[2024-08-21 14:49:45,331][03870] Saving configuration to /content/train_dir/default_experiment/config.json...
[2024-08-21 14:49:45,333][03870] Rollout worker 0 uses device cpu
[2024-08-21 14:49:45,334][03870] Rollout worker 1 uses device cpu
[2024-08-21 14:49:45,335][03870] Rollout worker 2 uses device cpu
[2024-08-21 14:49:45,337][03870] Rollout worker 3 uses device cpu
[2024-08-21 14:49:45,338][03870] Rollout worker 4 uses device cpu
[2024-08-21 14:49:45,339][03870] Rollout worker 5 uses device cpu
[2024-08-21 14:49:45,340][03870] Rollout worker 6 uses device cpu
[2024-08-21 14:49:45,343][03870] Rollout worker 7 uses device cpu
[2024-08-21 14:49:45,497][03870] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-08-21 14:49:45,499][03870] InferenceWorker_p0-w0: min num requests: 2
[2024-08-21 14:49:45,532][03870] Starting all processes...
[2024-08-21 14:49:45,534][03870] Starting process learner_proc0
[2024-08-21 14:49:45,582][03870] Starting all processes...
[2024-08-21 14:49:45,593][03870] Starting process inference_proc0-0
[2024-08-21 14:49:45,593][03870] Starting process rollout_proc0
[2024-08-21 14:49:45,611][03870] Starting process rollout_proc1
[2024-08-21 14:49:45,611][03870] Starting process rollout_proc2
[2024-08-21 14:49:45,613][03870] Starting process rollout_proc3
[2024-08-21 14:49:45,613][03870] Starting process rollout_proc4
[2024-08-21 14:49:45,613][03870] Starting process rollout_proc5
[2024-08-21 14:49:45,613][03870] Starting process rollout_proc6
[2024-08-21 14:49:45,613][03870] Starting process rollout_proc7
[2024-08-21 14:49:57,021][05207] Worker 1 uses CPU cores [1]
[2024-08-21 14:49:57,030][05206] Worker 0 uses CPU cores [0]
[2024-08-21 14:49:57,048][05192] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-08-21 14:49:57,048][05192] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
[2024-08-21 14:49:57,099][05210] Worker 4 uses CPU cores [0]
[2024-08-21 14:49:57,106][05192] Num visible devices: 1
[2024-08-21 14:49:57,114][05211] Worker 5 uses CPU cores [1]
[2024-08-21 14:49:57,136][05192] Starting seed is not provided
[2024-08-21 14:49:57,136][05192] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-08-21 14:49:57,137][05192] Initializing actor-critic model on device cuda:0
[2024-08-21 14:49:57,138][05192] RunningMeanStd input shape: (3, 72, 128)
[2024-08-21 14:49:57,139][05192] RunningMeanStd input shape: (1,)
[2024-08-21 14:49:57,151][05213] Worker 7 uses CPU cores [1]
[2024-08-21 14:49:57,173][05192] ConvEncoder: input_channels=3
[2024-08-21 14:49:57,217][05212] Worker 6 uses CPU cores [0]
[2024-08-21 14:49:57,236][05209] Worker 3 uses CPU cores [1]
[2024-08-21 14:49:57,242][05205] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-08-21 14:49:57,242][05205] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
[2024-08-21 14:49:57,282][05205] Num visible devices: 1
[2024-08-21 14:49:57,302][05208] Worker 2 uses CPU cores [0]
[2024-08-21 14:49:57,385][05192] Conv encoder output size: 512
[2024-08-21 14:49:57,385][05192] Policy head output size: 512
[2024-08-21 14:49:57,401][05192] Created Actor Critic model with architecture:
[2024-08-21 14:49:57,401][05192] ActorCriticSharedWeights(
  (obs_normalizer): ObservationNormalizer(
    (running_mean_std): RunningMeanStdDictInPlace(
      (running_mean_std): ModuleDict(
        (obs): RunningMeanStdInPlace()
      )
    )
  )
  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
  (encoder): VizdoomEncoder(
    (basic_encoder): ConvEncoder(
      (enc): RecursiveScriptModule(
        original_name=ConvEncoderImpl
        (conv_head): RecursiveScriptModule(
          original_name=Sequential
          (0): RecursiveScriptModule(original_name=Conv2d)
          (1): RecursiveScriptModule(original_name=ELU)
          (2): RecursiveScriptModule(original_name=Conv2d)
          (3): RecursiveScriptModule(original_name=ELU)
          (4): RecursiveScriptModule(original_name=Conv2d)
          (5): RecursiveScriptModule(original_name=ELU)
        )
        (mlp_layers): RecursiveScriptModule(
          original_name=Sequential
          (0): RecursiveScriptModule(original_name=Linear)
          (1): RecursiveScriptModule(original_name=ELU)
        )
      )
    )
  )
  (core): ModelCoreRNN(
    (core): GRU(512, 512)
  )
  (decoder): MlpDecoder(
    (mlp): Identity()
  )
  (critic_linear): Linear(in_features=512, out_features=1, bias=True)
  (action_parameterization): ActionParameterizationDefault(
    (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
  )
)
[2024-08-21 14:50:01,491][05192] Using optimizer <class 'torch.optim.adam.Adam'>
[2024-08-21 14:50:01,492][05192] No checkpoints found
[2024-08-21 14:50:01,492][05192] Did not load from checkpoint, starting from scratch!
[2024-08-21 14:50:01,492][05192] Initialized policy 0 weights for model version 0
[2024-08-21 14:50:01,495][05192] LearnerWorker_p0 finished initialization!
[2024-08-21 14:50:01,497][05192] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-08-21 14:50:01,698][05205] RunningMeanStd input shape: (3, 72, 128)
[2024-08-21 14:50:01,699][05205] RunningMeanStd input shape: (1,)
[2024-08-21 14:50:01,719][05205] ConvEncoder: input_channels=3
[2024-08-21 14:50:01,897][05205] Conv encoder output size: 512
[2024-08-21 14:50:01,898][05205] Policy head output size: 512
[2024-08-21 14:50:02,055][03870] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2024-08-21 14:50:03,911][03870] Inference worker 0-0 is ready!
[2024-08-21 14:50:03,913][03870] All inference workers are ready! Signal rollout workers to start!
[2024-08-21 14:50:04,025][05211] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-08-21 14:50:04,039][05209] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-08-21 14:50:04,065][05212] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-08-21 14:50:04,072][05208] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-08-21 14:50:04,074][05206] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-08-21 14:50:04,074][05207] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-08-21 14:50:04,077][05213] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-08-21 14:50:04,097][05210] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-08-21 14:50:05,258][05209] Decorrelating experience for 0 frames...
[2024-08-21 14:50:05,258][05212] Decorrelating experience for 0 frames...
[2024-08-21 14:50:05,261][05213] Decorrelating experience for 0 frames...
[2024-08-21 14:50:05,259][05208] Decorrelating experience for 0 frames...
[2024-08-21 14:50:05,260][05211] Decorrelating experience for 0 frames...
[2024-08-21 14:50:05,490][03870] Heartbeat connected on Batcher_0
[2024-08-21 14:50:05,496][03870] Heartbeat connected on LearnerWorker_p0
[2024-08-21 14:50:05,529][03870] Heartbeat connected on InferenceWorker_p0-w0
[2024-08-21 14:50:06,387][05211] Decorrelating experience for 32 frames...
[2024-08-21 14:50:06,385][05213] Decorrelating experience for 32 frames...
[2024-08-21 14:50:06,410][05212] Decorrelating experience for 32 frames...
[2024-08-21 14:50:06,410][05208] Decorrelating experience for 32 frames...
[2024-08-21 14:50:06,406][05210] Decorrelating experience for 0 frames...
[2024-08-21 14:50:06,452][05207] Decorrelating experience for 0 frames...
[2024-08-21 14:50:07,055][03870] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2024-08-21 14:50:07,639][05210] Decorrelating experience for 32 frames...
[2024-08-21 14:50:07,638][05206] Decorrelating experience for 0 frames...
[2024-08-21 14:50:07,761][05212] Decorrelating experience for 64 frames...
[2024-08-21 14:50:07,902][05209] Decorrelating experience for 32 frames...
[2024-08-21 14:50:07,956][05207] Decorrelating experience for 32 frames...
[2024-08-21 14:50:08,106][05211] Decorrelating experience for 64 frames...
[2024-08-21 14:50:08,108][05213] Decorrelating experience for 64 frames...
[2024-08-21 14:50:08,565][05210] Decorrelating experience for 64 frames...
[2024-08-21 14:50:09,067][05212] Decorrelating experience for 96 frames...
[2024-08-21 14:50:09,290][03870] Heartbeat connected on RolloutWorker_w6
[2024-08-21 14:50:09,657][05209] Decorrelating experience for 64 frames...
[2024-08-21 14:50:09,713][05207] Decorrelating experience for 64 frames...
[2024-08-21 14:50:09,848][05213] Decorrelating experience for 96 frames...
[2024-08-21 14:50:09,851][05211] Decorrelating experience for 96 frames...
[2024-08-21 14:50:10,022][05208] Decorrelating experience for 64 frames...
[2024-08-21 14:50:10,073][05210] Decorrelating experience for 96 frames...
[2024-08-21 14:50:10,121][03870] Heartbeat connected on RolloutWorker_w7
[2024-08-21 14:50:10,126][03870] Heartbeat connected on RolloutWorker_w5
[2024-08-21 14:50:10,275][03870] Heartbeat connected on RolloutWorker_w4
[2024-08-21 14:50:10,420][05206] Decorrelating experience for 32 frames...
[2024-08-21 14:50:10,567][05209] Decorrelating experience for 96 frames...
[2024-08-21 14:50:10,760][03870] Heartbeat connected on RolloutWorker_w3
[2024-08-21 14:50:11,099][05207] Decorrelating experience for 96 frames...
[2024-08-21 14:50:11,207][03870] Heartbeat connected on RolloutWorker_w1
[2024-08-21 14:50:11,298][05206] Decorrelating experience for 64 frames...
[2024-08-21 14:50:11,450][05208] Decorrelating experience for 96 frames...
[2024-08-21 14:50:11,551][03870] Heartbeat connected on RolloutWorker_w2
[2024-08-21 14:50:11,773][05206] Decorrelating experience for 96 frames...
[2024-08-21 14:50:11,839][03870] Heartbeat connected on RolloutWorker_w0
[2024-08-21 14:50:12,055][03870] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2024-08-21 14:50:16,353][05192] Signal inference workers to stop experience collection...
[2024-08-21 14:50:16,371][05205] InferenceWorker_p0-w0: stopping experience collection
[2024-08-21 14:50:17,058][03870] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 140.4. Samples: 2106. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2024-08-21 14:50:17,062][03870] Avg episode reward: [(0, '1.769')]
[2024-08-21 14:50:18,700][05192] Signal inference workers to resume experience collection...
[2024-08-21 14:50:18,703][05205] InferenceWorker_p0-w0: resuming experience collection
[2024-08-21 14:50:22,055][03870] Fps is (10 sec: 1638.4, 60 sec: 819.2, 300 sec: 819.2). Total num frames: 16384. Throughput: 0: 217.7. Samples: 4354. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2024-08-21 14:50:22,061][03870] Avg episode reward: [(0, '3.196')]
[2024-08-21 14:50:27,055][03870] Fps is (10 sec: 3687.4, 60 sec: 1474.5, 300 sec: 1474.5). Total num frames: 36864. Throughput: 0: 308.8. Samples: 7720. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
[2024-08-21 14:50:27,062][03870] Avg episode reward: [(0, '3.994')]
[2024-08-21 14:50:27,446][05205] Updated weights for policy 0, policy_version 10 (0.0620)
[2024-08-21 14:50:32,055][03870] Fps is (10 sec: 3686.4, 60 sec: 1774.9, 300 sec: 1774.9). Total num frames: 53248. Throughput: 0: 459.4. Samples: 13782. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 14:50:32,062][03870] Avg episode reward: [(0, '4.453')]
[2024-08-21 14:50:37,055][03870] Fps is (10 sec: 3276.8, 60 sec: 1989.5, 300 sec: 1989.5). Total num frames: 69632. Throughput: 0: 516.1. Samples: 18064. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 14:50:37,058][03870] Avg episode reward: [(0, '4.508')]
[2024-08-21 14:50:39,601][05205] Updated weights for policy 0, policy_version 20 (0.0036)
[2024-08-21 14:50:42,055][03870] Fps is (10 sec: 3686.4, 60 sec: 2252.8, 300 sec: 2252.8). Total num frames: 90112. Throughput: 0: 535.4. Samples: 21414. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:50:42,060][03870] Avg episode reward: [(0, '4.456')]
[2024-08-21 14:50:47,055][03870] Fps is (10 sec: 4505.7, 60 sec: 2548.6, 300 sec: 2548.6). Total num frames: 114688. Throughput: 0: 621.0. Samples: 27946. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-08-21 14:50:47,062][03870] Avg episode reward: [(0, '4.506')]
[2024-08-21 14:50:47,068][05192] Saving new best policy, reward=4.506!
[2024-08-21 14:50:49,888][05205] Updated weights for policy 0, policy_version 30 (0.0026)
[2024-08-21 14:50:52,055][03870] Fps is (10 sec: 3686.4, 60 sec: 2539.5, 300 sec: 2539.5). Total num frames: 126976. Throughput: 0: 722.5. Samples: 32512. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-08-21 14:50:52,058][03870] Avg episode reward: [(0, '4.498')]
[2024-08-21 14:50:57,055][03870] Fps is (10 sec: 2867.2, 60 sec: 2606.6, 300 sec: 2606.6). Total num frames: 143360. Throughput: 0: 770.2. Samples: 34658. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 14:50:57,060][03870] Avg episode reward: [(0, '4.567')]
[2024-08-21 14:50:57,064][05192] Saving new best policy, reward=4.567!
[2024-08-21 14:51:00,847][05205] Updated weights for policy 0, policy_version 40 (0.0017)
[2024-08-21 14:51:02,055][03870] Fps is (10 sec: 4096.0, 60 sec: 2798.9, 300 sec: 2798.9). Total num frames: 167936. Throughput: 0: 875.2. Samples: 41488. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-08-21 14:51:02,062][03870] Avg episode reward: [(0, '4.464')]
[2024-08-21 14:51:07,055][03870] Fps is (10 sec: 4095.9, 60 sec: 3072.0, 300 sec: 2835.7). Total num frames: 184320. Throughput: 0: 959.4. Samples: 47526. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-08-21 14:51:07,062][03870] Avg episode reward: [(0, '4.401')]
[2024-08-21 14:51:12,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 2867.2). Total num frames: 200704. Throughput: 0: 932.1. Samples: 49664. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:51:12,063][03870] Avg episode reward: [(0, '4.432')]
[2024-08-21 14:51:12,718][05205] Updated weights for policy 0, policy_version 50 (0.0012)
[2024-08-21 14:51:17,059][03870] Fps is (10 sec: 4094.5, 60 sec: 3754.6, 300 sec: 3003.6). Total num frames: 225280. Throughput: 0: 928.5. Samples: 55566. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-08-21 14:51:17,067][03870] Avg episode reward: [(0, '4.388')]
[2024-08-21 14:51:21,683][05205] Updated weights for policy 0, policy_version 60 (0.0018)
[2024-08-21 14:51:22,055][03870] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3072.0). Total num frames: 245760. Throughput: 0: 984.0. Samples: 62342. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 14:51:22,061][03870] Avg episode reward: [(0, '4.526')]
[2024-08-21 14:51:27,055][03870] Fps is (10 sec: 3687.9, 60 sec: 3754.7, 300 sec: 3084.1). Total num frames: 262144. Throughput: 0: 959.1. Samples: 64572. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-08-21 14:51:27,059][03870] Avg episode reward: [(0, '4.664')]
[2024-08-21 14:51:27,063][05192] Saving new best policy, reward=4.664!
[2024-08-21 14:51:32,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3094.8). Total num frames: 278528. Throughput: 0: 920.5. Samples: 69368. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 14:51:32,062][03870] Avg episode reward: [(0, '4.654')]
[2024-08-21 14:51:33,446][05205] Updated weights for policy 0, policy_version 70 (0.0024)
[2024-08-21 14:51:37,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3190.6). Total num frames: 303104. Throughput: 0: 973.9. Samples: 76338. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-08-21 14:51:37,058][03870] Avg episode reward: [(0, '4.493')]
[2024-08-21 14:51:42,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3194.9). Total num frames: 319488. Throughput: 0: 997.4. Samples: 79540. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 14:51:42,060][03870] Avg episode reward: [(0, '4.393')]
[2024-08-21 14:51:42,075][05192] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000078_319488.pth...
[2024-08-21 14:51:44,307][05205] Updated weights for policy 0, policy_version 80 (0.0019)
[2024-08-21 14:51:47,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3198.8). Total num frames: 335872. Throughput: 0: 939.6. Samples: 83768. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-08-21 14:51:47,057][03870] Avg episode reward: [(0, '4.298')]
[2024-08-21 14:51:52,055][03870] Fps is (10 sec: 3686.3, 60 sec: 3822.9, 300 sec: 3239.6). Total num frames: 356352. Throughput: 0: 947.2. Samples: 90150. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-08-21 14:51:52,058][03870] Avg episode reward: [(0, '4.188')]
[2024-08-21 14:51:54,137][05205] Updated weights for policy 0, policy_version 90 (0.0023)
[2024-08-21 14:51:57,055][03870] Fps is (10 sec: 4505.7, 60 sec: 3959.5, 300 sec: 3312.4). Total num frames: 380928. Throughput: 0: 976.4. Samples: 93600. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 14:51:57,064][03870] Avg episode reward: [(0, '4.393')]
[2024-08-21 14:52:02,057][03870] Fps is (10 sec: 3685.6, 60 sec: 3754.5, 300 sec: 3276.7). Total num frames: 393216. Throughput: 0: 959.9. Samples: 98760. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-08-21 14:52:02,060][03870] Avg episode reward: [(0, '4.610')]
[2024-08-21 14:52:06,042][05205] Updated weights for policy 0, policy_version 100 (0.0024)
[2024-08-21 14:52:07,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3823.0, 300 sec: 3309.6). Total num frames: 413696. Throughput: 0: 926.3. Samples: 104026. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 14:52:07,063][03870] Avg episode reward: [(0, '4.628')]
[2024-08-21 14:52:12,055][03870] Fps is (10 sec: 4097.0, 60 sec: 3891.2, 300 sec: 3339.8). Total num frames: 434176. Throughput: 0: 953.3. Samples: 107472. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-08-21 14:52:12,057][03870] Avg episode reward: [(0, '4.618')]
[2024-08-21 14:52:15,077][05205] Updated weights for policy 0, policy_version 110 (0.0013)
[2024-08-21 14:52:17,055][03870] Fps is (10 sec: 4095.9, 60 sec: 3823.2, 300 sec: 3367.8). Total num frames: 454656. Throughput: 0: 987.9. Samples: 113822. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-08-21 14:52:17,063][03870] Avg episode reward: [(0, '4.525')]
[2024-08-21 14:52:22,055][03870] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3335.3). Total num frames: 466944. Throughput: 0: 926.7. Samples: 118040. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-08-21 14:52:22,060][03870] Avg episode reward: [(0, '4.490')]
[2024-08-21 14:52:26,618][05205] Updated weights for policy 0, policy_version 120 (0.0019)
[2024-08-21 14:52:27,055][03870] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3389.8). Total num frames: 491520. Throughput: 0: 927.6. Samples: 121284. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-08-21 14:52:27,058][03870] Avg episode reward: [(0, '4.728')]
[2024-08-21 14:52:27,060][05192] Saving new best policy, reward=4.728!
[2024-08-21 14:52:32,055][03870] Fps is (10 sec: 4505.7, 60 sec: 3891.2, 300 sec: 3413.3). Total num frames: 512000. Throughput: 0: 985.2. Samples: 128100. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:52:32,059][03870] Avg episode reward: [(0, '4.511')]
[2024-08-21 14:52:37,059][03870] Fps is (10 sec: 3684.9, 60 sec: 3754.4, 300 sec: 3408.8). Total num frames: 528384. Throughput: 0: 948.6. Samples: 132840. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
[2024-08-21 14:52:37,066][03870] Avg episode reward: [(0, '4.520')]
[2024-08-21 14:52:37,887][05205] Updated weights for policy 0, policy_version 130 (0.0018)
[2024-08-21 14:52:42,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3404.8). Total num frames: 544768. Throughput: 0: 923.2. Samples: 135146. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-08-21 14:52:42,057][03870] Avg episode reward: [(0, '4.655')]
[2024-08-21 14:52:47,055][03870] Fps is (10 sec: 4097.6, 60 sec: 3891.2, 300 sec: 3450.6). Total num frames: 569344. Throughput: 0: 961.7. Samples: 142032. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 14:52:47,060][03870] Avg episode reward: [(0, '4.457')]
[2024-08-21 14:52:47,569][05205] Updated weights for policy 0, policy_version 140 (0.0026)
[2024-08-21 14:52:52,057][03870] Fps is (10 sec: 4504.9, 60 sec: 3891.1, 300 sec: 3469.5). Total num frames: 589824. Throughput: 0: 977.3. Samples: 148004. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:52:52,061][03870] Avg episode reward: [(0, '4.314')]
[2024-08-21 14:52:57,055][03870] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3440.6). Total num frames: 602112. Throughput: 0: 947.2. Samples: 150098. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 14:52:57,062][03870] Avg episode reward: [(0, '4.401')]
[2024-08-21 14:52:59,164][05205] Updated weights for policy 0, policy_version 150 (0.0027)
[2024-08-21 14:53:02,055][03870] Fps is (10 sec: 3686.9, 60 sec: 3891.4, 300 sec: 3481.6). Total num frames: 626688. Throughput: 0: 939.3. Samples: 156090. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
[2024-08-21 14:53:02,057][03870] Avg episode reward: [(0, '4.630')]
[2024-08-21 14:53:07,055][03870] Fps is (10 sec: 4505.7, 60 sec: 3891.2, 300 sec: 3498.2). Total num frames: 647168. Throughput: 0: 1000.7. Samples: 163070. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 14:53:07,060][03870] Avg episode reward: [(0, '4.766')]
[2024-08-21 14:53:07,142][05192] Saving new best policy, reward=4.766!
[2024-08-21 14:53:08,643][05205] Updated weights for policy 0, policy_version 160 (0.0026)
[2024-08-21 14:53:12,055][03870] Fps is (10 sec: 3686.5, 60 sec: 3822.9, 300 sec: 3492.4). Total num frames: 663552. Throughput: 0: 975.3. Samples: 165172. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-08-21 14:53:12,058][03870] Avg episode reward: [(0, '4.772')]
[2024-08-21 14:53:12,072][05192] Saving new best policy, reward=4.772!
[2024-08-21 14:53:17,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3486.8). Total num frames: 679936. Throughput: 0: 933.5. Samples: 170106. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:53:17,058][03870] Avg episode reward: [(0, '4.692')]
[2024-08-21 14:53:19,917][05205] Updated weights for policy 0, policy_version 170 (0.0022)
[2024-08-21 14:53:22,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3522.6). Total num frames: 704512. Throughput: 0: 978.8. Samples: 176880. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:53:22,057][03870] Avg episode reward: [(0, '4.575')]
[2024-08-21 14:53:27,055][03870] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3516.6). Total num frames: 720896. Throughput: 0: 995.5. Samples: 179942. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-08-21 14:53:27,058][03870] Avg episode reward: [(0, '4.708')]
[2024-08-21 14:53:31,734][05205] Updated weights for policy 0, policy_version 180 (0.0021)
[2024-08-21 14:53:32,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3510.9). Total num frames: 737280. Throughput: 0: 937.1. Samples: 184202. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 14:53:32,057][03870] Avg episode reward: [(0, '4.621')]
[2024-08-21 14:53:37,055][03870] Fps is (10 sec: 3686.4, 60 sec: 3823.2, 300 sec: 3524.5). Total num frames: 757760. Throughput: 0: 950.5. Samples: 190776. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 14:53:37,057][03870] Avg episode reward: [(0, '4.962')]
[2024-08-21 14:53:37,064][05192] Saving new best policy, reward=4.962!
[2024-08-21 14:53:40,774][05205] Updated weights for policy 0, policy_version 190 (0.0027)
[2024-08-21 14:53:42,055][03870] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3556.1). Total num frames: 782336. Throughput: 0: 978.0. Samples: 194110. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 14:53:42,058][03870] Avg episode reward: [(0, '5.096')]
[2024-08-21 14:53:42,073][05192] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000191_782336.pth...
[2024-08-21 14:53:42,271][05192] Saving new best policy, reward=5.096!
[2024-08-21 14:53:47,061][03870] Fps is (10 sec: 3684.2, 60 sec: 3754.3, 300 sec: 3531.6). Total num frames: 794624. Throughput: 0: 955.3. Samples: 199084. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 14:53:47,066][03870] Avg episode reward: [(0, '5.165')]
[2024-08-21 14:53:47,072][05192] Saving new best policy, reward=5.165!
[2024-08-21 14:53:52,055][03870] Fps is (10 sec: 3276.7, 60 sec: 3754.7, 300 sec: 3543.9). Total num frames: 815104. Throughput: 0: 921.4. Samples: 204532. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-08-21 14:53:52,058][03870] Avg episode reward: [(0, '5.434')]
[2024-08-21 14:53:52,074][05192] Saving new best policy, reward=5.434!
[2024-08-21 14:53:53,000][05205] Updated weights for policy 0, policy_version 200 (0.0029)
[2024-08-21 14:53:57,055][03870] Fps is (10 sec: 4098.4, 60 sec: 3891.2, 300 sec: 3555.7). Total num frames: 835584. Throughput: 0: 945.0. Samples: 207696. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:53:57,057][03870] Avg episode reward: [(0, '5.388')]
[2024-08-21 14:54:02,055][03870] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3549.9). Total num frames: 851968. Throughput: 0: 969.5. Samples: 213734. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:54:02,059][03870] Avg episode reward: [(0, '5.342')]
[2024-08-21 14:54:03,795][05205] Updated weights for policy 0, policy_version 210 (0.0021)
[2024-08-21 14:54:07,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3544.3). Total num frames: 868352. Throughput: 0: 915.2. Samples: 218064. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:54:07,057][03870] Avg episode reward: [(0, '5.639')]
[2024-08-21 14:54:07,063][05192] Saving new best policy, reward=5.639!
[2024-08-21 14:54:12,055][03870] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3571.7). Total num frames: 892928. Throughput: 0: 921.7. Samples: 221418. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:54:12,062][03870] Avg episode reward: [(0, '6.242')]
[2024-08-21 14:54:12,074][05192] Saving new best policy, reward=6.242!
[2024-08-21 14:54:13,867][05205] Updated weights for policy 0, policy_version 220 (0.0014)
[2024-08-21 14:54:17,055][03870] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3582.0). Total num frames: 913408. Throughput: 0: 977.3. Samples: 228182. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 14:54:17,059][03870] Avg episode reward: [(0, '5.935')]
[2024-08-21 14:54:22,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3560.4). Total num frames: 925696. Throughput: 0: 935.2. Samples: 232860. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 14:54:22,063][03870] Avg episode reward: [(0, '5.923')]
[2024-08-21 14:54:25,634][05205] Updated weights for policy 0, policy_version 230 (0.0030)
[2024-08-21 14:54:27,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3570.5). Total num frames: 946176. Throughput: 0: 914.1. Samples: 235244. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 14:54:27,059][03870] Avg episode reward: [(0, '5.913')]
[2024-08-21 14:54:32,055][03870] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3595.4). Total num frames: 970752. Throughput: 0: 957.2. Samples: 242154. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-08-21 14:54:32,057][03870] Avg episode reward: [(0, '5.664')]
[2024-08-21 14:54:34,735][05205] Updated weights for policy 0, policy_version 240 (0.0014)
[2024-08-21 14:54:37,055][03870] Fps is (10 sec: 4095.9, 60 sec: 3822.9, 300 sec: 3589.6). Total num frames: 987136. Throughput: 0: 961.6. Samples: 247806. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 14:54:37,062][03870] Avg episode reward: [(0, '5.858')]
[2024-08-21 14:54:42,055][03870] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3584.0). Total num frames: 1003520. Throughput: 0: 938.8. Samples: 249942. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 14:54:42,058][03870] Avg episode reward: [(0, '5.975')]
[2024-08-21 14:54:46,214][05205] Updated weights for policy 0, policy_version 250 (0.0015)
[2024-08-21 14:54:47,055][03870] Fps is (10 sec: 3686.4, 60 sec: 3823.3, 300 sec: 3593.0). Total num frames: 1024000. Throughput: 0: 945.0. Samples: 256258. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-08-21 14:54:47,063][03870] Avg episode reward: [(0, '6.357')]
[2024-08-21 14:54:47,065][05192] Saving new best policy, reward=6.357!
[2024-08-21 14:54:52,055][03870] Fps is (10 sec: 4505.8, 60 sec: 3891.2, 300 sec: 3615.8). Total num frames: 1048576. Throughput: 0: 996.5. Samples: 262908. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:54:52,059][03870] Avg episode reward: [(0, '6.900')]
[2024-08-21 14:54:52,072][05192] Saving new best policy, reward=6.900!
[2024-08-21 14:54:57,055][03870] Fps is (10 sec: 3686.5, 60 sec: 3754.7, 300 sec: 3596.1). Total num frames: 1060864. Throughput: 0: 966.5. Samples: 264910. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:54:57,061][03870] Avg episode reward: [(0, '6.894')]
[2024-08-21 14:54:57,736][05205] Updated weights for policy 0, policy_version 260 (0.0019)
[2024-08-21 14:55:02,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3665.6). Total num frames: 1081344. Throughput: 0: 930.5. Samples: 270054. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:55:02,061][03870] Avg episode reward: [(0, '6.508')]
[2024-08-21 14:55:07,008][05205] Updated weights for policy 0, policy_version 270 (0.0014)
[2024-08-21 14:55:07,055][03870] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3748.9). Total num frames: 1105920. Throughput: 0: 981.6. Samples: 277034. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:55:07,060][03870] Avg episode reward: [(0, '6.279')]
[2024-08-21 14:55:12,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3804.5). Total num frames: 1122304. Throughput: 0: 997.3. Samples: 280124. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:55:12,059][03870] Avg episode reward: [(0, '6.228')]
[2024-08-21 14:55:17,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3804.4). Total num frames: 1138688. Throughput: 0: 939.4. Samples: 284426. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:55:17,057][03870] Avg episode reward: [(0, '5.807')]
[2024-08-21 14:55:18,590][05205] Updated weights for policy 0, policy_version 280 (0.0019)
[2024-08-21 14:55:22,055][03870] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3804.4). Total num frames: 1159168. Throughput: 0: 961.9. Samples: 291092. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:55:22,057][03870] Avg episode reward: [(0, '6.128')]
[2024-08-21 14:55:27,055][03870] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3832.2). Total num frames: 1183744. Throughput: 0: 987.2. Samples: 294366. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 14:55:27,061][03870] Avg episode reward: [(0, '6.219')]
[2024-08-21 14:55:28,168][05205] Updated weights for policy 0, policy_version 290 (0.0017)
[2024-08-21 14:55:32,062][03870] Fps is (10 sec: 3683.9, 60 sec: 3754.2, 300 sec: 3818.2). Total num frames: 1196032. Throughput: 0: 957.2. Samples: 299336. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-08-21 14:55:32,065][03870] Avg episode reward: [(0, '6.291')]
[2024-08-21 14:55:37,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3823.0, 300 sec: 3818.3). Total num frames: 1216512. Throughput: 0: 936.4. Samples: 305046. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 14:55:37,057][03870] Avg episode reward: [(0, '7.135')]
[2024-08-21 14:55:37,060][05192] Saving new best policy, reward=7.135!
[2024-08-21 14:55:39,300][05205] Updated weights for policy 0, policy_version 300 (0.0013)
[2024-08-21 14:55:42,055][03870] Fps is (10 sec: 4508.5, 60 sec: 3959.5, 300 sec: 3818.3). Total num frames: 1241088. Throughput: 0: 967.3. Samples: 308438. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-08-21 14:55:42,062][03870] Avg episode reward: [(0, '7.847')]
[2024-08-21 14:55:42,076][05192] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000303_1241088.pth...
[2024-08-21 14:55:42,220][05192] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000078_319488.pth
[2024-08-21 14:55:42,234][05192] Saving new best policy, reward=7.847!
[2024-08-21 14:55:47,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 1257472. Throughput: 0: 981.9. Samples: 314240. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 14:55:47,058][03870] Avg episode reward: [(0, '8.068')]
[2024-08-21 14:55:47,062][05192] Saving new best policy, reward=8.068!
[2024-08-21 14:55:51,072][05205] Updated weights for policy 0, policy_version 310 (0.0023)
[2024-08-21 14:55:52,055][03870] Fps is (10 sec: 3276.9, 60 sec: 3754.7, 300 sec: 3832.2). Total num frames: 1273856. Throughput: 0: 930.0. Samples: 318884. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-08-21 14:55:52,060][03870] Avg episode reward: [(0, '7.744')]
[2024-08-21 14:55:57,055][03870] Fps is (10 sec: 3686.3, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 1294336. Throughput: 0: 933.1. Samples: 322112. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:55:57,062][03870] Avg episode reward: [(0, '7.851')]
[2024-08-21 14:56:00,255][05205] Updated weights for policy 0, policy_version 320 (0.0022)
[2024-08-21 14:56:02,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 1314816. Throughput: 0: 992.5. Samples: 329088. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 14:56:02,057][03870] Avg episode reward: [(0, '7.779')]
[2024-08-21 14:56:07,055][03870] Fps is (10 sec: 3686.5, 60 sec: 3754.7, 300 sec: 3832.2). Total num frames: 1331200. Throughput: 0: 937.5. Samples: 333280. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 14:56:07,059][03870] Avg episode reward: [(0, '8.993')]
[2024-08-21 14:56:07,061][05192] Saving new best policy, reward=8.993!
[2024-08-21 14:56:12,016][05205] Updated weights for policy 0, policy_version 330 (0.0020)
[2024-08-21 14:56:12,055][03870] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3818.4). Total num frames: 1351680. Throughput: 0: 925.2. Samples: 336002. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:56:12,059][03870] Avg episode reward: [(0, '9.755')]
[2024-08-21 14:56:12,069][05192] Saving new best policy, reward=9.755!
[2024-08-21 14:56:17,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 1372160. Throughput: 0: 967.6. Samples: 342870. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:56:17,061][03870] Avg episode reward: [(0, '10.114')]
[2024-08-21 14:56:17,063][05192] Saving new best policy, reward=10.114!
[2024-08-21 14:56:22,055][03870] Fps is (10 sec: 3686.3, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 1388544. Throughput: 0: 957.8. Samples: 348148. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:56:22,058][03870] Avg episode reward: [(0, '10.727')]
[2024-08-21 14:56:22,071][05192] Saving new best policy, reward=10.727!
[2024-08-21 14:56:23,181][05205] Updated weights for policy 0, policy_version 340 (0.0014)
[2024-08-21 14:56:27,058][03870] Fps is (10 sec: 3275.9, 60 sec: 3686.2, 300 sec: 3818.3). Total num frames: 1404928. Throughput: 0: 926.2. Samples: 350120. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:56:27,059][03870] Avg episode reward: [(0, '10.763')]
[2024-08-21 14:56:27,071][05192] Saving new best policy, reward=10.763!
[2024-08-21 14:56:32,055][03870] Fps is (10 sec: 3686.5, 60 sec: 3823.4, 300 sec: 3804.4). Total num frames: 1425408. Throughput: 0: 941.9. Samples: 356624. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:56:32,062][03870] Avg episode reward: [(0, '11.124')]
[2024-08-21 14:56:32,135][05192] Saving new best policy, reward=11.124!
[2024-08-21 14:56:33,105][05205] Updated weights for policy 0, policy_version 350 (0.0020)
[2024-08-21 14:56:37,055][03870] Fps is (10 sec: 4097.1, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 1445888. Throughput: 0: 980.9. Samples: 363026. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:56:37,058][03870] Avg episode reward: [(0, '11.371')]
[2024-08-21 14:56:37,065][05192] Saving new best policy, reward=11.371!
[2024-08-21 14:56:42,057][03870] Fps is (10 sec: 3685.6, 60 sec: 3686.3, 300 sec: 3818.3). Total num frames: 1462272. Throughput: 0: 953.2. Samples: 365006. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:56:42,062][03870] Avg episode reward: [(0, '11.643')]
[2024-08-21 14:56:42,080][05192] Saving new best policy, reward=11.643!
[2024-08-21 14:56:44,863][05205] Updated weights for policy 0, policy_version 360 (0.0030)
[2024-08-21 14:56:47,055][03870] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 1482752. Throughput: 0: 918.5. Samples: 370422. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 14:56:47,057][03870] Avg episode reward: [(0, '12.084')]
[2024-08-21 14:56:47,067][05192] Saving new best policy, reward=12.084!
[2024-08-21 14:56:52,055][03870] Fps is (10 sec: 4096.9, 60 sec: 3822.9, 300 sec: 3804.4). Total num frames: 1503232. Throughput: 0: 978.1. Samples: 377296. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 14:56:52,057][03870] Avg episode reward: [(0, '11.820')]
[2024-08-21 14:56:54,273][05205] Updated weights for policy 0, policy_version 370 (0.0016)
[2024-08-21 14:56:57,055][03870] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 1519616. Throughput: 0: 974.9. Samples: 379872. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:56:57,058][03870] Avg episode reward: [(0, '11.213')]
[2024-08-21 14:57:02,055][03870] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 1540096. Throughput: 0: 923.2. Samples: 384416. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-08-21 14:57:02,057][03870] Avg episode reward: [(0, '11.395')]
[2024-08-21 14:57:05,350][05205] Updated weights for policy 0, policy_version 380 (0.0015)
[2024-08-21 14:57:07,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 1560576. Throughput: 0: 961.3. Samples: 391404. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 14:57:07,057][03870] Avg episode reward: [(0, '11.563')]
[2024-08-21 14:57:12,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 1581056. Throughput: 0: 995.1. Samples: 394896. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-08-21 14:57:12,066][03870] Avg episode reward: [(0, '12.006')]
[2024-08-21 14:57:16,443][05205] Updated weights for policy 0, policy_version 390 (0.0017)
[2024-08-21 14:57:17,061][03870] Fps is (10 sec: 3684.3, 60 sec: 3754.3, 300 sec: 3832.1). Total num frames: 1597440. Throughput: 0: 950.1. Samples: 399384. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 14:57:17,064][03870] Avg episode reward: [(0, '12.136')]
[2024-08-21 14:57:17,065][05192] Saving new best policy, reward=12.136!
[2024-08-21 14:57:22,055][03870] Fps is (10 sec: 3686.3, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 1617920. Throughput: 0: 944.8. Samples: 405542. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 14:57:22,061][03870] Avg episode reward: [(0, '12.529')]
[2024-08-21 14:57:22,070][05192] Saving new best policy, reward=12.529!
[2024-08-21 14:57:26,188][05205] Updated weights for policy 0, policy_version 400 (0.0017)
[2024-08-21 14:57:27,055][03870] Fps is (10 sec: 4098.4, 60 sec: 3891.4, 300 sec: 3818.3). Total num frames: 1638400. Throughput: 0: 973.5. Samples: 408810. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-08-21 14:57:27,057][03870] Avg episode reward: [(0, '12.013')]
[2024-08-21 14:57:32,059][03870] Fps is (10 sec: 3685.0, 60 sec: 3822.7, 300 sec: 3818.3). Total num frames: 1654784. Throughput: 0: 969.3. Samples: 414044. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-08-21 14:57:32,061][03870] Avg episode reward: [(0, '12.149')]
[2024-08-21 14:57:37,055][03870] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 1675264. Throughput: 0: 931.1. Samples: 419194. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 14:57:37,058][03870] Avg episode reward: [(0, '12.991')]
[2024-08-21 14:57:37,063][05192] Saving new best policy, reward=12.991!
[2024-08-21 14:57:38,027][05205] Updated weights for policy 0, policy_version 410 (0.0022)
[2024-08-21 14:57:42,055][03870] Fps is (10 sec: 4097.6, 60 sec: 3891.3, 300 sec: 3818.3). Total num frames: 1695744. Throughput: 0: 947.7. Samples: 422518. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 14:57:42,057][03870] Avg episode reward: [(0, '13.216')]
[2024-08-21 14:57:42,065][05192] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000414_1695744.pth...
[2024-08-21 14:57:42,183][05192] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000191_782336.pth
[2024-08-21 14:57:42,204][05192] Saving new best policy, reward=13.216!
[2024-08-21 14:57:47,057][03870] Fps is (10 sec: 4095.2, 60 sec: 3891.1, 300 sec: 3818.3). Total num frames: 1716224. Throughput: 0: 988.8. Samples: 428912. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 14:57:47,059][03870] Avg episode reward: [(0, '14.315')]
[2024-08-21 14:57:47,065][05192] Saving new best policy, reward=14.315!
[2024-08-21 14:57:48,464][05205] Updated weights for policy 0, policy_version 420 (0.0023)
[2024-08-21 14:57:52,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 1728512. Throughput: 0: 926.8. Samples: 433108. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 14:57:52,060][03870] Avg episode reward: [(0, '14.327')]
[2024-08-21 14:57:52,078][05192] Saving new best policy, reward=14.327!
[2024-08-21 14:57:57,055][03870] Fps is (10 sec: 3277.3, 60 sec: 3822.9, 300 sec: 3804.4). Total num frames: 1748992. Throughput: 0: 921.0. Samples: 436342. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:57:57,058][03870] Avg episode reward: [(0, '14.182')]
[2024-08-21 14:57:58,843][05205] Updated weights for policy 0, policy_version 430 (0.0016)
[2024-08-21 14:58:02,055][03870] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 1773568. Throughput: 0: 973.1. Samples: 443168. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 14:58:02,057][03870] Avg episode reward: [(0, '15.608')]
[2024-08-21 14:58:02,071][05192] Saving new best policy, reward=15.608!
[2024-08-21 14:58:07,055][03870] Fps is (10 sec: 4096.2, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 1789952. Throughput: 0: 944.2. Samples: 448032. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:58:07,058][03870] Avg episode reward: [(0, '16.056')]
[2024-08-21 14:58:07,063][05192] Saving new best policy, reward=16.056!
[2024-08-21 14:58:10,842][05205] Updated weights for policy 0, policy_version 440 (0.0014)
[2024-08-21 14:58:12,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 1806336. Throughput: 0: 917.8. Samples: 450112. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-08-21 14:58:12,061][03870] Avg episode reward: [(0, '16.585')]
[2024-08-21 14:58:12,072][05192] Saving new best policy, reward=16.585!
[2024-08-21 14:58:17,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3891.6, 300 sec: 3818.3). Total num frames: 1830912. Throughput: 0: 951.9. Samples: 456874. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-08-21 14:58:17,061][03870] Avg episode reward: [(0, '18.063')]
[2024-08-21 14:58:17,063][05192] Saving new best policy, reward=18.063!
[2024-08-21 14:58:19,793][05205] Updated weights for policy 0, policy_version 450 (0.0015)
[2024-08-21 14:58:22,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 1847296. Throughput: 0: 970.5. Samples: 462866. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-08-21 14:58:22,059][03870] Avg episode reward: [(0, '18.469')]
[2024-08-21 14:58:22,069][05192] Saving new best policy, reward=18.469!
[2024-08-21 14:58:27,055][03870] Fps is (10 sec: 3276.7, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 1863680. Throughput: 0: 943.1. Samples: 464956. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 14:58:27,058][03870] Avg episode reward: [(0, '18.040')]
[2024-08-21 14:58:31,676][05205] Updated weights for policy 0, policy_version 460 (0.0022)
[2024-08-21 14:58:32,055][03870] Fps is (10 sec: 3686.3, 60 sec: 3823.2, 300 sec: 3818.3). Total num frames: 1884160. Throughput: 0: 930.1. Samples: 470766. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-08-21 14:58:32,058][03870] Avg episode reward: [(0, '18.323')]
[2024-08-21 14:58:37,055][03870] Fps is (10 sec: 4505.7, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 1908736. Throughput: 0: 991.7. Samples: 477736. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-08-21 14:58:37,058][03870] Avg episode reward: [(0, '17.190')]
[2024-08-21 14:58:42,056][03870] Fps is (10 sec: 3686.1, 60 sec: 3754.6, 300 sec: 3818.4). Total num frames: 1921024. Throughput: 0: 974.6. Samples: 480200. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-08-21 14:58:42,062][03870] Avg episode reward: [(0, '16.725')]
[2024-08-21 14:58:42,252][05205] Updated weights for policy 0, policy_version 470 (0.0016)
[2024-08-21 14:58:47,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3754.8, 300 sec: 3818.3). Total num frames: 1941504. Throughput: 0: 930.4. Samples: 485038. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-08-21 14:58:47,058][03870] Avg episode reward: [(0, '17.767')]
[2024-08-21 14:58:52,055][03870] Fps is (10 sec: 4096.4, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 1961984. Throughput: 0: 977.8. Samples: 492034. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 14:58:52,058][03870] Avg episode reward: [(0, '17.346')]
[2024-08-21 14:58:52,143][05205] Updated weights for policy 0, policy_version 480 (0.0024)
[2024-08-21 14:58:57,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 1982464. Throughput: 0: 1007.2. Samples: 495434. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-08-21 14:58:57,057][03870] Avg episode reward: [(0, '16.981')]
[2024-08-21 14:59:02,056][03870] Fps is (10 sec: 3686.1, 60 sec: 3754.6, 300 sec: 3832.2). Total num frames: 1998848. Throughput: 0: 951.4. Samples: 499688. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-08-21 14:59:02,058][03870] Avg episode reward: [(0, '17.739')]
[2024-08-21 14:59:03,677][05205] Updated weights for policy 0, policy_version 490 (0.0012)
[2024-08-21 14:59:07,055][03870] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 2019328. Throughput: 0: 957.9. Samples: 505970. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-08-21 14:59:07,061][03870] Avg episode reward: [(0, '18.833')]
[2024-08-21 14:59:07,065][05192] Saving new best policy, reward=18.833!
[2024-08-21 14:59:12,055][03870] Fps is (10 sec: 4506.0, 60 sec: 3959.5, 300 sec: 3832.2). Total num frames: 2043904. Throughput: 0: 986.3. Samples: 509338. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-08-21 14:59:12,058][03870] Avg episode reward: [(0, '17.849')]
[2024-08-21 14:59:12,667][05205] Updated weights for policy 0, policy_version 500 (0.0027)
[2024-08-21 14:59:17,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3846.1). Total num frames: 2060288. Throughput: 0: 976.1. Samples: 514692. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0)
[2024-08-21 14:59:17,058][03870] Avg episode reward: [(0, '17.960')]
[2024-08-21 14:59:22,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 2076672. Throughput: 0: 940.9. Samples: 520078. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0)
[2024-08-21 14:59:22,061][03870] Avg episode reward: [(0, '17.934')]
[2024-08-21 14:59:24,211][05205] Updated weights for policy 0, policy_version 510 (0.0037)
[2024-08-21 14:59:27,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3832.2). Total num frames: 2101248. Throughput: 0: 963.4. Samples: 523554. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-08-21 14:59:27,062][03870] Avg episode reward: [(0, '18.559')]
[2024-08-21 14:59:32,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 2117632. Throughput: 0: 994.0. Samples: 529766. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-08-21 14:59:32,063][03870] Avg episode reward: [(0, '18.996')]
[2024-08-21 14:59:32,070][05192] Saving new best policy, reward=18.996!
[2024-08-21 14:59:35,563][05205] Updated weights for policy 0, policy_version 520 (0.0016)
[2024-08-21 14:59:37,055][03870] Fps is (10 sec: 3276.7, 60 sec: 3754.7, 300 sec: 3832.2). Total num frames: 2134016. Throughput: 0: 930.4. Samples: 533902. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-08-21 14:59:37,060][03870] Avg episode reward: [(0, '20.783')]
[2024-08-21 14:59:37,063][05192] Saving new best policy, reward=20.783!
[2024-08-21 14:59:42,055][03870] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 2154496. Throughput: 0: 930.6. Samples: 537312. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-08-21 14:59:42,061][03870] Avg episode reward: [(0, '21.916')]
[2024-08-21 14:59:42,070][05192] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000526_2154496.pth...
[2024-08-21 14:59:42,240][05192] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000303_1241088.pth
[2024-08-21 14:59:42,256][05192] Saving new best policy, reward=21.916!
[2024-08-21 14:59:45,344][05205] Updated weights for policy 0, policy_version 530 (0.0017)
[2024-08-21 14:59:47,055][03870] Fps is (10 sec: 4505.7, 60 sec: 3959.5, 300 sec: 3832.2). Total num frames: 2179072. Throughput: 0: 985.9. Samples: 544052. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-08-21 14:59:47,057][03870] Avg episode reward: [(0, '23.098')]
[2024-08-21 14:59:47,065][05192] Saving new best policy, reward=23.098!
[2024-08-21 14:59:52,055][03870] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 2191360. Throughput: 0: 948.3. Samples: 548642. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-08-21 14:59:52,061][03870] Avg episode reward: [(0, '22.317')]
[2024-08-21 14:59:57,055][03870] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 2207744. Throughput: 0: 927.3. Samples: 551066. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 14:59:57,057][03870] Avg episode reward: [(0, '22.462')]
[2024-08-21 14:59:57,258][05205] Updated weights for policy 0, policy_version 540 (0.0029)
[2024-08-21 15:00:02,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3891.3, 300 sec: 3818.3). Total num frames: 2232320. Throughput: 0: 957.9. Samples: 557798. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 15:00:02,058][03870] Avg episode reward: [(0, '21.436')]
[2024-08-21 15:00:07,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 2248704. Throughput: 0: 966.6. Samples: 563576. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 15:00:07,057][03870] Avg episode reward: [(0, '20.184')]
[2024-08-21 15:00:07,180][05205] Updated weights for policy 0, policy_version 550 (0.0023)
[2024-08-21 15:00:12,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3818.3). Total num frames: 2265088. Throughput: 0: 937.0. Samples: 565718. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 15:00:12,061][03870] Avg episode reward: [(0, '20.460')]
[2024-08-21 15:00:17,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 2289664. Throughput: 0: 939.7. Samples: 572054. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 15:00:17,057][03870] Avg episode reward: [(0, '20.293')]
[2024-08-21 15:00:17,590][05205] Updated weights for policy 0, policy_version 560 (0.0034)
[2024-08-21 15:00:22,055][03870] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 2310144. Throughput: 0: 996.2. Samples: 578730. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:00:22,059][03870] Avg episode reward: [(0, '19.806')]
[2024-08-21 15:00:27,055][03870] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3832.3). Total num frames: 2326528. Throughput: 0: 966.5. Samples: 580806. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:00:27,061][03870] Avg episode reward: [(0, '19.632')]
[2024-08-21 15:00:29,536][05205] Updated weights for policy 0, policy_version 570 (0.0025)
[2024-08-21 15:00:32,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 2342912. Throughput: 0: 931.6. Samples: 585976. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 15:00:32,057][03870] Avg episode reward: [(0, '20.236')]
[2024-08-21 15:00:37,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 2367488. Throughput: 0: 983.9. Samples: 592918. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 15:00:37,061][03870] Avg episode reward: [(0, '19.927')]
[2024-08-21 15:00:38,287][05205] Updated weights for policy 0, policy_version 580 (0.0021)
[2024-08-21 15:00:42,057][03870] Fps is (10 sec: 4095.3, 60 sec: 3822.8, 300 sec: 3818.3). Total num frames: 2383872. Throughput: 0: 994.5. Samples: 595818. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:00:42,059][03870] Avg episode reward: [(0, '20.304')]
[2024-08-21 15:00:47,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3818.3). Total num frames: 2400256. Throughput: 0: 933.3. Samples: 599798. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 15:00:47,061][03870] Avg episode reward: [(0, '20.903')]
[2024-08-21 15:00:50,488][05205] Updated weights for policy 0, policy_version 590 (0.0039)
[2024-08-21 15:00:52,055][03870] Fps is (10 sec: 3687.0, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 2420736. Throughput: 0: 953.9. Samples: 606500. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-08-21 15:00:52,062][03870] Avg episode reward: [(0, '20.470')]
[2024-08-21 15:00:57,055][03870] Fps is (10 sec: 4095.9, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 2441216. Throughput: 0: 981.6. Samples: 609892. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-08-21 15:00:57,062][03870] Avg episode reward: [(0, '20.787')]
[2024-08-21 15:01:01,467][05205] Updated weights for policy 0, policy_version 600 (0.0016)
[2024-08-21 15:01:02,055][03870] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 2457600. Throughput: 0: 947.0. Samples: 614670. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-08-21 15:01:02,063][03870] Avg episode reward: [(0, '21.180')]
[2024-08-21 15:01:07,055][03870] Fps is (10 sec: 3686.5, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 2478080. Throughput: 0: 917.7. Samples: 620028. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 15:01:07,060][03870] Avg episode reward: [(0, '21.144')]
[2024-08-21 15:01:11,564][05205] Updated weights for policy 0, policy_version 610 (0.0019)
[2024-08-21 15:01:12,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 2498560. Throughput: 0: 946.5. Samples: 623400. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:01:12,059][03870] Avg episode reward: [(0, '20.265')]
[2024-08-21 15:01:17,057][03870] Fps is (10 sec: 3685.7, 60 sec: 3754.6, 300 sec: 3818.3). Total num frames: 2514944. Throughput: 0: 958.8. Samples: 629124. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-08-21 15:01:17,060][03870] Avg episode reward: [(0, '20.879')]
[2024-08-21 15:01:22,055][03870] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3804.5). Total num frames: 2527232. Throughput: 0: 894.2. Samples: 633156. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-08-21 15:01:22,059][03870] Avg episode reward: [(0, '20.569')]
[2024-08-21 15:01:24,093][05205] Updated weights for policy 0, policy_version 620 (0.0018)
[2024-08-21 15:01:27,055][03870] Fps is (10 sec: 3687.1, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 2551808. Throughput: 0: 898.3. Samples: 636242. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:01:27,057][03870] Avg episode reward: [(0, '21.881')]
[2024-08-21 15:01:32,055][03870] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 2572288. Throughput: 0: 953.0. Samples: 642684. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:01:32,058][03870] Avg episode reward: [(0, '23.626')]
[2024-08-21 15:01:32,076][05192] Saving new best policy, reward=23.626!
[2024-08-21 15:01:34,909][05205] Updated weights for policy 0, policy_version 630 (0.0013)
[2024-08-21 15:01:37,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3804.5). Total num frames: 2584576. Throughput: 0: 895.9. Samples: 646816. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-08-21 15:01:37,057][03870] Avg episode reward: [(0, '23.477')]
[2024-08-21 15:01:42,055][03870] Fps is (10 sec: 2867.2, 60 sec: 3618.2, 300 sec: 3790.5). Total num frames: 2600960. Throughput: 0: 875.0. Samples: 649266. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 15:01:42,058][03870] Avg episode reward: [(0, '23.801')]
[2024-08-21 15:01:42,069][05192] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000635_2600960.pth...
[2024-08-21 15:01:42,209][05192] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000414_1695744.pth
[2024-08-21 15:01:42,224][05192] Saving new best policy, reward=23.801!
[2024-08-21 15:01:46,264][05205] Updated weights for policy 0, policy_version 640 (0.0012)
[2024-08-21 15:01:47,057][03870] Fps is (10 sec: 3685.5, 60 sec: 3686.2, 300 sec: 3790.5). Total num frames: 2621440. Throughput: 0: 909.1. Samples: 655582. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:01:47,060][03870] Avg episode reward: [(0, '23.857')]
[2024-08-21 15:01:47,065][05192] Saving new best policy, reward=23.857!
[2024-08-21 15:01:52,055][03870] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3790.5). Total num frames: 2637824. Throughput: 0: 903.2. Samples: 660674. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:01:52,062][03870] Avg episode reward: [(0, '23.774')]
[2024-08-21 15:01:57,055][03870] Fps is (10 sec: 3277.6, 60 sec: 3549.9, 300 sec: 3776.7). Total num frames: 2654208. Throughput: 0: 872.4. Samples: 662660. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:01:57,063][03870] Avg episode reward: [(0, '23.616')]
[2024-08-21 15:01:58,775][05205] Updated weights for policy 0, policy_version 650 (0.0022)
[2024-08-21 15:02:02,055][03870] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3776.6). Total num frames: 2674688. Throughput: 0: 873.6. Samples: 668434. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:02:02,063][03870] Avg episode reward: [(0, '22.400')]
[2024-08-21 15:02:07,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3776.6). Total num frames: 2695168. Throughput: 0: 924.3. Samples: 674748. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-08-21 15:02:07,059][03870] Avg episode reward: [(0, '21.841')]
[2024-08-21 15:02:09,541][05205] Updated weights for policy 0, policy_version 660 (0.0024)
[2024-08-21 15:02:12,055][03870] Fps is (10 sec: 3276.7, 60 sec: 3481.6, 300 sec: 3762.8). Total num frames: 2707456. Throughput: 0: 900.7. Samples: 676772. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-08-21 15:02:12,058][03870] Avg episode reward: [(0, '22.252')]
[2024-08-21 15:02:17,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3550.0, 300 sec: 3762.8). Total num frames: 2727936. Throughput: 0: 868.9. Samples: 681784. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:02:17,057][03870] Avg episode reward: [(0, '23.392')]
[2024-08-21 15:02:20,043][05205] Updated weights for policy 0, policy_version 670 (0.0014)
[2024-08-21 15:02:22,055][03870] Fps is (10 sec: 4505.7, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 2752512. Throughput: 0: 930.7. Samples: 688696. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 15:02:22,062][03870] Avg episode reward: [(0, '23.483')]
[2024-08-21 15:02:27,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3776.7). Total num frames: 2768896. Throughput: 0: 944.8. Samples: 691780. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 15:02:27,058][03870] Avg episode reward: [(0, '24.727')]
[2024-08-21 15:02:27,059][05192] Saving new best policy, reward=24.727!
[2024-08-21 15:02:32,055][03870] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3748.9). Total num frames: 2781184. Throughput: 0: 896.3. Samples: 695912. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 15:02:32,062][03870] Avg episode reward: [(0, '26.223')]
[2024-08-21 15:02:32,144][05192] Saving new best policy, reward=26.223!
[2024-08-21 15:02:32,156][05205] Updated weights for policy 0, policy_version 680 (0.0032)
[2024-08-21 15:02:37,055][03870] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3762.8). Total num frames: 2805760. Throughput: 0: 925.8. Samples: 702336. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 15:02:37,063][03870] Avg episode reward: [(0, '26.225')]
[2024-08-21 15:02:37,065][05192] Saving new best policy, reward=26.225!
[2024-08-21 15:02:41,177][05205] Updated weights for policy 0, policy_version 690 (0.0025)
[2024-08-21 15:02:42,055][03870] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 2826240. Throughput: 0: 956.4. Samples: 705698. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-08-21 15:02:42,059][03870] Avg episode reward: [(0, '25.611')]
[2024-08-21 15:02:47,059][03870] Fps is (10 sec: 3684.9, 60 sec: 3686.3, 300 sec: 3776.6). Total num frames: 2842624. Throughput: 0: 940.6. Samples: 710764. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 15:02:47,061][03870] Avg episode reward: [(0, '24.308')]
[2024-08-21 15:02:52,055][03870] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 2863104. Throughput: 0: 924.4. Samples: 716344. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:02:52,062][03870] Avg episode reward: [(0, '24.399')]
[2024-08-21 15:02:52,818][05205] Updated weights for policy 0, policy_version 700 (0.0013)
[2024-08-21 15:02:57,055][03870] Fps is (10 sec: 4097.6, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 2883584. Throughput: 0: 955.8. Samples: 719784. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:02:57,063][03870] Avg episode reward: [(0, '21.818')]
[2024-08-21 15:03:02,056][03870] Fps is (10 sec: 4095.6, 60 sec: 3822.9, 300 sec: 3776.6). Total num frames: 2904064. Throughput: 0: 978.8. Samples: 725830. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:03:02,062][03870] Avg episode reward: [(0, '21.356')]
[2024-08-21 15:03:03,456][05205] Updated weights for policy 0, policy_version 710 (0.0027)
[2024-08-21 15:03:07,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3762.8). Total num frames: 2916352. Throughput: 0: 924.4. Samples: 730294. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 15:03:07,062][03870] Avg episode reward: [(0, '21.262')]
[2024-08-21 15:03:12,055][03870] Fps is (10 sec: 3686.7, 60 sec: 3891.2, 300 sec: 3762.8). Total num frames: 2940928. Throughput: 0: 930.8. Samples: 733668. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-08-21 15:03:12,057][03870] Avg episode reward: [(0, '22.012')]
[2024-08-21 15:03:13,501][05205] Updated weights for policy 0, policy_version 720 (0.0015)
[2024-08-21 15:03:17,055][03870] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3776.7). Total num frames: 2961408. Throughput: 0: 989.5. Samples: 740440. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:03:17,060][03870] Avg episode reward: [(0, '20.580')]
[2024-08-21 15:03:22,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3762.8). Total num frames: 2973696. Throughput: 0: 946.2. Samples: 744916. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:03:22,061][03870] Avg episode reward: [(0, '21.644')]
[2024-08-21 15:03:25,496][05205] Updated weights for policy 0, policy_version 730 (0.0020)
[2024-08-21 15:03:27,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 2994176. Throughput: 0: 926.9. Samples: 747408. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:03:27,057][03870] Avg episode reward: [(0, '20.887')]
[2024-08-21 15:03:32,055][03870] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3762.8). Total num frames: 3018752. Throughput: 0: 965.5. Samples: 754208. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 15:03:32,057][03870] Avg episode reward: [(0, '20.595')]
[2024-08-21 15:03:34,728][05205] Updated weights for policy 0, policy_version 740 (0.0017)
[2024-08-21 15:03:37,055][03870] Fps is (10 sec: 4095.9, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 3035136. Throughput: 0: 966.0. Samples: 759812. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:03:37,057][03870] Avg episode reward: [(0, '21.060')]
[2024-08-21 15:03:42,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 3051520. Throughput: 0: 937.0. Samples: 761950. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:03:42,061][03870] Avg episode reward: [(0, '21.663')]
[2024-08-21 15:03:42,069][05192] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000745_3051520.pth...
[2024-08-21 15:03:42,203][05192] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000526_2154496.pth
[2024-08-21 15:03:46,250][05205] Updated weights for policy 0, policy_version 750 (0.0029)
[2024-08-21 15:03:47,055][03870] Fps is (10 sec: 3686.5, 60 sec: 3823.2, 300 sec: 3762.8). Total num frames: 3072000. Throughput: 0: 940.9. Samples: 768170. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:03:47,058][03870] Avg episode reward: [(0, '20.751')]
[2024-08-21 15:03:52,057][03870] Fps is (10 sec: 4504.8, 60 sec: 3891.1, 300 sec: 3776.6). Total num frames: 3096576. Throughput: 0: 990.4. Samples: 774864. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-08-21 15:03:52,060][03870] Avg episode reward: [(0, '19.478')]
[2024-08-21 15:03:57,055][03870] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 3108864. Throughput: 0: 960.9. Samples: 776910. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 15:03:57,059][03870] Avg episode reward: [(0, '19.503')]
[2024-08-21 15:03:57,837][05205] Updated weights for policy 0, policy_version 760 (0.0025)
[2024-08-21 15:04:02,055][03870] Fps is (10 sec: 2867.8, 60 sec: 3686.5, 300 sec: 3748.9). Total num frames: 3125248. Throughput: 0: 916.0. Samples: 781662. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-08-21 15:04:02,057][03870] Avg episode reward: [(0, '20.400')]
[2024-08-21 15:04:07,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3748.9). Total num frames: 3149824. Throughput: 0: 962.6. Samples: 788232. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-08-21 15:04:07,062][03870] Avg episode reward: [(0, '20.110')]
[2024-08-21 15:04:07,722][05205] Updated weights for policy 0, policy_version 770 (0.0023)
[2024-08-21 15:04:12,055][03870] Fps is (10 sec: 4095.9, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 3166208. Throughput: 0: 971.9. Samples: 791142. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 15:04:12,058][03870] Avg episode reward: [(0, '20.884')]
[2024-08-21 15:04:17,055][03870] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3735.0). Total num frames: 3178496. Throughput: 0: 912.5. Samples: 795270. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:04:17,058][03870] Avg episode reward: [(0, '22.462')]
[2024-08-21 15:04:19,982][05205] Updated weights for policy 0, policy_version 780 (0.0030)
[2024-08-21 15:04:22,055][03870] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 3203072. Throughput: 0: 926.4. Samples: 801498. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 15:04:22,057][03870] Avg episode reward: [(0, '22.944')]
[2024-08-21 15:04:27,061][03870] Fps is (10 sec: 4502.9, 60 sec: 3822.6, 300 sec: 3748.8). Total num frames: 3223552. Throughput: 0: 953.6. Samples: 804868. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:04:27,063][03870] Avg episode reward: [(0, '21.821')]
[2024-08-21 15:04:31,099][05205] Updated weights for policy 0, policy_version 790 (0.0025)
[2024-08-21 15:04:32,055][03870] Fps is (10 sec: 3276.7, 60 sec: 3618.1, 300 sec: 3735.0). Total num frames: 3235840. Throughput: 0: 919.9. Samples: 809566. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 15:04:32,059][03870] Avg episode reward: [(0, '23.153')]
[2024-08-21 15:04:37,055][03870] Fps is (10 sec: 2868.9, 60 sec: 3618.1, 300 sec: 3721.1). Total num frames: 3252224. Throughput: 0: 881.6. Samples: 814536. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-08-21 15:04:37,062][03870] Avg episode reward: [(0, '23.246')]
[2024-08-21 15:04:41,933][05205] Updated weights for policy 0, policy_version 800 (0.0022)
[2024-08-21 15:04:42,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 3276800. Throughput: 0: 907.1. Samples: 817730. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-08-21 15:04:42,063][03870] Avg episode reward: [(0, '21.923')]
[2024-08-21 15:04:47,055][03870] Fps is (10 sec: 4095.8, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 3293184. Throughput: 0: 926.4. Samples: 823352. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 15:04:47,059][03870] Avg episode reward: [(0, '22.408')]
[2024-08-21 15:04:52,055][03870] Fps is (10 sec: 2867.3, 60 sec: 3481.7, 300 sec: 3721.1). Total num frames: 3305472. Throughput: 0: 867.1. Samples: 827250. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-08-21 15:04:52,064][03870] Avg episode reward: [(0, '22.264')]
[2024-08-21 15:04:54,839][05205] Updated weights for policy 0, policy_version 810 (0.0022)
[2024-08-21 15:04:57,055][03870] Fps is (10 sec: 3276.9, 60 sec: 3618.1, 300 sec: 3707.2). Total num frames: 3325952. Throughput: 0: 869.4. Samples: 830266. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-08-21 15:04:57,063][03870] Avg episode reward: [(0, '25.312')]
[2024-08-21 15:05:02,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 3346432. Throughput: 0: 920.6. Samples: 836696. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-08-21 15:05:02,057][03870] Avg episode reward: [(0, '24.335')]
[2024-08-21 15:05:05,780][05205] Updated weights for policy 0, policy_version 820 (0.0020)
[2024-08-21 15:05:07,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3707.2). Total num frames: 3358720. Throughput: 0: 880.0. Samples: 841096. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-08-21 15:05:07,060][03870] Avg episode reward: [(0, '25.378')]
[2024-08-21 15:05:12,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3693.3). Total num frames: 3379200. Throughput: 0: 853.0. Samples: 843248. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2024-08-21 15:05:12,063][03870] Avg episode reward: [(0, '25.126')]
[2024-08-21 15:05:16,755][05205] Updated weights for policy 0, policy_version 830 (0.0013)
[2024-08-21 15:05:17,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 3399680. Throughput: 0: 892.1. Samples: 849712. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2024-08-21 15:05:17,063][03870] Avg episode reward: [(0, '24.993')]
[2024-08-21 15:05:22,057][03870] Fps is (10 sec: 3685.7, 60 sec: 3549.8, 300 sec: 3693.3). Total num frames: 3416064. Throughput: 0: 908.9. Samples: 855436. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-08-21 15:05:22,060][03870] Avg episode reward: [(0, '24.854')]
[2024-08-21 15:05:27,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3481.9, 300 sec: 3693.3). Total num frames: 3432448. Throughput: 0: 882.4. Samples: 857438. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:05:27,060][03870] Avg episode reward: [(0, '23.699')]
[2024-08-21 15:05:28,776][05205] Updated weights for policy 0, policy_version 840 (0.0043)
[2024-08-21 15:05:32,055][03870] Fps is (10 sec: 3687.1, 60 sec: 3618.2, 300 sec: 3679.5). Total num frames: 3452928. Throughput: 0: 883.9. Samples: 863126. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:05:32,065][03870] Avg episode reward: [(0, '22.673')]
[2024-08-21 15:05:37,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3693.4). Total num frames: 3473408. Throughput: 0: 945.4. Samples: 869794. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-08-21 15:05:37,070][03870] Avg episode reward: [(0, '22.231')]
[2024-08-21 15:05:38,641][05205] Updated weights for policy 0, policy_version 850 (0.0018)
[2024-08-21 15:05:42,055][03870] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3693.3). Total num frames: 3489792. Throughput: 0: 925.9. Samples: 871932. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-08-21 15:05:42,058][03870] Avg episode reward: [(0, '22.556')]
[2024-08-21 15:05:42,073][05192] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000852_3489792.pth...
[2024-08-21 15:05:42,219][05192] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000635_2600960.pth
[2024-08-21 15:05:47,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3679.5). Total num frames: 3506176. Throughput: 0: 880.6. Samples: 876322. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 15:05:47,057][03870] Avg episode reward: [(0, '22.565')]
[2024-08-21 15:05:50,510][05205] Updated weights for policy 0, policy_version 860 (0.0022)
[2024-08-21 15:05:52,055][03870] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 3526656. Throughput: 0: 927.2. Samples: 882818. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 15:05:52,062][03870] Avg episode reward: [(0, '21.371')]
[2024-08-21 15:05:57,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 3547136. Throughput: 0: 949.3. Samples: 885966. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:05:57,058][03870] Avg episode reward: [(0, '23.462')]
[2024-08-21 15:06:02,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3665.6). Total num frames: 3559424. Throughput: 0: 892.7. Samples: 889882. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-08-21 15:06:02,062][03870] Avg episode reward: [(0, '22.969')]
[2024-08-21 15:06:03,264][05205] Updated weights for policy 0, policy_version 870 (0.0024)
[2024-08-21 15:06:07,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3579904. Throughput: 0: 891.3. Samples: 895544. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 15:06:07,057][03870] Avg episode reward: [(0, '23.713')]
[2024-08-21 15:06:12,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 3600384. Throughput: 0: 919.2. Samples: 898802. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 15:06:12,059][03870] Avg episode reward: [(0, '25.340')]
[2024-08-21 15:06:12,697][05205] Updated weights for policy 0, policy_version 880 (0.0029)
[2024-08-21 15:06:17,058][03870] Fps is (10 sec: 3275.8, 60 sec: 3549.7, 300 sec: 3679.4). Total num frames: 3612672. Throughput: 0: 906.3. Samples: 903914. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 15:06:17,060][03870] Avg episode reward: [(0, '25.137')]
[2024-08-21 15:06:22,055][03870] Fps is (10 sec: 2867.2, 60 sec: 3550.0, 300 sec: 3651.7). Total num frames: 3629056. Throughput: 0: 861.6. Samples: 908568. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 15:06:22,061][03870] Avg episode reward: [(0, '25.549')]
[2024-08-21 15:06:25,018][05205] Updated weights for policy 0, policy_version 890 (0.0038)
[2024-08-21 15:06:27,055][03870] Fps is (10 sec: 4097.2, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3653632. Throughput: 0: 886.5. Samples: 911824. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 15:06:27,061][03870] Avg episode reward: [(0, '24.811')]
[2024-08-21 15:06:32,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3679.5). Total num frames: 3670016. Throughput: 0: 925.8. Samples: 917982. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-08-21 15:06:32,059][03870] Avg episode reward: [(0, '23.219')]
[2024-08-21 15:06:37,055][03870] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3665.6). Total num frames: 3682304. Throughput: 0: 871.0. Samples: 922014. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-08-21 15:06:37,062][03870] Avg episode reward: [(0, '22.661')]
[2024-08-21 15:06:37,178][05205] Updated weights for policy 0, policy_version 900 (0.0035)
[2024-08-21 15:06:42,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3665.6). Total num frames: 3702784. Throughput: 0: 862.6. Samples: 924782. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:06:42,061][03870] Avg episode reward: [(0, '20.757')]
[2024-08-21 15:06:47,029][05205] Updated weights for policy 0, policy_version 910 (0.0019)
[2024-08-21 15:06:47,055][03870] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 3727360. Throughput: 0: 920.2. Samples: 931292. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:06:47,057][03870] Avg episode reward: [(0, '21.552')]
[2024-08-21 15:06:52,055][03870] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3679.5). Total num frames: 3739648. Throughput: 0: 904.6. Samples: 936250. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-08-21 15:06:52,057][03870] Avg episode reward: [(0, '20.555')]
[2024-08-21 15:06:57,055][03870] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3665.6). Total num frames: 3756032. Throughput: 0: 878.0. Samples: 938310. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 15:06:57,057][03870] Avg episode reward: [(0, '20.290')]
[2024-08-21 15:06:59,345][05205] Updated weights for policy 0, policy_version 920 (0.0024)
[2024-08-21 15:07:02,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 3780608. Throughput: 0: 903.1. Samples: 944550. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:07:02,058][03870] Avg episode reward: [(0, '19.987')]
[2024-08-21 15:07:07,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3693.3). Total num frames: 3796992. Throughput: 0: 933.7. Samples: 950584. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-08-21 15:07:07,057][03870] Avg episode reward: [(0, '20.286')]
[2024-08-21 15:07:10,311][05205] Updated weights for policy 0, policy_version 930 (0.0032)
[2024-08-21 15:07:12,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3679.5). Total num frames: 3813376. Throughput: 0: 905.1. Samples: 952554. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 15:07:12,061][03870] Avg episode reward: [(0, '19.763')]
[2024-08-21 15:07:17,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3618.3, 300 sec: 3651.7). Total num frames: 3829760. Throughput: 0: 883.8. Samples: 957752. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-08-21 15:07:17,058][03870] Avg episode reward: [(0, '19.514')]
[2024-08-21 15:07:20,876][05205] Updated weights for policy 0, policy_version 940 (0.0019)
[2024-08-21 15:07:22,056][03870] Fps is (10 sec: 4095.6, 60 sec: 3754.6, 300 sec: 3679.4). Total num frames: 3854336. Throughput: 0: 939.2. Samples: 964280. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-08-21 15:07:22,058][03870] Avg episode reward: [(0, '19.752')]
[2024-08-21 15:07:27,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3693.3). Total num frames: 3870720. Throughput: 0: 936.0. Samples: 966904. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 15:07:27,057][03870] Avg episode reward: [(0, '20.861')]
[2024-08-21 15:07:32,055][03870] Fps is (10 sec: 2867.5, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 3883008. Throughput: 0: 879.4. Samples: 970866. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2024-08-21 15:07:32,058][03870] Avg episode reward: [(0, '21.917')]
[2024-08-21 15:07:33,522][05205] Updated weights for policy 0, policy_version 950 (0.0015)
[2024-08-21 15:07:37,055][03870] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 3903488. Throughput: 0: 907.4. Samples: 977082. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 15:07:37,058][03870] Avg episode reward: [(0, '22.439')]
[2024-08-21 15:07:42,062][03870] Fps is (10 sec: 4093.2, 60 sec: 3686.0, 300 sec: 3665.5). Total num frames: 3923968. Throughput: 0: 934.3. Samples: 980360. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 15:07:42,064][03870] Avg episode reward: [(0, '24.520')]
[2024-08-21 15:07:42,082][05192] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000958_3923968.pth...
[2024-08-21 15:07:42,255][05192] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000745_3051520.pth
[2024-08-21 15:07:43,976][05205] Updated weights for policy 0, policy_version 960 (0.0015)
[2024-08-21 15:07:47,055][03870] Fps is (10 sec: 3276.7, 60 sec: 3481.6, 300 sec: 3637.8). Total num frames: 3936256. Throughput: 0: 895.4. Samples: 984844. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-08-21 15:07:47,057][03870] Avg episode reward: [(0, '24.836')]
[2024-08-21 15:07:52,055][03870] Fps is (10 sec: 3279.1, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 3956736. Throughput: 0: 884.4. Samples: 990382. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 15:07:52,057][03870] Avg episode reward: [(0, '25.830')]
[2024-08-21 15:07:54,957][05205] Updated weights for policy 0, policy_version 970 (0.0022)
[2024-08-21 15:07:57,055][03870] Fps is (10 sec: 4505.7, 60 sec: 3754.7, 300 sec: 3651.7). Total num frames: 3981312. Throughput: 0: 915.2. Samples: 993740. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-08-21 15:07:57,060][03870] Avg episode reward: [(0, '26.238')]
[2024-08-21 15:07:57,062][05192] Saving new best policy, reward=26.238!
[2024-08-21 15:08:02,055][03870] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3665.6). Total num frames: 3997696. Throughput: 0: 925.2. Samples: 999386. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-08-21 15:08:02,064][03870] Avg episode reward: [(0, '25.468')]
[2024-08-21 15:08:04,840][05192] Stopping Batcher_0...
[2024-08-21 15:08:04,841][05192] Loop batcher_evt_loop terminating...
[2024-08-21 15:08:04,842][03870] Component Batcher_0 stopped!
[2024-08-21 15:08:04,848][05192] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2024-08-21 15:08:04,912][05205] Weights refcount: 2 0
[2024-08-21 15:08:04,923][03870] Component InferenceWorker_p0-w0 stopped!
[2024-08-21 15:08:04,927][05205] Stopping InferenceWorker_p0-w0...
[2024-08-21 15:08:04,928][05205] Loop inference_proc0-0_evt_loop terminating...
[2024-08-21 15:08:05,022][05192] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000852_3489792.pth
[2024-08-21 15:08:05,036][05192] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2024-08-21 15:08:05,270][03870] Component LearnerWorker_p0 stopped!
[2024-08-21 15:08:05,272][05192] Stopping LearnerWorker_p0...
[2024-08-21 15:08:05,273][05192] Loop learner_proc0_evt_loop terminating...
[2024-08-21 15:08:05,466][03870] Component RolloutWorker_w2 stopped!
[2024-08-21 15:08:05,465][05208] Stopping RolloutWorker_w2...
[2024-08-21 15:08:05,472][05208] Loop rollout_proc2_evt_loop terminating...
[2024-08-21 15:08:05,529][05206] Stopping RolloutWorker_w0...
[2024-08-21 15:08:05,530][05206] Loop rollout_proc0_evt_loop terminating...
[2024-08-21 15:08:05,530][03870] Component RolloutWorker_w0 stopped!
[2024-08-21 15:08:05,631][03870] Component RolloutWorker_w6 stopped!
[2024-08-21 15:08:05,639][03870] Component RolloutWorker_w4 stopped!
[2024-08-21 15:08:05,638][05210] Stopping RolloutWorker_w4...
[2024-08-21 15:08:05,630][05212] Stopping RolloutWorker_w6...
[2024-08-21 15:08:05,646][05212] Loop rollout_proc6_evt_loop terminating...
[2024-08-21 15:08:05,645][05210] Loop rollout_proc4_evt_loop terminating...
[2024-08-21 15:08:05,713][03870] Component RolloutWorker_w3 stopped!
[2024-08-21 15:08:05,716][05209] Stopping RolloutWorker_w3...
[2024-08-21 15:08:05,716][05209] Loop rollout_proc3_evt_loop terminating...
[2024-08-21 15:08:05,729][03870] Component RolloutWorker_w5 stopped!
[2024-08-21 15:08:05,731][05211] Stopping RolloutWorker_w5...
[2024-08-21 15:08:05,737][03870] Component RolloutWorker_w7 stopped!
[2024-08-21 15:08:05,739][05213] Stopping RolloutWorker_w7...
[2024-08-21 15:08:05,739][05213] Loop rollout_proc7_evt_loop terminating...
[2024-08-21 15:08:05,740][05211] Loop rollout_proc5_evt_loop terminating...
[2024-08-21 15:08:05,769][03870] Component RolloutWorker_w1 stopped!
[2024-08-21 15:08:05,772][03870] Waiting for process learner_proc0 to stop...
[2024-08-21 15:08:05,775][05207] Stopping RolloutWorker_w1...
[2024-08-21 15:08:05,776][05207] Loop rollout_proc1_evt_loop terminating...
[2024-08-21 15:08:07,180][03870] Waiting for process inference_proc0-0 to join...
[2024-08-21 15:08:07,426][03870] Waiting for process rollout_proc0 to join...
[2024-08-21 15:08:08,715][03870] Waiting for process rollout_proc1 to join...
[2024-08-21 15:08:08,723][03870] Waiting for process rollout_proc2 to join...
[2024-08-21 15:08:08,727][03870] Waiting for process rollout_proc3 to join...
[2024-08-21 15:08:08,732][03870] Waiting for process rollout_proc4 to join...
[2024-08-21 15:08:08,734][03870] Waiting for process rollout_proc5 to join...
[2024-08-21 15:08:08,739][03870] Waiting for process rollout_proc6 to join...
[2024-08-21 15:08:08,743][03870] Waiting for process rollout_proc7 to join...
[2024-08-21 15:08:08,746][03870] Batcher 0 profile tree view:
batching: 25.8921, releasing_batches: 0.0255
[2024-08-21 15:08:08,748][03870] InferenceWorker_p0-w0 profile tree view:
wait_policy: 0.0001
  wait_policy_total: 453.6315
update_model: 8.4067
  weight_update: 0.0012
one_step: 0.0141
  handle_policy_step: 573.6477
    deserialize: 14.7889, stack: 3.0817, obs_to_device_normalize: 118.8507, forward: 289.5693, send_messages: 28.6958
    prepare_outputs: 89.6752
      to_cpu: 56.2569
[2024-08-21 15:08:08,750][03870] Learner 0 profile tree view:
misc: 0.0051, prepare_batch: 17.0808
train: 74.8022
  epoch_init: 0.0122, minibatch_init: 0.0157, losses_postprocess: 0.5738, kl_divergence: 0.6322, after_optimizer: 33.5126
  calculate_losses: 24.8185
    losses_init: 0.0037, forward_head: 1.7217, bptt_initial: 15.8632, tail: 1.1034, advantages_returns: 0.3077, losses: 2.9928
    bptt: 2.4379
      bptt_forward_core: 2.3364
  update: 14.6129
    clip: 1.4352
[2024-08-21 15:08:08,752][03870] RolloutWorker_w0 profile tree view:
wait_for_trajectories: 0.3191, enqueue_policy_requests: 114.5895, env_step: 834.7235, overhead: 14.2164, complete_rollouts: 6.9117
save_policy_outputs: 27.2778
  split_output_tensors: 9.2283
[2024-08-21 15:08:08,753][03870] RolloutWorker_w7 profile tree view:
wait_for_trajectories: 0.3561, enqueue_policy_requests: 113.6438, env_step: 837.6109, overhead: 14.6146, complete_rollouts: 7.0266
save_policy_outputs: 25.3165
  split_output_tensors: 8.6268
[2024-08-21 15:08:08,754][03870] Loop Runner_EvtLoop terminating...
[2024-08-21 15:08:08,756][03870] Runner profile tree view:
main_loop: 1103.2235
[2024-08-21 15:08:08,757][03870] Collected {0: 4005888}, FPS: 3631.1
[2024-08-21 15:08:08,985][03870] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
[2024-08-21 15:08:08,987][03870] Overriding arg 'num_workers' with value 1 passed from command line
[2024-08-21 15:08:08,988][03870] Adding new argument 'no_render'=True that is not in the saved config file!
[2024-08-21 15:08:08,990][03870] Adding new argument 'save_video'=True that is not in the saved config file!
[2024-08-21 15:08:08,992][03870] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2024-08-21 15:08:08,994][03870] Adding new argument 'video_name'=None that is not in the saved config file!
[2024-08-21 15:08:08,995][03870] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
[2024-08-21 15:08:08,997][03870] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2024-08-21 15:08:08,998][03870] Adding new argument 'push_to_hub'=False that is not in the saved config file!
[2024-08-21 15:08:08,999][03870] Adding new argument 'hf_repository'=None that is not in the saved config file!
[2024-08-21 15:08:09,000][03870] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2024-08-21 15:08:09,001][03870] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2024-08-21 15:08:09,002][03870] Adding new argument 'train_script'=None that is not in the saved config file!
[2024-08-21 15:08:09,006][03870] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2024-08-21 15:08:09,008][03870] Using frameskip 1 and render_action_repeat=4 for evaluation
[2024-08-21 15:08:09,024][03870] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-08-21 15:08:09,026][03870] RunningMeanStd input shape: (3, 72, 128)
[2024-08-21 15:08:09,028][03870] RunningMeanStd input shape: (1,)
[2024-08-21 15:08:09,044][03870] ConvEncoder: input_channels=3
[2024-08-21 15:08:09,170][03870] Conv encoder output size: 512
[2024-08-21 15:08:09,173][03870] Policy head output size: 512
[2024-08-21 15:08:10,770][03870] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2024-08-21 15:08:11,646][03870] Num frames 100...
[2024-08-21 15:08:11,765][03870] Num frames 200...
[2024-08-21 15:08:11,884][03870] Num frames 300...
[2024-08-21 15:08:12,008][03870] Num frames 400...
[2024-08-21 15:08:12,135][03870] Num frames 500...
[2024-08-21 15:08:12,251][03870] Num frames 600...
[2024-08-21 15:08:12,396][03870] Avg episode rewards: #0: 12.720, true rewards: #0: 6.720
[2024-08-21 15:08:12,398][03870] Avg episode reward: 12.720, avg true_objective: 6.720
[2024-08-21 15:08:12,438][03870] Num frames 700...
[2024-08-21 15:08:12,562][03870] Num frames 800...
[2024-08-21 15:08:12,692][03870] Num frames 900...
[2024-08-21 15:08:12,815][03870] Num frames 1000...
[2024-08-21 15:08:12,936][03870] Num frames 1100...
[2024-08-21 15:08:13,062][03870] Num frames 1200...
[2024-08-21 15:08:13,138][03870] Avg episode rewards: #0: 10.080, true rewards: #0: 6.080
[2024-08-21 15:08:13,140][03870] Avg episode reward: 10.080, avg true_objective: 6.080
[2024-08-21 15:08:13,244][03870] Num frames 1300...
[2024-08-21 15:08:13,363][03870] Num frames 1400...
[2024-08-21 15:08:13,485][03870] Num frames 1500...
[2024-08-21 15:08:13,609][03870] Num frames 1600...
[2024-08-21 15:08:13,730][03870] Num frames 1700...
[2024-08-21 15:08:13,851][03870] Num frames 1800...
[2024-08-21 15:08:13,974][03870] Num frames 1900...
[2024-08-21 15:08:14,106][03870] Num frames 2000...
[2024-08-21 15:08:14,225][03870] Num frames 2100...
[2024-08-21 15:08:14,342][03870] Num frames 2200...
[2024-08-21 15:08:14,466][03870] Num frames 2300...
[2024-08-21 15:08:14,598][03870] Num frames 2400...
[2024-08-21 15:08:14,724][03870] Num frames 2500...
[2024-08-21 15:08:14,844][03870] Num frames 2600...
[2024-08-21 15:08:14,928][03870] Avg episode rewards: #0: 19.747, true rewards: #0: 8.747
[2024-08-21 15:08:14,930][03870] Avg episode reward: 19.747, avg true_objective: 8.747
[2024-08-21 15:08:15,019][03870] Num frames 2700...
[2024-08-21 15:08:15,148][03870] Num frames 2800...
[2024-08-21 15:08:15,271][03870] Num frames 2900...
[2024-08-21 15:08:15,397][03870] Num frames 3000...
[2024-08-21 15:08:15,518][03870] Num frames 3100...
[2024-08-21 15:08:15,644][03870] Num frames 3200...
[2024-08-21 15:08:15,763][03870] Num frames 3300...
[2024-08-21 15:08:15,882][03870] Num frames 3400...
[2024-08-21 15:08:16,002][03870] Num frames 3500...
[2024-08-21 15:08:16,082][03870] Avg episode rewards: #0: 19.550, true rewards: #0: 8.800
[2024-08-21 15:08:16,083][03870] Avg episode reward: 19.550, avg true_objective: 8.800
[2024-08-21 15:08:16,199][03870] Num frames 3600...
[2024-08-21 15:08:16,365][03870] Num frames 3700...
[2024-08-21 15:08:16,532][03870] Num frames 3800...
[2024-08-21 15:08:16,706][03870] Num frames 3900...
[2024-08-21 15:08:16,874][03870] Num frames 4000...
[2024-08-21 15:08:17,036][03870] Num frames 4100...
[2024-08-21 15:08:17,212][03870] Num frames 4200...
[2024-08-21 15:08:17,367][03870] Num frames 4300...
[2024-08-21 15:08:17,536][03870] Num frames 4400...
[2024-08-21 15:08:17,623][03870] Avg episode rewards: #0: 19.432, true rewards: #0: 8.832
[2024-08-21 15:08:17,626][03870] Avg episode reward: 19.432, avg true_objective: 8.832
[2024-08-21 15:08:17,768][03870] Num frames 4500...
[2024-08-21 15:08:17,947][03870] Num frames 4600...
[2024-08-21 15:08:18,124][03870] Num frames 4700...
[2024-08-21 15:08:18,298][03870] Num frames 4800...
[2024-08-21 15:08:18,471][03870] Num frames 4900...
[2024-08-21 15:08:18,657][03870] Num frames 5000...
[2024-08-21 15:08:18,815][03870] Num frames 5100...
[2024-08-21 15:08:18,940][03870] Num frames 5200...
[2024-08-21 15:08:19,058][03870] Num frames 5300...
[2024-08-21 15:08:19,179][03870] Num frames 5400...
[2024-08-21 15:08:19,306][03870] Num frames 5500...
[2024-08-21 15:08:19,433][03870] Num frames 5600...
[2024-08-21 15:08:19,604][03870] Avg episode rewards: #0: 21.323, true rewards: #0: 9.490
[2024-08-21 15:08:19,606][03870] Avg episode reward: 21.323, avg true_objective: 9.490
[2024-08-21 15:08:19,618][03870] Num frames 5700...
[2024-08-21 15:08:19,738][03870] Num frames 5800...
[2024-08-21 15:08:19,857][03870] Num frames 5900...
[2024-08-21 15:08:19,976][03870] Num frames 6000...
[2024-08-21 15:08:20,092][03870] Num frames 6100...
[2024-08-21 15:08:20,212][03870] Num frames 6200...
[2024-08-21 15:08:20,342][03870] Num frames 6300...
[2024-08-21 15:08:20,462][03870] Num frames 6400...
[2024-08-21 15:08:20,590][03870] Avg episode rewards: #0: 20.374, true rewards: #0: 9.231
[2024-08-21 15:08:20,592][03870] Avg episode reward: 20.374, avg true_objective: 9.231
[2024-08-21 15:08:20,647][03870] Num frames 6500...
[2024-08-21 15:08:20,770][03870] Num frames 6600...
[2024-08-21 15:08:20,891][03870] Num frames 6700...
[2024-08-21 15:08:21,013][03870] Num frames 6800...
[2024-08-21 15:08:21,132][03870] Num frames 6900...
[2024-08-21 15:08:21,261][03870] Num frames 7000...
[2024-08-21 15:08:21,391][03870] Num frames 7100...
[2024-08-21 15:08:21,513][03870] Num frames 7200...
[2024-08-21 15:08:21,642][03870] Num frames 7300...
[2024-08-21 15:08:21,762][03870] Num frames 7400...
[2024-08-21 15:08:21,882][03870] Num frames 7500...
[2024-08-21 15:08:22,002][03870] Num frames 7600...
[2024-08-21 15:08:22,125][03870] Num frames 7700...
[2024-08-21 15:08:22,246][03870] Num frames 7800...
[2024-08-21 15:08:22,374][03870] Num frames 7900...
[2024-08-21 15:08:22,497][03870] Num frames 8000...
[2024-08-21 15:08:22,670][03870] Avg episode rewards: #0: 23.243, true rewards: #0: 10.117
[2024-08-21 15:08:22,672][03870] Avg episode reward: 23.243, avg true_objective: 10.117
[2024-08-21 15:08:22,682][03870] Num frames 8100...
[2024-08-21 15:08:22,805][03870] Num frames 8200...
[2024-08-21 15:08:22,923][03870] Num frames 8300...
[2024-08-21 15:08:23,040][03870] Num frames 8400...
[2024-08-21 15:08:23,164][03870] Num frames 8500...
[2024-08-21 15:08:23,282][03870] Num frames 8600...
[2024-08-21 15:08:23,410][03870] Num frames 8700...
[2024-08-21 15:08:23,530][03870] Num frames 8800...
[2024-08-21 15:08:23,660][03870] Num frames 8900...
[2024-08-21 15:08:23,790][03870] Num frames 9000...
[2024-08-21 15:08:23,911][03870] Num frames 9100...
[2024-08-21 15:08:24,031][03870] Num frames 9200...
[2024-08-21 15:08:24,154][03870] Num frames 9300...
[2024-08-21 15:08:24,277][03870] Num frames 9400...
[2024-08-21 15:08:24,404][03870] Num frames 9500...
[2024-08-21 15:08:24,564][03870] Avg episode rewards: #0: 24.987, true rewards: #0: 10.653
[2024-08-21 15:08:24,565][03870] Avg episode reward: 24.987, avg true_objective: 10.653
[2024-08-21 15:08:24,585][03870] Num frames 9600...
[2024-08-21 15:08:24,714][03870] Num frames 9700...
[2024-08-21 15:08:24,836][03870] Num frames 9800...
[2024-08-21 15:08:24,957][03870] Num frames 9900...
[2024-08-21 15:08:25,078][03870] Num frames 10000...
[2024-08-21 15:08:25,197][03870] Num frames 10100...
[2024-08-21 15:08:25,317][03870] Num frames 10200...
[2024-08-21 15:08:25,444][03870] Num frames 10300...
[2024-08-21 15:08:25,565][03870] Num frames 10400...
[2024-08-21 15:08:25,725][03870] Avg episode rewards: #0: 24.484, true rewards: #0: 10.484
[2024-08-21 15:08:25,727][03870] Avg episode reward: 24.484, avg true_objective: 10.484
[2024-08-21 15:09:32,736][03870] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
[2024-08-21 15:12:51,960][03870] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
[2024-08-21 15:12:51,963][03870] Overriding arg 'num_workers' with value 1 passed from command line
[2024-08-21 15:12:51,965][03870] Adding new argument 'no_render'=True that is not in the saved config file!
[2024-08-21 15:12:51,967][03870] Adding new argument 'save_video'=True that is not in the saved config file!
[2024-08-21 15:12:51,969][03870] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2024-08-21 15:12:51,971][03870] Adding new argument 'video_name'=None that is not in the saved config file!
[2024-08-21 15:12:51,972][03870] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
[2024-08-21 15:12:51,975][03870] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2024-08-21 15:12:51,977][03870] Adding new argument 'push_to_hub'=True that is not in the saved config file!
[2024-08-21 15:12:51,978][03870] Adding new argument 'hf_repository'='oookayamaswallow/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
[2024-08-21 15:12:51,979][03870] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2024-08-21 15:12:51,980][03870] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2024-08-21 15:12:51,981][03870] Adding new argument 'train_script'=None that is not in the saved config file!
[2024-08-21 15:12:51,982][03870] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2024-08-21 15:12:51,986][03870] Using frameskip 1 and render_action_repeat=4 for evaluation
[2024-08-21 15:12:51,999][03870] RunningMeanStd input shape: (3, 72, 128)
[2024-08-21 15:12:52,010][03870] RunningMeanStd input shape: (1,)
[2024-08-21 15:12:52,034][03870] ConvEncoder: input_channels=3
[2024-08-21 15:12:52,093][03870] Conv encoder output size: 512
[2024-08-21 15:12:52,095][03870] Policy head output size: 512
[2024-08-21 15:12:52,123][03870] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2024-08-21 15:12:52,730][03870] Num frames 100...
[2024-08-21 15:12:52,848][03870] Num frames 200...
[2024-08-21 15:12:52,969][03870] Num frames 300...
[2024-08-21 15:12:53,099][03870] Num frames 400...
[2024-08-21 15:12:53,217][03870] Num frames 500...
[2024-08-21 15:12:53,338][03870] Num frames 600...
[2024-08-21 15:12:53,469][03870] Num frames 700...
[2024-08-21 15:12:53,620][03870] Avg episode rewards: #0: 17.820, true rewards: #0: 7.820
[2024-08-21 15:12:53,622][03870] Avg episode reward: 17.820, avg true_objective: 7.820
[2024-08-21 15:12:53,647][03870] Num frames 800...
[2024-08-21 15:12:53,761][03870] Num frames 900...
[2024-08-21 15:12:53,878][03870] Num frames 1000...
[2024-08-21 15:12:53,993][03870] Num frames 1100...
[2024-08-21 15:12:54,110][03870] Num frames 1200...
[2024-08-21 15:12:54,226][03870] Num frames 1300...
[2024-08-21 15:12:54,343][03870] Num frames 1400...
[2024-08-21 15:12:54,479][03870] Num frames 1500...
[2024-08-21 15:12:54,604][03870] Num frames 1600...
[2024-08-21 15:12:54,730][03870] Num frames 1700...
[2024-08-21 15:12:54,849][03870] Num frames 1800...
[2024-08-21 15:12:54,971][03870] Num frames 1900...
[2024-08-21 15:12:55,093][03870] Num frames 2000...
[2024-08-21 15:12:55,217][03870] Num frames 2100...
[2024-08-21 15:12:55,339][03870] Num frames 2200...
[2024-08-21 15:12:55,460][03870] Num frames 2300...
[2024-08-21 15:12:55,593][03870] Num frames 2400...
[2024-08-21 15:12:55,718][03870] Num frames 2500...
[2024-08-21 15:12:55,844][03870] Num frames 2600...
[2024-08-21 15:12:55,970][03870] Num frames 2700...
[2024-08-21 15:12:56,031][03870] Avg episode rewards: #0: 34.510, true rewards: #0: 13.510
[2024-08-21 15:12:56,032][03870] Avg episode reward: 34.510, avg true_objective: 13.510
[2024-08-21 15:12:56,155][03870] Num frames 2800...
[2024-08-21 15:12:56,276][03870] Num frames 2900...
[2024-08-21 15:12:56,402][03870] Num frames 3000...
[2024-08-21 15:12:56,526][03870] Num frames 3100...
[2024-08-21 15:12:56,657][03870] Num frames 3200...
[2024-08-21 15:12:56,778][03870] Num frames 3300...
[2024-08-21 15:12:56,899][03870] Num frames 3400...
[2024-08-21 15:12:57,020][03870] Num frames 3500...
[2024-08-21 15:12:57,141][03870] Num frames 3600...
[2024-08-21 15:12:57,263][03870] Num frames 3700...
[2024-08-21 15:12:57,383][03870] Num frames 3800...
[2024-08-21 15:12:57,506][03870] Num frames 3900...
[2024-08-21 15:12:57,641][03870] Num frames 4000...
[2024-08-21 15:12:57,768][03870] Num frames 4100...
[2024-08-21 15:12:57,886][03870] Num frames 4200...
[2024-08-21 15:12:58,003][03870] Num frames 4300...
[2024-08-21 15:12:58,133][03870] Num frames 4400...
[2024-08-21 15:12:58,262][03870] Avg episode rewards: #0: 38.203, true rewards: #0: 14.870
[2024-08-21 15:12:58,264][03870] Avg episode reward: 38.203, avg true_objective: 14.870
[2024-08-21 15:12:58,311][03870] Num frames 4500...
[2024-08-21 15:12:58,426][03870] Num frames 4600...
[2024-08-21 15:12:58,542][03870] Num frames 4700...
[2024-08-21 15:12:58,683][03870] Num frames 4800...
[2024-08-21 15:12:58,806][03870] Num frames 4900...
[2024-08-21 15:12:58,926][03870] Num frames 5000...
[2024-08-21 15:12:59,043][03870] Num frames 5100...
[2024-08-21 15:12:59,166][03870] Num frames 5200...
[2024-08-21 15:12:59,282][03870] Num frames 5300...
[2024-08-21 15:12:59,408][03870] Avg episode rewards: #0: 32.892, true rewards: #0: 13.392
[2024-08-21 15:12:59,410][03870] Avg episode reward: 32.892, avg true_objective: 13.392
[2024-08-21 15:12:59,466][03870] Num frames 5400...
[2024-08-21 15:12:59,593][03870] Num frames 5500...
[2024-08-21 15:12:59,729][03870] Num frames 5600...
[2024-08-21 15:12:59,848][03870] Num frames 5700...
[2024-08-21 15:12:59,967][03870] Num frames 5800...
[2024-08-21 15:13:00,089][03870] Num frames 5900...
[2024-08-21 15:13:00,211][03870] Num frames 6000...
[2024-08-21 15:13:00,331][03870] Num frames 6100...
[2024-08-21 15:13:00,447][03870] Num frames 6200...
[2024-08-21 15:13:00,572][03870] Num frames 6300...
[2024-08-21 15:13:00,711][03870] Num frames 6400...
[2024-08-21 15:13:00,832][03870] Num frames 6500...
[2024-08-21 15:13:00,987][03870] Avg episode rewards: #0: 32.568, true rewards: #0: 13.168
[2024-08-21 15:13:00,988][03870] Avg episode reward: 32.568, avg true_objective: 13.168
[2024-08-21 15:13:01,010][03870] Num frames 6600...
[2024-08-21 15:13:01,132][03870] Num frames 6700...
[2024-08-21 15:13:01,252][03870] Num frames 6800...
[2024-08-21 15:13:01,371][03870] Num frames 6900...
[2024-08-21 15:13:01,514][03870] Num frames 7000...
[2024-08-21 15:13:01,652][03870] Num frames 7100...
[2024-08-21 15:13:01,778][03870] Num frames 7200...
[2024-08-21 15:13:01,903][03870] Num frames 7300...
[2024-08-21 15:13:02,021][03870] Num frames 7400...
[2024-08-21 15:13:02,142][03870] Num frames 7500...
[2024-08-21 15:13:02,262][03870] Num frames 7600...
[2024-08-21 15:13:02,384][03870] Num frames 7700...
[2024-08-21 15:13:02,510][03870] Num frames 7800...
[2024-08-21 15:13:02,698][03870] Num frames 7900...
[2024-08-21 15:13:02,877][03870] Num frames 8000...
[2024-08-21 15:13:03,037][03870] Num frames 8100...
[2024-08-21 15:13:03,241][03870] Num frames 8200...
[2024-08-21 15:13:03,409][03870] Num frames 8300...
[2024-08-21 15:13:03,569][03870] Num frames 8400...
[2024-08-21 15:13:03,772][03870] Num frames 8500...
[2024-08-21 15:13:03,949][03870] Num frames 8600...
[2024-08-21 15:13:04,146][03870] Avg episode rewards: #0: 36.306, true rewards: #0: 14.473
[2024-08-21 15:13:04,149][03870] Avg episode reward: 36.306, avg true_objective: 14.473
[2024-08-21 15:13:04,177][03870] Num frames 8700...
[2024-08-21 15:13:04,352][03870] Num frames 8800...
[2024-08-21 15:13:04,525][03870] Num frames 8900...
[2024-08-21 15:13:04,703][03870] Num frames 9000...
[2024-08-21 15:13:04,882][03870] Num frames 9100...
[2024-08-21 15:13:05,056][03870] Num frames 9200...
[2024-08-21 15:13:05,132][03870] Avg episode rewards: #0: 32.300, true rewards: #0: 13.157
[2024-08-21 15:13:05,133][03870] Avg episode reward: 32.300, avg true_objective: 13.157
[2024-08-21 15:13:05,255][03870] Num frames 9300...
[2024-08-21 15:13:05,375][03870] Num frames 9400...
[2024-08-21 15:13:05,495][03870] Num frames 9500...
[2024-08-21 15:13:05,623][03870] Num frames 9600...
[2024-08-21 15:13:05,748][03870] Num frames 9700...
[2024-08-21 15:13:05,876][03870] Num frames 9800...
[2024-08-21 15:13:05,998][03870] Num frames 9900...
[2024-08-21 15:13:06,119][03870] Num frames 10000...
[2024-08-21 15:13:06,236][03870] Num frames 10100...
[2024-08-21 15:13:06,361][03870] Num frames 10200...
[2024-08-21 15:13:06,481][03870] Num frames 10300...
[2024-08-21 15:13:06,641][03870] Num frames 10400...
[2024-08-21 15:13:06,771][03870] Avg episode rewards: #0: 31.447, true rewards: #0: 13.072
[2024-08-21 15:13:06,773][03870] Avg episode reward: 31.447, avg true_objective: 13.072
[2024-08-21 15:13:06,826][03870] Num frames 10500...
[2024-08-21 15:13:06,955][03870] Num frames 10600...
[2024-08-21 15:13:07,076][03870] Num frames 10700...
[2024-08-21 15:13:07,204][03870] Num frames 10800...
[2024-08-21 15:13:07,329][03870] Num frames 10900...
[2024-08-21 15:13:07,448][03870] Num frames 11000...
[2024-08-21 15:13:07,566][03870] Num frames 11100...
[2024-08-21 15:13:07,701][03870] Num frames 11200...
[2024-08-21 15:13:07,819][03870] Avg episode rewards: #0: 29.835, true rewards: #0: 12.502
[2024-08-21 15:13:07,820][03870] Avg episode reward: 29.835, avg true_objective: 12.502
[2024-08-21 15:13:07,881][03870] Num frames 11300...
[2024-08-21 15:13:08,012][03870] Num frames 11400...
[2024-08-21 15:13:08,134][03870] Num frames 11500...
[2024-08-21 15:13:08,258][03870] Num frames 11600...
[2024-08-21 15:13:08,328][03870] Avg episode rewards: #0: 27.411, true rewards: #0: 11.611
[2024-08-21 15:13:08,329][03870] Avg episode reward: 27.411, avg true_objective: 11.611
[2024-08-21 15:14:21,447][03870] Replay video saved to /content/train_dir/default_experiment/replay.mp4!