[2023-02-24 10:25:35,706][00397] Saving configuration to /content/train_dir/default_experiment/config.json...
[2023-02-24 10:25:35,708][00397] Rollout worker 0 uses device cpu
[2023-02-24 10:25:35,712][00397] Rollout worker 1 uses device cpu
[2023-02-24 10:25:35,714][00397] Rollout worker 2 uses device cpu
[2023-02-24 10:25:35,715][00397] Rollout worker 3 uses device cpu
[2023-02-24 10:25:35,716][00397] Rollout worker 4 uses device cpu
[2023-02-24 10:25:35,717][00397] Rollout worker 5 uses device cpu
[2023-02-24 10:25:35,719][00397] Rollout worker 6 uses device cpu
[2023-02-24 10:25:35,720][00397] Rollout worker 7 uses device cpu
[2023-02-24 10:25:35,906][00397] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-24 10:25:35,908][00397] InferenceWorker_p0-w0: min num requests: 2
[2023-02-24 10:25:35,938][00397] Starting all processes...
[2023-02-24 10:25:35,940][00397] Starting process learner_proc0
[2023-02-24 10:25:35,999][00397] Starting all processes...
[2023-02-24 10:25:36,011][00397] Starting process inference_proc0-0
[2023-02-24 10:25:36,011][00397] Starting process rollout_proc0
[2023-02-24 10:25:36,015][00397] Starting process rollout_proc1
[2023-02-24 10:25:36,016][00397] Starting process rollout_proc2
[2023-02-24 10:25:36,016][00397] Starting process rollout_proc3
[2023-02-24 10:25:36,016][00397] Starting process rollout_proc4
[2023-02-24 10:25:36,016][00397] Starting process rollout_proc5
[2023-02-24 10:25:36,016][00397] Starting process rollout_proc6
[2023-02-24 10:25:36,016][00397] Starting process rollout_proc7
[2023-02-24 10:25:47,806][12747] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-24 10:25:47,811][12747] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
[2023-02-24 10:25:47,970][12764] Worker 1 uses CPU cores [1]
[2023-02-24 10:25:48,030][12767] Worker 5 uses CPU cores [1]
[2023-02-24 10:25:48,032][12763] Worker 2 uses CPU cores [0]
[2023-02-24 10:25:48,167][12769] Worker 6 uses CPU cores [0]
[2023-02-24 10:25:48,321][12761] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-24 10:25:48,321][12761] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
[2023-02-24 10:25:48,355][12766] Worker 4 uses CPU cores [0]
[2023-02-24 10:25:48,360][12762] Worker 0 uses CPU cores [0]
[2023-02-24 10:25:48,427][12768] Worker 7 uses CPU cores [1]
[2023-02-24 10:25:48,430][12765] Worker 3 uses CPU cores [1]
[2023-02-24 10:25:48,686][12747] Num visible devices: 1
[2023-02-24 10:25:48,686][12761] Num visible devices: 1
[2023-02-24 10:25:48,701][12747] Starting seed is not provided
[2023-02-24 10:25:48,702][12747] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-24 10:25:48,703][12747] Initializing actor-critic model on device cuda:0
[2023-02-24 10:25:48,703][12747] RunningMeanStd input shape: (3, 72, 128)
[2023-02-24 10:25:48,705][12747] RunningMeanStd input shape: (1,)
[2023-02-24 10:25:48,717][12747] ConvEncoder: input_channels=3
[2023-02-24 10:25:49,005][12747] Conv encoder output size: 512
[2023-02-24 10:25:49,005][12747] Policy head output size: 512
[2023-02-24 10:25:49,056][12747] Created Actor Critic model with architecture:
[2023-02-24 10:25:49,057][12747] ActorCriticSharedWeights(
  (obs_normalizer): ObservationNormalizer(
    (running_mean_std): RunningMeanStdDictInPlace(
      (running_mean_std): ModuleDict(
        (obs): RunningMeanStdInPlace()
      )
    )
  )
  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
  (encoder): VizdoomEncoder(
    (basic_encoder): ConvEncoder(
      (enc): RecursiveScriptModule(
        original_name=ConvEncoderImpl
        (conv_head): RecursiveScriptModule(
          original_name=Sequential
          (0): RecursiveScriptModule(original_name=Conv2d)
          (1): RecursiveScriptModule(original_name=ELU)
          (2): RecursiveScriptModule(original_name=Conv2d)
          (3): RecursiveScriptModule(original_name=ELU)
          (4): RecursiveScriptModule(original_name=Conv2d)
          (5): RecursiveScriptModule(original_name=ELU)
        )
        (mlp_layers): RecursiveScriptModule(
          original_name=Sequential
          (0): RecursiveScriptModule(original_name=Linear)
          (1): RecursiveScriptModule(original_name=ELU)
        )
      )
    )
  )
  (core): ModelCoreRNN(
    (core): GRU(512, 512)
  )
  (decoder): MlpDecoder(
    (mlp): Identity()
  )
  (critic_linear): Linear(in_features=512, out_features=1, bias=True)
  (action_parameterization): ActionParameterizationDefault(
    (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
  )
)
[2023-02-24 10:25:55,899][00397] Heartbeat connected on Batcher_0
[2023-02-24 10:25:55,906][00397] Heartbeat connected on InferenceWorker_p0-w0
[2023-02-24 10:25:55,915][00397] Heartbeat connected on RolloutWorker_w0
[2023-02-24 10:25:55,920][00397] Heartbeat connected on RolloutWorker_w1
[2023-02-24 10:25:55,922][00397] Heartbeat connected on RolloutWorker_w2
[2023-02-24 10:25:55,927][00397] Heartbeat connected on RolloutWorker_w3
[2023-02-24 10:25:55,928][00397] Heartbeat connected on RolloutWorker_w4
[2023-02-24 10:25:55,934][00397] Heartbeat connected on RolloutWorker_w5
[2023-02-24 10:25:55,936][00397] Heartbeat connected on RolloutWorker_w6
[2023-02-24 10:25:55,940][00397] Heartbeat connected on RolloutWorker_w7
[2023-02-24 10:25:56,669][12747] Using optimizer <class 'torch.optim.adam.Adam'>
[2023-02-24 10:25:56,670][12747] No checkpoints found
[2023-02-24 10:25:56,670][12747] Did not load from checkpoint, starting from scratch!
[2023-02-24 10:25:56,671][12747] Initialized policy 0 weights for model version 0
[2023-02-24 10:25:56,681][12747] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-24 10:25:56,692][12747] LearnerWorker_p0 finished initialization!
[2023-02-24 10:25:56,693][00397] Heartbeat connected on LearnerWorker_p0
[2023-02-24 10:25:56,959][12761] RunningMeanStd input shape: (3, 72, 128)
[2023-02-24 10:25:56,961][12761] RunningMeanStd input shape: (1,)
[2023-02-24 10:25:56,979][12761] ConvEncoder: input_channels=3
[2023-02-24 10:25:57,145][12761] Conv encoder output size: 512
[2023-02-24 10:25:57,146][12761] Policy head output size: 512
[2023-02-24 10:25:59,624][00397] Inference worker 0-0 is ready!
[2023-02-24 10:25:59,626][00397] All inference workers are ready! Signal rollout workers to start!
[2023-02-24 10:25:59,759][12768] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 10:25:59,764][12764] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 10:25:59,770][12767] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 10:25:59,777][12765] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 10:25:59,791][12763] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 10:25:59,794][12766] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 10:25:59,795][12762] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 10:25:59,799][12769] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 10:26:00,644][12766] Decorrelating experience for 0 frames...
[2023-02-24 10:26:00,645][12763] Decorrelating experience for 0 frames...
[2023-02-24 10:26:00,890][12765] Decorrelating experience for 0 frames...
[2023-02-24 10:26:00,897][12768] Decorrelating experience for 0 frames...
[2023-02-24 10:26:00,903][12767] Decorrelating experience for 0 frames...
[2023-02-24 10:26:01,542][00397] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2023-02-24 10:26:01,551][12763] Decorrelating experience for 32 frames...
[2023-02-24 10:26:01,634][12762] Decorrelating experience for 0 frames...
[2023-02-24 10:26:01,928][12766] Decorrelating experience for 32 frames...
[2023-02-24 10:26:01,929][12765] Decorrelating experience for 32 frames...
[2023-02-24 10:26:01,942][12768] Decorrelating experience for 32 frames...
[2023-02-24 10:26:01,946][12767] Decorrelating experience for 32 frames...
[2023-02-24 10:26:02,687][12762] Decorrelating experience for 32 frames...
[2023-02-24 10:26:02,877][12768] Decorrelating experience for 64 frames...
[2023-02-24 10:26:02,887][12767] Decorrelating experience for 64 frames...
[2023-02-24 10:26:03,090][12769] Decorrelating experience for 0 frames...
[2023-02-24 10:26:03,100][12763] Decorrelating experience for 64 frames...
[2023-02-24 10:26:03,701][12762] Decorrelating experience for 64 frames...
[2023-02-24 10:26:03,830][12766] Decorrelating experience for 64 frames...
[2023-02-24 10:26:03,946][12767] Decorrelating experience for 96 frames...
[2023-02-24 10:26:03,950][12768] Decorrelating experience for 96 frames...
[2023-02-24 10:26:04,219][12764] Decorrelating experience for 0 frames...
[2023-02-24 10:26:04,940][12762] Decorrelating experience for 96 frames...
[2023-02-24 10:26:05,056][12766] Decorrelating experience for 96 frames...
[2023-02-24 10:26:05,320][12769] Decorrelating experience for 32 frames...
[2023-02-24 10:26:05,345][12765] Decorrelating experience for 64 frames...
[2023-02-24 10:26:05,365][12763] Decorrelating experience for 96 frames...
[2023-02-24 10:26:06,090][12764] Decorrelating experience for 32 frames...
[2023-02-24 10:26:06,179][12765] Decorrelating experience for 96 frames...
[2023-02-24 10:26:06,237][12769] Decorrelating experience for 64 frames...
[2023-02-24 10:26:06,542][00397] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2023-02-24 10:26:06,653][12764] Decorrelating experience for 64 frames...
[2023-02-24 10:26:06,819][12769] Decorrelating experience for 96 frames...
[2023-02-24 10:26:07,163][12764] Decorrelating experience for 96 frames...
[2023-02-24 10:26:11,542][00397] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 42.6. Samples: 426. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2023-02-24 10:26:11,547][00397] Avg episode reward: [(0, '1.077')]
[2023-02-24 10:26:12,475][12747] Signal inference workers to stop experience collection...
[2023-02-24 10:26:12,500][12761] InferenceWorker_p0-w0: stopping experience collection
[2023-02-24 10:26:14,856][12747] Signal inference workers to resume experience collection...
[2023-02-24 10:26:14,857][12761] InferenceWorker_p0-w0: resuming experience collection
[2023-02-24 10:26:16,542][00397] Fps is (10 sec: 409.6, 60 sec: 273.1, 300 sec: 273.1). Total num frames: 4096. Throughput: 0: 142.9. Samples: 2144. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-02-24 10:26:16,549][00397] Avg episode reward: [(0, '1.762')]
[2023-02-24 10:26:21,542][00397] Fps is (10 sec: 2867.2, 60 sec: 1433.6, 300 sec: 1433.6). Total num frames: 28672. Throughput: 0: 351.0. Samples: 7020. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0)
[2023-02-24 10:26:21,545][00397] Avg episode reward: [(0, '3.635')]
[2023-02-24 10:26:23,873][12761] Updated weights for policy 0, policy_version 10 (0.0018)
[2023-02-24 10:26:26,542][00397] Fps is (10 sec: 4505.6, 60 sec: 1966.1, 300 sec: 1966.1). Total num frames: 49152. Throughput: 0: 407.7. Samples: 10192. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0)
[2023-02-24 10:26:26,546][00397] Avg episode reward: [(0, '4.339')]
[2023-02-24 10:26:31,543][00397] Fps is (10 sec: 3276.2, 60 sec: 2047.9, 300 sec: 2047.9). Total num frames: 61440. Throughput: 0: 504.0. Samples: 15120. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0)
[2023-02-24 10:26:31,553][00397] Avg episode reward: [(0, '4.359')]
[2023-02-24 10:26:36,542][00397] Fps is (10 sec: 2457.6, 60 sec: 2106.5, 300 sec: 2106.5). Total num frames: 73728. Throughput: 0: 543.5. Samples: 19024. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0)
[2023-02-24 10:26:36,544][00397] Avg episode reward: [(0, '4.488')]
[2023-02-24 10:26:37,533][12761] Updated weights for policy 0, policy_version 20 (0.0017)
[2023-02-24 10:26:41,542][00397] Fps is (10 sec: 3687.0, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 98304. Throughput: 0: 554.3. Samples: 22170. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:26:41,545][00397] Avg episode reward: [(0, '4.469')]
[2023-02-24 10:26:46,550][00397] Fps is (10 sec: 4501.9, 60 sec: 2639.2, 300 sec: 2639.2). Total num frames: 118784. Throughput: 0: 634.7. Samples: 28568. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:26:46,553][00397] Avg episode reward: [(0, '4.440')]
[2023-02-24 10:26:46,555][12747] Saving new best policy, reward=4.440!
[2023-02-24 10:26:47,689][12761] Updated weights for policy 0, policy_version 30 (0.0024)
[2023-02-24 10:26:51,543][00397] Fps is (10 sec: 3276.4, 60 sec: 2621.4, 300 sec: 2621.4). Total num frames: 131072. Throughput: 0: 737.4. Samples: 33184. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-24 10:26:51,546][00397] Avg episode reward: [(0, '4.400')]
[2023-02-24 10:26:56,542][00397] Fps is (10 sec: 2459.6, 60 sec: 2606.6, 300 sec: 2606.6). Total num frames: 143360. Throughput: 0: 770.6. Samples: 35102. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:26:56,544][00397] Avg episode reward: [(0, '4.308')]
[2023-02-24 10:27:00,326][12761] Updated weights for policy 0, policy_version 40 (0.0013)
[2023-02-24 10:27:01,542][00397] Fps is (10 sec: 3686.9, 60 sec: 2798.9, 300 sec: 2798.9). Total num frames: 167936. Throughput: 0: 857.8. Samples: 40746. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:27:01,547][00397] Avg episode reward: [(0, '4.336')]
[2023-02-24 10:27:06,546][00397] Fps is (10 sec: 4094.2, 60 sec: 3071.8, 300 sec: 2835.5). Total num frames: 184320. Throughput: 0: 889.6. Samples: 47056. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-24 10:27:06,549][00397] Avg episode reward: [(0, '4.565')]
[2023-02-24 10:27:06,582][12747] Saving new best policy, reward=4.565!
[2023-02-24 10:27:11,543][00397] Fps is (10 sec: 3276.2, 60 sec: 3345.0, 300 sec: 2867.1). Total num frames: 200704. Throughput: 0: 861.2. Samples: 48948. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:27:11,552][00397] Avg episode reward: [(0, '4.570')]
[2023-02-24 10:27:11,568][12747] Saving new best policy, reward=4.570!
[2023-02-24 10:27:12,965][12761] Updated weights for policy 0, policy_version 50 (0.0037)
[2023-02-24 10:27:16,542][00397] Fps is (10 sec: 2868.4, 60 sec: 3481.6, 300 sec: 2839.9). Total num frames: 212992. Throughput: 0: 840.6. Samples: 52946. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:27:16,544][00397] Avg episode reward: [(0, '4.430')]
[2023-02-24 10:27:21,542][00397] Fps is (10 sec: 3687.1, 60 sec: 3481.6, 300 sec: 2969.6). Total num frames: 237568. Throughput: 0: 890.4. Samples: 59092. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:27:21,549][00397] Avg episode reward: [(0, '4.445')]
[2023-02-24 10:27:23,339][12761] Updated weights for policy 0, policy_version 60 (0.0031)
[2023-02-24 10:27:26,543][00397] Fps is (10 sec: 4095.5, 60 sec: 3413.3, 300 sec: 2987.6). Total num frames: 253952. Throughput: 0: 890.6. Samples: 62248. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:27:26,546][00397] Avg episode reward: [(0, '4.562')]
[2023-02-24 10:27:31,549][00397] Fps is (10 sec: 3274.4, 60 sec: 3481.3, 300 sec: 3003.5). Total num frames: 270336. Throughput: 0: 850.5. Samples: 66838. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:27:31,552][00397] Avg episode reward: [(0, '4.560')]
[2023-02-24 10:27:31,562][12747] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000066_270336.pth...
[2023-02-24 10:27:36,557][00397] Fps is (10 sec: 2863.2, 60 sec: 3480.7, 300 sec: 2974.5). Total num frames: 282624. Throughput: 0: 845.7. Samples: 71252. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:27:36,563][00397] Avg episode reward: [(0, '4.396')]
[2023-02-24 10:27:36,626][12761] Updated weights for policy 0, policy_version 70 (0.0020)
[2023-02-24 10:27:41,542][00397] Fps is (10 sec: 3689.1, 60 sec: 3481.6, 300 sec: 3072.0). Total num frames: 307200. Throughput: 0: 876.0. Samples: 74524. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:27:41,544][00397] Avg episode reward: [(0, '4.420')]
[2023-02-24 10:27:46,542][00397] Fps is (10 sec: 4102.3, 60 sec: 3413.8, 300 sec: 3081.8). Total num frames: 323584. Throughput: 0: 893.7. Samples: 80962. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:27:46,547][00397] Avg episode reward: [(0, '4.498')]
[2023-02-24 10:27:46,761][12761] Updated weights for policy 0, policy_version 80 (0.0013)
[2023-02-24 10:27:51,547][00397] Fps is (10 sec: 3275.1, 60 sec: 3481.4, 300 sec: 3090.5). Total num frames: 339968. Throughput: 0: 843.9. Samples: 85034. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:27:51,549][00397] Avg episode reward: [(0, '4.251')]
[2023-02-24 10:27:56,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3098.7). Total num frames: 356352. Throughput: 0: 846.3. Samples: 87030. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:27:56,545][00397] Avg episode reward: [(0, '4.144')]
[2023-02-24 10:27:59,421][12761] Updated weights for policy 0, policy_version 90 (0.0013)
[2023-02-24 10:28:01,542][00397] Fps is (10 sec: 3688.3, 60 sec: 3481.6, 300 sec: 3140.3). Total num frames: 376832. Throughput: 0: 887.2. Samples: 92868. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:28:01,550][00397] Avg episode reward: [(0, '4.316')]
[2023-02-24 10:28:06,546][00397] Fps is (10 sec: 3684.8, 60 sec: 3481.6, 300 sec: 3145.6). Total num frames: 393216. Throughput: 0: 886.2. Samples: 98976. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:28:06,549][00397] Avg episode reward: [(0, '4.524')]
[2023-02-24 10:28:11,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3413.4, 300 sec: 3119.3). Total num frames: 405504. Throughput: 0: 858.3. Samples: 100872. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:28:11,546][00397] Avg episode reward: [(0, '4.503')]
[2023-02-24 10:28:11,582][12761] Updated weights for policy 0, policy_version 100 (0.0024)
[2023-02-24 10:28:16,542][00397] Fps is (10 sec: 2868.4, 60 sec: 3481.6, 300 sec: 3125.1). Total num frames: 421888. Throughput: 0: 847.0. Samples: 104946. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:28:16,544][00397] Avg episode reward: [(0, '4.497')]
[2023-02-24 10:28:21,547][00397] Fps is (10 sec: 4093.7, 60 sec: 3481.3, 300 sec: 3188.9). Total num frames: 446464. Throughput: 0: 889.7. Samples: 111280. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:28:21,550][00397] Avg episode reward: [(0, '4.344')]
[2023-02-24 10:28:22,526][12761] Updated weights for policy 0, policy_version 110 (0.0017)
[2023-02-24 10:28:26,542][00397] Fps is (10 sec: 4096.0, 60 sec: 3481.7, 300 sec: 3192.1). Total num frames: 462848. Throughput: 0: 886.8. Samples: 114430. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:28:26,547][00397] Avg episode reward: [(0, '4.426')]
[2023-02-24 10:28:31,542][00397] Fps is (10 sec: 2868.8, 60 sec: 3413.8, 300 sec: 3167.6). Total num frames: 475136. Throughput: 0: 840.5. Samples: 118786. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:28:31,548][00397] Avg episode reward: [(0, '4.379')]
[2023-02-24 10:28:36,134][12761] Updated weights for policy 0, policy_version 120 (0.0016)
[2023-02-24 10:28:36,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3482.5, 300 sec: 3171.1). Total num frames: 491520. Throughput: 0: 846.2. Samples: 123108. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-24 10:28:36,551][00397] Avg episode reward: [(0, '4.322')]
[2023-02-24 10:28:41,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3148.8). Total num frames: 503808. Throughput: 0: 846.0. Samples: 125100. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:28:41,546][00397] Avg episode reward: [(0, '4.458')]
[2023-02-24 10:28:46,543][00397] Fps is (10 sec: 2457.4, 60 sec: 3208.5, 300 sec: 3127.8). Total num frames: 516096. Throughput: 0: 806.4. Samples: 129156. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:28:46,548][00397] Avg episode reward: [(0, '4.490')]
[2023-02-24 10:28:51,542][00397] Fps is (10 sec: 2457.5, 60 sec: 3140.5, 300 sec: 3108.1). Total num frames: 528384. Throughput: 0: 756.6. Samples: 133020. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:28:51,546][00397] Avg episode reward: [(0, '4.598')]
[2023-02-24 10:28:51,571][12761] Updated weights for policy 0, policy_version 130 (0.0029)
[2023-02-24 10:28:51,574][12747] Saving new best policy, reward=4.598!
[2023-02-24 10:28:56,542][00397] Fps is (10 sec: 3277.2, 60 sec: 3208.5, 300 sec: 3136.4). Total num frames: 548864. Throughput: 0: 756.5. Samples: 134916. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:28:56,549][00397] Avg episode reward: [(0, '4.536')]
[2023-02-24 10:29:01,542][00397] Fps is (10 sec: 4096.1, 60 sec: 3208.5, 300 sec: 3163.0). Total num frames: 569344. Throughput: 0: 807.4. Samples: 141280. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:29:01,547][00397] Avg episode reward: [(0, '4.551')]
[2023-02-24 10:29:02,254][12761] Updated weights for policy 0, policy_version 140 (0.0014)
[2023-02-24 10:29:06,542][00397] Fps is (10 sec: 3686.4, 60 sec: 3208.8, 300 sec: 3166.1). Total num frames: 585728. Throughput: 0: 793.2. Samples: 146970. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:29:06,548][00397] Avg episode reward: [(0, '4.605')]
[2023-02-24 10:29:06,553][12747] Saving new best policy, reward=4.605!
[2023-02-24 10:29:11,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3208.5, 300 sec: 3147.5). Total num frames: 598016. Throughput: 0: 765.6. Samples: 148882. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:29:11,551][00397] Avg episode reward: [(0, '4.576')]
[2023-02-24 10:29:15,844][12761] Updated weights for policy 0, policy_version 150 (0.0019)
[2023-02-24 10:29:16,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3208.5, 300 sec: 3150.8). Total num frames: 614400. Throughput: 0: 759.2. Samples: 152950. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:29:16,544][00397] Avg episode reward: [(0, '4.458')]
[2023-02-24 10:29:21,542][00397] Fps is (10 sec: 4096.0, 60 sec: 3208.8, 300 sec: 3194.9). Total num frames: 638976. Throughput: 0: 804.4. Samples: 159306. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:29:21,551][00397] Avg episode reward: [(0, '4.245')]
[2023-02-24 10:29:25,921][12761] Updated weights for policy 0, policy_version 160 (0.0015)
[2023-02-24 10:29:26,542][00397] Fps is (10 sec: 4096.0, 60 sec: 3208.5, 300 sec: 3196.9). Total num frames: 655360. Throughput: 0: 831.9. Samples: 162536. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:29:26,550][00397] Avg episode reward: [(0, '4.534')]
[2023-02-24 10:29:31,544][00397] Fps is (10 sec: 2866.6, 60 sec: 3208.4, 300 sec: 3179.2). Total num frames: 667648. Throughput: 0: 839.1. Samples: 166916. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:29:31,551][00397] Avg episode reward: [(0, '4.596')]
[2023-02-24 10:29:31,566][12747] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000163_667648.pth...
[2023-02-24 10:29:36,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3208.5, 300 sec: 3181.5). Total num frames: 684032. Throughput: 0: 855.6. Samples: 171522. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:29:36,550][00397] Avg episode reward: [(0, '4.746')]
[2023-02-24 10:29:36,557][12747] Saving new best policy, reward=4.746!
[2023-02-24 10:29:38,391][12761] Updated weights for policy 0, policy_version 170 (0.0014)
[2023-02-24 10:29:41,542][00397] Fps is (10 sec: 4096.9, 60 sec: 3413.3, 300 sec: 3220.9). Total num frames: 708608. Throughput: 0: 886.6. Samples: 174814. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:29:41,545][00397] Avg episode reward: [(0, '4.525')]
[2023-02-24 10:29:46,542][00397] Fps is (10 sec: 4096.0, 60 sec: 3481.7, 300 sec: 3222.2). Total num frames: 724992. Throughput: 0: 891.3. Samples: 181388. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:29:46,552][00397] Avg episode reward: [(0, '4.321')]
[2023-02-24 10:29:49,587][12761] Updated weights for policy 0, policy_version 180 (0.0018)
[2023-02-24 10:29:51,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3223.4). Total num frames: 741376. Throughput: 0: 857.0. Samples: 185536. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:29:51,548][00397] Avg episode reward: [(0, '4.437')]
[2023-02-24 10:29:56,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3224.5). Total num frames: 757760. Throughput: 0: 862.2. Samples: 187680. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-24 10:29:56,544][00397] Avg episode reward: [(0, '4.576')]
[2023-02-24 10:30:00,526][12761] Updated weights for policy 0, policy_version 190 (0.0022)
[2023-02-24 10:30:01,542][00397] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3259.7). Total num frames: 782336. Throughput: 0: 915.2. Samples: 194136. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:30:01,544][00397] Avg episode reward: [(0, '4.475')]
[2023-02-24 10:30:06,542][00397] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3260.1). Total num frames: 798720. Throughput: 0: 902.9. Samples: 199938. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:30:06,546][00397] Avg episode reward: [(0, '4.353')]
[2023-02-24 10:30:11,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3244.0). Total num frames: 811008. Throughput: 0: 876.8. Samples: 201992. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:30:11,551][00397] Avg episode reward: [(0, '4.365')]
[2023-02-24 10:30:13,575][12761] Updated weights for policy 0, policy_version 200 (0.0013)
[2023-02-24 10:30:16,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3244.7). Total num frames: 827392. Throughput: 0: 876.0. Samples: 206336. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:30:16,543][00397] Avg episode reward: [(0, '4.261')]
[2023-02-24 10:30:21,545][00397] Fps is (10 sec: 4094.8, 60 sec: 3549.7, 300 sec: 3276.8). Total num frames: 851968. Throughput: 0: 918.4. Samples: 212854. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:30:21,547][00397] Avg episode reward: [(0, '4.196')]
[2023-02-24 10:30:22,989][12761] Updated weights for policy 0, policy_version 210 (0.0012)
[2023-02-24 10:30:26,544][00397] Fps is (10 sec: 4095.1, 60 sec: 3549.7, 300 sec: 3276.8). Total num frames: 868352. Throughput: 0: 918.9. Samples: 216166. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:30:26,547][00397] Avg episode reward: [(0, '4.383')]
[2023-02-24 10:30:31,542][00397] Fps is (10 sec: 2868.1, 60 sec: 3550.0, 300 sec: 3261.6). Total num frames: 880640. Throughput: 0: 860.3. Samples: 220100. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:30:31,549][00397] Avg episode reward: [(0, '4.563')]
[2023-02-24 10:30:36,284][12761] Updated weights for policy 0, policy_version 220 (0.0018)
[2023-02-24 10:30:36,542][00397] Fps is (10 sec: 3277.5, 60 sec: 3618.1, 300 sec: 3276.8). Total num frames: 901120. Throughput: 0: 879.1. Samples: 225094. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:30:36,544][00397] Avg episode reward: [(0, '4.423')]
[2023-02-24 10:30:41,542][00397] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3291.4). Total num frames: 921600. Throughput: 0: 900.9. Samples: 228220. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:30:41,544][00397] Avg episode reward: [(0, '4.441')]
[2023-02-24 10:30:46,542][00397] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3291.2). Total num frames: 937984. Throughput: 0: 885.6. Samples: 233986. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-24 10:30:46,548][00397] Avg episode reward: [(0, '4.573')]
[2023-02-24 10:30:47,629][12761] Updated weights for policy 0, policy_version 230 (0.0012)
[2023-02-24 10:30:51,543][00397] Fps is (10 sec: 2866.7, 60 sec: 3481.5, 300 sec: 3276.8). Total num frames: 950272. Throughput: 0: 843.9. Samples: 237916. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-24 10:30:51,546][00397] Avg episode reward: [(0, '4.610')]
[2023-02-24 10:30:56,542][00397] Fps is (10 sec: 2867.3, 60 sec: 3481.6, 300 sec: 3276.8). Total num frames: 966656. Throughput: 0: 845.1. Samples: 240022. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-24 10:30:56,543][00397] Avg episode reward: [(0, '4.339')]
[2023-02-24 10:30:59,783][12761] Updated weights for policy 0, policy_version 240 (0.0013)
[2023-02-24 10:31:01,542][00397] Fps is (10 sec: 4096.7, 60 sec: 3481.6, 300 sec: 3360.1). Total num frames: 991232. Throughput: 0: 889.5. Samples: 246364. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 10:31:01,548][00397] Avg episode reward: [(0, '4.437')]
[2023-02-24 10:31:06,542][00397] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3401.8). Total num frames: 1003520. Throughput: 0: 866.8. Samples: 251858. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:31:06,546][00397] Avg episode reward: [(0, '4.627')]
[2023-02-24 10:31:11,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3443.4). Total num frames: 1019904. Throughput: 0: 835.9. Samples: 253780. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:31:11,551][00397] Avg episode reward: [(0, '4.617')]
[2023-02-24 10:31:12,876][12761] Updated weights for policy 0, policy_version 250 (0.0019)
[2023-02-24 10:31:16,542][00397] Fps is (10 sec: 3276.7, 60 sec: 3481.6, 300 sec: 3415.6). Total num frames: 1036288. Throughput: 0: 852.1. Samples: 258446. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 10:31:16,549][00397] Avg episode reward: [(0, '4.685')]
[2023-02-24 10:31:21,542][00397] Fps is (10 sec: 4096.0, 60 sec: 3481.8, 300 sec: 3429.5). Total num frames: 1060864. Throughput: 0: 881.5. Samples: 264762. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:31:21,549][00397] Avg episode reward: [(0, '4.758')]
[2023-02-24 10:31:21,562][12747] Saving new best policy, reward=4.758!
[2023-02-24 10:31:22,579][12761] Updated weights for policy 0, policy_version 260 (0.0017)
[2023-02-24 10:31:26,542][00397] Fps is (10 sec: 3686.5, 60 sec: 3413.5, 300 sec: 3429.6). Total num frames: 1073152. Throughput: 0: 880.0. Samples: 267818. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:31:26,544][00397] Avg episode reward: [(0, '4.728')]
[2023-02-24 10:31:31,542][00397] Fps is (10 sec: 2867.1, 60 sec: 3481.6, 300 sec: 3443.4). Total num frames: 1089536. Throughput: 0: 842.3. Samples: 271888. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:31:31,547][00397] Avg episode reward: [(0, '4.426')]
[2023-02-24 10:31:31,563][12747] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000266_1089536.pth...
[2023-02-24 10:31:31,720][12747] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000066_270336.pth
[2023-02-24 10:31:35,849][12761] Updated weights for policy 0, policy_version 270 (0.0030)
[2023-02-24 10:31:36,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3415.6). Total num frames: 1105920. Throughput: 0: 864.5. Samples: 276818. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:31:36,549][00397] Avg episode reward: [(0, '4.500')]
[2023-02-24 10:31:41,542][00397] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3415.7). Total num frames: 1126400. Throughput: 0: 889.2. Samples: 280034. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:31:41,544][00397] Avg episode reward: [(0, '4.643')]
[2023-02-24 10:31:46,438][12761] Updated weights for policy 0, policy_version 280 (0.0017)
[2023-02-24 10:31:46,542][00397] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3443.4). Total num frames: 1146880. Throughput: 0: 878.3. Samples: 285888. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:31:46,548][00397] Avg episode reward: [(0, '4.479')]
[2023-02-24 10:31:51,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3481.7, 300 sec: 3443.4). Total num frames: 1159168. Throughput: 0: 850.4. Samples: 290124. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-24 10:31:51,544][00397] Avg episode reward: [(0, '4.579')]
[2023-02-24 10:31:56,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3415.6). Total num frames: 1175552. Throughput: 0: 856.6. Samples: 292328. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:31:56,544][00397] Avg episode reward: [(0, '4.613')]
[2023-02-24 10:31:58,543][12761] Updated weights for policy 0, policy_version 290 (0.0017)
[2023-02-24 10:32:01,545][00397] Fps is (10 sec: 4094.6, 60 sec: 3481.4, 300 sec: 3443.4). Total num frames: 1200128. Throughput: 0: 894.4. Samples: 298698. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:32:01,551][00397] Avg episode reward: [(0, '4.516')]
[2023-02-24 10:32:06,547][00397] Fps is (10 sec: 3684.5, 60 sec: 3481.3, 300 sec: 3429.5). Total num frames: 1212416. Throughput: 0: 873.0. Samples: 304050. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-24 10:32:06,550][00397] Avg episode reward: [(0, '4.454')]
[2023-02-24 10:32:11,185][12761] Updated weights for policy 0, policy_version 300 (0.0018)
[2023-02-24 10:32:11,542][00397] Fps is (10 sec: 2868.1, 60 sec: 3481.6, 300 sec: 3443.4). Total num frames: 1228800. Throughput: 0: 848.3. Samples: 305992. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-24 10:32:11,545][00397] Avg episode reward: [(0, '4.673')]
[2023-02-24 10:32:16,542][00397] Fps is (10 sec: 2868.7, 60 sec: 3413.3, 300 sec: 3401.8). Total num frames: 1241088. Throughput: 0: 845.0. Samples: 309914. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-24 10:32:16,550][00397] Avg episode reward: [(0, '4.879')]
[2023-02-24 10:32:16,556][12747] Saving new best policy, reward=4.879!
[2023-02-24 10:32:21,542][00397] Fps is (10 sec: 2457.6, 60 sec: 3208.5, 300 sec: 3387.9). Total num frames: 1253376. Throughput: 0: 823.9. Samples: 313892. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:32:21,545][00397] Avg episode reward: [(0, '4.866')]
[2023-02-24 10:32:26,304][12761] Updated weights for policy 0, policy_version 310 (0.0043)
[2023-02-24 10:32:26,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3388.0). Total num frames: 1269760. Throughput: 0: 803.8. Samples: 316204. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:32:26,552][00397] Avg episode reward: [(0, '4.879')]
[2023-02-24 10:32:31,543][00397] Fps is (10 sec: 2867.0, 60 sec: 3208.5, 300 sec: 3388.0). Total num frames: 1282048. Throughput: 0: 763.3. Samples: 320238. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:32:31,550][00397] Avg episode reward: [(0, '4.774')]
[2023-02-24 10:32:36,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3374.0). Total num frames: 1302528. Throughput: 0: 782.5. Samples: 325336. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-24 10:32:36,544][00397] Avg episode reward: [(0, '4.700')]
[2023-02-24 10:32:38,260][12761] Updated weights for policy 0, policy_version 320 (0.0015)
[2023-02-24 10:32:41,542][00397] Fps is (10 sec: 4096.3, 60 sec: 3276.8, 300 sec: 3387.9). Total num frames: 1323008. Throughput: 0: 806.2. Samples: 328608. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:32:41,544][00397] Avg episode reward: [(0, '4.723')]
[2023-02-24 10:32:46,548][00397] Fps is (10 sec: 3684.1, 60 sec: 3208.2, 300 sec: 3387.9). Total num frames: 1339392. Throughput: 0: 794.1. Samples: 334434. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:32:46,555][00397] Avg episode reward: [(0, '4.640')]
[2023-02-24 10:32:50,666][12761] Updated weights for policy 0, policy_version 330 (0.0026)
[2023-02-24 10:32:51,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3208.5, 300 sec: 3374.0). Total num frames: 1351680. Throughput: 0: 766.2. Samples: 338524. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:32:51,551][00397] Avg episode reward: [(0, '4.509')]
[2023-02-24 10:32:56,542][00397] Fps is (10 sec: 3278.8, 60 sec: 3276.8, 300 sec: 3374.0). Total num frames: 1372160. Throughput: 0: 771.1. Samples: 340692. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:32:56,544][00397] Avg episode reward: [(0, '4.412')]
[2023-02-24 10:33:01,436][12761] Updated weights for policy 0, policy_version 340 (0.0021)
[2023-02-24 10:33:01,542][00397] Fps is (10 sec: 4096.0, 60 sec: 3208.7, 300 sec: 3387.9). Total num frames: 1392640. Throughput: 0: 823.1. Samples: 346954. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:33:01,547][00397] Avg episode reward: [(0, '4.491')]
[2023-02-24 10:33:06,542][00397] Fps is (10 sec: 3686.5, 60 sec: 3277.1, 300 sec: 3401.8). Total num frames: 1409024. Throughput: 0: 851.4. Samples: 352204. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:33:06,548][00397] Avg episode reward: [(0, '4.642')]
[2023-02-24 10:33:11,543][00397] Fps is (10 sec: 2866.9, 60 sec: 3208.5, 300 sec: 3387.9). Total num frames: 1421312. Throughput: 0: 842.2. Samples: 354102. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:33:11,545][00397] Avg episode reward: [(0, '4.627')]
[2023-02-24 10:33:14,471][12761] Updated weights for policy 0, policy_version 350 (0.0026)
[2023-02-24 10:33:16,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3374.1). Total num frames: 1441792. Throughput: 0: 863.7. Samples: 359104. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:33:16,549][00397] Avg episode reward: [(0, '4.632')]
[2023-02-24 10:33:21,542][00397] Fps is (10 sec: 4096.5, 60 sec: 3481.6, 300 sec: 3387.9). Total num frames: 1462272. Throughput: 0: 895.3. Samples: 365626. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 10:33:21,549][00397] Avg episode reward: [(0, '4.548')]
[2023-02-24 10:33:24,280][12761] Updated weights for policy 0, policy_version 360 (0.0016)
[2023-02-24 10:33:26,542][00397] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 1478656. Throughput: 0: 889.6. Samples: 368642. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:33:26,548][00397] Avg episode reward: [(0, '4.595')]
[2023-02-24 10:33:31,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3387.9). Total num frames: 1490944. Throughput: 0: 852.8. Samples: 372804. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:33:31,544][00397] Avg episode reward: [(0, '4.586')]
[2023-02-24 10:33:31,553][12747] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000364_1490944.pth...
[2023-02-24 10:33:31,774][12747] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000163_667648.pth
[2023-02-24 10:33:36,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3415.6). Total num frames: 1511424. Throughput: 0: 871.5. Samples: 377742. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:33:36,550][00397] Avg episode reward: [(0, '4.606')]
[2023-02-24 10:33:37,318][12761] Updated weights for policy 0, policy_version 370 (0.0011)
[2023-02-24 10:33:41,542][00397] Fps is (10 sec: 4095.9, 60 sec: 3481.6, 300 sec: 3443.4). Total num frames: 1531904. Throughput: 0: 890.4. Samples: 380762. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:33:41,544][00397] Avg episode reward: [(0, '4.647')]
[2023-02-24 10:33:46,544][00397] Fps is (10 sec: 3685.6, 60 sec: 3481.8, 300 sec: 3457.3). Total num frames: 1548288. Throughput: 0: 877.7. Samples: 386452. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:33:46,548][00397] Avg episode reward: [(0, '4.819')]
[2023-02-24 10:33:49,294][12761] Updated weights for policy 0, policy_version 380 (0.0021)
[2023-02-24 10:33:51,542][00397] Fps is (10 sec: 2867.3, 60 sec: 3481.6, 300 sec: 3429.5). Total num frames: 1560576. Throughput: 0: 849.9. Samples: 390450. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-24 10:33:51,544][00397] Avg episode reward: [(0, '4.937')]
[2023-02-24 10:33:51,570][12747] Saving new best policy, reward=4.937!
[2023-02-24 10:33:56,542][00397] Fps is (10 sec: 3277.5, 60 sec: 3481.6, 300 sec: 3429.5). Total num frames: 1581056. Throughput: 0: 861.4. Samples: 392866. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:33:56,547][00397] Avg episode reward: [(0, '4.622')]
[2023-02-24 10:34:00,027][12761] Updated weights for policy 0, policy_version 390 (0.0020)
[2023-02-24 10:34:01,542][00397] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3443.4). Total num frames: 1601536. Throughput: 0: 898.4. Samples: 399530. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:34:01,544][00397] Avg episode reward: [(0, '4.789')]
[2023-02-24 10:34:06,542][00397] Fps is (10 sec: 3686.2, 60 sec: 3481.6, 300 sec: 3457.3). Total num frames: 1617920. Throughput: 0: 868.7. Samples: 404720. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:34:06,550][00397] Avg episode reward: [(0, '4.960')]
[2023-02-24 10:34:06,553][12747] Saving new best policy, reward=4.960!
[2023-02-24 10:34:11,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3481.7, 300 sec: 3443.4). Total num frames: 1630208. Throughput: 0: 845.6. Samples: 406692. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:34:11,544][00397] Avg episode reward: [(0, '4.873')]
[2023-02-24 10:34:13,241][12761] Updated weights for policy 0, policy_version 400 (0.0020)
[2023-02-24 10:34:16,542][00397] Fps is (10 sec: 3277.0, 60 sec: 3481.6, 300 sec: 3429.5). Total num frames: 1650688. Throughput: 0: 866.5. Samples: 411798. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:34:16,544][00397] Avg episode reward: [(0, '4.936')]
[2023-02-24 10:34:21,542][00397] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3443.4). Total num frames: 1671168. Throughput: 0: 902.3. Samples: 418346. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:34:21,544][00397] Avg episode reward: [(0, '4.999')]
[2023-02-24 10:34:21,581][12747] Saving new best policy, reward=4.999!
[2023-02-24 10:34:22,653][12761] Updated weights for policy 0, policy_version 410 (0.0028)
[2023-02-24 10:34:26,542][00397] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3457.3). Total num frames: 1687552. Throughput: 0: 893.3. Samples: 420960. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-24 10:34:26,549][00397] Avg episode reward: [(0, '4.886')]
[2023-02-24 10:34:31,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3443.4). Total num frames: 1699840. Throughput: 0: 856.3. Samples: 424984. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-24 10:34:31,544][00397] Avg episode reward: [(0, '4.727')]
[2023-02-24 10:34:35,634][12761] Updated weights for policy 0, policy_version 420 (0.0020)
[2023-02-24 10:34:36,542][00397] Fps is (10 sec: 3276.7, 60 sec: 3481.6, 300 sec: 3429.5). Total num frames: 1720320. Throughput: 0: 890.3. Samples: 430514. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:34:36,551][00397] Avg episode reward: [(0, '5.020')]
[2023-02-24 10:34:36,554][12747] Saving new best policy, reward=5.020!
[2023-02-24 10:34:41,542][00397] Fps is (10 sec: 4505.6, 60 sec: 3549.9, 300 sec: 3457.3). Total num frames: 1744896. Throughput: 0: 911.1. Samples: 433866. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:34:41,544][00397] Avg episode reward: [(0, '5.240')]
[2023-02-24 10:34:41,561][12747] Saving new best policy, reward=5.240!
[2023-02-24 10:34:46,543][00397] Fps is (10 sec: 3686.0, 60 sec: 3481.7, 300 sec: 3443.4). Total num frames: 1757184. Throughput: 0: 881.1. Samples: 439182. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:34:46,546][00397] Avg episode reward: [(0, '5.235')]
[2023-02-24 10:34:47,007][12761] Updated weights for policy 0, policy_version 430 (0.0019)
[2023-02-24 10:34:51,542][00397] Fps is (10 sec: 2867.1, 60 sec: 3549.9, 300 sec: 3443.4). Total num frames: 1773568. Throughput: 0: 856.0. Samples: 443238. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-24 10:34:51,544][00397] Avg episode reward: [(0, '5.292')]
[2023-02-24 10:34:51,559][12747] Saving new best policy, reward=5.292!
[2023-02-24 10:34:56,542][00397] Fps is (10 sec: 3277.2, 60 sec: 3481.6, 300 sec: 3415.6). Total num frames: 1789952. Throughput: 0: 872.5. Samples: 445954. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:34:56,549][00397] Avg episode reward: [(0, '5.452')]
[2023-02-24 10:34:56,553][12747] Saving new best policy, reward=5.452!
[2023-02-24 10:34:58,600][12761] Updated weights for policy 0, policy_version 440 (0.0032)
[2023-02-24 10:35:01,542][00397] Fps is (10 sec: 4096.1, 60 sec: 3549.9, 300 sec: 3443.4). Total num frames: 1814528. Throughput: 0: 898.6. Samples: 452234. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:35:01,547][00397] Avg episode reward: [(0, '5.290')]
[2023-02-24 10:35:06,542][00397] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3443.4). Total num frames: 1826816. Throughput: 0: 863.3. Samples: 457196. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:35:06,546][00397] Avg episode reward: [(0, '5.209')]
[2023-02-24 10:35:11,542][00397] Fps is (10 sec: 2457.4, 60 sec: 3481.6, 300 sec: 3429.5). Total num frames: 1839104. Throughput: 0: 850.4. Samples: 459228. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:35:11,552][00397] Avg episode reward: [(0, '5.116')]
[2023-02-24 10:35:11,835][12761] Updated weights for policy 0, policy_version 450 (0.0012)
[2023-02-24 10:35:16,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3415.7). Total num frames: 1859584. Throughput: 0: 878.0. Samples: 464492. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:35:16,544][00397] Avg episode reward: [(0, '5.529')]
[2023-02-24 10:35:16,599][12747] Saving new best policy, reward=5.529!
[2023-02-24 10:35:21,115][12761] Updated weights for policy 0, policy_version 460 (0.0023)
[2023-02-24 10:35:21,542][00397] Fps is (10 sec: 4505.9, 60 sec: 3549.9, 300 sec: 3443.4). Total num frames: 1884160. Throughput: 0: 902.2. Samples: 471114. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 10:35:21,547][00397] Avg episode reward: [(0, '5.977')]
[2023-02-24 10:35:21,560][12747] Saving new best policy, reward=5.977!
[2023-02-24 10:35:26,546][00397] Fps is (10 sec: 3684.8, 60 sec: 3481.3, 300 sec: 3443.4). Total num frames: 1896448. Throughput: 0: 882.2. Samples: 473570. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-24 10:35:26,551][00397] Avg episode reward: [(0, '5.943')]
[2023-02-24 10:35:31,543][00397] Fps is (10 sec: 2866.8, 60 sec: 3549.8, 300 sec: 3429.5). Total num frames: 1912832. Throughput: 0: 854.3. Samples: 477624. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:35:31,546][00397] Avg episode reward: [(0, '6.249')]
[2023-02-24 10:35:31,557][12747] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000467_1912832.pth...
[2023-02-24 10:35:31,671][12747] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000266_1089536.pth
[2023-02-24 10:35:31,684][12747] Saving new best policy, reward=6.249!
[2023-02-24 10:35:34,391][12761] Updated weights for policy 0, policy_version 470 (0.0026)
[2023-02-24 10:35:36,542][00397] Fps is (10 sec: 3688.0, 60 sec: 3549.9, 300 sec: 3429.5). Total num frames: 1933312. Throughput: 0: 885.3. Samples: 483076. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:35:36,549][00397] Avg episode reward: [(0, '6.168')]
[2023-02-24 10:35:41,542][00397] Fps is (10 sec: 4096.5, 60 sec: 3481.6, 300 sec: 3443.4). Total num frames: 1953792. Throughput: 0: 897.5. Samples: 486342. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:35:41,545][00397] Avg episode reward: [(0, '6.467')]
[2023-02-24 10:35:41,562][12747] Saving new best policy, reward=6.467!
[2023-02-24 10:35:45,342][12761] Updated weights for policy 0, policy_version 480 (0.0017)
[2023-02-24 10:35:46,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3481.7, 300 sec: 3443.4). Total num frames: 1966080. Throughput: 0: 872.9. Samples: 491516. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:35:46,547][00397] Avg episode reward: [(0, '6.520')]
[2023-02-24 10:35:46,552][12747] Saving new best policy, reward=6.520!
[2023-02-24 10:35:51,547][00397] Fps is (10 sec: 2456.3, 60 sec: 3413.0, 300 sec: 3429.5). Total num frames: 1978368. Throughput: 0: 852.8. Samples: 495576. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:35:51,550][00397] Avg episode reward: [(0, '6.268')]
[2023-02-24 10:35:56,543][00397] Fps is (10 sec: 2866.8, 60 sec: 3413.3, 300 sec: 3401.7). Total num frames: 1994752. Throughput: 0: 849.9. Samples: 497472. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:35:56,550][00397] Avg episode reward: [(0, '6.402')]
[2023-02-24 10:36:00,651][12761] Updated weights for policy 0, policy_version 490 (0.0032)
[2023-02-24 10:36:01,542][00397] Fps is (10 sec: 2868.7, 60 sec: 3208.5, 300 sec: 3401.8). Total num frames: 2007040. Throughput: 0: 823.9. Samples: 501566. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:36:01,553][00397] Avg episode reward: [(0, '6.270')]
[2023-02-24 10:36:06,542][00397] Fps is (10 sec: 2867.6, 60 sec: 3276.8, 300 sec: 3401.8). Total num frames: 2023424. Throughput: 0: 779.7. Samples: 506202. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-24 10:36:06,544][00397] Avg episode reward: [(0, '6.493')]
[2023-02-24 10:36:11,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3387.9). Total num frames: 2035712. Throughput: 0: 769.9. Samples: 508214. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 10:36:11,547][00397] Avg episode reward: [(0, '6.902')]
[2023-02-24 10:36:11,568][12747] Saving new best policy, reward=6.902!
[2023-02-24 10:36:13,967][12761] Updated weights for policy 0, policy_version 500 (0.0013)
[2023-02-24 10:36:16,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3374.0). Total num frames: 2056192. Throughput: 0: 795.8. Samples: 513436. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 10:36:16,548][00397] Avg episode reward: [(0, '6.981')]
[2023-02-24 10:36:16,553][12747] Saving new best policy, reward=6.981!
[2023-02-24 10:36:21,542][00397] Fps is (10 sec: 4505.7, 60 sec: 3276.8, 300 sec: 3415.6). Total num frames: 2080768. Throughput: 0: 815.5. Samples: 519772. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:36:21,549][00397] Avg episode reward: [(0, '7.023')]
[2023-02-24 10:36:21,561][12747] Saving new best policy, reward=7.023!
[2023-02-24 10:36:24,480][12761] Updated weights for policy 0, policy_version 510 (0.0023)
[2023-02-24 10:36:26,542][00397] Fps is (10 sec: 3686.4, 60 sec: 3277.0, 300 sec: 3401.8). Total num frames: 2093056. Throughput: 0: 794.9. Samples: 522114. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:36:26,550][00397] Avg episode reward: [(0, '6.686')]
[2023-02-24 10:36:31,542][00397] Fps is (10 sec: 2457.6, 60 sec: 3208.6, 300 sec: 3387.9). Total num frames: 2105344. Throughput: 0: 770.4. Samples: 526184. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:36:31,544][00397] Avg episode reward: [(0, '6.744')]
[2023-02-24 10:36:36,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3208.5, 300 sec: 3387.9). Total num frames: 2125824. Throughput: 0: 807.4. Samples: 531904. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:36:36,544][00397] Avg episode reward: [(0, '6.563')]
[2023-02-24 10:36:36,614][12761] Updated weights for policy 0, policy_version 520 (0.0040)
[2023-02-24 10:36:41,542][00397] Fps is (10 sec: 4505.6, 60 sec: 3276.8, 300 sec: 3401.8). Total num frames: 2150400. Throughput: 0: 837.9. Samples: 535176. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:36:41,551][00397] Avg episode reward: [(0, '7.035')]
[2023-02-24 10:36:41,565][12747] Saving new best policy, reward=7.035!
[2023-02-24 10:36:46,542][00397] Fps is (10 sec: 3686.4, 60 sec: 3276.8, 300 sec: 3401.8). Total num frames: 2162688. Throughput: 0: 862.2. Samples: 540364. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:36:46,549][00397] Avg episode reward: [(0, '7.575')]
[2023-02-24 10:36:46,552][12747] Saving new best policy, reward=7.575!
[2023-02-24 10:36:48,873][12761] Updated weights for policy 0, policy_version 530 (0.0012)
[2023-02-24 10:36:51,542][00397] Fps is (10 sec: 2457.6, 60 sec: 3277.1, 300 sec: 3387.9). Total num frames: 2174976. Throughput: 0: 850.4. Samples: 544470. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:36:51,546][00397] Avg episode reward: [(0, '7.452')]
[2023-02-24 10:36:56,542][00397] Fps is (10 sec: 3686.4, 60 sec: 3413.4, 300 sec: 3387.9). Total num frames: 2199552. Throughput: 0: 871.1. Samples: 547412. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:36:56,549][00397] Avg episode reward: [(0, '8.899')]
[2023-02-24 10:36:56,555][12747] Saving new best policy, reward=8.899!
[2023-02-24 10:36:59,437][12761] Updated weights for policy 0, policy_version 540 (0.0016)
[2023-02-24 10:37:01,549][00397] Fps is (10 sec: 4502.4, 60 sec: 3549.4, 300 sec: 3415.6). Total num frames: 2220032. Throughput: 0: 896.1. Samples: 553768. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:37:01,560][00397] Avg episode reward: [(0, '9.282')]
[2023-02-24 10:37:01,573][12747] Saving new best policy, reward=9.282!
[2023-02-24 10:37:06,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 2232320. Throughput: 0: 857.8. Samples: 558374. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:37:06,552][00397] Avg episode reward: [(0, '9.562')]
[2023-02-24 10:37:06,562][12747] Saving new best policy, reward=9.562!
[2023-02-24 10:37:11,542][00397] Fps is (10 sec: 2459.4, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 2244608. Throughput: 0: 849.1. Samples: 560324. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:37:11,544][00397] Avg episode reward: [(0, '10.419')]
[2023-02-24 10:37:11,563][12747] Saving new best policy, reward=10.419!
[2023-02-24 10:37:12,924][12761] Updated weights for policy 0, policy_version 550 (0.0018)
[2023-02-24 10:37:16,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3429.5). Total num frames: 2265088. Throughput: 0: 877.9. Samples: 565688. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:37:16,550][00397] Avg episode reward: [(0, '10.634')]
[2023-02-24 10:37:16,610][12747] Saving new best policy, reward=10.634!
[2023-02-24 10:37:21,542][00397] Fps is (10 sec: 4505.6, 60 sec: 3481.6, 300 sec: 3457.3). Total num frames: 2289664. Throughput: 0: 892.2. Samples: 572054. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:37:21,546][00397] Avg episode reward: [(0, '11.379')]
[2023-02-24 10:37:21,561][12747] Saving new best policy, reward=11.379!
[2023-02-24 10:37:22,975][12761] Updated weights for policy 0, policy_version 560 (0.0019)
[2023-02-24 10:37:26,542][00397] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3457.3). Total num frames: 2301952. Throughput: 0: 870.7. Samples: 574358. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:37:26,546][00397] Avg episode reward: [(0, '11.885')]
[2023-02-24 10:37:26,552][12747] Saving new best policy, reward=11.885!
[2023-02-24 10:37:31,542][00397] Fps is (10 sec: 2457.6, 60 sec: 3481.6, 300 sec: 3429.5). Total num frames: 2314240. Throughput: 0: 852.0. Samples: 578706. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:37:31,548][00397] Avg episode reward: [(0, '11.252')]
[2023-02-24 10:37:31,625][12747] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000566_2318336.pth...
[2023-02-24 10:37:31,759][12747] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000364_1490944.pth
[2023-02-24 10:37:35,633][12761] Updated weights for policy 0, policy_version 570 (0.0021)
[2023-02-24 10:37:36,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3429.5). Total num frames: 2334720. Throughput: 0: 886.0. Samples: 584340. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:37:36,544][00397] Avg episode reward: [(0, '11.801')]
[2023-02-24 10:37:41,542][00397] Fps is (10 sec: 4505.6, 60 sec: 3481.6, 300 sec: 3457.4). Total num frames: 2359296. Throughput: 0: 890.6. Samples: 587488. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:37:41,547][00397] Avg episode reward: [(0, '12.648')]
[2023-02-24 10:37:41,556][12747] Saving new best policy, reward=12.648!
[2023-02-24 10:37:46,545][00397] Fps is (10 sec: 3685.2, 60 sec: 3481.4, 300 sec: 3457.3). Total num frames: 2371584. Throughput: 0: 862.9. Samples: 592596. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:37:46,549][00397] Avg episode reward: [(0, '13.506')]
[2023-02-24 10:37:46,554][12747] Saving new best policy, reward=13.506!
[2023-02-24 10:37:47,558][12761] Updated weights for policy 0, policy_version 580 (0.0032)
[2023-02-24 10:37:51,545][00397] Fps is (10 sec: 2456.8, 60 sec: 3481.4, 300 sec: 3429.5). Total num frames: 2383872. Throughput: 0: 847.7. Samples: 596522. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:37:51,548][00397] Avg episode reward: [(0, '13.849')]
[2023-02-24 10:37:51,556][12747] Saving new best policy, reward=13.849!
[2023-02-24 10:37:56,542][00397] Fps is (10 sec: 3277.9, 60 sec: 3413.3, 300 sec: 3429.5). Total num frames: 2404352. Throughput: 0: 869.9. Samples: 599468. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:37:56,550][00397] Avg episode reward: [(0, '14.924')]
[2023-02-24 10:37:56,555][12747] Saving new best policy, reward=14.924!
[2023-02-24 10:37:58,739][12761] Updated weights for policy 0, policy_version 590 (0.0024)
[2023-02-24 10:38:01,544][00397] Fps is (10 sec: 4096.5, 60 sec: 3413.6, 300 sec: 3443.4). Total num frames: 2424832. Throughput: 0: 890.1. Samples: 605744. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:38:01,547][00397] Avg episode reward: [(0, '14.506')]
[2023-02-24 10:38:06,544][00397] Fps is (10 sec: 3685.5, 60 sec: 3481.5, 300 sec: 3457.3). Total num frames: 2441216. Throughput: 0: 852.1. Samples: 610402. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:38:06,550][00397] Avg episode reward: [(0, '13.757')]
[2023-02-24 10:38:11,542][00397] Fps is (10 sec: 2867.8, 60 sec: 3481.6, 300 sec: 3429.5). Total num frames: 2453504. Throughput: 0: 845.9. Samples: 612424. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:38:11,547][00397] Avg episode reward: [(0, '13.112')]
[2023-02-24 10:38:11,789][12761] Updated weights for policy 0, policy_version 600 (0.0023)
[2023-02-24 10:38:16,542][00397] Fps is (10 sec: 3687.2, 60 sec: 3549.9, 300 sec: 3443.4). Total num frames: 2478080. Throughput: 0: 876.2. Samples: 618134. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
[2023-02-24 10:38:16,548][00397] Avg episode reward: [(0, '12.554')]
[2023-02-24 10:38:20,898][12761] Updated weights for policy 0, policy_version 610 (0.0014)
[2023-02-24 10:38:21,542][00397] Fps is (10 sec: 4505.6, 60 sec: 3481.6, 300 sec: 3457.3). Total num frames: 2498560. Throughput: 0: 901.6. Samples: 624912. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:38:21,547][00397] Avg episode reward: [(0, '12.514')]
[2023-02-24 10:38:26,542][00397] Fps is (10 sec: 3686.3, 60 sec: 3549.9, 300 sec: 3471.2). Total num frames: 2514944. Throughput: 0: 884.2. Samples: 627276. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-24 10:38:26,549][00397] Avg episode reward: [(0, '13.858')]
[2023-02-24 10:38:31,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3443.4). Total num frames: 2527232. Throughput: 0: 865.8. Samples: 631552. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:38:31,544][00397] Avg episode reward: [(0, '16.050')]
[2023-02-24 10:38:31,560][12747] Saving new best policy, reward=16.050!
[2023-02-24 10:38:33,641][12761] Updated weights for policy 0, policy_version 620 (0.0027)
[2023-02-24 10:38:36,542][00397] Fps is (10 sec: 3686.3, 60 sec: 3618.1, 300 sec: 3457.3). Total num frames: 2551808. Throughput: 0: 913.5. Samples: 637626. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:38:36,554][00397] Avg episode reward: [(0, '16.308')]
[2023-02-24 10:38:36,557][12747] Saving new best policy, reward=16.308!
[2023-02-24 10:38:41,542][00397] Fps is (10 sec: 4505.6, 60 sec: 3549.9, 300 sec: 3471.2). Total num frames: 2572288. Throughput: 0: 920.0. Samples: 640866. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-24 10:38:41,544][00397] Avg episode reward: [(0, '16.464')]
[2023-02-24 10:38:41,571][12747] Saving new best policy, reward=16.464!
[2023-02-24 10:38:44,122][12761] Updated weights for policy 0, policy_version 630 (0.0016)
[2023-02-24 10:38:46,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3550.0, 300 sec: 3471.2). Total num frames: 2584576. Throughput: 0: 891.6. Samples: 645864. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:38:46,549][00397] Avg episode reward: [(0, '15.841')]
[2023-02-24 10:38:51,542][00397] Fps is (10 sec: 2457.6, 60 sec: 3550.1, 300 sec: 3443.4). Total num frames: 2596864. Throughput: 0: 877.0. Samples: 649866. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:38:51,544][00397] Avg episode reward: [(0, '15.872')]
[2023-02-24 10:38:56,440][12761] Updated weights for policy 0, policy_version 640 (0.0032)
[2023-02-24 10:38:56,542][00397] Fps is (10 sec: 3686.5, 60 sec: 3618.1, 300 sec: 3457.3). Total num frames: 2621440. Throughput: 0: 902.8. Samples: 653050. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:38:56,549][00397] Avg episode reward: [(0, '16.378')]
[2023-02-24 10:39:01,547][00397] Fps is (10 sec: 4503.2, 60 sec: 3617.9, 300 sec: 3471.1). Total num frames: 2641920. Throughput: 0: 918.4. Samples: 659468. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:39:01,550][00397] Avg episode reward: [(0, '16.883')]
[2023-02-24 10:39:01,564][12747] Saving new best policy, reward=16.883!
[2023-02-24 10:39:06,542][00397] Fps is (10 sec: 3276.7, 60 sec: 3550.0, 300 sec: 3471.2). Total num frames: 2654208. Throughput: 0: 869.9. Samples: 664056. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:39:06,545][00397] Avg episode reward: [(0, '17.849')]
[2023-02-24 10:39:06,551][12747] Saving new best policy, reward=17.849!
[2023-02-24 10:39:08,849][12761] Updated weights for policy 0, policy_version 650 (0.0013)
[2023-02-24 10:39:11,542][00397] Fps is (10 sec: 2868.7, 60 sec: 3618.1, 300 sec: 3457.3). Total num frames: 2670592. Throughput: 0: 860.9. Samples: 666016. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:39:11,545][00397] Avg episode reward: [(0, '17.880')]
[2023-02-24 10:39:11,553][12747] Saving new best policy, reward=17.880!
[2023-02-24 10:39:16,543][00397] Fps is (10 sec: 3276.5, 60 sec: 3481.5, 300 sec: 3443.4). Total num frames: 2686976. Throughput: 0: 881.7. Samples: 671228. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:39:16,550][00397] Avg episode reward: [(0, '17.675')]
[2023-02-24 10:39:19,496][12761] Updated weights for policy 0, policy_version 660 (0.0025)
[2023-02-24 10:39:21,542][00397] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3471.2). Total num frames: 2711552. Throughput: 0: 889.5. Samples: 677652. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:39:21,549][00397] Avg episode reward: [(0, '17.247')]
[2023-02-24 10:39:26,542][00397] Fps is (10 sec: 3686.7, 60 sec: 3481.6, 300 sec: 3471.2). Total num frames: 2723840. Throughput: 0: 864.9. Samples: 679788. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 10:39:26,547][00397] Avg episode reward: [(0, '17.597')]
[2023-02-24 10:39:31,542][00397] Fps is (10 sec: 2047.9, 60 sec: 3413.3, 300 sec: 3429.5). Total num frames: 2732032. Throughput: 0: 831.6. Samples: 683288. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:39:31,545][00397] Avg episode reward: [(0, '17.362')]
[2023-02-24 10:39:31,564][12747] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000667_2732032.pth...
[2023-02-24 10:39:31,748][12747] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000467_1912832.pth
[2023-02-24 10:39:35,682][12761] Updated weights for policy 0, policy_version 670 (0.0017)
[2023-02-24 10:39:36,542][00397] Fps is (10 sec: 2048.1, 60 sec: 3208.5, 300 sec: 3387.9). Total num frames: 2744320. Throughput: 0: 821.2. Samples: 686822. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:39:36,545][00397] Avg episode reward: [(0, '18.070')]
[2023-02-24 10:39:36,548][12747] Saving new best policy, reward=18.070!
[2023-02-24 10:39:41,542][00397] Fps is (10 sec: 2867.3, 60 sec: 3140.3, 300 sec: 3401.8). Total num frames: 2760704. Throughput: 0: 793.8. Samples: 688770. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:39:41,544][00397] Avg episode reward: [(0, '18.944')]
[2023-02-24 10:39:41,560][12747] Saving new best policy, reward=18.944!
[2023-02-24 10:39:46,542][00397] Fps is (10 sec: 3276.7, 60 sec: 3208.5, 300 sec: 3401.8). Total num frames: 2777088. Throughput: 0: 767.5. Samples: 694000. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:39:46,546][00397] Avg episode reward: [(0, '19.577')]
[2023-02-24 10:39:46,551][12747] Saving new best policy, reward=19.577!
[2023-02-24 10:39:49,002][12761] Updated weights for policy 0, policy_version 680 (0.0024)
[2023-02-24 10:39:51,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3208.5, 300 sec: 3387.9). Total num frames: 2789376. Throughput: 0: 752.1. Samples: 697898. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:39:51,544][00397] Avg episode reward: [(0, '18.399')]
[2023-02-24 10:39:56,542][00397] Fps is (10 sec: 3276.9, 60 sec: 3140.3, 300 sec: 3374.0). Total num frames: 2809856. Throughput: 0: 765.6. Samples: 700468. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:39:56,549][00397] Avg episode reward: [(0, '18.473')]
[2023-02-24 10:39:59,924][12761] Updated weights for policy 0, policy_version 690 (0.0028)
[2023-02-24 10:40:01,542][00397] Fps is (10 sec: 4096.0, 60 sec: 3140.5, 300 sec: 3401.8). Total num frames: 2830336. Throughput: 0: 790.5. Samples: 706798. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:40:01,549][00397] Avg episode reward: [(0, '18.547')]
[2023-02-24 10:40:06,545][00397] Fps is (10 sec: 3275.7, 60 sec: 3140.1, 300 sec: 3401.7). Total num frames: 2842624. Throughput: 0: 755.5. Samples: 711652. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:40:06,548][00397] Avg episode reward: [(0, '18.487')]
[2023-02-24 10:40:11,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3140.3, 300 sec: 3387.9). Total num frames: 2859008. Throughput: 0: 751.7. Samples: 713614. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:40:11,545][00397] Avg episode reward: [(0, '17.444')]
[2023-02-24 10:40:13,482][12761] Updated weights for policy 0, policy_version 700 (0.0012)
[2023-02-24 10:40:16,542][00397] Fps is (10 sec: 3687.6, 60 sec: 3208.6, 300 sec: 3374.0). Total num frames: 2879488. Throughput: 0: 784.4. Samples: 718586. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:40:16,544][00397] Avg episode reward: [(0, '18.513')]
[2023-02-24 10:40:21,542][00397] Fps is (10 sec: 4095.9, 60 sec: 3140.3, 300 sec: 3401.8). Total num frames: 2899968. Throughput: 0: 850.3. Samples: 725084. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:40:21,544][00397] Avg episode reward: [(0, '18.193')]
[2023-02-24 10:40:23,616][12761] Updated weights for policy 0, policy_version 710 (0.0023)
[2023-02-24 10:40:26,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3387.9). Total num frames: 2912256. Throughput: 0: 861.3. Samples: 727530. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:40:26,549][00397] Avg episode reward: [(0, '17.958')]
[2023-02-24 10:40:31,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3374.0). Total num frames: 2928640. Throughput: 0: 834.0. Samples: 731528. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:40:31,544][00397] Avg episode reward: [(0, '18.287')]
[2023-02-24 10:40:36,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3360.1). Total num frames: 2945024. Throughput: 0: 867.0. Samples: 736912. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:40:36,544][00397] Avg episode reward: [(0, '18.157')]
[2023-02-24 10:40:36,557][12761] Updated weights for policy 0, policy_version 720 (0.0019)
[2023-02-24 10:40:41,542][00397] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 2969600. Throughput: 0: 880.4. Samples: 740086. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:40:41,547][00397] Avg episode reward: [(0, '18.209')]
[2023-02-24 10:40:46,542][00397] Fps is (10 sec: 3686.4, 60 sec: 3413.4, 300 sec: 3401.8). Total num frames: 2981888. Throughput: 0: 856.4. Samples: 745334. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:40:46,550][00397] Avg episode reward: [(0, '18.556')]
[2023-02-24 10:40:48,971][12761] Updated weights for policy 0, policy_version 730 (0.0018)
[2023-02-24 10:40:51,542][00397] Fps is (10 sec: 2457.6, 60 sec: 3413.3, 300 sec: 3387.9). Total num frames: 2994176. Throughput: 0: 835.4. Samples: 749240. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:40:51,544][00397] Avg episode reward: [(0, '18.760')]
[2023-02-24 10:40:56,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3415.6). Total num frames: 3014656. Throughput: 0: 852.3. Samples: 751966. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:40:56,544][00397] Avg episode reward: [(0, '19.041')]
[2023-02-24 10:40:59,702][12761] Updated weights for policy 0, policy_version 740 (0.0021)
[2023-02-24 10:41:01,542][00397] Fps is (10 sec: 4505.6, 60 sec: 3481.6, 300 sec: 3443.4). Total num frames: 3039232. Throughput: 0: 884.2. Samples: 758376. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-24 10:41:01,551][00397] Avg episode reward: [(0, '19.427')]
[2023-02-24 10:41:06,543][00397] Fps is (10 sec: 3685.8, 60 sec: 3481.7, 300 sec: 3443.4). Total num frames: 3051520. Throughput: 0: 850.7. Samples: 763368. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:41:06,545][00397] Avg episode reward: [(0, '20.028')]
[2023-02-24 10:41:06,553][12747] Saving new best policy, reward=20.028!
[2023-02-24 10:41:11,542][00397] Fps is (10 sec: 2457.6, 60 sec: 3413.3, 300 sec: 3415.6). Total num frames: 3063808. Throughput: 0: 838.2. Samples: 765248. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-24 10:41:11,544][00397] Avg episode reward: [(0, '20.465')]
[2023-02-24 10:41:11,554][12747] Saving new best policy, reward=20.465!
[2023-02-24 10:41:12,918][12761] Updated weights for policy 0, policy_version 750 (0.0020)
[2023-02-24 10:41:16,542][00397] Fps is (10 sec: 3277.3, 60 sec: 3413.3, 300 sec: 3401.8). Total num frames: 3084288. Throughput: 0: 865.6. Samples: 770478. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:41:16,544][00397] Avg episode reward: [(0, '20.317')]
[2023-02-24 10:41:21,542][00397] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3429.5). Total num frames: 3104768. Throughput: 0: 886.7. Samples: 776812. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:41:21,544][00397] Avg episode reward: [(0, '20.717')]
[2023-02-24 10:41:21,557][12747] Saving new best policy, reward=20.717!
[2023-02-24 10:41:23,387][12761] Updated weights for policy 0, policy_version 760 (0.0012)
[2023-02-24 10:41:26,542][00397] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3443.4). Total num frames: 3121152. Throughput: 0: 868.0. Samples: 779144. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:41:26,549][00397] Avg episode reward: [(0, '22.091')]
[2023-02-24 10:41:26,561][12747] Saving new best policy, reward=22.091!
[2023-02-24 10:41:31,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3415.6). Total num frames: 3133440. Throughput: 0: 840.9. Samples: 783174. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:41:31,552][00397] Avg episode reward: [(0, '21.025')]
[2023-02-24 10:41:31,562][12747] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000765_3133440.pth...
[2023-02-24 10:41:31,679][12747] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000566_2318336.pth
[2023-02-24 10:41:35,957][12761] Updated weights for policy 0, policy_version 770 (0.0044)
[2023-02-24 10:41:36,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 3153920. Throughput: 0: 881.7. Samples: 788916. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-24 10:41:36,545][00397] Avg episode reward: [(0, '21.090')]
[2023-02-24 10:41:41,542][00397] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3429.5). Total num frames: 3174400. Throughput: 0: 891.4. Samples: 792080. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-24 10:41:41,547][00397] Avg episode reward: [(0, '21.272')]
[2023-02-24 10:41:46,543][00397] Fps is (10 sec: 3685.9, 60 sec: 3481.5, 300 sec: 3443.4). Total num frames: 3190784. Throughput: 0: 862.7. Samples: 797200. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:41:46,547][00397] Avg episode reward: [(0, '21.030')]
[2023-02-24 10:41:47,715][12761] Updated weights for policy 0, policy_version 780 (0.0018)
[2023-02-24 10:41:51,544][00397] Fps is (10 sec: 2866.6, 60 sec: 3481.5, 300 sec: 3401.7). Total num frames: 3203072. Throughput: 0: 842.8. Samples: 801294. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:41:51,552][00397] Avg episode reward: [(0, '22.160')]
[2023-02-24 10:41:51,568][12747] Saving new best policy, reward=22.160!
[2023-02-24 10:41:56,542][00397] Fps is (10 sec: 3277.2, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 3223552. Throughput: 0: 867.3. Samples: 804276. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:41:56,549][00397] Avg episode reward: [(0, '21.076')]
[2023-02-24 10:41:58,455][12761] Updated weights for policy 0, policy_version 790 (0.0014)
[2023-02-24 10:42:01,544][00397] Fps is (10 sec: 4505.6, 60 sec: 3481.5, 300 sec: 3443.4). Total num frames: 3248128. Throughput: 0: 895.4. Samples: 810774. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:42:01,547][00397] Avg episode reward: [(0, '21.135')]
[2023-02-24 10:42:06,542][00397] Fps is (10 sec: 3686.4, 60 sec: 3481.7, 300 sec: 3443.4). Total num frames: 3260416. Throughput: 0: 855.8. Samples: 815324. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:42:06,544][00397] Avg episode reward: [(0, '20.155')]
[2023-02-24 10:42:11,542][00397] Fps is (10 sec: 2458.1, 60 sec: 3481.6, 300 sec: 3415.6). Total num frames: 3272704. Throughput: 0: 847.6. Samples: 817284. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:42:11,549][00397] Avg episode reward: [(0, '20.994')]
[2023-02-24 10:42:11,862][12761] Updated weights for policy 0, policy_version 800 (0.0026)
[2023-02-24 10:42:16,542][00397] Fps is (10 sec: 3276.7, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 3293184. Throughput: 0: 880.6. Samples: 822800. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:42:16,549][00397] Avg episode reward: [(0, '19.746')]
[2023-02-24 10:42:21,542][00397] Fps is (10 sec: 4096.1, 60 sec: 3481.6, 300 sec: 3429.5). Total num frames: 3313664. Throughput: 0: 894.1. Samples: 829152. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:42:21,547][00397] Avg episode reward: [(0, '19.621')]
[2023-02-24 10:42:21,637][12761] Updated weights for policy 0, policy_version 810 (0.0020)
[2023-02-24 10:42:26,543][00397] Fps is (10 sec: 3686.1, 60 sec: 3481.5, 300 sec: 3443.4). Total num frames: 3330048. Throughput: 0: 874.7. Samples: 831442. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:42:26,547][00397] Avg episode reward: [(0, '19.762')]
[2023-02-24 10:42:31,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3429.5). Total num frames: 3346432. Throughput: 0: 854.6. Samples: 835658. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:42:31,552][00397] Avg episode reward: [(0, '20.909')]
[2023-02-24 10:42:34,417][12761] Updated weights for policy 0, policy_version 820 (0.0017)
[2023-02-24 10:42:36,542][00397] Fps is (10 sec: 3686.8, 60 sec: 3549.9, 300 sec: 3415.6). Total num frames: 3366912. Throughput: 0: 897.3. Samples: 841670. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:42:36,544][00397] Avg episode reward: [(0, '20.931')]
[2023-02-24 10:42:41,544][00397] Fps is (10 sec: 4095.1, 60 sec: 3549.7, 300 sec: 3443.4). Total num frames: 3387392. Throughput: 0: 903.2. Samples: 844920. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 10:42:41,547][00397] Avg episode reward: [(0, '20.491')]
[2023-02-24 10:42:45,634][12761] Updated weights for policy 0, policy_version 830 (0.0023)
[2023-02-24 10:42:46,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3481.7, 300 sec: 3443.5). Total num frames: 3399680. Throughput: 0: 869.6. Samples: 849902. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:42:46,544][00397] Avg episode reward: [(0, '21.798')]
[2023-02-24 10:42:51,542][00397] Fps is (10 sec: 2867.8, 60 sec: 3550.0, 300 sec: 3429.5). Total num frames: 3416064. Throughput: 0: 859.1. Samples: 853984. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:42:51,549][00397] Avg episode reward: [(0, '20.931')]
[2023-02-24 10:42:56,542][00397] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3429.6). Total num frames: 3436544. Throughput: 0: 885.0. Samples: 857110. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:42:56,544][00397] Avg episode reward: [(0, '21.026')]
[2023-02-24 10:42:57,144][12761] Updated weights for policy 0, policy_version 840 (0.0021)
[2023-02-24 10:43:01,542][00397] Fps is (10 sec: 4096.0, 60 sec: 3481.7, 300 sec: 3443.4). Total num frames: 3457024. Throughput: 0: 904.9. Samples: 863518. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:43:01,546][00397] Avg episode reward: [(0, '20.184')]
[2023-02-24 10:43:06,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3443.4). Total num frames: 3469312. Throughput: 0: 859.9. Samples: 867848. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 10:43:06,544][00397] Avg episode reward: [(0, '19.842')]
[2023-02-24 10:43:11,461][12761] Updated weights for policy 0, policy_version 850 (0.0028)
[2023-02-24 10:43:11,543][00397] Fps is (10 sec: 2457.3, 60 sec: 3481.5, 300 sec: 3401.7). Total num frames: 3481600. Throughput: 0: 845.6. Samples: 869494. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 10:43:11,546][00397] Avg episode reward: [(0, '19.154')]
[2023-02-24 10:43:16,543][00397] Fps is (10 sec: 2457.4, 60 sec: 3345.0, 300 sec: 3374.0). Total num frames: 3493888. Throughput: 0: 823.7. Samples: 872724. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:43:16,547][00397] Avg episode reward: [(0, '18.908')]
[2023-02-24 10:43:21,542][00397] Fps is (10 sec: 3277.2, 60 sec: 3345.1, 300 sec: 3387.9). Total num frames: 3514368. Throughput: 0: 813.3. Samples: 878268. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:43:21,549][00397] Avg episode reward: [(0, '18.639')]
[2023-02-24 10:43:23,395][12761] Updated weights for policy 0, policy_version 860 (0.0030)
[2023-02-24 10:43:26,542][00397] Fps is (10 sec: 3686.8, 60 sec: 3345.1, 300 sec: 3401.8). Total num frames: 3530752. Throughput: 0: 812.9. Samples: 881500. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:43:26,555][00397] Avg episode reward: [(0, '18.780')]
[2023-02-24 10:43:31,543][00397] Fps is (10 sec: 2866.8, 60 sec: 3276.7, 300 sec: 3360.1). Total num frames: 3543040. Throughput: 0: 798.4. Samples: 885830. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:43:31,548][00397] Avg episode reward: [(0, '20.090')]
[2023-02-24 10:43:31,566][12747] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000865_3543040.pth...
[2023-02-24 10:43:31,723][12747] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000667_2732032.pth
[2023-02-24 10:43:36,362][12761] Updated weights for policy 0, policy_version 870 (0.0038)
[2023-02-24 10:43:36,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3360.1). Total num frames: 3563520. Throughput: 0: 812.6. Samples: 890550. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:43:36,544][00397] Avg episode reward: [(0, '21.596')]
[2023-02-24 10:43:41,542][00397] Fps is (10 sec: 4096.5, 60 sec: 3276.9, 300 sec: 3387.9). Total num frames: 3584000. Throughput: 0: 812.8. Samples: 893688. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:43:41,547][00397] Avg episode reward: [(0, '21.124')]
[2023-02-24 10:43:46,542][00397] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3401.8). Total num frames: 3600384. Throughput: 0: 809.0. Samples: 899922. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:43:46,544][00397] Avg episode reward: [(0, '22.416')]
[2023-02-24 10:43:46,549][12747] Saving new best policy, reward=22.416!
[2023-02-24 10:43:47,363][12761] Updated weights for policy 0, policy_version 880 (0.0024)
[2023-02-24 10:43:51,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3360.1). Total num frames: 3612672. Throughput: 0: 803.2. Samples: 903994. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 10:43:51,546][00397] Avg episode reward: [(0, '24.392')]
[2023-02-24 10:43:51,557][12747] Saving new best policy, reward=24.392!
[2023-02-24 10:43:56,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3360.2). Total num frames: 3633152. Throughput: 0: 813.8. Samples: 906116. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 10:43:56,544][00397] Avg episode reward: [(0, '23.679')]
[2023-02-24 10:43:59,095][12761] Updated weights for policy 0, policy_version 890 (0.0030)
[2023-02-24 10:44:01,542][00397] Fps is (10 sec: 4096.1, 60 sec: 3276.8, 300 sec: 3387.9). Total num frames: 3653632. Throughput: 0: 881.0. Samples: 912370. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:44:01,548][00397] Avg episode reward: [(0, '22.403')]
[2023-02-24 10:44:06,542][00397] Fps is (10 sec: 3686.3, 60 sec: 3345.1, 300 sec: 3387.9). Total num frames: 3670016. Throughput: 0: 884.8. Samples: 918086. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-24 10:44:06,546][00397] Avg episode reward: [(0, '21.287')]
[2023-02-24 10:44:11,543][00397] Fps is (10 sec: 2866.8, 60 sec: 3345.1, 300 sec: 3374.0). Total num frames: 3682304. Throughput: 0: 856.8. Samples: 920058. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:44:11,546][00397] Avg episode reward: [(0, '20.960')]
[2023-02-24 10:44:11,575][12761] Updated weights for policy 0, policy_version 900 (0.0015)
[2023-02-24 10:44:16,542][00397] Fps is (10 sec: 3276.9, 60 sec: 3481.7, 300 sec: 3360.1). Total num frames: 3702784. Throughput: 0: 859.9. Samples: 924526. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:44:16,550][00397] Avg episode reward: [(0, '19.070')]
[2023-02-24 10:44:21,542][00397] Fps is (10 sec: 4096.6, 60 sec: 3481.6, 300 sec: 3387.9). Total num frames: 3723264. Throughput: 0: 895.6. Samples: 930852. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 10:44:21,548][00397] Avg episode reward: [(0, '19.823')]
[2023-02-24 10:44:22,053][12761] Updated weights for policy 0, policy_version 910 (0.0012)
[2023-02-24 10:44:26,542][00397] Fps is (10 sec: 3686.3, 60 sec: 3481.6, 300 sec: 3415.6). Total num frames: 3739648. Throughput: 0: 898.0. Samples: 934098. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-24 10:44:26,548][00397] Avg episode reward: [(0, '19.563')]
[2023-02-24 10:44:31,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3429.5). Total num frames: 3756032. Throughput: 0: 852.7. Samples: 938294. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:44:31,547][00397] Avg episode reward: [(0, '19.353')]
[2023-02-24 10:44:35,015][12761] Updated weights for policy 0, policy_version 920 (0.0042)
[2023-02-24 10:44:36,542][00397] Fps is (10 sec: 3276.9, 60 sec: 3481.6, 300 sec: 3429.5). Total num frames: 3772416. Throughput: 0: 874.8. Samples: 943360. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:44:36,544][00397] Avg episode reward: [(0, '19.664')]
[2023-02-24 10:44:41,542][00397] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3443.4). Total num frames: 3792896. Throughput: 0: 899.3. Samples: 946584. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:44:41,544][00397] Avg episode reward: [(0, '20.194')]
[2023-02-24 10:44:45,212][12761] Updated weights for policy 0, policy_version 930 (0.0012)
[2023-02-24 10:44:46,542][00397] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3471.2). Total num frames: 3813376. Throughput: 0: 893.2. Samples: 952564. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-24 10:44:46,549][00397] Avg episode reward: [(0, '20.486')]
[2023-02-24 10:44:51,544][00397] Fps is (10 sec: 3275.9, 60 sec: 3549.7, 300 sec: 3443.4). Total num frames: 3825664. Throughput: 0: 854.6. Samples: 956544. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:44:51,550][00397] Avg episode reward: [(0, '19.819')]
[2023-02-24 10:44:56,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3429.5). Total num frames: 3842048. Throughput: 0: 858.4. Samples: 958686. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:44:56,549][00397] Avg episode reward: [(0, '20.291')]
[2023-02-24 10:44:57,695][12761] Updated weights for policy 0, policy_version 940 (0.0029)
[2023-02-24 10:45:01,544][00397] Fps is (10 sec: 4096.2, 60 sec: 3549.7, 300 sec: 3471.2). Total num frames: 3866624. Throughput: 0: 902.4. Samples: 965138. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-24 10:45:01,546][00397] Avg episode reward: [(0, '21.595')]
[2023-02-24 10:45:06,542][00397] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3471.2). Total num frames: 3883008. Throughput: 0: 886.3. Samples: 970736. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:45:06,551][00397] Avg episode reward: [(0, '21.612')]
[2023-02-24 10:45:09,554][12761] Updated weights for policy 0, policy_version 950 (0.0028)
[2023-02-24 10:45:11,542][00397] Fps is (10 sec: 2867.8, 60 sec: 3550.0, 300 sec: 3443.4). Total num frames: 3895296. Throughput: 0: 858.8. Samples: 972744. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-24 10:45:11,550][00397] Avg episode reward: [(0, '21.260')]
[2023-02-24 10:45:16,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3429.5). Total num frames: 3911680. Throughput: 0: 868.3. Samples: 977366. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-24 10:45:16,546][00397] Avg episode reward: [(0, '21.973')]
[2023-02-24 10:45:20,391][12761] Updated weights for policy 0, policy_version 960 (0.0012)
[2023-02-24 10:45:21,542][00397] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3471.2). Total num frames: 3936256. Throughput: 0: 904.6. Samples: 984066. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 10:45:21,549][00397] Avg episode reward: [(0, '23.475')]
[2023-02-24 10:45:26,542][00397] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3471.2). Total num frames: 3952640. Throughput: 0: 900.6. Samples: 987110. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-24 10:45:26,547][00397] Avg episode reward: [(0, '23.064')]
[2023-02-24 10:45:31,542][00397] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3457.3). Total num frames: 3964928. Throughput: 0: 860.0. Samples: 991264. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 10:45:31,551][00397] Avg episode reward: [(0, '22.880')]
[2023-02-24 10:45:31,564][12747] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000968_3964928.pth...
[2023-02-24 10:45:31,720][12747] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000765_3133440.pth
[2023-02-24 10:45:33,452][12761] Updated weights for policy 0, policy_version 970 (0.0024)
[2023-02-24 10:45:36,542][00397] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3443.4). Total num frames: 3985408. Throughput: 0: 885.3. Samples: 996380. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-24 10:45:36,545][00397] Avg episode reward: [(0, '23.247')]
[2023-02-24 10:45:40,999][12747] Stopping Batcher_0...
[2023-02-24 10:45:41,000][12747] Loop batcher_evt_loop terminating...
[2023-02-24 10:45:41,000][00397] Component Batcher_0 stopped!
[2023-02-24 10:45:41,004][12747] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2023-02-24 10:45:41,040][12761] Weights refcount: 2 0
[2023-02-24 10:45:41,056][12761] Stopping InferenceWorker_p0-w0...
[2023-02-24 10:45:41,058][12761] Loop inference_proc0-0_evt_loop terminating...
[2023-02-24 10:45:41,057][00397] Component InferenceWorker_p0-w0 stopped!
[2023-02-24 10:45:41,077][12767] Stopping RolloutWorker_w5...
[2023-02-24 10:45:41,077][00397] Component RolloutWorker_w5 stopped!
[2023-02-24 10:45:41,086][00397] Component RolloutWorker_w7 stopped!
[2023-02-24 10:45:41,098][12764] Stopping RolloutWorker_w1...
[2023-02-24 10:45:41,100][00397] Component RolloutWorker_w1 stopped!
[2023-02-24 10:45:41,086][12768] Stopping RolloutWorker_w7...
[2023-02-24 10:45:41,111][12767] Loop rollout_proc5_evt_loop terminating...
[2023-02-24 10:45:41,127][00397] Component RolloutWorker_w4 stopped!
[2023-02-24 10:45:41,099][12764] Loop rollout_proc1_evt_loop terminating...
[2023-02-24 10:45:41,151][12763] Stopping RolloutWorker_w2...
[2023-02-24 10:45:41,152][12763] Loop rollout_proc2_evt_loop terminating...
[2023-02-24 10:45:41,126][12766] Stopping RolloutWorker_w4...
[2023-02-24 10:45:41,153][12766] Loop rollout_proc4_evt_loop terminating...
[2023-02-24 10:45:41,146][00397] Component RolloutWorker_w3 stopped!
[2023-02-24 10:45:41,157][12762] Stopping RolloutWorker_w0...
[2023-02-24 10:45:41,157][00397] Component RolloutWorker_w2 stopped!
[2023-02-24 10:45:41,158][12762] Loop rollout_proc0_evt_loop terminating...
[2023-02-24 10:45:41,160][12765] Stopping RolloutWorker_w3...
[2023-02-24 10:45:41,160][12769] Stopping RolloutWorker_w6...
[2023-02-24 10:45:41,158][00397] Component RolloutWorker_w0 stopped!
[2023-02-24 10:45:41,163][12769] Loop rollout_proc6_evt_loop terminating...
[2023-02-24 10:45:41,162][00397] Component RolloutWorker_w6 stopped!
[2023-02-24 10:45:41,125][12768] Loop rollout_proc7_evt_loop terminating...
[2023-02-24 10:45:41,183][12765] Loop rollout_proc3_evt_loop terminating...
[2023-02-24 10:45:41,249][12747] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000865_3543040.pth
[2023-02-24 10:45:41,268][12747] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2023-02-24 10:45:41,474][00397] Component LearnerWorker_p0 stopped!
[2023-02-24 10:45:41,481][00397] Waiting for process learner_proc0 to stop...
[2023-02-24 10:45:41,488][12747] Stopping LearnerWorker_p0...
[2023-02-24 10:45:41,488][12747] Loop learner_proc0_evt_loop terminating...
[2023-02-24 10:45:43,508][00397] Waiting for process inference_proc0-0 to join...
[2023-02-24 10:45:44,057][00397] Waiting for process rollout_proc0 to join...
[2023-02-24 10:45:44,060][00397] Waiting for process rollout_proc1 to join...
[2023-02-24 10:45:44,911][00397] Waiting for process rollout_proc2 to join...
[2023-02-24 10:45:44,915][00397] Waiting for process rollout_proc3 to join...
[2023-02-24 10:45:44,923][00397] Waiting for process rollout_proc4 to join...
[2023-02-24 10:45:44,925][00397] Waiting for process rollout_proc5 to join...
[2023-02-24 10:45:44,926][00397] Waiting for process rollout_proc6 to join...
[2023-02-24 10:45:44,928][00397] Waiting for process rollout_proc7 to join...
[2023-02-24 10:45:44,961][00397] Batcher 0 profile tree view:
batching: 26.5562, releasing_batches: 0.0289
[2023-02-24 10:45:44,969][00397] InferenceWorker_p0-w0 profile tree view:
wait_policy: 0.0075
  wait_policy_total: 582.7002
update_model: 8.4019
  weight_update: 0.0013
one_step: 0.0025
  handle_policy_step: 545.4967
    deserialize: 16.4375, stack: 3.2876, obs_to_device_normalize: 120.2653, forward: 265.9622, send_messages: 27.7392
    prepare_outputs: 84.5947
      to_cpu: 51.1742
[2023-02-24 10:45:44,971][00397] Learner 0 profile tree view:
misc: 0.0056, prepare_batch: 17.5079
train: 76.7898
  epoch_init: 0.0135, minibatch_init: 0.0062, losses_postprocess: 0.5833, kl_divergence: 0.7025, after_optimizer: 33.2808
  calculate_losses: 27.2141
    losses_init: 0.0092, forward_head: 1.8706, bptt_initial: 17.9257, tail: 1.0741, advantages_returns: 0.2674, losses: 3.5588
    bptt: 2.1899
      bptt_forward_core: 2.0940
  update: 14.2959
    clip: 1.4149
[2023-02-24 10:45:44,972][00397] RolloutWorker_w0 profile tree view:
wait_for_trajectories: 0.3440, enqueue_policy_requests: 167.7715, env_step: 877.0880, overhead: 24.8764, complete_rollouts: 7.1423
save_policy_outputs: 22.0396
  split_output_tensors: 10.6108
[2023-02-24 10:45:44,977][00397] RolloutWorker_w7 profile tree view:
wait_for_trajectories: 0.3963, enqueue_policy_requests: 169.0908, env_step: 874.9294, overhead: 24.2458, complete_rollouts: 7.5913
save_policy_outputs: 21.5778
  split_output_tensors: 10.2615
[2023-02-24 10:45:44,982][00397] Loop Runner_EvtLoop terminating...
[2023-02-24 10:45:44,984][00397] Runner profile tree view:
main_loop: 1209.0462
[2023-02-24 10:45:44,987][00397] Collected {0: 4005888}, FPS: 3313.3
[2023-02-24 10:47:12,729][00397] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
[2023-02-24 10:47:12,732][00397] Overriding arg 'num_workers' with value 1 passed from command line
[2023-02-24 10:47:12,735][00397] Adding new argument 'no_render'=True that is not in the saved config file!
[2023-02-24 10:47:12,739][00397] Adding new argument 'save_video'=True that is not in the saved config file!
[2023-02-24 10:47:12,741][00397] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2023-02-24 10:47:12,743][00397] Adding new argument 'video_name'=None that is not in the saved config file!
[2023-02-24 10:47:12,746][00397] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
[2023-02-24 10:47:12,747][00397] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2023-02-24 10:47:12,748][00397] Adding new argument 'push_to_hub'=False that is not in the saved config file!
[2023-02-24 10:47:12,749][00397] Adding new argument 'hf_repository'=None that is not in the saved config file!
[2023-02-24 10:47:12,751][00397] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2023-02-24 10:47:12,754][00397] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2023-02-24 10:47:12,755][00397] Adding new argument 'train_script'=None that is not in the saved config file!
[2023-02-24 10:47:12,756][00397] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2023-02-24 10:47:12,757][00397] Using frameskip 1 and render_action_repeat=4 for evaluation
[2023-02-24 10:47:12,794][00397] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-24 10:47:12,798][00397] RunningMeanStd input shape: (3, 72, 128)
[2023-02-24 10:47:12,802][00397] RunningMeanStd input shape: (1,)
[2023-02-24 10:47:12,832][00397] ConvEncoder: input_channels=3
[2023-02-24 10:47:13,675][00397] Conv encoder output size: 512
[2023-02-24 10:47:13,677][00397] Policy head output size: 512
[2023-02-24 10:47:16,164][00397] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2023-02-24 10:47:17,453][00397] Num frames 100...
[2023-02-24 10:47:17,575][00397] Num frames 200...
[2023-02-24 10:47:17,684][00397] Num frames 300...
[2023-02-24 10:47:17,805][00397] Num frames 400...
[2023-02-24 10:47:17,914][00397] Avg episode rewards: #0: 8.480, true rewards: #0: 4.480
[2023-02-24 10:47:17,916][00397] Avg episode reward: 8.480, avg true_objective: 4.480
[2023-02-24 10:47:17,977][00397] Num frames 500...
[2023-02-24 10:47:18,087][00397] Num frames 600...
[2023-02-24 10:47:18,214][00397] Num frames 700...
[2023-02-24 10:47:18,327][00397] Num frames 800...
[2023-02-24 10:47:18,446][00397] Num frames 900...
[2023-02-24 10:47:18,563][00397] Num frames 1000...
[2023-02-24 10:47:18,718][00397] Avg episode rewards: #0: 9.940, true rewards: #0: 5.440
[2023-02-24 10:47:18,719][00397] Avg episode reward: 9.940, avg true_objective: 5.440
[2023-02-24 10:47:18,739][00397] Num frames 1100...
[2023-02-24 10:47:18,851][00397] Num frames 1200...
[2023-02-24 10:47:18,965][00397] Num frames 1300...
[2023-02-24 10:47:19,078][00397] Num frames 1400...
[2023-02-24 10:47:19,194][00397] Num frames 1500...
[2023-02-24 10:47:19,305][00397] Num frames 1600...
[2023-02-24 10:47:19,419][00397] Num frames 1700...
[2023-02-24 10:47:19,533][00397] Num frames 1800...
[2023-02-24 10:47:19,654][00397] Num frames 1900...
[2023-02-24 10:47:19,764][00397] Num frames 2000...
[2023-02-24 10:47:19,873][00397] Num frames 2100...
[2023-02-24 10:47:19,991][00397] Num frames 2200...
[2023-02-24 10:47:20,106][00397] Num frames 2300...
[2023-02-24 10:47:20,225][00397] Num frames 2400...
[2023-02-24 10:47:20,344][00397] Num frames 2500...
[2023-02-24 10:47:20,466][00397] Num frames 2600...
[2023-02-24 10:47:20,580][00397] Num frames 2700...
[2023-02-24 10:47:20,709][00397] Num frames 2800...
[2023-02-24 10:47:20,821][00397] Num frames 2900...
[2023-02-24 10:47:20,945][00397] Num frames 3000...
[2023-02-24 10:47:21,056][00397] Num frames 3100...
[2023-02-24 10:47:21,207][00397] Avg episode rewards: #0: 23.960, true rewards: #0: 10.627
[2023-02-24 10:47:21,209][00397] Avg episode reward: 23.960, avg true_objective: 10.627
[2023-02-24 10:47:21,228][00397] Num frames 3200...
[2023-02-24 10:47:21,341][00397] Num frames 3300...
[2023-02-24 10:47:21,452][00397] Num frames 3400...
[2023-02-24 10:47:21,578][00397] Num frames 3500...
[2023-02-24 10:47:21,696][00397] Num frames 3600...
[2023-02-24 10:47:21,809][00397] Num frames 3700...
[2023-02-24 10:47:21,922][00397] Num frames 3800...
[2023-02-24 10:47:22,039][00397] Num frames 3900...
[2023-02-24 10:47:22,157][00397] Num frames 4000...
[2023-02-24 10:47:22,269][00397] Num frames 4100...
[2023-02-24 10:47:22,391][00397] Num frames 4200...
[2023-02-24 10:47:22,510][00397] Num frames 4300...
[2023-02-24 10:47:22,621][00397] Num frames 4400...
[2023-02-24 10:47:22,747][00397] Num frames 4500...
[2023-02-24 10:47:22,858][00397] Num frames 4600...
[2023-02-24 10:47:22,970][00397] Num frames 4700...
[2023-02-24 10:47:23,097][00397] Avg episode rewards: #0: 26.640, true rewards: #0: 11.890
[2023-02-24 10:47:23,100][00397] Avg episode reward: 26.640, avg true_objective: 11.890
[2023-02-24 10:47:23,151][00397] Num frames 4800...
[2023-02-24 10:47:23,263][00397] Num frames 4900...
[2023-02-24 10:47:23,379][00397] Num frames 5000...
[2023-02-24 10:47:23,488][00397] Num frames 5100...
[2023-02-24 10:47:23,602][00397] Num frames 5200...
[2023-02-24 10:47:23,742][00397] Num frames 5300...
[2023-02-24 10:47:23,909][00397] Num frames 5400...
[2023-02-24 10:47:24,064][00397] Num frames 5500...
[2023-02-24 10:47:24,220][00397] Num frames 5600...
[2023-02-24 10:47:24,382][00397] Num frames 5700...
[2023-02-24 10:47:24,547][00397] Num frames 5800...
[2023-02-24 10:47:24,707][00397] Num frames 5900...
[2023-02-24 10:47:24,873][00397] Num frames 6000...
[2023-02-24 10:47:25,035][00397] Num frames 6100...
[2023-02-24 10:47:25,194][00397] Num frames 6200...
[2023-02-24 10:47:25,375][00397] Num frames 6300...
[2023-02-24 10:47:25,535][00397] Num frames 6400...
[2023-02-24 10:47:25,702][00397] Num frames 6500...
[2023-02-24 10:47:25,875][00397] Num frames 6600...
[2023-02-24 10:47:26,043][00397] Num frames 6700...
[2023-02-24 10:47:26,208][00397] Num frames 6800...
[2023-02-24 10:47:26,292][00397] Avg episode rewards: #0: 32.232, true rewards: #0: 13.632
[2023-02-24 10:47:26,294][00397] Avg episode reward: 32.232, avg true_objective: 13.632
[2023-02-24 10:47:26,432][00397] Num frames 6900...
[2023-02-24 10:47:26,599][00397] Num frames 7000...
[2023-02-24 10:47:26,761][00397] Num frames 7100...
[2023-02-24 10:47:26,937][00397] Num frames 7200...
[2023-02-24 10:47:27,104][00397] Num frames 7300...
[2023-02-24 10:47:27,264][00397] Num frames 7400...
[2023-02-24 10:47:27,382][00397] Num frames 7500...
[2023-02-24 10:47:27,495][00397] Num frames 7600...
[2023-02-24 10:47:27,610][00397] Num frames 7700...
[2023-02-24 10:47:27,720][00397] Num frames 7800...
[2023-02-24 10:47:27,836][00397] Num frames 7900...
[2023-02-24 10:47:27,947][00397] Num frames 8000...
[2023-02-24 10:47:28,058][00397] Num frames 8100...
[2023-02-24 10:47:28,171][00397] Num frames 8200...
[2023-02-24 10:47:28,255][00397] Avg episode rewards: #0: 31.873, true rewards: #0: 13.707
[2023-02-24 10:47:28,256][00397] Avg episode reward: 31.873, avg true_objective: 13.707
[2023-02-24 10:47:28,347][00397] Num frames 8300...
[2023-02-24 10:47:28,468][00397] Num frames 8400...
[2023-02-24 10:47:28,579][00397] Num frames 8500...
[2023-02-24 10:47:28,689][00397] Num frames 8600...
[2023-02-24 10:47:28,791][00397] Avg episode rewards: #0: 28.200, true rewards: #0: 12.343
[2023-02-24 10:47:28,793][00397] Avg episode reward: 28.200, avg true_objective: 12.343
[2023-02-24 10:47:28,871][00397] Num frames 8700...
[2023-02-24 10:47:28,991][00397] Num frames 8800...
[2023-02-24 10:47:29,104][00397] Num frames 8900...
[2023-02-24 10:47:29,219][00397] Num frames 9000...
[2023-02-24 10:47:29,334][00397] Num frames 9100...
[2023-02-24 10:47:29,452][00397] Num frames 9200...
[2023-02-24 10:47:29,564][00397] Num frames 9300...
[2023-02-24 10:47:29,683][00397] Num frames 9400...
[2023-02-24 10:47:29,796][00397] Num frames 9500...
[2023-02-24 10:47:29,921][00397] Num frames 9600...
[2023-02-24 10:47:29,974][00397] Avg episode rewards: #0: 27.750, true rewards: #0: 12.000
[2023-02-24 10:47:29,975][00397] Avg episode reward: 27.750, avg true_objective: 12.000
[2023-02-24 10:47:30,089][00397] Num frames 9700...
[2023-02-24 10:47:30,203][00397] Num frames 9800...
[2023-02-24 10:47:30,316][00397] Num frames 9900...
[2023-02-24 10:47:30,429][00397] Num frames 10000...
[2023-02-24 10:47:30,543][00397] Num frames 10100...
[2023-02-24 10:47:30,647][00397] Avg episode rewards: #0: 25.493, true rewards: #0: 11.271
[2023-02-24 10:47:30,648][00397] Avg episode reward: 25.493, avg true_objective: 11.271
[2023-02-24 10:47:30,716][00397] Num frames 10200...
[2023-02-24 10:47:30,834][00397] Num frames 10300...
[2023-02-24 10:47:30,950][00397] Num frames 10400...
[2023-02-24 10:47:31,068][00397] Num frames 10500...
[2023-02-24 10:47:31,180][00397] Num frames 10600...
[2023-02-24 10:47:31,296][00397] Num frames 10700...
[2023-02-24 10:47:31,409][00397] Num frames 10800...
[2023-02-24 10:47:31,520][00397] Num frames 10900...
[2023-02-24 10:47:31,632][00397] Num frames 11000...
[2023-02-24 10:47:31,744][00397] Num frames 11100...
[2023-02-24 10:47:31,853][00397] Num frames 11200...
[2023-02-24 10:47:31,951][00397] Avg episode rewards: #0: 25.132, true rewards: #0: 11.232
[2023-02-24 10:47:31,954][00397] Avg episode reward: 25.132, avg true_objective: 11.232
[2023-02-24 10:48:39,599][00397] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
[2023-02-24 11:05:47,665][00397] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
[2023-02-24 11:05:47,671][00397] Overriding arg 'num_workers' with value 1 passed from command line
[2023-02-24 11:05:47,675][00397] Adding new argument 'no_render'=True that is not in the saved config file!
[2023-02-24 11:05:47,680][00397] Adding new argument 'save_video'=True that is not in the saved config file!
[2023-02-24 11:05:47,684][00397] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2023-02-24 11:05:47,686][00397] Adding new argument 'video_name'=None that is not in the saved config file!
[2023-02-24 11:05:47,693][00397] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
[2023-02-24 11:05:47,696][00397] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2023-02-24 11:05:47,699][00397] Adding new argument 'push_to_hub'=True that is not in the saved config file!
[2023-02-24 11:05:47,703][00397] Adding new argument 'hf_repository'='eldraco/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
[2023-02-24 11:05:47,704][00397] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2023-02-24 11:05:47,707][00397] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2023-02-24 11:05:47,710][00397] Adding new argument 'train_script'=None that is not in the saved config file!
[2023-02-24 11:05:47,712][00397] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2023-02-24 11:05:47,715][00397] Using frameskip 1 and render_action_repeat=4 for evaluation
[2023-02-24 11:05:47,747][00397] RunningMeanStd input shape: (3, 72, 128)
[2023-02-24 11:05:47,752][00397] RunningMeanStd input shape: (1,)
[2023-02-24 11:05:47,776][00397] ConvEncoder: input_channels=3
[2023-02-24 11:05:47,841][00397] Conv encoder output size: 512
[2023-02-24 11:05:47,849][00397] Policy head output size: 512
[2023-02-24 11:05:47,897][00397] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2023-02-24 11:05:48,839][00397] Num frames 100...
[2023-02-24 11:05:49,051][00397] Num frames 200...
[2023-02-24 11:05:49,247][00397] Num frames 300...
[2023-02-24 11:05:49,451][00397] Num frames 400...
[2023-02-24 11:05:49,648][00397] Avg episode rewards: #0: 6.610, true rewards: #0: 4.610
[2023-02-24 11:05:49,655][00397] Avg episode reward: 6.610, avg true_objective: 4.610
[2023-02-24 11:05:49,756][00397] Num frames 500...
[2023-02-24 11:05:49,997][00397] Num frames 600...
[2023-02-24 11:05:50,235][00397] Num frames 700...
[2023-02-24 11:05:50,489][00397] Num frames 800...
[2023-02-24 11:05:50,646][00397] Num frames 900...
[2023-02-24 11:05:50,759][00397] Num frames 1000...
[2023-02-24 11:05:50,905][00397] Avg episode rewards: #0: 9.900, true rewards: #0: 5.400
[2023-02-24 11:05:50,908][00397] Avg episode reward: 9.900, avg true_objective: 5.400
[2023-02-24 11:05:50,935][00397] Num frames 1100...
[2023-02-24 11:05:51,045][00397] Num frames 1200...
[2023-02-24 11:05:51,160][00397] Num frames 1300...
[2023-02-24 11:05:51,274][00397] Num frames 1400...
[2023-02-24 11:05:51,453][00397] Avg episode rewards: #0: 8.977, true rewards: #0: 4.977
[2023-02-24 11:05:51,455][00397] Avg episode reward: 8.977, avg true_objective: 4.977
[2023-02-24 11:05:51,468][00397] Num frames 1500...
[2023-02-24 11:05:51,579][00397] Num frames 1600...
[2023-02-24 11:05:51,694][00397] Num frames 1700...
[2023-02-24 11:05:51,806][00397] Num frames 1800...
[2023-02-24 11:05:51,927][00397] Num frames 1900...
[2023-02-24 11:05:52,041][00397] Num frames 2000...
[2023-02-24 11:05:52,161][00397] Num frames 2100...
[2023-02-24 11:05:52,275][00397] Num frames 2200...
[2023-02-24 11:05:52,405][00397] Num frames 2300...
[2023-02-24 11:05:52,535][00397] Num frames 2400...
[2023-02-24 11:05:52,654][00397] Num frames 2500...
[2023-02-24 11:05:52,767][00397] Num frames 2600...
[2023-02-24 11:05:52,889][00397] Num frames 2700...
[2023-02-24 11:05:53,003][00397] Num frames 2800...
[2023-02-24 11:05:53,116][00397] Num frames 2900...
[2023-02-24 11:05:53,228][00397] Num frames 3000...
[2023-02-24 11:05:53,344][00397] Num frames 3100...
[2023-02-24 11:05:53,466][00397] Num frames 3200...
[2023-02-24 11:05:53,583][00397] Num frames 3300...
[2023-02-24 11:05:53,703][00397] Num frames 3400...
[2023-02-24 11:05:53,815][00397] Num frames 3500...
[2023-02-24 11:05:53,980][00397] Avg episode rewards: #0: 20.982, true rewards: #0: 8.983
[2023-02-24 11:05:53,982][00397] Avg episode reward: 20.982, avg true_objective: 8.983
[2023-02-24 11:05:53,993][00397] Num frames 3600...
[2023-02-24 11:05:54,109][00397] Num frames 3700...
[2023-02-24 11:05:54,230][00397] Num frames 3800...
[2023-02-24 11:05:54,347][00397] Num frames 3900...
[2023-02-24 11:05:54,468][00397] Num frames 4000...
[2023-02-24 11:05:54,581][00397] Num frames 4100...
[2023-02-24 11:05:54,698][00397] Num frames 4200...
[2023-02-24 11:05:54,809][00397] Num frames 4300...
[2023-02-24 11:05:54,925][00397] Num frames 4400...
[2023-02-24 11:05:55,054][00397] Num frames 4500...
[2023-02-24 11:05:55,220][00397] Num frames 4600...
[2023-02-24 11:05:55,389][00397] Num frames 4700...
[2023-02-24 11:05:55,555][00397] Num frames 4800...
[2023-02-24 11:05:55,718][00397] Num frames 4900...
[2023-02-24 11:05:55,876][00397] Num frames 5000...
[2023-02-24 11:05:56,050][00397] Num frames 5100...
[2023-02-24 11:05:56,219][00397] Num frames 5200...
[2023-02-24 11:05:56,386][00397] Num frames 5300...
[2023-02-24 11:05:56,552][00397] Num frames 5400...
[2023-02-24 11:05:56,714][00397] Num frames 5500...
[2023-02-24 11:05:56,882][00397] Num frames 5600...
[2023-02-24 11:05:57,095][00397] Avg episode rewards: #0: 27.986, true rewards: #0: 11.386
[2023-02-24 11:05:57,098][00397] Avg episode reward: 27.986, avg true_objective: 11.386
[2023-02-24 11:05:57,114][00397] Num frames 5700...
[2023-02-24 11:05:57,292][00397] Num frames 5800...
[2023-02-24 11:05:57,475][00397] Num frames 5900...
[2023-02-24 11:05:57,647][00397] Num frames 6000...
[2023-02-24 11:05:57,810][00397] Num frames 6100...
[2023-02-24 11:05:57,978][00397] Num frames 6200...
[2023-02-24 11:05:58,144][00397] Num frames 6300...
[2023-02-24 11:05:58,316][00397] Num frames 6400...
[2023-02-24 11:05:58,490][00397] Num frames 6500...
[2023-02-24 11:05:58,633][00397] Num frames 6600...
[2023-02-24 11:05:58,749][00397] Num frames 6700...
[2023-02-24 11:05:58,871][00397] Num frames 6800...
[2023-02-24 11:05:58,991][00397] Num frames 6900...
[2023-02-24 11:05:59,109][00397] Num frames 7000...
[2023-02-24 11:05:59,224][00397] Num frames 7100...
[2023-02-24 11:05:59,349][00397] Num frames 7200...
[2023-02-24 11:05:59,468][00397] Num frames 7300...
[2023-02-24 11:05:59,597][00397] Avg episode rewards: #0: 30.095, true rewards: #0: 12.262
[2023-02-24 11:05:59,599][00397] Avg episode reward: 30.095, avg true_objective: 12.262
[2023-02-24 11:05:59,651][00397] Num frames 7400...
[2023-02-24 11:05:59,762][00397] Num frames 7500...
[2023-02-24 11:05:59,880][00397] Num frames 7600...
[2023-02-24 11:06:00,008][00397] Num frames 7700...
[2023-02-24 11:06:00,122][00397] Num frames 7800...
[2023-02-24 11:06:00,258][00397] Avg episode rewards: #0: 26.955, true rewards: #0: 11.241
[2023-02-24 11:06:00,261][00397] Avg episode reward: 26.955, avg true_objective: 11.241
[2023-02-24 11:06:00,301][00397] Num frames 7900...
[2023-02-24 11:06:00,419][00397] Num frames 8000...
[2023-02-24 11:06:00,531][00397] Num frames 8100...
[2023-02-24 11:06:00,654][00397] Num frames 8200...
[2023-02-24 11:06:00,768][00397] Num frames 8300...
[2023-02-24 11:06:00,889][00397] Num frames 8400...
[2023-02-24 11:06:01,003][00397] Num frames 8500...
[2023-02-24 11:06:01,118][00397] Num frames 8600...
[2023-02-24 11:06:01,240][00397] Num frames 8700...
[2023-02-24 11:06:01,356][00397] Num frames 8800...
[2023-02-24 11:06:01,474][00397] Num frames 8900...
[2023-02-24 11:06:01,588][00397] Num frames 9000...
[2023-02-24 11:06:01,715][00397] Num frames 9100...
[2023-02-24 11:06:01,832][00397] Avg episode rewards: #0: 27.441, true rewards: #0: 11.441
[2023-02-24 11:06:01,834][00397] Avg episode reward: 27.441, avg true_objective: 11.441
[2023-02-24 11:06:01,891][00397] Num frames 9200...
[2023-02-24 11:06:02,015][00397] Num frames 9300...
[2023-02-24 11:06:02,134][00397] Num frames 9400...
[2023-02-24 11:06:02,253][00397] Num frames 9500...
[2023-02-24 11:06:02,316][00397] Avg episode rewards: #0: 25.116, true rewards: #0: 10.561
[2023-02-24 11:06:02,318][00397] Avg episode reward: 25.116, avg true_objective: 10.561
[2023-02-24 11:06:02,427][00397] Num frames 9600...
[2023-02-24 11:06:02,541][00397] Num frames 9700...
[2023-02-24 11:06:02,660][00397] Num frames 9800...
[2023-02-24 11:06:02,773][00397] Num frames 9900...
[2023-02-24 11:06:02,885][00397] Num frames 10000...
[2023-02-24 11:06:03,003][00397] Num frames 10100...
[2023-02-24 11:06:03,131][00397] Num frames 10200...
[2023-02-24 11:06:03,252][00397] Num frames 10300...
[2023-02-24 11:06:03,367][00397] Num frames 10400...
[2023-02-24 11:06:03,487][00397] Num frames 10500...
[2023-02-24 11:06:03,604][00397] Num frames 10600...
[2023-02-24 11:06:03,730][00397] Num frames 10700...
[2023-02-24 11:06:03,812][00397] Avg episode rewards: #0: 25.321, true rewards: #0: 10.721
[2023-02-24 11:06:03,814][00397] Avg episode reward: 25.321, avg true_objective: 10.721
[2023-02-24 11:07:09,092][00397] Replay video saved to /content/train_dir/default_experiment/replay.mp4!