02-22 16:55:30,851][12864] Saving new best policy, reward=9.027!
[2023-02-22 16:55:35,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 4012.7). Total num frames: 1290240. Throughput: 0: 1017.3. Samples: 323018. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 16:55:35,845][07386] Avg episode reward: [(0, '8.763')]
[2023-02-22 16:55:40,843][07386] Fps is (10 sec: 3685.1, 60 sec: 4096.3, 300 sec: 3998.8). Total num frames: 1306624. Throughput: 0: 986.8. Samples: 325398. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 16:55:40,846][07386] Avg episode reward: [(0, '9.690')]
[2023-02-22 16:55:40,851][12864] Saving new best policy, reward=9.690!
[2023-02-22 16:55:41,899][12878] Updated weights for policy 0, policy_version 320 (0.0017)
[2023-02-22 16:55:45,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 3984.9). Total num frames: 1327104. Throughput: 0: 998.3. Samples: 330686. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 16:55:45,843][07386] Avg episode reward: [(0, '10.470')]
[2023-02-22 16:55:45,850][12864] Saving new best policy, reward=10.470!
[2023-02-22 16:55:50,693][12878] Updated weights for policy 0, policy_version 330 (0.0016)
[2023-02-22 16:55:50,840][07386] Fps is (10 sec: 4507.1, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 1351680. Throughput: 0: 1039.1. Samples: 338048. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 16:55:50,843][07386] Avg episode reward: [(0, '11.031')]
[2023-02-22 16:55:50,850][12864] Saving new best policy, reward=11.031!
[2023-02-22 16:55:55,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4096.1, 300 sec: 4026.6). Total num frames: 1372160. Throughput: 0: 1038.1. Samples: 341648. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:55:55,845][07386] Avg episode reward: [(0, '10.020')]
[2023-02-22 16:56:00,840][07386] Fps is (10 sec: 3276.8, 60 sec: 4027.7, 300 sec: 3984.9). Total num frames: 1384448. Throughput: 0: 986.8. Samples: 346354. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:56:00,843][07386] Avg episode reward: [(0, '10.357')]
[2023-02-22 16:56:02,540][12878] Updated weights for policy 0, policy_version 340 (0.0027)
[2023-02-22 16:56:05,840][07386] Fps is (10 sec: 3276.8, 60 sec: 4027.7, 300 sec: 3971.0). Total num frames: 1404928. Throughput: 0: 1010.0. Samples: 352090. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 16:56:05,843][07386] Avg episode reward: [(0, '11.255')]
[2023-02-22 16:56:05,873][12864] Saving new best policy, reward=11.255!
[2023-02-22 16:56:10,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3998.8). Total num frames: 1429504. Throughput: 0: 1034.6. Samples: 355718. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:56:10,843][07386] Avg episode reward: [(0, '12.440')]
[2023-02-22 16:56:10,845][12864] Saving new best policy, reward=12.440!
[2023-02-22 16:56:11,170][12878] Updated weights for policy 0, policy_version 350 (0.0015)
[2023-02-22 16:56:15,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 4012.7). Total num frames: 1449984. Throughput: 0: 1015.7. Samples: 362356. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:56:15,845][07386] Avg episode reward: [(0, '13.175')]
[2023-02-22 16:56:15,861][12864] Saving new best policy, reward=13.175!
[2023-02-22 16:56:20,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3984.9). Total num frames: 1466368. Throughput: 0: 976.2. Samples: 366946. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:56:20,842][07386] Avg episode reward: [(0, '13.293')]
[2023-02-22 16:56:20,849][12864] Saving new best policy, reward=13.293!
[2023-02-22 16:56:23,087][12878] Updated weights for policy 0, policy_version 360 (0.0032)
[2023-02-22 16:56:25,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3985.0). Total num frames: 1486848. Throughput: 0: 980.9. Samples: 369534. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:56:25,847][07386] Avg episode reward: [(0, '13.347')]
[2023-02-22 16:56:25,859][12864] Saving new best policy, reward=13.347!
[2023-02-22 16:56:30,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 4026.6). Total num frames: 1511424. Throughput: 0: 1028.3. Samples: 376960. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:56:30,842][07386] Avg episode reward: [(0, '13.709')]
[2023-02-22 16:56:30,849][12864] Saving new best policy, reward=13.709!
[2023-02-22 16:56:31,372][12878] Updated weights for policy 0, policy_version 370 (0.0023)
[2023-02-22 16:56:35,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 4054.3). Total num frames: 1531904. Throughput: 0: 1004.4. Samples: 383248. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:56:35,848][07386] Avg episode reward: [(0, '13.681')]
[2023-02-22 16:56:40,840][07386] Fps is (10 sec: 3276.7, 60 sec: 3959.7, 300 sec: 4040.5). Total num frames: 1544192. Throughput: 0: 977.9. Samples: 385654. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 16:56:40,848][07386] Avg episode reward: [(0, '13.907')]
[2023-02-22 16:56:40,850][12864] Saving new best policy, reward=13.907!
[2023-02-22 16:56:43,298][12878] Updated weights for policy 0, policy_version 380 (0.0015)
[2023-02-22 16:56:45,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4040.5). Total num frames: 1568768. Throughput: 0: 993.0. Samples: 391038. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 16:56:45,843][07386] Avg episode reward: [(0, '14.872')]
[2023-02-22 16:56:45,850][12864] Saving new best policy, reward=14.872!
[2023-02-22 16:56:50,840][07386] Fps is (10 sec: 4915.4, 60 sec: 4027.7, 300 sec: 4040.5). Total num frames: 1593344. Throughput: 0: 1029.3. Samples: 398410. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 16:56:50,847][07386] Avg episode reward: [(0, '15.005')]
[2023-02-22 16:56:50,854][12864] Saving new best policy, reward=15.005!
[2023-02-22 16:56:51,609][12878] Updated weights for policy 0, policy_version 390 (0.0019)
[2023-02-22 16:56:55,844][07386] Fps is (10 sec: 4094.2, 60 sec: 3959.2, 300 sec: 4040.4). Total num frames: 1609728. Throughput: 0: 1025.6. Samples: 401874. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 16:56:55,847][07386] Avg episode reward: [(0, '15.782')]
[2023-02-22 16:56:55,862][12864] Saving new best policy, reward=15.782!
[2023-02-22 16:57:00,840][07386] Fps is (10 sec: 3276.8, 60 sec: 4027.7, 300 sec: 4040.5). Total num frames: 1626112. Throughput: 0: 982.2. Samples: 406554. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:57:00,846][07386] Avg episode reward: [(0, '15.475')]
[2023-02-22 16:57:03,345][12878] Updated weights for policy 0, policy_version 400 (0.0019)
[2023-02-22 16:57:05,840][07386] Fps is (10 sec: 4097.8, 60 sec: 4096.0, 300 sec: 4040.5). Total num frames: 1650688. Throughput: 0: 1014.4. Samples: 412594. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 16:57:05,843][07386] Avg episode reward: [(0, '17.212')]
[2023-02-22 16:57:05,852][12864] Saving new best policy, reward=17.212!
[2023-02-22 16:57:10,840][07386] Fps is (10 sec: 4915.2, 60 sec: 4096.0, 300 sec: 4054.4). Total num frames: 1675264. Throughput: 0: 1038.8. Samples: 416278. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 16:57:10,843][07386] Avg episode reward: [(0, '16.254')]
[2023-02-22 16:57:11,697][12878] Updated weights for policy 0, policy_version 410 (0.0016)
[2023-02-22 16:57:15,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 4054.3). Total num frames: 1691648. Throughput: 0: 1016.4. Samples: 422696. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 16:57:15,842][07386] Avg episode reward: [(0, '14.996')]
[2023-02-22 16:57:20,842][07386] Fps is (10 sec: 3276.1, 60 sec: 4027.6, 300 sec: 4040.4). Total num frames: 1708032. Throughput: 0: 979.2. Samples: 427312. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 16:57:20,851][07386] Avg episode reward: [(0, '14.278')]
[2023-02-22 16:57:23,473][12878] Updated weights for policy 0, policy_version 420 (0.0018)
[2023-02-22 16:57:25,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4026.6). Total num frames: 1728512. Throughput: 0: 992.0. Samples: 430294. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
[2023-02-22 16:57:25,849][07386] Avg episode reward: [(0, '14.211')]
[2023-02-22 16:57:25,948][12864] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000423_1732608.pth...
[2023-02-22 16:57:26,082][12864] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000185_757760.pth
[2023-02-22 16:57:30,840][07386] Fps is (10 sec: 4506.5, 60 sec: 4027.7, 300 sec: 4040.5). Total num frames: 1753088. Throughput: 0: 1035.3. Samples: 437628. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 16:57:30,842][07386] Avg episode reward: [(0, '14.795')]
[2023-02-22 16:57:31,913][12878] Updated weights for policy 0, policy_version 430 (0.0017)
[2023-02-22 16:57:35,845][07386] Fps is (10 sec: 4093.8, 60 sec: 3959.1, 300 sec: 4040.4). Total num frames: 1769472. Throughput: 0: 1003.3. Samples: 443562. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:57:35,848][07386] Avg episode reward: [(0, '15.696')]
[2023-02-22 16:57:40,840][07386] Fps is (10 sec: 3276.8, 60 sec: 4027.8, 300 sec: 4026.6). Total num frames: 1785856. Throughput: 0: 977.9. Samples: 445876. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 16:57:40,846][07386] Avg episode reward: [(0, '17.089')]
[2023-02-22 16:57:43,705][12878] Updated weights for policy 0, policy_version 440 (0.0015)
[2023-02-22 16:57:45,840][07386] Fps is (10 sec: 4098.2, 60 sec: 4027.7, 300 sec: 4040.5). Total num frames: 1810432. Throughput: 0: 1005.6. Samples: 451808. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 16:57:45,848][07386] Avg episode reward: [(0, '18.740')]
[2023-02-22 16:57:45,861][12864] Saving new best policy, reward=18.740!
[2023-02-22 16:57:50,840][07386] Fps is (10 sec: 4915.2, 60 sec: 4027.7, 300 sec: 4040.5). Total num frames: 1835008. Throughput: 0: 1036.9. Samples: 459254. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 16:57:50,843][07386] Avg episode reward: [(0, '18.380')]
[2023-02-22 16:57:52,132][12878] Updated weights for policy 0, policy_version 450 (0.0019)
[2023-02-22 16:57:55,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4028.0, 300 sec: 4040.5). Total num frames: 1851392. Throughput: 0: 1021.2. Samples: 462230. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 16:57:55,849][07386] Avg episode reward: [(0, '19.476')]
[2023-02-22 16:57:55,862][12864] Saving new best policy, reward=19.476!
[2023-02-22 16:58:00,840][07386] Fps is (10 sec: 3276.8, 60 sec: 4027.7, 300 sec: 4040.5). Total num frames: 1867776. Throughput: 0: 980.3. Samples: 466810. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:58:00,847][07386] Avg episode reward: [(0, '19.358')]
[2023-02-22 16:58:03,943][12878] Updated weights for policy 0, policy_version 460 (0.0020)
[2023-02-22 16:58:05,840][07386] Fps is (10 sec: 4095.9, 60 sec: 4027.7, 300 sec: 4040.5). Total num frames: 1892352. Throughput: 0: 1022.7. Samples: 473330. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 16:58:05,847][07386] Avg episode reward: [(0, '19.403')]
[2023-02-22 16:58:10,840][07386] Fps is (10 sec: 4915.2, 60 sec: 4027.7, 300 sec: 4040.6). Total num frames: 1916928. Throughput: 0: 1039.4. Samples: 477068. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:58:10,848][07386] Avg episode reward: [(0, '19.351')]
[2023-02-22 16:58:12,711][12878] Updated weights for policy 0, policy_version 470 (0.0026)
[2023-02-22 16:58:15,840][07386] Fps is (10 sec: 4096.1, 60 sec: 4027.7, 300 sec: 4040.5). Total num frames: 1933312. Throughput: 0: 1013.2. Samples: 483220. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 16:58:15,848][07386] Avg episode reward: [(0, '20.792')]
[2023-02-22 16:58:15,860][12864] Saving new best policy, reward=20.792!
[2023-02-22 16:58:20,840][07386] Fps is (10 sec: 3276.8, 60 sec: 4027.9, 300 sec: 4040.5). Total num frames: 1949696. Throughput: 0: 983.8. Samples: 487826. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 16:58:20,850][07386] Avg episode reward: [(0, '21.208')]
[2023-02-22 16:58:20,855][12864] Saving new best policy, reward=21.208!
[2023-02-22 16:58:25,841][07386] Fps is (10 sec: 2866.9, 60 sec: 3891.1, 300 sec: 3998.8). Total num frames: 1961984. Throughput: 0: 977.7. Samples: 489872. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:58:25,845][07386] Avg episode reward: [(0, '21.064')]
[2023-02-22 16:58:26,110][12878] Updated weights for policy 0, policy_version 480 (0.0022)
[2023-02-22 16:58:30,840][07386] Fps is (10 sec: 3276.9, 60 sec: 3822.9, 300 sec: 3998.8). Total num frames: 1982464. Throughput: 0: 951.3. Samples: 494616. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:58:30,842][07386] Avg episode reward: [(0, '21.726')]
[2023-02-22 16:58:30,847][12864] Saving new best policy, reward=21.726!
[2023-02-22 16:58:35,842][07386] Fps is (10 sec: 3686.0, 60 sec: 3823.1, 300 sec: 3998.8). Total num frames: 1998848. Throughput: 0: 905.4. Samples: 500000. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 16:58:35,845][07386] Avg episode reward: [(0, '22.223')]
[2023-02-22 16:58:35,853][12864] Saving new best policy, reward=22.223!
[2023-02-22 16:58:38,382][12878] Updated weights for policy 0, policy_version 490 (0.0021)
[2023-02-22 16:58:40,840][07386] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3971.0). Total num frames: 2011136. Throughput: 0: 890.4. Samples: 502296. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:58:40,844][07386] Avg episode reward: [(0, '23.733')]
[2023-02-22 16:58:40,898][12864] Saving new best policy, reward=23.733!
[2023-02-22 16:58:45,840][07386] Fps is (10 sec: 3687.2, 60 sec: 3754.7, 300 sec: 3971.0). Total num frames: 2035712. Throughput: 0: 922.2. Samples: 508310. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 16:58:45,843][07386] Avg episode reward: [(0, '24.654')]
[2023-02-22 16:58:45,851][12864] Saving new best policy, reward=24.654!
[2023-02-22 16:58:47,768][12878] Updated weights for policy 0, policy_version 500 (0.0021)
[2023-02-22 16:58:50,840][07386] Fps is (10 sec: 4915.2, 60 sec: 3754.7, 300 sec: 3985.0). Total num frames: 2060288. Throughput: 0: 938.6. Samples: 515568. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:58:50,843][07386] Avg episode reward: [(0, '23.514')]
[2023-02-22 16:58:55,842][07386] Fps is (10 sec: 4095.0, 60 sec: 3754.5, 300 sec: 3985.0). Total num frames: 2076672. Throughput: 0: 919.2. Samples: 518436. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 16:58:55,851][07386] Avg episode reward: [(0, '22.468')]
[2023-02-22 16:58:58,774][12878] Updated weights for policy 0, policy_version 510 (0.0022)
[2023-02-22 16:59:00,840][07386] Fps is (10 sec: 3276.6, 60 sec: 3754.6, 300 sec: 3971.0). Total num frames: 2093056. Throughput: 0: 887.4. Samples: 523154. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 16:59:00,843][07386] Avg episode reward: [(0, '21.673')]
[2023-02-22 16:59:05,840][07386] Fps is (10 sec: 4096.9, 60 sec: 3754.7, 300 sec: 3971.0). Total num frames: 2117632. Throughput: 0: 931.6. Samples: 529746. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 16:59:05,846][07386] Avg episode reward: [(0, '19.508')]
[2023-02-22 16:59:08,125][12878] Updated weights for policy 0, policy_version 520 (0.0027)
[2023-02-22 16:59:10,840][07386] Fps is (10 sec: 4915.4, 60 sec: 3754.7, 300 sec: 3984.9). Total num frames: 2142208. Throughput: 0: 968.6. Samples: 533460. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-22 16:59:10,847][07386] Avg episode reward: [(0, '17.313')]
[2023-02-22 16:59:15,841][07386] Fps is (10 sec: 4095.5, 60 sec: 3754.6, 300 sec: 3984.9). Total num frames: 2158592. Throughput: 0: 997.0. Samples: 539482. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 16:59:15,843][07386] Avg episode reward: [(0, '17.731')]
[2023-02-22 16:59:19,392][12878] Updated weights for policy 0, policy_version 530 (0.0023)
[2023-02-22 16:59:20,840][07386] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3984.9). Total num frames: 2174976. Throughput: 0: 980.8. Samples: 544136. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:59:20,845][07386] Avg episode reward: [(0, '17.449')]
[2023-02-22 16:59:25,840][07386] Fps is (10 sec: 4096.6, 60 sec: 3959.5, 300 sec: 3971.0). Total num frames: 2199552. Throughput: 0: 1004.7. Samples: 547506. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
[2023-02-22 16:59:25,847][07386] Avg episode reward: [(0, '18.066')]
[2023-02-22 16:59:25,859][12864] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000537_2199552.pth...
[2023-02-22 16:59:25,972][12864] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000304_1245184.pth
[2023-02-22 16:59:28,281][12878] Updated weights for policy 0, policy_version 540 (0.0012)
[2023-02-22 16:59:30,840][07386] Fps is (10 sec: 4915.2, 60 sec: 4027.7, 300 sec: 3984.9). Total num frames: 2224128. Throughput: 0: 1035.7. Samples: 554916. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 16:59:30,847][07386] Avg episode reward: [(0, '19.319')]
[2023-02-22 16:59:35,842][07386] Fps is (10 sec: 4095.3, 60 sec: 4027.8, 300 sec: 3998.9). Total num frames: 2240512. Throughput: 0: 999.3. Samples: 560540. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
[2023-02-22 16:59:35,847][07386] Avg episode reward: [(0, '20.362')]
[2023-02-22 16:59:39,649][12878] Updated weights for policy 0, policy_version 550 (0.0037)
[2023-02-22 16:59:40,840][07386] Fps is (10 sec: 2867.2, 60 sec: 4027.7, 300 sec: 3971.0). Total num frames: 2252800. Throughput: 0: 988.6. Samples: 562920. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 16:59:40,852][07386] Avg episode reward: [(0, '21.332')]
[2023-02-22 16:59:45,840][07386] Fps is (10 sec: 4096.8, 60 sec: 4096.0, 300 sec: 3984.9). Total num frames: 2281472. Throughput: 0: 1024.2. Samples: 569244. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 16:59:45,845][07386] Avg episode reward: [(0, '22.027')]
[2023-02-22 16:59:48,219][12878] Updated weights for policy 0, policy_version 560 (0.0018)
[2023-02-22 16:59:50,840][07386] Fps is (10 sec: 5324.8, 60 sec: 4096.0, 300 sec: 3998.8). Total num frames: 2306048. Throughput: 0: 1044.5. Samples: 576750. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 16:59:50,846][07386] Avg episode reward: [(0, '23.066')]
[2023-02-22 16:59:55,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4096.2, 300 sec: 3998.8). Total num frames: 2322432. Throughput: 0: 1018.1. Samples: 579274. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 16:59:55,849][07386] Avg episode reward: [(0, '23.090')]
[2023-02-22 16:59:59,376][12878] Updated weights for policy 0, policy_version 570 (0.0011)
[2023-02-22 17:00:00,840][07386] Fps is (10 sec: 3276.8, 60 sec: 4096.0, 300 sec: 3984.9). Total num frames: 2338816. Throughput: 0: 990.1. Samples: 584034. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-22 17:00:00,847][07386] Avg episode reward: [(0, '23.314')]
[2023-02-22 17:00:05,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 3984.9). Total num frames: 2363392. Throughput: 0: 1040.6. Samples: 590962. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-22 17:00:05,843][07386] Avg episode reward: [(0, '21.278')]
[2023-02-22 17:00:08,083][12878] Updated weights for policy 0, policy_version 580 (0.0012)
[2023-02-22 17:00:10,845][07386] Fps is (10 sec: 4912.5, 60 sec: 4095.6, 300 sec: 3998.7). Total num frames: 2387968. Throughput: 0: 1047.5. Samples: 594650. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:00:10,848][07386] Avg episode reward: [(0, '18.908')]
[2023-02-22 17:00:15,841][07386] Fps is (10 sec: 3686.0, 60 sec: 4027.7, 300 sec: 3984.9). Total num frames: 2400256. Throughput: 0: 1010.4. Samples: 600384. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:00:15,845][07386] Avg episode reward: [(0, '18.640')]
[2023-02-22 17:00:19,841][12878] Updated weights for policy 0, policy_version 590 (0.0020)
[2023-02-22 17:00:20,840][07386] Fps is (10 sec: 2868.8, 60 sec: 4027.7, 300 sec: 3971.0). Total num frames: 2416640. Throughput: 0: 988.4. Samples: 605014. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:00:20,842][07386] Avg episode reward: [(0, '18.689')]
[2023-02-22 17:00:25,840][07386] Fps is (10 sec: 4506.2, 60 sec: 4096.0, 300 sec: 3984.9). Total num frames: 2445312. Throughput: 0: 1017.7. Samples: 608716. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
[2023-02-22 17:00:25,842][07386] Avg episode reward: [(0, '20.410')]
[2023-02-22 17:00:28,175][12878] Updated weights for policy 0, policy_version 600 (0.0019)
[2023-02-22 17:00:30,843][07386] Fps is (10 sec: 5323.0, 60 sec: 4095.8, 300 sec: 3998.8). Total num frames: 2469888. Throughput: 0: 1044.7. Samples: 616260. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:00:30,851][07386] Avg episode reward: [(0, '21.887')]
[2023-02-22 17:00:35,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4027.9, 300 sec: 3985.0). Total num frames: 2482176. Throughput: 0: 994.3. Samples: 621494. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
[2023-02-22 17:00:35,843][07386] Avg episode reward: [(0, '21.130')]
[2023-02-22 17:00:40,052][12878] Updated weights for policy 0, policy_version 610 (0.0015)
[2023-02-22 17:00:40,840][07386] Fps is (10 sec: 2868.2, 60 sec: 4096.0, 300 sec: 3971.0). Total num frames: 2498560. Throughput: 0: 990.4. Samples: 623840. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:00:40,843][07386] Avg episode reward: [(0, '22.528')]
[2023-02-22 17:00:45,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3971.0). Total num frames: 2523136. Throughput: 0: 1030.1. Samples: 630390. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:00:45,844][07386] Avg episode reward: [(0, '21.084')]
[2023-02-22 17:00:48,244][12878] Updated weights for policy 0, policy_version 620 (0.0018)
[2023-02-22 17:00:50,840][07386] Fps is (10 sec: 4915.2, 60 sec: 4027.7, 300 sec: 3984.9). Total num frames: 2547712. Throughput: 0: 1045.2. Samples: 637994. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:00:50,845][07386] Avg episode reward: [(0, '19.979')]
[2023-02-22 17:00:55,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3998.8). Total num frames: 2564096. Throughput: 0: 1015.6. Samples: 640346. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 17:00:55,847][07386] Avg episode reward: [(0, '19.027')]
[2023-02-22 17:01:00,042][12878] Updated weights for policy 0, policy_version 630 (0.0030)
[2023-02-22 17:01:00,840][07386] Fps is (10 sec: 3276.8, 60 sec: 4027.7, 300 sec: 3984.9). Total num frames: 2580480. Throughput: 0: 992.2. Samples: 645032. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:01:00,847][07386] Avg episode reward: [(0, '21.506')]
[2023-02-22 17:01:05,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 3998.8). Total num frames: 2609152. Throughput: 0: 1048.8. Samples: 652212. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:01:05,847][07386] Avg episode reward: [(0, '21.371')]
[2023-02-22 17:01:08,170][12878] Updated weights for policy 0, policy_version 640 (0.0020)
[2023-02-22 17:01:10,842][07386] Fps is (10 sec: 4914.0, 60 sec: 4027.9, 300 sec: 3998.8). Total num frames: 2629632. Throughput: 0: 1049.9. Samples: 655964. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-22 17:01:10,845][07386] Avg episode reward: [(0, '23.294')]
[2023-02-22 17:01:15,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4096.1, 300 sec: 3998.8). Total num frames: 2646016. Throughput: 0: 1004.7. Samples: 661466. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 17:01:15,845][07386] Avg episode reward: [(0, '23.643')]
[2023-02-22 17:01:20,063][12878] Updated weights for policy 0, policy_version 650 (0.0033)
[2023-02-22 17:01:20,840][07386] Fps is (10 sec: 3277.6, 60 sec: 4096.0, 300 sec: 3984.9). Total num frames: 2662400. Throughput: 0: 996.6. Samples: 666340. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-22 17:01:20,842][07386] Avg episode reward: [(0, '24.741')]
[2023-02-22 17:01:20,912][12864] Saving new best policy, reward=24.741!
[2023-02-22 17:01:25,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3984.9). Total num frames: 2686976. Throughput: 0: 1028.2. Samples: 670110. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:01:25,848][07386] Avg episode reward: [(0, '24.582')]
[2023-02-22 17:01:25,898][12864] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000657_2691072.pth...
[2023-02-22 17:01:26,047][12864] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000423_1732608.pth
[2023-02-22 17:01:28,380][12878] Updated weights for policy 0, policy_version 660 (0.0015)
[2023-02-22 17:01:30,840][07386] Fps is (10 sec: 4915.2, 60 sec: 4028.0, 300 sec: 3998.8). Total num frames: 2711552. Throughput: 0: 1046.2. Samples: 677468. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:01:30,844][07386] Avg episode reward: [(0, '25.772')]
[2023-02-22 17:01:30,852][12864] Saving new best policy, reward=25.772!
[2023-02-22 17:01:35,840][07386] Fps is (10 sec: 4095.9, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 2727936. Throughput: 0: 985.5. Samples: 682344. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:01:35,847][07386] Avg episode reward: [(0, '25.535')]
[2023-02-22 17:01:40,391][12878] Updated weights for policy 0, policy_version 670 (0.0016)
[2023-02-22 17:01:40,840][07386] Fps is (10 sec: 3276.8, 60 sec: 4096.0, 300 sec: 3984.9). Total num frames: 2744320. Throughput: 0: 984.4. Samples: 684642. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:01:40,843][07386] Avg episode reward: [(0, '24.494')]
[2023-02-22 17:01:45,840][07386] Fps is (10 sec: 4096.1, 60 sec: 4096.0, 300 sec: 3984.9). Total num frames: 2768896. Throughput: 0: 1034.0. Samples: 691562. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 17:01:45,843][07386] Avg episode reward: [(0, '25.292')]
[2023-02-22 17:01:48,615][12878] Updated weights for policy 0, policy_version 680 (0.0013)
[2023-02-22 17:01:50,840][07386] Fps is (10 sec: 4915.2, 60 sec: 4096.0, 300 sec: 4012.8). Total num frames: 2793472. Throughput: 0: 1033.2. Samples: 698704. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 17:01:50,850][07386] Avg episode reward: [(0, '24.173')]
[2023-02-22 17:01:55,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3998.8). Total num frames: 2805760. Throughput: 0: 1001.7. Samples: 701038. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:01:55,846][07386] Avg episode reward: [(0, '23.008')]
[2023-02-22 17:02:00,415][12878] Updated weights for policy 0, policy_version 690 (0.0029)
[2023-02-22 17:02:00,840][07386] Fps is (10 sec: 3276.8, 60 sec: 4096.0, 300 sec: 3984.9). Total num frames: 2826240. Throughput: 0: 986.7. Samples: 705866. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:02:00,847][07386] Avg episode reward: [(0, '23.104')]
[2023-02-22 17:02:05,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3984.9). Total num frames: 2850816. Throughput: 0: 1042.7. Samples: 713262. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:02:05,843][07386] Avg episode reward: [(0, '23.220')]
[2023-02-22 17:02:08,617][12878] Updated weights for policy 0, policy_version 700 (0.0012)
[2023-02-22 17:02:10,842][07386] Fps is (10 sec: 4914.4, 60 sec: 4096.1, 300 sec: 4012.7). Total num frames: 2875392. Throughput: 0: 1041.8. Samples: 716994. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:02:10,847][07386] Avg episode reward: [(0, '21.770')]
[2023-02-22 17:02:15,846][07386] Fps is (10 sec: 3684.1, 60 sec: 4027.3, 300 sec: 3998.7). Total num frames: 2887680. Throughput: 0: 995.5. Samples: 722272. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:02:15,849][07386] Avg episode reward: [(0, '22.464')]
[2023-02-22 17:02:20,433][12878] Updated weights for policy 0, policy_version 710 (0.0038)
[2023-02-22 17:02:20,840][07386] Fps is (10 sec: 3277.2, 60 sec: 4096.0, 300 sec: 3998.8). Total num frames: 2908160. Throughput: 0: 1005.0. Samples: 727570. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:02:20,848][07386] Avg episode reward: [(0, '23.672')]
[2023-02-22 17:02:25,840][07386] Fps is (10 sec: 4508.4, 60 sec: 4096.0, 300 sec: 3998.8). Total num frames: 2932736. Throughput: 0: 1034.8. Samples: 731206. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:02:25,847][07386] Avg episode reward: [(0, '23.626')]
[2023-02-22 17:02:28,700][12878] Updated weights for policy 0, policy_version 720 (0.0017)
[2023-02-22 17:02:30,841][07386] Fps is (10 sec: 4505.1, 60 sec: 4027.6, 300 sec: 4012.7). Total num frames: 2953216. Throughput: 0: 1048.4. Samples: 738742. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:02:30,844][07386] Avg episode reward: [(0, '23.055')]
[2023-02-22 17:02:35,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4027.8, 300 sec: 4012.7). Total num frames: 2969600. Throughput: 0: 993.4. Samples: 743406. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:02:35,843][07386] Avg episode reward: [(0, '24.215')]
[2023-02-22 17:02:40,419][12878] Updated weights for policy 0, policy_version 730 (0.0020)
[2023-02-22 17:02:40,840][07386] Fps is (10 sec: 3686.9, 60 sec: 4096.0, 300 sec: 3998.8). Total num frames: 2990080. Throughput: 0: 993.0. Samples: 745722. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:02:40,843][07386] Avg episode reward: [(0, '24.813')]
[2023-02-22 17:02:45,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 3998.8). Total num frames: 3014656. Throughput: 0: 1046.8. Samples: 752972. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:02:45,842][07386] Avg episode reward: [(0, '25.997')]
[2023-02-22 17:02:45,859][12864] Saving new best policy, reward=25.997!
[2023-02-22 17:02:48,779][12878] Updated weights for policy 0, policy_version 740 (0.0013)
[2023-02-22 17:02:50,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 4012.7). Total num frames: 3035136. Throughput: 0: 1033.2. Samples: 759758. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:02:50,842][07386] Avg episode reward: [(0, '25.261')]
[2023-02-22 17:02:55,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 3051520. Throughput: 0: 1001.5. Samples: 762058. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:02:55,847][07386] Avg episode reward: [(0, '26.022')]
[2023-02-22 17:02:55,857][12864] Saving new best policy, reward=26.022!
[2023-02-22 17:03:00,600][12878] Updated weights for policy 0, policy_version 750 (0.0013)
[2023-02-22 17:03:00,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 3998.8). Total num frames: 3072000. Throughput: 0: 989.7. Samples: 766804. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:03:00,847][07386] Avg episode reward: [(0, '24.745')]
[2023-02-22 17:03:05,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 3998.8). Total num frames: 3096576. Throughput: 0: 1039.0. Samples: 774326. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:03:05,848][07386] Avg episode reward: [(0, '23.122')]
[2023-02-22 17:03:08,929][12878] Updated weights for policy 0, policy_version 760 (0.0021)
[2023-02-22 17:03:10,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4027.8, 300 sec: 4012.7). Total num frames: 3117056. Throughput: 0: 1041.5. Samples: 778074. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:03:10,846][07386] Avg episode reward: [(0, '22.308')]
[2023-02-22 17:03:15,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4096.4, 300 sec: 4012.7). Total num frames: 3133440. Throughput: 0: 985.9. Samples: 783104. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:03:15,844][07386] Avg episode reward: [(0, '22.994')]
[2023-02-22 17:03:20,598][12878] Updated weights for policy 0, policy_version 770 (0.0027)
[2023-02-22 17:03:20,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4040.5). Total num frames: 3153920. Throughput: 0: 1004.1. Samples: 788590. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:03:20,843][07386] Avg episode reward: [(0, '22.570')]
[2023-02-22 17:03:25,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 4054.3). Total num frames: 3178496. Throughput: 0: 1034.4. Samples: 792272. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 17:03:25,846][07386] Avg episode reward: [(0, '22.107')]
[2023-02-22 17:03:25,859][12864] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000776_3178496.pth...
[2023-02-22 17:03:25,968][12864] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000537_2199552.pth
[2023-02-22 17:03:28,894][12878] Updated weights for policy 0, policy_version 780 (0.0013)
[2023-02-22 17:03:30,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4096.1, 300 sec: 4068.3). Total num frames: 3198976. Throughput: 0: 1032.5. Samples: 799434. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 17:03:30,843][07386] Avg episode reward: [(0, '22.099')]
[2023-02-22 17:03:35,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4082.1). Total num frames: 3215360. Throughput: 0: 987.5. Samples: 804194. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:03:35,845][07386] Avg episode reward: [(0, '22.017')]
[2023-02-22 17:03:40,805][12878] Updated weights for policy 0, policy_version 790 (0.0023)
[2023-02-22 17:03:40,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4068.2). Total num frames: 3235840. Throughput: 0: 989.7. Samples: 806596. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:03:40,843][07386] Avg episode reward: [(0, '22.757')]
[2023-02-22 17:03:45,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 4068.2). Total num frames: 3260416. Throughput: 0: 1048.4. Samples: 813982. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:03:45,848][07386] Avg episode reward: [(0, '24.025')]
[2023-02-22 17:03:49,160][12878] Updated weights for policy 0, policy_version 800 (0.0018)
[2023-02-22 17:03:50,840][07386] Fps is (10 sec: 4505.4, 60 sec: 4096.0, 300 sec: 4082.1). Total num frames: 3280896. Throughput: 0: 1033.2. Samples: 820820. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:03:50,845][07386] Avg episode reward: [(0, '24.079')]
[2023-02-22 17:03:55,843][07386] Fps is (10 sec: 3685.2, 60 sec: 4095.8, 300 sec: 4082.1). Total num frames: 3297280. Throughput: 0: 1001.0. Samples: 823122. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 17:03:55,846][07386] Avg episode reward: [(0, '24.267')]
[2023-02-22 17:04:00,653][12878] Updated weights for policy 0, policy_version 810 (0.0011)
[2023-02-22 17:04:00,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4068.2). Total num frames: 3317760. Throughput: 0: 1004.5. Samples: 828308. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:04:00,848][07386] Avg episode reward: [(0, '23.784')]
[2023-02-22 17:04:05,840][07386] Fps is (10 sec: 4507.0, 60 sec: 4096.0, 300 sec: 4068.2). Total num frames: 3342336. Throughput: 0: 1045.4. Samples: 835632. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 17:04:05,843][07386] Avg episode reward: [(0, '23.906')]
[2023-02-22 17:04:09,015][12878] Updated weights for policy 0, policy_version 820 (0.0012)
[2023-02-22 17:04:10,840][07386] Fps is (10 sec: 4505.7, 60 sec: 4096.0, 300 sec: 4082.1). Total num frames: 3362816. Throughput: 0: 1047.1. Samples: 839390. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 17:04:10,846][07386] Avg episode reward: [(0, '22.805')]
[2023-02-22 17:04:15,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4082.1). Total num frames: 3379200. Throughput: 0: 993.7. Samples: 844150. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:04:15,843][07386] Avg episode reward: [(0, '23.461')]
[2023-02-22 17:04:20,840][07386] Fps is (10 sec: 3276.8, 60 sec: 4027.7, 300 sec: 4054.3). Total num frames: 3395584. Throughput: 0: 1012.8. Samples: 849772. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:04:20,847][07386] Avg episode reward: [(0, '22.688')]
[2023-02-22 17:04:20,914][12878] Updated weights for policy 0, policy_version 830 (0.0026)
[2023-02-22 17:04:25,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 4054.3). Total num frames: 3420160. Throughput: 0: 1042.9. Samples: 853526. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:04:25,843][07386] Avg episode reward: [(0, '23.105')]
[2023-02-22 17:04:29,579][12878] Updated weights for policy 0, policy_version 840 (0.0012)
[2023-02-22 17:04:30,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 4068.3). Total num frames: 3440640. Throughput: 0: 1033.0. Samples: 860468. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:04:30,842][07386] Avg episode reward: [(0, '22.752')]
[2023-02-22 17:04:35,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4082.1). Total num frames: 3457024. Throughput: 0: 982.1. Samples: 865016. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 17:04:35,843][07386] Avg episode reward: [(0, '23.395')]
[2023-02-22 17:04:40,840][07386] Fps is (10 sec: 3686.3, 60 sec: 4027.7, 300 sec: 4054.3). Total num frames: 3477504. Throughput: 0: 987.8. Samples: 867570. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:04:40,843][07386] Avg episode reward: [(0, '22.951')]
[2023-02-22 17:04:41,030][12878] Updated weights for policy 0, policy_version 850 (0.0015)
[2023-02-22 17:04:45,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 4054.3). Total num frames: 3502080. Throughput: 0: 1039.6. Samples: 875088. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:04:45,849][07386] Avg episode reward: [(0, '24.161')]
[2023-02-22 17:04:50,133][12878] Updated weights for policy 0, policy_version 860 (0.0012)
[2023-02-22 17:04:50,840][07386] Fps is (10 sec: 4505.7, 60 sec: 4027.8, 300 sec: 4068.2). Total num frames: 3522560. Throughput: 0: 1019.1. Samples: 881490. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
[2023-02-22 17:04:50,845][07386] Avg episode reward: [(0, '24.982')]
[2023-02-22 17:04:55,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4027.9, 300 sec: 4068.2). Total num frames: 3538944. Throughput: 0: 987.0. Samples: 883804. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:04:55,848][07386] Avg episode reward: [(0, '25.526')]
[2023-02-22 17:05:00,840][07386] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 4040.5). Total num frames: 3555328. Throughput: 0: 989.9. Samples: 888694. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:05:00,845][07386] Avg episode reward: [(0, '26.304')]
[2023-02-22 17:05:00,847][12864] Saving new best policy, reward=26.304!
[2023-02-22 17:05:03,100][12878] Updated weights for policy 0, policy_version 870 (0.0016)
[2023-02-22 17:05:05,840][07386] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3998.9). Total num frames: 3567616. Throughput: 0: 966.9. Samples: 893284. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:05:05,843][07386] Avg episode reward: [(0, '26.666')]
[2023-02-22 17:05:05,862][12864] Saving new best policy, reward=26.666!
[2023-02-22 17:05:10,840][07386] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 4012.7). Total num frames: 3584000. Throughput: 0: 936.6. Samples: 895674. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:05:10,846][07386] Avg episode reward: [(0, '26.628')]
[2023-02-22 17:05:15,843][07386] Fps is (10 sec: 3275.7, 60 sec: 3686.2, 300 sec: 4012.6). Total num frames: 3600384. Throughput: 0: 887.0. Samples: 900384. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 17:05:15,847][07386] Avg episode reward: [(0, '26.462')]
[2023-02-22 17:05:16,111][12878] Updated weights for policy 0, policy_version 880 (0.0033)
[2023-02-22 17:05:20,840][07386] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3998.8). Total num frames: 3624960. Throughput: 0: 924.5. Samples: 906620. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 17:05:20,842][07386] Avg episode reward: [(0, '25.454')]
[2023-02-22 17:05:24,632][12878] Updated weights for policy 0, policy_version 890 (0.0014)
[2023-02-22 17:05:25,840][07386] Fps is (10 sec: 4916.8, 60 sec: 3822.9, 300 sec: 3998.9). Total num frames: 3649536. Throughput: 0: 950.4. Samples: 910340. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:05:25,848][07386] Avg episode reward: [(0, '26.093')]
[2023-02-22 17:05:25,859][12864] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000891_3649536.pth...
[2023-02-22 17:05:25,978][12864] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000657_2691072.pth
[2023-02-22 17:05:30,840][07386] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 4012.7). Total num frames: 3665920. Throughput: 0: 927.1. Samples: 916808. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:05:30,845][07386] Avg episode reward: [(0, '23.813')]
[2023-02-22 17:05:35,840][07386] Fps is (10 sec: 3276.7, 60 sec: 3754.6, 300 sec: 4012.7). Total num frames: 3682304. Throughput: 0: 888.0. Samples: 921450. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:05:35,855][07386] Avg episode reward: [(0, '24.235')]
[2023-02-22 17:05:36,300][12878] Updated weights for policy 0, policy_version 900 (0.0015)
[2023-02-22 17:05:40,840][07386] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 4012.7). Total num frames: 3706880. Throughput: 0: 902.4. Samples: 924412. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:05:40,842][07386] Avg episode reward: [(0, '23.987')]
[2023-02-22 17:05:44,753][12878] Updated weights for policy 0, policy_version 910 (0.0013)
[2023-02-22 17:05:45,840][07386] Fps is (10 sec: 4915.4, 60 sec: 3822.9, 300 sec: 4012.7). Total num frames: 3731456. Throughput: 0: 961.1. Samples: 931942. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:05:45,843][07386] Avg episode reward: [(0, '24.496')]
[2023-02-22 17:05:50,841][07386] Fps is (10 sec: 4095.6, 60 sec: 3754.6, 300 sec: 4012.7). Total num frames: 3747840. Throughput: 0: 991.2. Samples: 937888. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
[2023-02-22 17:05:50,847][07386] Avg episode reward: [(0, '24.538')]
[2023-02-22 17:05:55,840][07386] Fps is (10 sec: 3276.6, 60 sec: 3754.6, 300 sec: 4012.7). Total num frames: 3764224. Throughput: 0: 990.5. Samples: 940246. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:05:55,847][07386] Avg episode reward: [(0, '23.812')]
[2023-02-22 17:05:56,231][12878] Updated weights for policy 0, policy_version 920 (0.0011)
[2023-02-22 17:06:00,840][07386] Fps is (10 sec: 4096.4, 60 sec: 3891.2, 300 sec: 3998.8). Total num frames: 3788800. Throughput: 0: 1017.3. Samples: 946158. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:06:00,848][07386] Avg episode reward: [(0, '23.573')]
[2023-02-22 17:06:04,628][12878] Updated weights for policy 0, policy_version 930 (0.0023)
[2023-02-22 17:06:05,840][07386] Fps is (10 sec: 4915.4, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 3813376. Throughput: 0: 1046.4. Samples: 953708. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:06:05,842][07386] Avg episode reward: [(0, '23.891')]
[2023-02-22 17:06:10,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 3829760. Throughput: 0: 1032.1. Samples: 956786. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:06:10,844][07386] Avg episode reward: [(0, '24.242')]
[2023-02-22 17:06:15,840][07386] Fps is (10 sec: 3276.7, 60 sec: 4096.2, 300 sec: 4012.7). Total num frames: 3846144. Throughput: 0: 990.0. Samples: 961356. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:06:15,843][07386] Avg episode reward: [(0, '23.623')]
[2023-02-22 17:06:16,555][12878] Updated weights for policy 0, policy_version 940 (0.0027)
[2023-02-22 17:06:20,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 3870720. Throughput: 0: 1028.6. Samples: 967736. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:06:20,842][07386] Avg episode reward: [(0, '24.183')]
[2023-02-22 17:06:24,752][12878] Updated weights for policy 0, policy_version 950 (0.0020)
[2023-02-22 17:06:25,840][07386] Fps is (10 sec: 4915.3, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 3895296. Throughput: 0: 1045.7. Samples: 971468. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:06:25,842][07386] Avg episode reward: [(0, '24.441')]
[2023-02-22 17:06:30,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 3911680. Throughput: 0: 1017.2. Samples: 977718. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:06:30,845][07386] Avg episode reward: [(0, '24.529')]
[2023-02-22 17:06:35,841][07386] Fps is (10 sec: 3276.3, 60 sec: 4095.9, 300 sec: 4012.7). Total num frames: 3928064. Throughput: 0: 991.1. Samples: 982486. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:06:35,848][07386] Avg episode reward: [(0, '24.976')]
[2023-02-22 17:06:36,730][12878] Updated weights for policy 0, policy_version 960 (0.0012)
[2023-02-22 17:06:40,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 3952640. Throughput: 0: 1010.2. Samples: 985704. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:06:40,843][07386] Avg episode reward: [(0, '23.367')]
[2023-02-22 17:06:44,843][12878] Updated weights for policy 0, policy_version 970 (0.0018)
[2023-02-22 17:06:45,840][07386] Fps is (10 sec: 4915.8, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 3977216. Throughput: 0: 1045.3. Samples: 993198. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 17:06:45,843][07386] Avg episode reward: [(0, '23.114')]
[2023-02-22 17:06:50,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4096.1, 300 sec: 4026.6). Total num frames: 3993600. Throughput: 0: 1007.1. Samples: 999028. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:06:50,846][07386] Avg episode reward: [(0, '23.773')]
[2023-02-22 17:06:55,840][07386] Fps is (10 sec: 3276.8, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 4009984. Throughput: 0: 990.5. Samples: 1001360. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:06:55,844][07386] Avg episode reward: [(0, '24.821')]
[2023-02-22 17:06:56,609][12878] Updated weights for policy 0, policy_version 980 (0.0016)
[2023-02-22 17:07:00,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 4034560. Throughput: 0: 1023.0. Samples: 1007392. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:07:00,848][07386] Avg episode reward: [(0, '24.667')]
[2023-02-22 17:07:04,887][12878] Updated weights for policy 0, policy_version 990 (0.0014)
[2023-02-22 17:07:05,840][07386] Fps is (10 sec: 4915.2, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 4059136. Throughput: 0: 1048.3. Samples: 1014908. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:07:05,843][07386] Avg episode reward: [(0, '25.587')]
[2023-02-22 17:07:10,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4026.7). Total num frames: 4075520. Throughput: 0: 1025.3. Samples: 1017608. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 17:07:10,845][07386] Avg episode reward: [(0, '25.866')]
[2023-02-22 17:07:15,840][07386] Fps is (10 sec: 3276.8, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 4091904. Throughput: 0: 990.7. Samples: 1022300. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-22 17:07:15,846][07386] Avg episode reward: [(0, '26.649')]
[2023-02-22 17:07:16,584][12878] Updated weights for policy 0, policy_version 1000 (0.0016)
[2023-02-22 17:07:20,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 4116480. Throughput: 0: 1036.4. Samples: 1029122. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-22 17:07:20,842][07386] Avg episode reward: [(0, '28.292')]
[2023-02-22 17:07:20,849][12864] Saving new best policy, reward=28.292!
[2023-02-22 17:07:24,831][12878] Updated weights for policy 0, policy_version 1010 (0.0015)
[2023-02-22 17:07:25,843][07386] Fps is (10 sec: 4913.7, 60 sec: 4095.8, 300 sec: 4026.6). Total num frames: 4141056. Throughput: 0: 1046.0. Samples: 1032778. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:07:25,850][07386] Avg episode reward: [(0, '28.587')]
[2023-02-22 17:07:25,869][12864] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001011_4141056.pth...
[2023-02-22 17:07:26,067][12864] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000776_3178496.pth
[2023-02-22 17:07:26,085][12864] Saving new best policy, reward=28.587!
[2023-02-22 17:07:30,845][07386] Fps is (10 sec: 3684.4, 60 sec: 4027.4, 300 sec: 4012.6). Total num frames: 4153344. Throughput: 0: 1007.9. Samples: 1038558. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:07:30,848][07386] Avg episode reward: [(0, '28.868')]
[2023-02-22 17:07:30,851][12864] Saving new best policy, reward=28.868!
[2023-02-22 17:07:35,840][07386] Fps is (10 sec: 2868.1, 60 sec: 4027.8, 300 sec: 3998.8). Total num frames: 4169728. Throughput: 0: 982.0. Samples: 1043216. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:07:35,849][07386] Avg episode reward: [(0, '29.040')]
[2023-02-22 17:07:35,863][12864] Saving new best policy, reward=29.040!
[2023-02-22 17:07:37,015][12878] Updated weights for policy 0, policy_version 1020 (0.0015)
[2023-02-22 17:07:40,840][07386] Fps is (10 sec: 4098.2, 60 sec: 4027.7, 300 sec: 3998.8). Total num frames: 4194304. Throughput: 0: 1008.8. Samples: 1046758. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:07:40,843][07386] Avg episode reward: [(0, '28.733')]
[2023-02-22 17:07:45,169][12878] Updated weights for policy 0, policy_version 1030 (0.0012)
[2023-02-22 17:07:45,840][07386] Fps is (10 sec: 4915.2, 60 sec: 4027.7, 300 sec: 4012.7). Total num frames: 4218880. Throughput: 0: 1041.7. Samples: 1054268. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:07:45,847][07386] Avg episode reward: [(0, '27.603')]
[2023-02-22 17:07:50,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 4012.7). Total num frames: 4235264. Throughput: 0: 992.6. Samples: 1059574. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:07:50,844][07386] Avg episode reward: [(0, '26.248')]
[2023-02-22 17:07:55,847][07386] Fps is (10 sec: 3274.6, 60 sec: 4027.3, 300 sec: 3998.7). Total num frames: 4251648. Throughput: 0: 985.9. Samples: 1061978. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:07:55,853][07386] Avg episode reward: [(0, '25.470')]
[2023-02-22 17:07:56,781][12878] Updated weights for policy 0, policy_version 1040 (0.0016)
[2023-02-22 17:08:00,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3998.8). Total num frames: 4276224. Throughput: 0: 1028.9. Samples: 1068600. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:08:00,842][07386] Avg episode reward: [(0, '25.348')]
[2023-02-22 17:08:05,170][12878] Updated weights for policy 0, policy_version 1050 (0.0025)
[2023-02-22 17:08:05,840][07386] Fps is (10 sec: 4918.5, 60 sec: 4027.7, 300 sec: 4012.7). Total num frames: 4300800. Throughput: 0: 1042.4. Samples: 1076028. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:08:05,846][07386] Avg episode reward: [(0, '24.651')]
[2023-02-22 17:08:10,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 4012.7). Total num frames: 4317184. Throughput: 0: 1013.1. Samples: 1078366. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:08:10,846][07386] Avg episode reward: [(0, '24.665')]
[2023-02-22 17:08:15,840][07386] Fps is (10 sec: 3276.8, 60 sec: 4027.7, 300 sec: 3998.8). Total num frames: 4333568. Throughput: 0: 989.1. Samples: 1083060. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-22 17:08:15,850][07386] Avg episode reward: [(0, '24.008')]
[2023-02-22 17:08:16,911][12878] Updated weights for policy 0, policy_version 1060 (0.0021)
[2023-02-22 17:08:20,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3998.8). Total num frames: 4358144. Throughput: 0: 1042.0. Samples: 1090108. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 17:08:20,845][07386] Avg episode reward: [(0, '25.613')]
[2023-02-22 17:08:25,170][12878] Updated weights for policy 0, policy_version 1070 (0.0018)
[2023-02-22 17:08:25,844][07386] Fps is (10 sec: 4913.2, 60 sec: 4027.7, 300 sec: 4012.6). Total num frames: 4382720. Throughput: 0: 1044.7. Samples: 1093774. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:08:25,847][07386] Avg episode reward: [(0, '27.372')]
[2023-02-22 17:08:30,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4096.4, 300 sec: 4012.7). Total num frames: 4399104. Throughput: 0: 1000.8. Samples: 1099304. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-22 17:08:30,845][07386] Avg episode reward: [(0, '26.831')]
[2023-02-22 17:08:35,840][07386] Fps is (10 sec: 3278.1, 60 sec: 4096.0, 300 sec: 3998.8). Total num frames: 4415488. Throughput: 0: 991.8. Samples: 1104204. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 17:08:35,848][07386] Avg episode reward: [(0, '28.187')]
[2023-02-22 17:08:37,015][12878] Updated weights for policy 0, policy_version 1080 (0.0020)
[2023-02-22 17:08:40,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 3998.8). Total num frames: 4440064. Throughput: 0: 1021.1. Samples: 1107922. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 17:08:40,843][07386] Avg episode reward: [(0, '27.709')]
[2023-02-22 17:08:45,203][12878] Updated weights for policy 0, policy_version 1090 (0.0015)
[2023-02-22 17:08:45,840][07386] Fps is (10 sec: 4915.2, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 4464640. Throughput: 0: 1042.8. Samples: 1115524. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:08:45,846][07386] Avg episode reward: [(0, '27.911')]
[2023-02-22 17:08:50,841][07386] Fps is (10 sec: 4095.5, 60 sec: 4095.9, 300 sec: 4012.7). Total num frames: 4481024. Throughput: 0: 991.7. Samples: 1120654. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 17:08:50,843][07386] Avg episode reward: [(0, '26.787')]
[2023-02-22 17:08:55,840][07386] Fps is (10 sec: 3276.8, 60 sec: 4096.5, 300 sec: 3998.8). Total num frames: 4497408. Throughput: 0: 992.7. Samples: 1123036. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:08:55,843][07386] Avg episode reward: [(0, '28.062')]
[2023-02-22 17:08:56,890][12878] Updated weights for policy 0, policy_version 1100 (0.0015)
[2023-02-22 17:09:00,840][07386] Fps is (10 sec: 4096.5, 60 sec: 4096.0, 300 sec: 3998.8). Total num frames: 4521984. Throughput: 0: 1037.5. Samples: 1129746. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:09:00,847][07386] Avg episode reward: [(0, '26.396')]
[2023-02-22 17:09:05,431][12878] Updated weights for policy 0, policy_version 1110 (0.0013)
[2023-02-22 17:09:05,840][07386] Fps is (10 sec: 4915.2, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 4546560. Throughput: 0: 1044.2. Samples: 1137096. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:09:05,847][07386] Avg episode reward: [(0, '25.326')]
[2023-02-22 17:09:10,843][07386] Fps is (10 sec: 4094.6, 60 sec: 4095.8, 300 sec: 4012.6). Total num frames: 4562944. Throughput: 0: 1013.6. Samples: 1139384. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:09:10,846][07386] Avg episode reward: [(0, '24.814')]
[2023-02-22 17:09:15,840][07386] Fps is (10 sec: 3276.8, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 4579328. Throughput: 0: 996.8. Samples: 1144158. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:09:15,846][07386] Avg episode reward: [(0, '25.125')]
[2023-02-22 17:09:17,078][12878] Updated weights for policy 0, policy_version 1120 (0.0029)
[2023-02-22 17:09:20,840][07386] Fps is (10 sec: 4097.4, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 4603904. Throughput: 0: 1050.4. Samples: 1151472. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:09:20,842][07386] Avg episode reward: [(0, '23.933')]
[2023-02-22 17:09:25,667][12878] Updated weights for policy 0, policy_version 1130 (0.0012)
[2023-02-22 17:09:25,840][07386] Fps is (10 sec: 4915.2, 60 sec: 4096.3, 300 sec: 4026.6). Total num frames: 4628480. Throughput: 0: 1051.5. Samples: 1155238. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:09:25,849][07386] Avg episode reward: [(0, '24.100')]
[2023-02-22 17:09:25,869][12864] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001130_4628480.pth...
[2023-02-22 17:09:26,022][12864] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000891_3649536.pth
[2023-02-22 17:09:30,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4012.7). Total num frames: 4640768. Throughput: 0: 1000.9. Samples: 1160566. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:09:30,847][07386] Avg episode reward: [(0, '24.528')]
[2023-02-22 17:09:35,840][07386] Fps is (10 sec: 3276.8, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 4661248. Throughput: 0: 998.0. Samples: 1165564. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:09:35,843][07386] Avg episode reward: [(0, '24.617')]
[2023-02-22 17:09:37,266][12878] Updated weights for policy 0, policy_version 1140 (0.0018)
[2023-02-22 17:09:40,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 4685824. Throughput: 0: 1025.8. Samples: 1169196. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:09:40,843][07386] Avg episode reward: [(0, '24.753')]
[2023-02-22 17:09:45,844][07386] Fps is (10 sec: 4503.9, 60 sec: 4027.5, 300 sec: 4012.6). Total num frames: 4706304. Throughput: 0: 1041.3. Samples: 1176608. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:09:45,849][07386] Avg episode reward: [(0, '25.503')]
[2023-02-22 17:09:46,131][12878] Updated weights for policy 0, policy_version 1150 (0.0017)
[2023-02-22 17:09:50,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4027.8, 300 sec: 4012.7). Total num frames: 4722688. Throughput: 0: 985.5. Samples: 1181442. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:09:50,844][07386] Avg episode reward: [(0, '25.588')]
[2023-02-22 17:09:55,840][07386] Fps is (10 sec: 3687.8, 60 sec: 4096.0, 300 sec: 4026.6). Total num frames: 4743168. Throughput: 0: 987.4. Samples: 1183814. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:09:55,842][07386] Avg episode reward: [(0, '27.609')]
[2023-02-22 17:09:57,225][12878] Updated weights for policy 0, policy_version 1160 (0.0019)
[2023-02-22 17:10:00,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 4068.2). Total num frames: 4767744. Throughput: 0: 1039.4. Samples: 1190932. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 17:10:00,849][07386] Avg episode reward: [(0, '28.370')]
[2023-02-22 17:10:05,842][07386] Fps is (10 sec: 4504.8, 60 sec: 4027.6, 300 sec: 4082.1). Total num frames: 4788224. Throughput: 0: 1028.6. Samples: 1197762. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:10:05,844][07386] Avg episode reward: [(0, '30.213')]
[2023-02-22 17:10:05,855][12864] Saving new best policy, reward=30.213!
[2023-02-22 17:10:06,542][12878] Updated weights for policy 0, policy_version 1170 (0.0022)
[2023-02-22 17:10:10,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4028.0, 300 sec: 4082.2). Total num frames: 4804608. Throughput: 0: 996.0. Samples: 1200060. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:10:10,844][07386] Avg episode reward: [(0, '29.719')]
[2023-02-22 17:10:15,840][07386] Fps is (10 sec: 3687.1, 60 sec: 4096.0, 300 sec: 4068.2). Total num frames: 4825088. Throughput: 0: 986.5. Samples: 1204958. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:10:15,847][07386] Avg episode reward: [(0, '28.482')]
[2023-02-22 17:10:17,391][12878] Updated weights for policy 0, policy_version 1180 (0.0019)
[2023-02-22 17:10:20,840][07386] Fps is (10 sec: 4505.5, 60 sec: 4096.0, 300 sec: 4068.2). Total num frames: 4849664. Throughput: 0: 1043.1. Samples: 1212502. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:10:20,842][07386] Avg episode reward: [(0, '27.066')]
[2023-02-22 17:10:25,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 4082.1). Total num frames: 4870144. Throughput: 0: 1044.3. Samples: 1216188. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:10:25,843][07386] Avg episode reward: [(0, '24.855')]
[2023-02-22 17:10:26,702][12878] Updated weights for policy 0, policy_version 1190 (0.0027)
[2023-02-22 17:10:30,840][07386] Fps is (10 sec: 3686.5, 60 sec: 4096.0, 300 sec: 4082.1). Total num frames: 4886528. Throughput: 0: 990.9. Samples: 1221194. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:10:30,845][07386] Avg episode reward: [(0, '23.956')]
[2023-02-22 17:10:35,840][07386] Fps is (10 sec: 3276.8, 60 sec: 4027.7, 300 sec: 4054.3). Total num frames: 4902912. Throughput: 0: 1006.4. Samples: 1226732. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 17:10:35,842][07386] Avg episode reward: [(0, '24.626')]
[2023-02-22 17:10:37,486][12878] Updated weights for policy 0, policy_version 1200 (0.0022)
[2023-02-22 17:10:40,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 4068.2). Total num frames: 4931584. Throughput: 0: 1037.0. Samples: 1230480. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:10:40,846][07386] Avg episode reward: [(0, '24.854')]
[2023-02-22 17:10:45,840][07386] Fps is (10 sec: 4915.2, 60 sec: 4096.2, 300 sec: 4082.1). Total num frames: 4952064. Throughput: 0: 1039.0. Samples: 1237686. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:10:45,842][07386] Avg episode reward: [(0, '25.913')]
[2023-02-22 17:10:46,869][12878] Updated weights for policy 0, policy_version 1210 (0.0019)
[2023-02-22 17:10:50,840][07386] Fps is (10 sec: 3276.7, 60 sec: 4027.7, 300 sec: 4068.2). Total num frames: 4964352. Throughput: 0: 991.1. Samples: 1242362. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:10:50,843][07386] Avg episode reward: [(0, '27.733')]
[2023-02-22 17:10:55,840][07386] Fps is (10 sec: 3276.8, 60 sec: 4027.7, 300 sec: 4054.3). Total num frames: 4984832. Throughput: 0: 993.8. Samples: 1244782. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:10:55,843][07386] Avg episode reward: [(0, '26.671')]
[2023-02-22 17:10:57,505][12878] Updated weights for policy 0, policy_version 1220 (0.0033)
[2023-02-22 17:11:00,840][07386] Fps is (10 sec: 4505.7, 60 sec: 4027.7, 300 sec: 4054.3). Total num frames: 5009408. Throughput: 0: 1048.6. Samples: 1252144. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:11:00,845][07386] Avg episode reward: [(0, '25.829')]
[2023-02-22 17:11:05,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4027.9, 300 sec: 4068.2). Total num frames: 5029888. Throughput: 0: 1023.6. Samples: 1258564. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-22 17:11:05,846][07386] Avg episode reward: [(0, '24.789')]
[2023-02-22 17:11:07,383][12878] Updated weights for policy 0, policy_version 1230 (0.0019)
[2023-02-22 17:11:10,840][07386] Fps is (10 sec: 3686.3, 60 sec: 4027.7, 300 sec: 4068.2). Total num frames: 5046272. Throughput: 0: 996.0. Samples: 1261008. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:11:10,848][07386] Avg episode reward: [(0, '23.997')]
[2023-02-22 17:11:15,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4054.3). Total num frames: 5066752. Throughput: 0: 1002.7. Samples: 1266314. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:11:15,847][07386] Avg episode reward: [(0, '23.381')]
[2023-02-22 17:11:17,664][12878] Updated weights for policy 0, policy_version 1240 (0.0017)
[2023-02-22 17:11:20,840][07386] Fps is (10 sec: 4505.8, 60 sec: 4027.7, 300 sec: 4054.3). Total num frames: 5091328. Throughput: 0: 1047.5. Samples: 1273868. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:11:20,842][07386] Avg episode reward: [(0, '24.666')]
[2023-02-22 17:11:25,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 4068.2). Total num frames: 5111808. Throughput: 0: 1045.0. Samples: 1277504. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:11:25,842][07386] Avg episode reward: [(0, '25.363')]
[2023-02-22 17:11:25,861][12864] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001248_5111808.pth...
[2023-02-22 17:11:26,032][12864] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001011_4141056.pth
[2023-02-22 17:11:27,582][12878] Updated weights for policy 0, policy_version 1250 (0.0013)
[2023-02-22 17:11:30,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4068.2). Total num frames: 5128192. Throughput: 0: 986.1. Samples: 1282062. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:11:30,846][07386] Avg episode reward: [(0, '26.556')]
[2023-02-22 17:11:35,842][07386] Fps is (10 sec: 3276.8, 60 sec: 4027.7, 300 sec: 4040.5). Total num frames: 5144576. Throughput: 0: 996.0. Samples: 1287180. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:11:35,844][07386] Avg episode reward: [(0, '27.694')]
[2023-02-22 17:11:40,000][12878] Updated weights for policy 0, policy_version 1260 (0.0018)
[2023-02-22 17:11:40,841][07386] Fps is (10 sec: 3276.4, 60 sec: 3822.8, 300 sec: 4012.7). Total num frames: 5160960. Throughput: 0: 995.2. Samples: 1289568. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:11:40,847][07386] Avg episode reward: [(0, '28.204')]
[2023-02-22 17:11:45,840][07386] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 4012.7). Total num frames: 5177344. Throughput: 0: 934.8. Samples: 1294208. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:11:45,843][07386] Avg episode reward: [(0, '29.315')]
[2023-02-22 17:11:50,840][07386] Fps is (10 sec: 3277.2, 60 sec: 3823.0, 300 sec: 4012.7). Total num frames: 5193728. Throughput: 0: 898.1. Samples: 1298980. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:11:50,847][07386] Avg episode reward: [(0, '28.472')]
[2023-02-22 17:11:52,955][12878] Updated weights for policy 0, policy_version 1270 (0.0014)
[2023-02-22 17:11:55,840][07386] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3998.8). Total num frames: 5214208. Throughput: 0: 903.2. Samples: 1301652. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
[2023-02-22 17:11:55,849][07386] Avg episode reward: [(0, '27.605')]
[2023-02-22 17:12:00,840][07386] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3998.8). Total num frames: 5238784. Throughput: 0: 953.3. Samples: 1309214. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:12:00,843][07386] Avg episode reward: [(0, '28.584')]
[2023-02-22 17:12:00,946][12878] Updated weights for policy 0, policy_version 1280 (0.0014)
[2023-02-22 17:12:05,840][07386] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 4012.7). Total num frames: 5259264. Throughput: 0: 923.6. Samples: 1315428. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:12:05,847][07386] Avg episode reward: [(0, '26.839')]
[2023-02-22 17:12:10,844][07386] Fps is (10 sec: 3684.8, 60 sec: 3822.7, 300 sec: 4012.6). Total num frames: 5275648. Throughput: 0: 894.6. Samples: 1317764. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:12:10,849][07386] Avg episode reward: [(0, '25.866')]
[2023-02-22 17:12:12,766][12878] Updated weights for policy 0, policy_version 1290 (0.0031)
[2023-02-22 17:12:15,840][07386] Fps is (10 sec: 3686.3, 60 sec: 3822.9, 300 sec: 3998.8). Total num frames: 5296128. Throughput: 0: 919.9. Samples: 1323458. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 17:12:15,842][07386] Avg episode reward: [(0, '26.346')]
[2023-02-22 17:12:20,840][07386] Fps is (10 sec: 4507.5, 60 sec: 3822.9, 300 sec: 3998.8). Total num frames: 5320704. Throughput: 0: 971.1. Samples: 1330878. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:12:20,847][07386] Avg episode reward: [(0, '28.029')]
[2023-02-22 17:12:20,998][12878] Updated weights for policy 0, policy_version 1300 (0.0033)
[2023-02-22 17:12:25,840][07386] Fps is (10 sec: 4505.7, 60 sec: 3822.9, 300 sec: 4026.6). Total num frames: 5341184. Throughput: 0: 991.1. Samples: 1334164. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:12:25,848][07386] Avg episode reward: [(0, '26.823')]
[2023-02-22 17:12:30,842][07386] Fps is (10 sec: 3686.5, 60 sec: 3822.9, 300 sec: 4026.6). Total num frames: 5357568. Throughput: 0: 993.0. Samples: 1338892. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:12:30,844][07386] Avg episode reward: [(0, '27.663')]
[2023-02-22 17:12:32,871][12878] Updated weights for policy 0, policy_version 1310 (0.0021)
[2023-02-22 17:12:35,840][07386] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 4012.7). Total num frames: 5378048. Throughput: 0: 1024.2. Samples: 1345070. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:12:35,847][07386] Avg episode reward: [(0, '28.432')]
[2023-02-22 17:12:40,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4027.8, 300 sec: 4012.7). Total num frames: 5402624. Throughput: 0: 1048.5. Samples: 1348834. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:12:40,853][07386] Avg episode reward: [(0, '28.907')]
[2023-02-22 17:12:40,939][12878] Updated weights for policy 0, policy_version 1320 (0.0014)
[2023-02-22 17:12:45,841][07386] Fps is (10 sec: 4505.1, 60 sec: 4095.9, 300 sec: 4026.6). Total num frames: 5423104. Throughput: 0: 1026.1. Samples: 1355390. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:12:45,846][07386] Avg episode reward: [(0, '27.155')]
[2023-02-22 17:12:50,842][07386] Fps is (10 sec: 3685.6, 60 sec: 4095.8, 300 sec: 4026.6). Total num frames: 5439488. Throughput: 0: 993.6. Samples: 1360142. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:12:50,845][07386] Avg episode reward: [(0, '25.902')]
[2023-02-22 17:12:52,862][12878] Updated weights for policy 0, policy_version 1330 (0.0024)
[2023-02-22 17:12:55,840][07386] Fps is (10 sec: 3686.8, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 5459968. Throughput: 0: 1009.6. Samples: 1363190. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 17:12:55,843][07386] Avg episode reward: [(0, '27.284')]
[2023-02-22 17:13:00,840][07386] Fps is (10 sec: 4506.7, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 5484544. Throughput: 0: 1048.5. Samples: 1370640. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 17:13:00,842][07386] Avg episode reward: [(0, '27.949')]
[2023-02-22 17:13:01,096][12878] Updated weights for policy 0, policy_version 1340 (0.0015)
[2023-02-22 17:13:05,842][07386] Fps is (10 sec: 4504.6, 60 sec: 4095.8, 300 sec: 4026.5). Total num frames: 5505024. Throughput: 0: 1014.5. Samples: 1376534. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:13:05,845][07386] Avg episode reward: [(0, '26.498')]
[2023-02-22 17:13:10,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4096.3, 300 sec: 4026.6). Total num frames: 5521408. Throughput: 0: 992.2. Samples: 1378814. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-22 17:13:10,850][07386] Avg episode reward: [(0, '27.019')]
[2023-02-22 17:13:12,686][12878] Updated weights for policy 0, policy_version 1350 (0.0022)
[2023-02-22 17:13:15,840][07386] Fps is (10 sec: 3687.3, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 5541888. Throughput: 0: 1021.4. Samples: 1384854. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 17:13:15,843][07386] Avg episode reward: [(0, '27.391')]
[2023-02-22 17:13:20,838][12878] Updated weights for policy 0, policy_version 1360 (0.0014)
[2023-02-22 17:13:20,840][07386] Fps is (10 sec: 4915.2, 60 sec: 4164.3, 300 sec: 4026.6). Total num frames: 5570560. Throughput: 0: 1052.1. Samples: 1392414. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:13:20,843][07386] Avg episode reward: [(0, '27.031')]
[2023-02-22 17:13:25,840][07386] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 4026.6). Total num frames: 5586944. Throughput: 0: 1031.5. Samples: 1395250. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0)
[2023-02-22 17:13:25,844][07386] Avg episode reward: [(0, '29.552')]
[2023-02-22 17:13:25,863][12864] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001364_5586944.pth...
[2023-02-22 17:13:25,990][12864] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001130_4628480.pth
[2023-02-22 17:13:30,840][07386] Fps is (10 sec: 2867.2, 60 sec: 4027.7, 300 sec: 4012.7). Total num frames: 5599232. Throughput: 0: 989.5. Samples: 1399918. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0)
[2023-02-22 17:13:30,842][07386] Avg episode reward: [(0, '27.420')]
[2023-02-22 17:13:32,886][12878] Updated weights for policy 0, policy_version 1370 (0.0013)
[2023-02-22 17:13:35,840][07386] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 5623808. Throughput: 0: 1028.9. Samples: 1406438. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:13:35,847][07386] Avg episode reward: [(0, '28.616')]
[2023-02-22 17:13:40,840][07386] Fps is (10 sec: 4915.0, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 5648384. Throughput: 0: 1044.0. Samples: 1410172. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:13:40,844][07386] Avg episode reward: [(0, '28.372')]
[2023-02-22 17:13:41,088][12878] Updated weights for policy 0, policy_version 1380 (0.0016)
[2023-02-22 17:13:45,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4027.8, 300 sec: 4012.7). Total num frames: 5664768. Throughput: 0: 1013.4. Samples: 1416244. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:13:45,842][07386] Avg episode reward: [(0, '29.044')]
[2023-02-22 17:13:50,840][07386] Fps is (10 sec: 3276.9, 60 sec: 4027.9, 300 sec: 4012.7). Total num frames: 5681152. Throughput: 0: 985.7. Samples: 1420890. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0)
[2023-02-22 17:13:50,843][07386] Avg episode reward: [(0, '29.150')]
[2023-02-22 17:13:52,856][12878] Updated weights for policy 0, policy_version 1390 (0.0024)
[2023-02-22 17:13:55,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 5705728. Throughput: 0: 1011.1. Samples: 1424312. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 17:13:55,842][07386] Avg episode reward: [(0, '27.052')]
[2023-02-22 17:14:00,840][07386] Fps is (10 sec: 4915.2, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 5730304. Throughput: 0: 1043.5. Samples: 1431810. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 17:14:00,843][07386] Avg episode reward: [(0, '28.184')]
[2023-02-22 17:14:01,102][12878] Updated weights for policy 0, policy_version 1400 (0.0025)
[2023-02-22 17:14:05,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4027.9, 300 sec: 4012.7). Total num frames: 5746688. Throughput: 0: 996.1. Samples: 1437238. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:14:05,843][07386] Avg episode reward: [(0, '28.454')]
[2023-02-22 17:14:10,843][07386] Fps is (10 sec: 3275.9, 60 sec: 4027.6, 300 sec: 4012.7). Total num frames: 5763072. Throughput: 0: 986.4. Samples: 1439640. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-22 17:14:10,845][07386] Avg episode reward: [(0, '30.128')]
[2023-02-22 17:14:12,987][12878] Updated weights for policy 0, policy_version 1410 (0.0029)
[2023-02-22 17:14:15,840][07386] Fps is (10 sec: 4096.1, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 5787648. Throughput: 0: 1022.9. Samples: 1445950. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:14:15,846][07386] Avg episode reward: [(0, '29.032')]
[2023-02-22 17:14:20,840][07386] Fps is (10 sec: 4916.5, 60 sec: 4027.7, 300 sec: 4012.7). Total num frames: 5812224. Throughput: 0: 1046.4. Samples: 1453528. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:14:20,847][07386] Avg episode reward: [(0, '27.371')]
[2023-02-22 17:14:21,299][12878] Updated weights for policy 0, policy_version 1420 (0.0012)
[2023-02-22 17:14:25,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 4026.6). Total num frames: 5828608. Throughput: 0: 1023.7. Samples: 1456236. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:14:25,847][07386] Avg episode reward: [(0, '26.318')]
[2023-02-22 17:14:30,840][07386] Fps is (10 sec: 3276.6, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 5844992. Throughput: 0: 993.7. Samples: 1460962. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:14:30,844][07386] Avg episode reward: [(0, '25.583')]
[2023-02-22 17:14:33,002][12878] Updated weights for policy 0, policy_version 1430 (0.0020)
[2023-02-22 17:14:35,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 5869568. Throughput: 0: 1042.6. Samples: 1467806. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:14:35,843][07386] Avg episode reward: [(0, '23.630')]
[2023-02-22 17:14:40,840][07386] Fps is (10 sec: 4915.5, 60 sec: 4096.0, 300 sec: 4026.6). Total num frames: 5894144. Throughput: 0: 1049.7. Samples: 1471550. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:14:40,843][07386] Avg episode reward: [(0, '23.874')]
[2023-02-22 17:14:41,062][12878] Updated weights for policy 0, policy_version 1440 (0.0026)
[2023-02-22 17:14:45,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4026.6). Total num frames: 5910528. Throughput: 0: 1018.5. Samples: 1477642. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:14:45,846][07386] Avg episode reward: [(0, '25.414')]
[2023-02-22 17:14:50,840][07386] Fps is (10 sec: 3276.7, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 5926912. Throughput: 0: 1004.1. Samples: 1482422. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:14:50,850][07386] Avg episode reward: [(0, '26.337')]
[2023-02-22 17:14:52,899][12878] Updated weights for policy 0, policy_version 1450 (0.0026)
[2023-02-22 17:14:55,840][07386] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4012.7). Total num frames: 5951488. Throughput: 0: 1029.7. Samples: 1485976. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:14:55,843][07386] Avg episode reward: [(0, '26.081')]
[2023-02-22 17:15:00,840][07386] Fps is (10 sec: 4915.4, 60 sec: 4096.0, 300 sec: 4026.6). Total num frames: 5976064. Throughput: 0: 1054.6. Samples: 1493406. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 17:15:00,847][07386] Avg episode reward: [(0, '25.418')]
[2023-02-22 17:15:01,018][12878] Updated weights for policy 0, policy_version 1460 (0.0018)
[2023-02-22 17:15:05,841][07386] Fps is (10 sec: 4095.5, 60 sec: 4095.9, 300 sec: 4026.6). Total num frames: 5992448. Throughput: 0: 1003.9. Samples: 1498706. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 17:15:05,848][07386] Avg episode reward: [(0, '26.362')]
[2023-02-22 17:15:09,135][12864] Stopping Batcher_0...
[2023-02-22 17:15:09,136][12864] Loop batcher_evt_loop terminating...
[2023-02-22 17:15:09,137][07386] Component Batcher_0 stopped!
[2023-02-22 17:15:09,146][12864] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001466_6004736.pth...
[2023-02-22 17:15:09,212][07386] Component RolloutWorker_w5 stopped!
[2023-02-22 17:15:09,222][12888] Stopping RolloutWorker_w5...
[2023-02-22 17:15:09,222][12888] Loop rollout_proc5_evt_loop terminating...
[2023-02-22 17:15:09,230][07386] Component RolloutWorker_w3 stopped!
[2023-02-22 17:15:09,236][12882] Stopping RolloutWorker_w3...
[2023-02-22 17:15:09,237][12882] Loop rollout_proc3_evt_loop terminating...
[2023-02-22 17:15:09,243][07386] Component RolloutWorker_w1 stopped!
[2023-02-22 17:15:09,248][12880] Stopping RolloutWorker_w1...
[2023-02-22 17:15:09,249][12880] Loop rollout_proc1_evt_loop terminating...
[2023-02-22 17:15:09,267][07386] Component RolloutWorker_w7 stopped!
[2023-02-22 17:15:09,272][12890] Stopping RolloutWorker_w7...
[2023-02-22 17:15:09,273][12890] Loop rollout_proc7_evt_loop terminating...
[2023-02-22 17:15:09,274][12878] Weights refcount: 2 0
[2023-02-22 17:15:09,286][07386] Component InferenceWorker_p0-w0 stopped!
[2023-02-22 17:15:09,290][12878] Stopping InferenceWorker_p0-w0...
[2023-02-22 17:15:09,291][12878] Loop inference_proc0-0_evt_loop terminating...
[2023-02-22 17:15:09,304][07386] Component RolloutWorker_w0 stopped!
[2023-02-22 17:15:09,326][07386] Component RolloutWorker_w2 stopped!
[2023-02-22 17:15:09,338][07386] Component RolloutWorker_w6 stopped!
[2023-02-22 17:15:09,344][12889] Stopping RolloutWorker_w6...
[2023-02-22 17:15:09,344][12889] Loop rollout_proc6_evt_loop terminating...
[2023-02-22 17:15:09,331][12881] Stopping RolloutWorker_w2...
[2023-02-22 17:15:09,347][12881] Loop rollout_proc2_evt_loop terminating...
[2023-02-22 17:15:09,304][12879] Stopping RolloutWorker_w0...
[2023-02-22 17:15:09,360][12879] Loop rollout_proc0_evt_loop terminating...
[2023-02-22 17:15:09,377][12864] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001248_5111808.pth
[2023-02-22 17:15:09,381][07386] Component RolloutWorker_w4 stopped!
[2023-02-22 17:15:09,390][12883] Stopping RolloutWorker_w4...
[2023-02-22 17:15:09,390][12883] Loop rollout_proc4_evt_loop terminating...
[2023-02-22 17:15:09,394][12864] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001466_6004736.pth...
[2023-02-22 17:15:09,710][07386] Component LearnerWorker_p0 stopped!
[2023-02-22 17:15:09,717][07386] Waiting for process learner_proc0 to stop...
[2023-02-22 17:15:09,719][12864] Stopping LearnerWorker_p0...
[2023-02-22 17:15:09,720][12864] Loop learner_proc0_evt_loop terminating...
[2023-02-22 17:15:11,621][07386] Waiting for process inference_proc0-0 to join...
[2023-02-22 17:15:12,058][07386] Waiting for process rollout_proc0 to join...
[2023-02-22 17:15:12,396][07386] Waiting for process rollout_proc1 to join...
[2023-02-22 17:15:12,401][07386] Waiting for process rollout_proc2 to join...
[2023-02-22 17:15:12,412][07386] Waiting for process rollout_proc3 to join...
[2023-02-22 17:15:12,414][07386] Waiting for process rollout_proc4 to join...
[2023-02-22 17:15:12,415][07386] Waiting for process rollout_proc5 to join...
[2023-02-22 17:15:12,417][07386] Waiting for process rollout_proc6 to join...
[2023-02-22 17:15:12,418][07386] Waiting for process rollout_proc7 to join...
[2023-02-22 17:15:12,420][07386] Batcher 0 profile tree view:
batching: 37.2901, releasing_batches: 0.0301
[2023-02-22 17:15:12,422][07386] InferenceWorker_p0-w0 profile tree view:
wait_policy: 0.0001
  wait_policy_total: 719.9142
update_model: 10.9808
  weight_update: 0.0015
one_step: 0.0260
  handle_policy_step: 723.6435
    deserialize: 21.1943, stack: 4.1596, obs_to_device_normalize: 164.2121, forward: 340.8552, send_messages: 38.1306
    prepare_outputs: 119.1084
      to_cpu: 75.9447
[2023-02-22 17:15:12,424][07386] Learner 0 profile tree view:
misc: 0.0083, prepare_batch: 22.0176
train: 111.7807
  epoch_init: 0.0108, minibatch_init: 0.0132, losses_postprocess: 0.9444, kl_divergence: 0.8800, after_optimizer: 49.0509
  calculate_losses: 39.5985
    losses_init: 0.0080, forward_head: 2.4882, bptt_initial: 26.3166, tail: 1.5593, advantages_returns: 0.4524, losses: 5.0774
    bptt: 3.2699
      bptt_forward_core: 3.1167
  update: 20.5213
    clip: 2.0635
[2023-02-22 17:15:12,426][07386] RolloutWorker_w0 profile tree view:
wait_for_trajectories: 0.5839, enqueue_policy_requests: 183.6712, env_step: 1151.8172, overhead: 26.4968, complete_rollouts: 9.8421
save_policy_outputs: 27.7910
  split_output_tensors: 13.3480
[2023-02-22 17:15:12,428][07386] RolloutWorker_w7 profile tree view:
wait_for_trajectories: 0.4598, enqueue_policy_requests: 176.9846, env_step: 1157.5401, overhead: 27.2702, complete_rollouts: 10.1002
save_policy_outputs: 28.0747
  split_output_tensors: 13.8348
[2023-02-22 17:15:12,431][07386] Loop Runner_EvtLoop terminating...
[2023-02-22 17:15:12,433][07386] Runner profile tree view:
main_loop: 1541.0943
[2023-02-22 17:15:12,435][07386] Collected {0: 6004736}, FPS: 3896.4
[2023-02-22 17:15:12,589][07386] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
[2023-02-22 17:15:12,593][07386] Overriding arg 'num_workers' with value 1 passed from command line
[2023-02-22 17:15:12,595][07386] Adding new argument 'no_render'=True that is not in the saved config file!
[2023-02-22 17:15:12,600][07386] Adding new argument 'save_video'=True that is not in the saved config file!
[2023-02-22 17:15:12,603][07386] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2023-02-22 17:15:12,606][07386] Adding new argument 'video_name'=None that is not in the saved config file!
[2023-02-22 17:15:12,609][07386] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
[2023-02-22 17:15:12,612][07386] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2023-02-22 17:15:12,615][07386] Adding new argument 'push_to_hub'=False that is not in the saved config file!
[2023-02-22 17:15:12,617][07386] Adding new argument 'hf_repository'=None that is not in the saved config file!
[2023-02-22 17:15:12,622][07386] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2023-02-22 17:15:12,624][07386] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2023-02-22 17:15:12,627][07386] Adding new argument 'train_script'=None that is not in the saved config file!
[2023-02-22 17:15:12,630][07386] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2023-02-22 17:15:12,633][07386] Using frameskip 1 and render_action_repeat=4 for evaluation
[2023-02-22 17:15:12,651][07386] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-22 17:15:12,653][07386] RunningMeanStd input shape: (3, 72, 128)
[2023-02-22 17:15:12,655][07386] RunningMeanStd input shape: (1,)
[2023-02-22 17:15:12,672][07386] ConvEncoder: input_channels=3
[2023-02-22 17:15:13,371][07386] Conv encoder output size: 512
[2023-02-22 17:15:13,373][07386] Policy head output size: 512
[2023-02-22 17:15:15,749][07386] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001466_6004736.pth...
[2023-02-22 17:15:17,047][07386] Num frames 100...
[2023-02-22 17:15:17,160][07386] Num frames 200...
[2023-02-22 17:15:17,270][07386] Num frames 300...
[2023-02-22 17:15:17,387][07386] Num frames 400...
[2023-02-22 17:15:17,498][07386] Num frames 500...
[2023-02-22 17:15:17,613][07386] Num frames 600...
[2023-02-22 17:15:17,723][07386] Num frames 700...
[2023-02-22 17:15:17,857][07386] Avg episode rewards: #0: 14.680, true rewards: #0: 7.680
[2023-02-22 17:15:17,859][07386] Avg episode reward: 14.680, avg true_objective: 7.680
[2023-02-22 17:15:17,897][07386] Num frames 800...
[2023-02-22 17:15:18,013][07386] Num frames 900...
[2023-02-22 17:15:18,120][07386] Num frames 1000...
[2023-02-22 17:15:18,240][07386] Num frames 1100...
[2023-02-22 17:15:18,350][07386] Num frames 1200...
[2023-02-22 17:15:18,460][07386] Num frames 1300...
[2023-02-22 17:15:18,578][07386] Num frames 1400...
[2023-02-22 17:15:18,701][07386] Num frames 1500...
[2023-02-22 17:15:18,809][07386] Num frames 1600...
[2023-02-22 17:15:18,919][07386] Num frames 1700...
[2023-02-22 17:15:19,028][07386] Num frames 1800...
[2023-02-22 17:15:19,149][07386] Num frames 1900...
[2023-02-22 17:15:19,259][07386] Num frames 2000...
[2023-02-22 17:15:19,371][07386] Num frames 2100...
[2023-02-22 17:15:19,491][07386] Avg episode rewards: #0: 25.295, true rewards: #0: 10.795
[2023-02-22 17:15:19,492][07386] Avg episode reward: 25.295, avg true_objective: 10.795
[2023-02-22 17:15:19,541][07386] Num frames 2200...
[2023-02-22 17:15:19,656][07386] Num frames 2300...
[2023-02-22 17:15:19,767][07386] Num frames 2400...
[2023-02-22 17:15:19,883][07386] Num frames 2500...
[2023-02-22 17:15:19,995][07386] Num frames 2600...
[2023-02-22 17:15:20,111][07386] Num frames 2700...
[2023-02-22 17:15:20,223][07386] Num frames 2800...
[2023-02-22 17:15:20,334][07386] Num frames 2900...
[2023-02-22 17:15:20,455][07386] Num frames 3000...
[2023-02-22 17:15:20,565][07386] Num frames 3100...
[2023-02-22 17:15:20,727][07386] Num frames 3200...
[2023-02-22 17:15:20,896][07386] Num frames 3300...
[2023-02-22 17:15:21,042][07386] Num frames 3400...
[2023-02-22 17:15:21,194][07386] Num frames 3500...
[2023-02-22 17:15:21,346][07386] Num frames 3600...
[2023-02-22 17:15:21,496][07386] Num frames 3700...
[2023-02-22 17:15:21,652][07386] Num frames 3800...
[2023-02-22 17:15:21,809][07386] Num frames 3900...
[2023-02-22 17:15:21,958][07386] Num frames 4000...
[2023-02-22 17:15:22,109][07386] Num frames 4100...
[2023-02-22 17:15:22,263][07386] Num frames 4200...
[2023-02-22 17:15:22,414][07386] Avg episode rewards: #0: 38.196, true rewards: #0: 14.197
[2023-02-22 17:15:22,417][07386] Avg episode reward: 38.196, avg true_objective: 14.197
[2023-02-22 17:15:22,485][07386] Num frames 4300...
[2023-02-22 17:15:22,640][07386] Num frames 4400...
[2023-02-22 17:15:22,795][07386] Num frames 4500...
[2023-02-22 17:15:22,946][07386] Num frames 4600...
[2023-02-22 17:15:23,101][07386] Num frames 4700...
[2023-02-22 17:15:23,254][07386] Num frames 4800...
[2023-02-22 17:15:23,361][07386] Avg episode rewards: #0: 30.837, true rewards: #0: 12.088
[2023-02-22 17:15:23,363][07386] Avg episode reward: 30.837, avg true_objective: 12.088
[2023-02-22 17:15:23,466][07386] Num frames 4900...
[2023-02-22 17:15:23,619][07386] Num frames 5000...
[2023-02-22 17:15:23,777][07386] Num frames 5100...
[2023-02-22 17:15:23,969][07386] Avg episode rewards: #0: 25.574, true rewards: #0: 10.374
[2023-02-22 17:15:23,971][07386] Avg episode reward: 25.574, avg true_objective: 10.374
[2023-02-22 17:15:23,994][07386] Num frames 5200...
[2023-02-22 17:15:24,137][07386] Num frames 5300...
[2023-02-22 17:15:24,249][07386] Num frames 5400...
[2023-02-22 17:15:24,358][07386] Num frames 5500...
[2023-02-22 17:15:24,469][07386] Num frames 5600...
[2023-02-22 17:15:24,578][07386] Num frames 5700...
[2023-02-22 17:15:24,688][07386] Num frames 5800...
[2023-02-22 17:15:24,804][07386] Num frames 5900...
[2023-02-22 17:15:24,916][07386] Num frames 6000...
[2023-02-22 17:15:25,037][07386] Num frames 6100...
[2023-02-22 17:15:25,145][07386] Avg episode rewards: #0: 24.575, true rewards: #0: 10.242
[2023-02-22 17:15:25,148][07386] Avg episode reward: 24.575, avg true_objective: 10.242
[2023-02-22 17:15:25,217][07386] Num frames 6200...
[2023-02-22 17:15:25,335][07386] Num frames 6300...
[2023-02-22 17:15:25,452][07386] Num frames 6400...
[2023-02-22 17:15:25,567][07386] Num frames 6500...
[2023-02-22 17:15:25,678][07386] Num frames 6600...
[2023-02-22 17:15:25,799][07386] Num frames 6700...
[2023-02-22 17:15:25,911][07386] Num frames 6800...
[2023-02-22 17:15:26,023][07386] Num frames 6900...
[2023-02-22 17:15:26,134][07386] Num frames 7000...
[2023-02-22 17:15:26,246][07386] Num frames 7100...
[2023-02-22 17:15:26,363][07386] Num frames 7200...
[2023-02-22 17:15:26,475][07386] Num frames 7300...
[2023-02-22 17:15:26,588][07386] Num frames 7400...
[2023-02-22 17:15:26,703][07386] Num frames 7500...
[2023-02-22 17:15:26,820][07386] Num frames 7600...
[2023-02-22 17:15:26,931][07386] Num frames 7700...
[2023-02-22 17:15:27,046][07386] Num frames 7800...
[2023-02-22 17:15:27,157][07386] Num frames 7900...
[2023-02-22 17:15:27,272][07386] Num frames 8000...
[2023-02-22 17:15:27,396][07386] Num frames 8100...
[2023-02-22 17:15:27,511][07386] Num frames 8200...
[2023-02-22 17:15:27,605][07386] Avg episode rewards: #0: 28.905, true rewards: #0: 11.763
[2023-02-22 17:15:27,607][07386] Avg episode reward: 28.905, avg true_objective: 11.763
[2023-02-22 17:15:27,690][07386] Num frames 8300...
[2023-02-22 17:15:27,802][07386] Num frames 8400...
[2023-02-22 17:15:27,918][07386] Num frames 8500...
[2023-02-22 17:15:28,029][07386] Num frames 8600...
[2023-02-22 17:15:28,147][07386] Num frames 8700...
[2023-02-22 17:15:28,267][07386] Num frames 8800...
[2023-02-22 17:15:28,377][07386] Num frames 8900...
[2023-02-22 17:15:28,488][07386] Num frames 9000...
[2023-02-22 17:15:28,609][07386] Num frames 9100...
[2023-02-22 17:15:28,719][07386] Num frames 9200...
[2023-02-22 17:15:28,838][07386] Num frames 9300...
[2023-02-22 17:15:28,952][07386] Num frames 9400...
[2023-02-22 17:15:29,065][07386] Num frames 9500...
[2023-02-22 17:15:29,174][07386] Num frames 9600...
[2023-02-22 17:15:29,288][07386] Num frames 9700...
[2023-02-22 17:15:29,403][07386] Num frames 9800...
[2023-02-22 17:15:29,522][07386] Num frames 9900...
[2023-02-22 17:15:29,637][07386] Num frames 10000...
[2023-02-22 17:15:29,747][07386] Num frames 10100...
[2023-02-22 17:15:29,876][07386] Num frames 10200...
[2023-02-22 17:15:29,993][07386] Avg episode rewards: #0: 32.062, true rewards: #0: 12.813
[2023-02-22 17:15:29,994][07386] Avg episode reward: 32.062, avg true_objective: 12.813
[2023-02-22 17:15:30,051][07386] Num frames 10300...
[2023-02-22 17:15:30,158][07386] Num frames 10400...
[2023-02-22 17:15:30,281][07386] Num frames 10500...
[2023-02-22 17:15:30,394][07386] Num frames 10600...
[2023-02-22 17:15:30,507][07386] Num frames 10700...
[2023-02-22 17:15:30,621][07386] Num frames 10800...
[2023-02-22 17:15:30,729][07386] Num frames 10900...
[2023-02-22 17:15:30,847][07386] Num frames 11000...
[2023-02-22 17:15:30,955][07386] Num frames 11100...
[2023-02-22 17:15:31,062][07386] Num frames 11200...
[2023-02-22 17:15:31,199][07386] Avg episode rewards: #0: 30.860, true rewards: #0: 12.527
[2023-02-22 17:15:31,200][07386] Avg episode reward: 30.860, avg true_objective: 12.527
[2023-02-22 17:15:31,231][07386] Num frames 11300...
[2023-02-22 17:15:31,340][07386] Num frames 11400...
[2023-02-22 17:15:31,449][07386] Num frames 11500...
[2023-02-22 17:15:31,559][07386] Num frames 11600...
[2023-02-22 17:15:31,669][07386] Num frames 11700...
[2023-02-22 17:15:31,778][07386] Num frames 11800...
[2023-02-22 17:15:31,891][07386] Num frames 11900...
[2023-02-22 17:15:32,001][07386] Num frames 12000...
[2023-02-22 17:15:32,117][07386] Num frames 12100...
[2023-02-22 17:15:32,234][07386] Num frames 12200...
[2023-02-22 17:15:32,343][07386] Num frames 12300...
[2023-02-22 17:15:32,463][07386] Num frames 12400...
[2023-02-22 17:15:32,622][07386] Avg episode rewards: #0: 30.390, true rewards: #0: 12.490
[2023-02-22 17:15:32,624][07386] Avg episode reward: 30.390, avg true_objective: 12.490
[2023-02-22 17:16:43,661][07386] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
[2023-02-22 17:29:09,577][07386] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
[2023-02-22 17:29:09,579][07386] Overriding arg 'num_workers' with value 1 passed from command line
[2023-02-22 17:29:09,582][07386] Adding new argument 'no_render'=True that is not in the saved config file!
[2023-02-22 17:29:09,584][07386] Adding new argument 'save_video'=True that is not in the saved config file!
[2023-02-22 17:29:09,586][07386] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2023-02-22 17:29:09,588][07386] Adding new argument 'video_name'=None that is not in the saved config file!
[2023-02-22 17:29:09,589][07386] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
[2023-02-22 17:29:09,591][07386] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2023-02-22 17:29:09,592][07386] Adding new argument 'push_to_hub'=True that is not in the saved config file!
[2023-02-22 17:29:09,593][07386] Adding new argument 'hf_repository'='YoriV/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
[2023-02-22 17:29:09,594][07386] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2023-02-22 17:29:09,596][07386] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2023-02-22 17:29:09,597][07386] Adding new argument 'train_script'=None that is not in the saved config file!
[2023-02-22 17:29:09,598][07386] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2023-02-22 17:29:09,599][07386] Using frameskip 1 and render_action_repeat=4 for evaluation
[2023-02-22 17:29:09,627][07386] RunningMeanStd input shape: (3, 72, 128)
[2023-02-22 17:29:09,630][07386] RunningMeanStd input shape: (1,)
[2023-02-22 17:29:09,648][07386] ConvEncoder: input_channels=3
[2023-02-22 17:29:09,686][07386] Conv encoder output size: 512
[2023-02-22 17:29:09,688][07386] Policy head output size: 512
[2023-02-22 17:29:09,708][07386] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001466_6004736.pth...
[2023-02-22 17:29:10,136][07386] Num frames 100...
[2023-02-22 17:29:10,249][07386] Num frames 200...
[2023-02-22 17:29:10,363][07386] Num frames 300...
[2023-02-22 17:29:10,476][07386] Num frames 400...
[2023-02-22 17:29:10,585][07386] Num frames 500...
[2023-02-22 17:29:10,693][07386] Num frames 600...
[2023-02-22 17:29:10,802][07386] Num frames 700...
[2023-02-22 17:29:10,910][07386] Num frames 800...
[2023-02-22 17:29:11,019][07386] Num frames 900...
[2023-02-22 17:29:11,149][07386] Num frames 1000...
[2023-02-22 17:29:11,265][07386] Num frames 1100...
[2023-02-22 17:29:11,386][07386] Num frames 1200...
[2023-02-22 17:29:11,521][07386] Num frames 1300...
[2023-02-22 17:29:11,633][07386] Num frames 1400...
[2023-02-22 17:29:11,745][07386] Num frames 1500...
[2023-02-22 17:29:11,858][07386] Num frames 1600...
[2023-02-22 17:29:12,017][07386] Avg episode rewards: #0: 43.960, true rewards: #0: 16.960
[2023-02-22 17:29:12,022][07386] Avg episode reward: 43.960, avg true_objective: 16.960
[2023-02-22 17:29:12,029][07386] Num frames 1700...
[2023-02-22 17:29:12,140][07386] Num frames 1800...
[2023-02-22 17:29:12,247][07386] Num frames 1900...
[2023-02-22 17:29:12,365][07386] Num frames 2000...
[2023-02-22 17:29:12,482][07386] Num frames 2100...
[2023-02-22 17:29:12,595][07386] Num frames 2200...
[2023-02-22 17:29:12,711][07386] Num frames 2300...
[2023-02-22 17:29:12,821][07386] Num frames 2400...
[2023-02-22 17:29:12,945][07386] Num frames 2500...
[2023-02-22 17:29:13,057][07386] Num frames 2600...
[2023-02-22 17:29:13,169][07386] Num frames 2700...
[2023-02-22 17:29:13,281][07386] Num frames 2800...
[2023-02-22 17:29:13,401][07386] Num frames 2900...
[2023-02-22 17:29:13,522][07386] Num frames 3000...
[2023-02-22 17:29:13,646][07386] Num frames 3100...
[2023-02-22 17:29:13,765][07386] Num frames 3200...
[2023-02-22 17:29:13,891][07386] Num frames 3300...
[2023-02-22 17:29:13,973][07386] Avg episode rewards: #0: 43.605, true rewards: #0: 16.605
[2023-02-22 17:29:13,976][07386] Avg episode reward: 43.605, avg true_objective: 16.605
[2023-02-22 17:29:14,060][07386] Num frames 3400...
[2023-02-22 17:29:14,178][07386] Num frames 3500...
[2023-02-22 17:29:14,294][07386] Num frames 3600...
[2023-02-22 17:29:14,419][07386] Num frames 3700...
[2023-02-22 17:29:14,537][07386] Num frames 3800...
[2023-02-22 17:29:14,656][07386] Num frames 3900...
[2023-02-22 17:29:14,771][07386] Num frames 4000...
[2023-02-22 17:29:14,885][07386] Num frames 4100...
[2023-02-22 17:29:14,995][07386] Num frames 4200...
[2023-02-22 17:29:15,114][07386] Num frames 4300...
[2023-02-22 17:29:15,225][07386] Num frames 4400...
[2023-02-22 17:29:15,348][07386] Avg episode rewards: #0: 37.860, true rewards: #0: 14.860
[2023-02-22 17:29:15,349][07386] Avg episode reward: 37.860, avg true_objective: 14.860
[2023-02-22 17:29:15,405][07386] Num frames 4500...
[2023-02-22 17:29:15,516][07386] Num frames 4600...
[2023-02-22 17:29:15,622][07386] Num frames 4700...
[2023-02-22 17:29:15,729][07386] Num frames 4800...
[2023-02-22 17:29:15,832][07386] Avg episode rewards: #0: 29.855, true rewards: #0: 12.105
[2023-02-22 17:29:15,833][07386] Avg episode reward: 29.855, avg true_objective: 12.105
[2023-02-22 17:29:15,899][07386] Num frames 4900...
[2023-02-22 17:29:16,014][07386] Num frames 5000...
[2023-02-22 17:29:16,122][07386] Num frames 5100...
[2023-02-22 17:29:16,239][07386] Num frames 5200...
[2023-02-22 17:29:16,348][07386] Num frames 5300...
[2023-02-22 17:29:16,466][07386] Num frames 5400...
[2023-02-22 17:29:16,575][07386] Num frames 5500...
[2023-02-22 17:29:16,694][07386] Num frames 5600...
[2023-02-22 17:29:16,812][07386] Num frames 5700...
[2023-02-22 17:29:16,936][07386] Num frames 5800...
[2023-02-22 17:29:17,104][07386] Avg episode rewards: #0: 29.398, true rewards: #0: 11.798
[2023-02-22 17:29:17,106][07386] Avg episode reward: 29.398, avg true_objective: 11.798
[2023-02-22 17:29:17,111][07386] Num frames 5900...
[2023-02-22 17:29:17,224][07386] Num frames 6000...
[2023-02-22 17:29:17,332][07386] Num frames 6100...
[2023-02-22 17:29:17,450][07386] Num frames 6200...
[2023-02-22 17:29:17,562][07386] Num frames 6300...
[2023-02-22 17:29:17,668][07386] Avg episode rewards: #0: 25.412, true rewards: #0: 10.578
[2023-02-22 17:29:17,670][07386] Avg episode reward: 25.412, avg true_objective: 10.578
[2023-02-22 17:29:17,744][07386] Num frames 6400...
[2023-02-22 17:29:17,904][07386] Num frames 6500...
[2023-02-22 17:29:18,056][07386] Num frames 6600...
[2023-02-22 17:29:18,204][07386] Num frames 6700...
[2023-02-22 17:29:18,348][07386] Num frames 6800...
[2023-02-22 17:29:18,535][07386] Avg episode rewards: #0: 22.974, true rewards: #0: 9.831
[2023-02-22 17:29:18,540][07386] Avg episode reward: 22.974, avg true_objective: 9.831
[2023-02-22 17:29:18,569][07386] Num frames 6900...
[2023-02-22 17:29:18,724][07386] Num frames 7000...
[2023-02-22 17:29:18,877][07386] Num frames 7100...
[2023-02-22 17:29:19,026][07386] Num frames 7200...
[2023-02-22 17:29:19,173][07386] Num frames 7300...
[2023-02-22 17:29:19,326][07386] Num frames 7400...
[2023-02-22 17:29:19,493][07386] Num frames 7500...
[2023-02-22 17:29:19,652][07386] Num frames 7600...
[2023-02-22 17:29:19,808][07386] Num frames 7700...
[2023-02-22 17:29:19,967][07386] Num frames 7800...
[2023-02-22 17:29:20,124][07386] Num frames 7900...
[2023-02-22 17:29:20,280][07386] Num frames 8000...
[2023-02-22 17:29:20,437][07386] Num frames 8100...
[2023-02-22 17:29:20,601][07386] Num frames 8200...
[2023-02-22 17:29:20,749][07386] Avg episode rewards: #0: 24.197, true rewards: #0: 10.322
[2023-02-22 17:29:20,752][07386] Avg episode reward: 24.197, avg true_objective: 10.322
[2023-02-22 17:29:20,817][07386] Num frames 8300...
[2023-02-22 17:29:20,976][07386] Num frames 8400...
[2023-02-22 17:29:21,139][07386] Num frames 8500...
[2023-02-22 17:29:21,272][07386] Num frames 8600...
[2023-02-22 17:29:21,384][07386] Num frames 8700...
[2023-02-22 17:29:21,513][07386] Num frames 8800...
[2023-02-22 17:29:21,640][07386] Num frames 8900...
[2023-02-22 17:29:21,756][07386] Num frames 9000...
[2023-02-22 17:29:21,867][07386] Num frames 9100...
[2023-02-22 17:29:21,977][07386] Num frames 9200...
[2023-02-22 17:29:22,091][07386] Num frames 9300...
[2023-02-22 17:29:22,202][07386] Num frames 9400...
[2023-02-22 17:29:22,314][07386] Num frames 9500...
[2023-02-22 17:29:22,427][07386] Num frames 9600...
[2023-02-22 17:29:22,542][07386] Num frames 9700...
[2023-02-22 17:29:22,666][07386] Num frames 9800...
[2023-02-22 17:29:22,780][07386] Num frames 9900...
[2023-02-22 17:29:22,891][07386] Num frames 10000...
[2023-02-22 17:29:23,001][07386] Num frames 10100...
[2023-02-22 17:29:23,112][07386] Num frames 10200...
[2023-02-22 17:29:23,232][07386] Num frames 10300...
[2023-02-22 17:29:23,350][07386] Avg episode rewards: #0: 28.731, true rewards: #0: 11.509
[2023-02-22 17:29:23,351][07386] Avg episode reward: 28.731, avg true_objective: 11.509
[2023-02-22 17:29:23,401][07386] Num frames 10400...
[2023-02-22 17:29:23,515][07386] Num frames 10500...
[2023-02-22 17:29:23,630][07386] Num frames 10600...
[2023-02-22 17:29:23,748][07386] Num frames 10700...
[2023-02-22 17:29:23,868][07386] Num frames 10800...
[2023-02-22 17:29:23,979][07386] Num frames 10900...
[2023-02-22 17:29:24,091][07386] Num frames 11000...
[2023-02-22 17:29:24,206][07386] Num frames 11100...
[2023-02-22 17:29:24,315][07386] Num frames 11200...
[2023-02-22 17:29:24,434][07386] Num frames 11300...
[2023-02-22 17:29:24,513][07386] Avg episode rewards: #0: 27.718, true rewards: #0: 11.318
[2023-02-22 17:29:24,515][07386] Avg episode reward: 27.718, avg true_objective: 11.318
[2023-02-22 17:30:32,217][07386] Replay video saved to /content/train_dir/default_experiment/replay.mp4!