[2023-02-22 17:51:13,665][00111] Saving configuration to /content/train_dir/default_experiment/config.json...
[2023-02-22 17:51:13,666][00111] Rollout worker 0 uses device cpu
[2023-02-22 17:51:13,670][00111] Rollout worker 1 uses device cpu
[2023-02-22 17:51:13,671][00111] Rollout worker 2 uses device cpu
[2023-02-22 17:51:13,673][00111] Rollout worker 3 uses device cpu
[2023-02-22 17:51:13,674][00111] Rollout worker 4 uses device cpu
[2023-02-22 17:51:13,676][00111] Rollout worker 5 uses device cpu
[2023-02-22 17:51:13,677][00111] Rollout worker 6 uses device cpu
[2023-02-22 17:51:13,678][00111] Rollout worker 7 uses device cpu
[2023-02-22 17:51:13,854][00111] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-22 17:51:13,855][00111] InferenceWorker_p0-w0: min num requests: 2
[2023-02-22 17:51:13,887][00111] Starting all processes...
[2023-02-22 17:51:13,888][00111] Starting process learner_proc0
[2023-02-22 17:51:13,944][00111] Starting all processes...
[2023-02-22 17:51:13,953][00111] Starting process inference_proc0-0
[2023-02-22 17:51:13,954][00111] Starting process rollout_proc0
[2023-02-22 17:51:13,956][00111] Starting process rollout_proc1
[2023-02-22 17:51:13,956][00111] Starting process rollout_proc2
[2023-02-22 17:51:13,956][00111] Starting process rollout_proc3
[2023-02-22 17:51:13,956][00111] Starting process rollout_proc4
[2023-02-22 17:51:13,956][00111] Starting process rollout_proc5
[2023-02-22 17:51:13,956][00111] Starting process rollout_proc6
[2023-02-22 17:51:13,956][00111] Starting process rollout_proc7
[2023-02-22 17:51:22,864][11391] Worker 1 uses CPU cores [1]
[2023-02-22 17:51:24,125][11394] Worker 5 uses CPU cores [1]
[2023-02-22 17:51:24,307][11375] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-22 17:51:24,308][11375] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
[2023-02-22 17:51:24,337][11393] Worker 4 uses CPU cores [0]
[2023-02-22 17:51:24,438][11396] Worker 3 uses CPU cores [1]
[2023-02-22 17:51:24,571][11389] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-22 17:51:24,577][11389] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
[2023-02-22 17:51:24,591][11390] Worker 0 uses CPU cores [0]
[2023-02-22 17:51:24,624][11397] Worker 7 uses CPU cores [1]
[2023-02-22 17:51:24,695][11392] Worker 2 uses CPU cores [0]
[2023-02-22 17:51:24,695][11395] Worker 6 uses CPU cores [0]
[2023-02-22 17:51:25,197][11389] Num visible devices: 1
[2023-02-22 17:51:25,202][11375] Num visible devices: 1
[2023-02-22 17:51:25,221][11375] Starting seed is not provided
[2023-02-22 17:51:25,222][11375] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-22 17:51:25,222][11375] Initializing actor-critic model on device cuda:0
[2023-02-22 17:51:25,223][11375] RunningMeanStd input shape: (3, 72, 128)
[2023-02-22 17:51:25,224][11375] RunningMeanStd input shape: (1,)
[2023-02-22 17:51:25,243][11375] ConvEncoder: input_channels=3
[2023-02-22 17:51:25,581][11375] Conv encoder output size: 512
[2023-02-22 17:51:25,581][11375] Policy head output size: 512
[2023-02-22 17:51:25,637][11375] Created Actor Critic model with architecture:
[2023-02-22 17:51:25,637][11375] ActorCriticSharedWeights(
  (obs_normalizer): ObservationNormalizer(
    (running_mean_std): RunningMeanStdDictInPlace(
      (running_mean_std): ModuleDict(
        (obs): RunningMeanStdInPlace()
      )
    )
  )
  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
  (encoder): VizdoomEncoder(
    (basic_encoder): ConvEncoder(
      (enc): RecursiveScriptModule(
        original_name=ConvEncoderImpl
        (conv_head): RecursiveScriptModule(
          original_name=Sequential
          (0): RecursiveScriptModule(original_name=Conv2d)
          (1): RecursiveScriptModule(original_name=ELU)
          (2): RecursiveScriptModule(original_name=Conv2d)
          (3): RecursiveScriptModule(original_name=ELU)
          (4): RecursiveScriptModule(original_name=Conv2d)
          (5): RecursiveScriptModule(original_name=ELU)
        )
        (mlp_layers): RecursiveScriptModule(
          original_name=Sequential
          (0): RecursiveScriptModule(original_name=Linear)
          (1): RecursiveScriptModule(original_name=ELU)
        )
      )
    )
  )
  (core): ModelCoreRNN(
    (core): GRU(512, 512)
  )
  (decoder): MlpDecoder(
    (mlp): Identity()
  )
  (critic_linear): Linear(in_features=512, out_features=1, bias=True)
  (action_parameterization): ActionParameterizationDefault(
    (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
  )
)
[2023-02-22 17:51:31,948][11375] Using optimizer <class 'torch.optim.adam.Adam'>
[2023-02-22 17:51:31,950][11375] No checkpoints found
[2023-02-22 17:51:31,950][11375] Did not load from checkpoint, starting from scratch!
[2023-02-22 17:51:31,951][11375] Initialized policy 0 weights for model version 0
[2023-02-22 17:51:31,957][11375] LearnerWorker_p0 finished initialization!
[2023-02-22 17:51:31,957][11375] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2023-02-22 17:51:32,064][11389] RunningMeanStd input shape: (3, 72, 128)
[2023-02-22 17:51:32,067][11389] RunningMeanStd input shape: (1,)
[2023-02-22 17:51:32,080][11389] ConvEncoder: input_channels=3
[2023-02-22 17:51:32,175][11389] Conv encoder output size: 512
[2023-02-22 17:51:32,175][11389] Policy head output size: 512
[2023-02-22 17:51:33,847][00111] Heartbeat connected on Batcher_0
[2023-02-22 17:51:33,850][00111] Heartbeat connected on LearnerWorker_p0
[2023-02-22 17:51:33,865][00111] Heartbeat connected on RolloutWorker_w0
[2023-02-22 17:51:33,870][00111] Heartbeat connected on RolloutWorker_w1
[2023-02-22 17:51:33,875][00111] Heartbeat connected on RolloutWorker_w3
[2023-02-22 17:51:33,877][00111] Heartbeat connected on RolloutWorker_w4
[2023-02-22 17:51:33,879][00111] Heartbeat connected on RolloutWorker_w2
[2023-02-22 17:51:33,883][00111] Heartbeat connected on RolloutWorker_w5
[2023-02-22 17:51:33,887][00111] Heartbeat connected on RolloutWorker_w6
[2023-02-22 17:51:33,890][00111] Heartbeat connected on RolloutWorker_w7
[2023-02-22 17:51:34,323][00111] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2023-02-22 17:51:34,381][00111] Inference worker 0-0 is ready!
[2023-02-22 17:51:34,383][00111] All inference workers are ready! Signal rollout workers to start!
[2023-02-22 17:51:34,386][00111] Heartbeat connected on InferenceWorker_p0-w0
[2023-02-22 17:51:34,516][11396] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-22 17:51:34,516][11393] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-22 17:51:34,529][11390] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-22 17:51:34,532][11397] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-22 17:51:34,531][11391] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-22 17:51:34,540][11394] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-22 17:51:34,584][11392] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-22 17:51:34,586][11395] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-22 17:51:35,057][11395] Decorrelating experience for 0 frames...
[2023-02-22 17:51:35,394][11395] Decorrelating experience for 32 frames...
[2023-02-22 17:51:35,809][11395] Decorrelating experience for 64 frames...
[2023-02-22 17:51:35,904][11396] Decorrelating experience for 0 frames...
[2023-02-22 17:51:35,909][11391] Decorrelating experience for 0 frames...
[2023-02-22 17:51:35,911][11394] Decorrelating experience for 0 frames...
[2023-02-22 17:51:35,914][11397] Decorrelating experience for 0 frames...
[2023-02-22 17:51:36,582][11396] Decorrelating experience for 32 frames...
[2023-02-22 17:51:36,595][11397] Decorrelating experience for 32 frames...
[2023-02-22 17:51:36,623][11395] Decorrelating experience for 96 frames...
[2023-02-22 17:51:36,704][11390] Decorrelating experience for 0 frames...
[2023-02-22 17:51:37,540][11393] Decorrelating experience for 0 frames...
[2023-02-22 17:51:37,573][11390] Decorrelating experience for 32 frames...
[2023-02-22 17:51:38,581][11393] Decorrelating experience for 32 frames...
[2023-02-22 17:51:38,635][11392] Decorrelating experience for 0 frames...
[2023-02-22 17:51:38,811][11390] Decorrelating experience for 64 frames...
[2023-02-22 17:51:39,323][00111] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2023-02-22 17:51:39,714][11393] Decorrelating experience for 64 frames...
[2023-02-22 17:51:39,811][11390] Decorrelating experience for 96 frames...
[2023-02-22 17:51:40,439][11393] Decorrelating experience for 96 frames...
[2023-02-22 17:51:40,601][11394] Decorrelating experience for 32 frames...
[2023-02-22 17:51:40,595][11391] Decorrelating experience for 32 frames...
[2023-02-22 17:51:40,926][11397] Decorrelating experience for 64 frames...
[2023-02-22 17:51:41,367][11396] Decorrelating experience for 64 frames...
[2023-02-22 17:51:41,548][11392] Decorrelating experience for 32 frames...
[2023-02-22 17:51:43,405][11391] Decorrelating experience for 64 frames...
[2023-02-22 17:51:43,413][11394] Decorrelating experience for 64 frames...
[2023-02-22 17:51:43,711][11397] Decorrelating experience for 96 frames...
[2023-02-22 17:51:43,921][11396] Decorrelating experience for 96 frames...
[2023-02-22 17:51:44,323][00111] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 25.0. Samples: 250. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2023-02-22 17:51:44,331][00111] Avg episode reward: [(0, '1.387')]
[2023-02-22 17:51:46,173][11391] Decorrelating experience for 96 frames...
[2023-02-22 17:51:46,598][11394] Decorrelating experience for 96 frames...
[2023-02-22 17:51:48,030][11375] Signal inference workers to stop experience collection...
[2023-02-22 17:51:48,037][11389] InferenceWorker_p0-w0: stopping experience collection
[2023-02-22 17:51:48,249][11392] Decorrelating experience for 64 frames...
[2023-02-22 17:51:48,566][11392] Decorrelating experience for 96 frames...
[2023-02-22 17:51:49,323][00111] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 108.9. Samples: 1634. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
[2023-02-22 17:51:49,325][00111] Avg episode reward: [(0, '3.090')]
[2023-02-22 17:51:50,010][11375] Signal inference workers to resume experience collection...
[2023-02-22 17:51:50,012][11389] InferenceWorker_p0-w0: resuming experience collection
[2023-02-22 17:51:54,323][00111] Fps is (10 sec: 2048.1, 60 sec: 1024.0, 300 sec: 1024.0). Total num frames: 20480. Throughput: 0: 214.0. Samples: 4280. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0)
[2023-02-22 17:51:54,326][00111] Avg episode reward: [(0, '3.434')]
[2023-02-22 17:51:59,323][00111] Fps is (10 sec: 3686.4, 60 sec: 1474.6, 300 sec: 1474.6). Total num frames: 36864. Throughput: 0: 385.1. Samples: 9628. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 17:51:59,329][00111] Avg episode reward: [(0, '3.778')]
[2023-02-22 17:52:00,221][11389] Updated weights for policy 0, policy_version 10 (0.0357)
[2023-02-22 17:52:04,324][00111] Fps is (10 sec: 2866.8, 60 sec: 1638.3, 300 sec: 1638.3). Total num frames: 49152. Throughput: 0: 391.4. Samples: 11742. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:52:04,334][00111] Avg episode reward: [(0, '4.215')]
[2023-02-22 17:52:09,323][00111] Fps is (10 sec: 3276.8, 60 sec: 1989.5, 300 sec: 1989.5). Total num frames: 69632. Throughput: 0: 477.6. Samples: 16716. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
[2023-02-22 17:52:09,328][00111] Avg episode reward: [(0, '4.355')]
[2023-02-22 17:52:11,217][11389] Updated weights for policy 0, policy_version 20 (0.0034)
[2023-02-22 17:52:14,323][00111] Fps is (10 sec: 4506.2, 60 sec: 2355.2, 300 sec: 2355.2). Total num frames: 94208. Throughput: 0: 587.6. Samples: 23506. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:52:14,326][00111] Avg episode reward: [(0, '4.312')]
[2023-02-22 17:52:19,323][00111] Fps is (10 sec: 4096.0, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 110592. Throughput: 0: 594.0. Samples: 26730. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:52:19,326][00111] Avg episode reward: [(0, '4.433')]
[2023-02-22 17:52:19,338][11375] Saving new best policy, reward=4.433!
[2023-02-22 17:52:22,972][11389] Updated weights for policy 0, policy_version 30 (0.0015)
[2023-02-22 17:52:24,324][00111] Fps is (10 sec: 2866.9, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 122880. Throughput: 0: 689.2. Samples: 31016. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:52:24,327][00111] Avg episode reward: [(0, '4.498')]
[2023-02-22 17:52:24,394][11375] Saving new best policy, reward=4.498!
[2023-02-22 17:52:29,323][00111] Fps is (10 sec: 3276.8, 60 sec: 2606.5, 300 sec: 2606.5). Total num frames: 143360. Throughput: 0: 798.5. Samples: 36184. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:52:29,332][00111] Avg episode reward: [(0, '4.416')]
[2023-02-22 17:52:33,214][11389] Updated weights for policy 0, policy_version 40 (0.0034)
[2023-02-22 17:52:34,323][00111] Fps is (10 sec: 4506.1, 60 sec: 2798.9, 300 sec: 2798.9). Total num frames: 167936. Throughput: 0: 842.5. Samples: 39546. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:52:34,326][00111] Avg episode reward: [(0, '4.471')]
[2023-02-22 17:52:39,323][00111] Fps is (10 sec: 4096.0, 60 sec: 3072.0, 300 sec: 2835.7). Total num frames: 184320. Throughput: 0: 922.6. Samples: 45798. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:52:39,326][00111] Avg episode reward: [(0, '4.617')]
[2023-02-22 17:52:39,332][11375] Saving new best policy, reward=4.617!
[2023-02-22 17:52:44,327][00111] Fps is (10 sec: 2866.0, 60 sec: 3276.6, 300 sec: 2808.5). Total num frames: 196608. Throughput: 0: 895.0. Samples: 49906. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:52:44,333][00111] Avg episode reward: [(0, '4.467')]
[2023-02-22 17:52:46,171][11389] Updated weights for policy 0, policy_version 50 (0.0012)
[2023-02-22 17:52:49,323][00111] Fps is (10 sec: 2867.1, 60 sec: 3549.8, 300 sec: 2839.9). Total num frames: 212992. Throughput: 0: 893.2. Samples: 51934. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:52:49,326][00111] Avg episode reward: [(0, '4.492')]
[2023-02-22 17:52:54,323][00111] Fps is (10 sec: 2868.4, 60 sec: 3413.3, 300 sec: 2816.0). Total num frames: 225280. Throughput: 0: 872.5. Samples: 55980. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:52:54,329][00111] Avg episode reward: [(0, '4.387')]
[2023-02-22 17:52:59,323][00111] Fps is (10 sec: 2457.7, 60 sec: 3345.1, 300 sec: 2794.9). Total num frames: 237568. Throughput: 0: 812.1. Samples: 60050. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:52:59,331][00111] Avg episode reward: [(0, '4.550')]
[2023-02-22 17:53:01,044][11389] Updated weights for policy 0, policy_version 60 (0.0027)
[2023-02-22 17:53:04,323][00111] Fps is (10 sec: 2867.2, 60 sec: 3413.4, 300 sec: 2821.7). Total num frames: 253952. Throughput: 0: 788.5. Samples: 62212. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:53:04,327][00111] Avg episode reward: [(0, '4.676')]
[2023-02-22 17:53:04,332][11375] Saving new best policy, reward=4.676!
[2023-02-22 17:53:09,323][00111] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 2845.6). Total num frames: 270336. Throughput: 0: 783.4. Samples: 66266. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-22 17:53:09,325][00111] Avg episode reward: [(0, '4.780')]
[2023-02-22 17:53:09,341][11375] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000066_270336.pth...
[2023-02-22 17:53:09,503][11375] Saving new best policy, reward=4.780!
[2023-02-22 17:53:13,241][11389] Updated weights for policy 0, policy_version 70 (0.0028)
[2023-02-22 17:53:14,323][00111] Fps is (10 sec: 3276.8, 60 sec: 3208.5, 300 sec: 2867.2). Total num frames: 286720. Throughput: 0: 803.2. Samples: 72330. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-22 17:53:14,329][00111] Avg episode reward: [(0, '4.642')]
[2023-02-22 17:53:19,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3276.8, 300 sec: 2925.7). Total num frames: 307200. Throughput: 0: 798.7. Samples: 75486. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 17:53:19,330][00111] Avg episode reward: [(0, '4.507')]
[2023-02-22 17:53:24,326][00111] Fps is (10 sec: 3275.9, 60 sec: 3276.7, 300 sec: 2904.4). Total num frames: 319488. Throughput: 0: 762.1. Samples: 80094. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:53:24,337][00111] Avg episode reward: [(0, '4.494')]
[2023-02-22 17:53:25,875][11389] Updated weights for policy 0, policy_version 80 (0.0012)
[2023-02-22 17:53:29,323][00111] Fps is (10 sec: 2867.2, 60 sec: 3208.5, 300 sec: 2920.6). Total num frames: 335872. Throughput: 0: 764.6. Samples: 84312. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:53:29,330][00111] Avg episode reward: [(0, '4.516')]
[2023-02-22 17:53:34,323][00111] Fps is (10 sec: 3687.4, 60 sec: 3140.3, 300 sec: 2969.6). Total num frames: 356352. Throughput: 0: 789.7. Samples: 87472. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:53:34,334][00111] Avg episode reward: [(0, '4.389')]
[2023-02-22 17:53:36,337][11389] Updated weights for policy 0, policy_version 90 (0.0013)
[2023-02-22 17:53:39,323][00111] Fps is (10 sec: 4096.0, 60 sec: 3208.5, 300 sec: 3014.7). Total num frames: 376832. Throughput: 0: 841.8. Samples: 93860. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 17:53:39,331][00111] Avg episode reward: [(0, '4.525')]
[2023-02-22 17:53:44,326][00111] Fps is (10 sec: 3275.8, 60 sec: 3208.6, 300 sec: 2993.2). Total num frames: 389120. Throughput: 0: 848.4. Samples: 98232. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:53:44,329][00111] Avg episode reward: [(0, '4.486')]
[2023-02-22 17:53:49,323][00111] Fps is (10 sec: 2867.2, 60 sec: 3208.5, 300 sec: 3003.7). Total num frames: 405504. Throughput: 0: 844.7. Samples: 100224. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:53:49,326][00111] Avg episode reward: [(0, '4.616')]
[2023-02-22 17:53:49,942][11389] Updated weights for policy 0, policy_version 100 (0.0033)
[2023-02-22 17:53:54,323][00111] Fps is (10 sec: 3687.6, 60 sec: 3345.1, 300 sec: 3042.7). Total num frames: 425984. Throughput: 0: 871.7. Samples: 105492. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:53:54,328][00111] Avg episode reward: [(0, '4.613')]
[2023-02-22 17:53:59,323][00111] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3079.1). Total num frames: 446464. Throughput: 0: 872.4. Samples: 111588. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:53:59,330][00111] Avg episode reward: [(0, '4.539')]
[2023-02-22 17:54:00,381][11389] Updated weights for policy 0, policy_version 110 (0.0024)
[2023-02-22 17:54:04,324][00111] Fps is (10 sec: 3276.5, 60 sec: 3413.3, 300 sec: 3058.3). Total num frames: 458752. Throughput: 0: 852.1. Samples: 113832. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:54:04,327][00111] Avg episode reward: [(0, '4.438')]
[2023-02-22 17:54:09,323][00111] Fps is (10 sec: 2457.6, 60 sec: 3345.1, 300 sec: 3039.0). Total num frames: 471040. Throughput: 0: 834.9. Samples: 117662. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:54:09,328][00111] Avg episode reward: [(0, '4.340')]
[2023-02-22 17:54:13,859][11389] Updated weights for policy 0, policy_version 120 (0.0017)
[2023-02-22 17:54:14,323][00111] Fps is (10 sec: 3277.1, 60 sec: 3413.3, 300 sec: 3072.0). Total num frames: 491520. Throughput: 0: 854.1. Samples: 122746. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
[2023-02-22 17:54:14,325][00111] Avg episode reward: [(0, '4.443')]
[2023-02-22 17:54:19,323][00111] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3103.0). Total num frames: 512000. Throughput: 0: 851.9. Samples: 125806. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:54:19,328][00111] Avg episode reward: [(0, '4.730')]
[2023-02-22 17:54:24,323][00111] Fps is (10 sec: 3276.7, 60 sec: 3413.5, 300 sec: 3084.0). Total num frames: 524288. Throughput: 0: 829.3. Samples: 131180. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:54:24,327][00111] Avg episode reward: [(0, '4.586')]
[2023-02-22 17:54:26,419][11389] Updated weights for policy 0, policy_version 130 (0.0024)
[2023-02-22 17:54:29,324][00111] Fps is (10 sec: 2457.4, 60 sec: 3345.0, 300 sec: 3066.1). Total num frames: 536576. Throughput: 0: 816.4. Samples: 134968. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:54:29,327][00111] Avg episode reward: [(0, '4.501')]
[2023-02-22 17:54:34,323][00111] Fps is (10 sec: 3276.9, 60 sec: 3345.1, 300 sec: 3094.8). Total num frames: 557056. Throughput: 0: 817.4. Samples: 137006. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:54:34,331][00111] Avg episode reward: [(0, '4.426')]
[2023-02-22 17:54:38,038][11389] Updated weights for policy 0, policy_version 140 (0.0016)
[2023-02-22 17:54:39,327][00111] Fps is (10 sec: 4094.6, 60 sec: 3344.8, 300 sec: 3121.7). Total num frames: 577536. Throughput: 0: 838.1. Samples: 143212. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:54:39,331][00111] Avg episode reward: [(0, '4.353')]
[2023-02-22 17:54:44,323][00111] Fps is (10 sec: 3686.3, 60 sec: 3413.5, 300 sec: 3125.9). Total num frames: 593920. Throughput: 0: 820.4. Samples: 148508. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:54:44,326][00111] Avg episode reward: [(0, '4.353')]
[2023-02-22 17:54:49,323][00111] Fps is (10 sec: 2868.4, 60 sec: 3345.1, 300 sec: 3108.8). Total num frames: 606208. Throughput: 0: 814.5. Samples: 150484. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:54:49,325][00111] Avg episode reward: [(0, '4.447')]
[2023-02-22 17:54:51,835][11389] Updated weights for policy 0, policy_version 150 (0.0022)
[2023-02-22 17:54:54,323][00111] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3113.0). Total num frames: 622592. Throughput: 0: 821.5. Samples: 154630. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-22 17:54:54,326][00111] Avg episode reward: [(0, '4.601')]
[2023-02-22 17:54:59,329][00111] Fps is (10 sec: 3684.1, 60 sec: 3276.5, 300 sec: 3136.8). Total num frames: 643072. Throughput: 0: 850.7. Samples: 161032. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:54:59,336][00111] Avg episode reward: [(0, '4.700')]
[2023-02-22 17:55:01,737][11389] Updated weights for policy 0, policy_version 160 (0.0014)
[2023-02-22 17:55:04,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3140.3). Total num frames: 659456. Throughput: 0: 852.4. Samples: 164166. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:55:04,329][00111] Avg episode reward: [(0, '4.774')]
[2023-02-22 17:55:09,323][00111] Fps is (10 sec: 3278.8, 60 sec: 3413.3, 300 sec: 3143.4). Total num frames: 675840. Throughput: 0: 825.2. Samples: 168314. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:55:09,329][00111] Avg episode reward: [(0, '4.631')]
[2023-02-22 17:55:09,340][11375] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000165_675840.pth...
[2023-02-22 17:55:14,323][00111] Fps is (10 sec: 3276.7, 60 sec: 3345.1, 300 sec: 3146.5). Total num frames: 692224. Throughput: 0: 837.8. Samples: 172668. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:55:14,327][00111] Avg episode reward: [(0, '4.735')]
[2023-02-22 17:55:15,173][11389] Updated weights for policy 0, policy_version 170 (0.0018)
[2023-02-22 17:55:19,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3167.6). Total num frames: 712704. Throughput: 0: 863.2. Samples: 175852. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:55:19,330][00111] Avg episode reward: [(0, '4.592')]
[2023-02-22 17:55:24,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3169.9). Total num frames: 729088. Throughput: 0: 869.2. Samples: 182322. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:55:24,331][00111] Avg episode reward: [(0, '4.781')]
[2023-02-22 17:55:26,088][11389] Updated weights for policy 0, policy_version 180 (0.0024)
[2023-02-22 17:55:29,323][00111] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3172.2). Total num frames: 745472. Throughput: 0: 841.5. Samples: 186374. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 17:55:29,327][00111] Avg episode reward: [(0, '5.060')]
[2023-02-22 17:55:29,342][11375] Saving new best policy, reward=5.060!
[2023-02-22 17:55:34,323][00111] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3157.3). Total num frames: 757760. Throughput: 0: 841.2. Samples: 188338. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 17:55:34,326][00111] Avg episode reward: [(0, '5.088')]
[2023-02-22 17:55:34,335][11375] Saving new best policy, reward=5.088!
[2023-02-22 17:55:38,419][11389] Updated weights for policy 0, policy_version 190 (0.0015)
[2023-02-22 17:55:39,323][00111] Fps is (10 sec: 3276.9, 60 sec: 3345.3, 300 sec: 3176.5). Total num frames: 778240. Throughput: 0: 878.3. Samples: 194152. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:55:39,329][00111] Avg episode reward: [(0, '5.113')]
[2023-02-22 17:55:39,366][11375] Saving new best policy, reward=5.113!
[2023-02-22 17:55:44,323][00111] Fps is (10 sec: 4095.9, 60 sec: 3413.3, 300 sec: 3194.9). Total num frames: 798720. Throughput: 0: 874.3. Samples: 200370. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:55:44,328][00111] Avg episode reward: [(0, '5.157')]
[2023-02-22 17:55:44,335][11375] Saving new best policy, reward=5.157!
[2023-02-22 17:55:49,323][00111] Fps is (10 sec: 3276.7, 60 sec: 3413.3, 300 sec: 3180.4). Total num frames: 811008. Throughput: 0: 848.4. Samples: 202342. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:55:49,326][00111] Avg episode reward: [(0, '5.025')]
[2023-02-22 17:55:50,945][11389] Updated weights for policy 0, policy_version 200 (0.0014)
[2023-02-22 17:55:54,323][00111] Fps is (10 sec: 2867.3, 60 sec: 3413.3, 300 sec: 3182.3). Total num frames: 827392. Throughput: 0: 844.0. Samples: 206296. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:55:54,326][00111] Avg episode reward: [(0, '5.178')]
[2023-02-22 17:55:54,330][11375] Saving new best policy, reward=5.178!
[2023-02-22 17:55:59,323][00111] Fps is (10 sec: 3686.5, 60 sec: 3413.7, 300 sec: 3199.5). Total num frames: 847872. Throughput: 0: 880.1. Samples: 212272. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:55:59,332][00111] Avg episode reward: [(0, '5.392')]
[2023-02-22 17:55:59,344][11375] Saving new best policy, reward=5.392!
[2023-02-22 17:56:01,496][11389] Updated weights for policy 0, policy_version 210 (0.0018)
[2023-02-22 17:56:04,326][00111] Fps is (10 sec: 4094.7, 60 sec: 3481.4, 300 sec: 3216.1). Total num frames: 868352. Throughput: 0: 881.3. Samples: 215512. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:56:04,329][00111] Avg episode reward: [(0, '5.558')]
[2023-02-22 17:56:04,414][11375] Saving new best policy, reward=5.558!
[2023-02-22 17:56:09,331][00111] Fps is (10 sec: 3685.4, 60 sec: 3481.4, 300 sec: 3217.2). Total num frames: 884736. Throughput: 0: 851.6. Samples: 220646. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 17:56:09,333][00111] Avg episode reward: [(0, '5.531')]
[2023-02-22 17:56:14,323][00111] Fps is (10 sec: 2868.1, 60 sec: 3413.3, 300 sec: 3203.7). Total num frames: 897024. Throughput: 0: 860.2. Samples: 225084. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:56:14,331][00111] Avg episode reward: [(0, '5.350')]
[2023-02-22 17:56:14,496][11389] Updated weights for policy 0, policy_version 220 (0.0021)
[2023-02-22 17:56:19,323][00111] Fps is (10 sec: 3687.4, 60 sec: 3481.6, 300 sec: 3233.7). Total num frames: 921600. Throughput: 0: 885.2. Samples: 228172. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:56:19,326][00111] Avg episode reward: [(0, '5.477')]
[2023-02-22 17:56:23,305][11389] Updated weights for policy 0, policy_version 230 (0.0033)
[2023-02-22 17:56:24,326][00111] Fps is (10 sec: 4913.7, 60 sec: 3617.9, 300 sec: 3262.6). Total num frames: 946176. Throughput: 0: 908.2. Samples: 235024. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:56:24,331][00111] Avg episode reward: [(0, '5.917')]
[2023-02-22 17:56:24,341][11375] Saving new best policy, reward=5.917!
[2023-02-22 17:56:29,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3249.0). Total num frames: 958464. Throughput: 0: 883.9. Samples: 240144. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:56:29,328][00111] Avg episode reward: [(0, '5.799')]
[2023-02-22 17:56:34,325][00111] Fps is (10 sec: 2867.5, 60 sec: 3618.0, 300 sec: 3304.5). Total num frames: 974848. Throughput: 0: 886.5. Samples: 242238. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 17:56:34,329][00111] Avg episode reward: [(0, '5.805')]
[2023-02-22 17:56:36,142][11389] Updated weights for policy 0, policy_version 240 (0.0012)
[2023-02-22 17:56:39,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3374.0). Total num frames: 995328. Throughput: 0: 922.9. Samples: 247826. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:56:39,332][00111] Avg episode reward: [(0, '5.717')]
[2023-02-22 17:56:44,324][00111] Fps is (10 sec: 4506.3, 60 sec: 3686.4, 300 sec: 3457.3). Total num frames: 1019904. Throughput: 0: 941.3. Samples: 254632. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:56:44,329][00111] Avg episode reward: [(0, '6.072')]
[2023-02-22 17:56:44,331][11375] Saving new best policy, reward=6.072!
[2023-02-22 17:56:45,674][11389] Updated weights for policy 0, policy_version 250 (0.0021)
[2023-02-22 17:56:49,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3429.5). Total num frames: 1032192. Throughput: 0: 924.4. Samples: 257108. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:56:49,327][00111] Avg episode reward: [(0, '6.527')]
[2023-02-22 17:56:49,340][11375] Saving new best policy, reward=6.527!
[2023-02-22 17:56:54,323][00111] Fps is (10 sec: 2457.7, 60 sec: 3618.1, 300 sec: 3415.6). Total num frames: 1044480. Throughput: 0: 904.8. Samples: 261360. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:56:54,327][00111] Avg episode reward: [(0, '6.489')]
[2023-02-22 17:56:58,140][11389] Updated weights for policy 0, policy_version 260 (0.0023)
[2023-02-22 17:56:59,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3457.3). Total num frames: 1069056. Throughput: 0: 934.3. Samples: 267128. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:56:59,326][00111] Avg episode reward: [(0, '6.674')]
[2023-02-22 17:56:59,335][11375] Saving new best policy, reward=6.674!
[2023-02-22 17:57:04,323][00111] Fps is (10 sec: 4505.6, 60 sec: 3686.6, 300 sec: 3457.3). Total num frames: 1089536. Throughput: 0: 936.0. Samples: 270294. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:57:04,329][00111] Avg episode reward: [(0, '6.848')]
[2023-02-22 17:57:04,332][11375] Saving new best policy, reward=6.848!
[2023-02-22 17:57:09,323][00111] Fps is (10 sec: 3276.8, 60 sec: 3618.3, 300 sec: 3415.6). Total num frames: 1101824. Throughput: 0: 905.1. Samples: 275752. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:57:09,326][00111] Avg episode reward: [(0, '6.414')]
[2023-02-22 17:57:09,354][11375] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000270_1105920.pth...
[2023-02-22 17:57:09,345][11389] Updated weights for policy 0, policy_version 270 (0.0024)
[2023-02-22 17:57:09,526][11375] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000066_270336.pth
[2023-02-22 17:57:14,324][00111] Fps is (10 sec: 2866.8, 60 sec: 3686.3, 300 sec: 3415.6). Total num frames: 1118208. Throughput: 0: 880.5. Samples: 279766. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 17:57:14,330][00111] Avg episode reward: [(0, '6.653')]
[2023-02-22 17:57:19,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3443.4). Total num frames: 1138688. Throughput: 0: 889.3. Samples: 282254. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 17:57:19,331][00111] Avg episode reward: [(0, '6.465')]
[2023-02-22 17:57:21,103][11389] Updated weights for policy 0, policy_version 280 (0.0032)
[2023-02-22 17:57:24,323][00111] Fps is (10 sec: 4096.6, 60 sec: 3550.1, 300 sec: 3443.4). Total num frames: 1159168. Throughput: 0: 907.6. Samples: 288670. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 17:57:24,325][00111] Avg episode reward: [(0, '7.144')]
[2023-02-22 17:57:24,327][11375] Saving new best policy, reward=7.144!
[2023-02-22 17:57:29,324][00111] Fps is (10 sec: 3686.0, 60 sec: 3618.1, 300 sec: 3415.6). Total num frames: 1175552. Throughput: 0: 874.5. Samples: 293984. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 17:57:29,328][00111] Avg episode reward: [(0, '7.806')]
[2023-02-22 17:57:29,349][11375] Saving new best policy, reward=7.806!
[2023-02-22 17:57:33,422][11389] Updated weights for policy 0, policy_version 290 (0.0013)
[2023-02-22 17:57:34,323][00111] Fps is (10 sec: 2867.2, 60 sec: 3550.0, 300 sec: 3401.8). Total num frames: 1187840. Throughput: 0: 865.0. Samples: 296034. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-22 17:57:34,332][00111] Avg episode reward: [(0, '7.992')]
[2023-02-22 17:57:34,336][11375] Saving new best policy, reward=7.992!
[2023-02-22 17:57:39,323][00111] Fps is (10 sec: 3277.2, 60 sec: 3549.9, 300 sec: 3429.6). Total num frames: 1208320. Throughput: 0: 878.3. Samples: 300882. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:57:39,326][00111] Avg episode reward: [(0, '8.754')]
[2023-02-22 17:57:39,335][11375] Saving new best policy, reward=8.754!
[2023-02-22 17:57:43,560][11389] Updated weights for policy 0, policy_version 300 (0.0014)
[2023-02-22 17:57:44,323][00111] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3443.4). Total num frames: 1228800. Throughput: 0: 898.5. Samples: 307562. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:57:44,327][00111] Avg episode reward: [(0, '7.739')]
[2023-02-22 17:57:49,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3457.3). Total num frames: 1245184. Throughput: 0: 895.9. Samples: 310610. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-22 17:57:49,326][00111] Avg episode reward: [(0, '7.569')]
[2023-02-22 17:57:54,327][00111] Fps is (10 sec: 2866.0, 60 sec: 3549.6, 300 sec: 3457.3). Total num frames: 1257472. Throughput: 0: 855.3. Samples: 314246. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 17:57:54,337][00111] Avg episode reward: [(0, '7.876')]
[2023-02-22 17:57:58,959][11389] Updated weights for policy 0, policy_version 310 (0.0016)
[2023-02-22 17:57:59,323][00111] Fps is (10 sec: 2457.6, 60 sec: 3345.1, 300 sec: 3443.4). Total num frames: 1269760. Throughput: 0: 842.1. Samples: 317660. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:57:59,327][00111] Avg episode reward: [(0, '8.363')]
[2023-02-22 17:58:04,323][00111] Fps is (10 sec: 2868.4, 60 sec: 3276.8, 300 sec: 3443.4). Total num frames: 1286144. Throughput: 0: 832.3. Samples: 319706. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 17:58:04,325][00111] Avg episode reward: [(0, '9.315')]
[2023-02-22 17:58:04,334][11375] Saving new best policy, reward=9.315!
[2023-02-22 17:58:09,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3457.3). Total num frames: 1306624. Throughput: 0: 824.0. Samples: 325752. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:58:09,325][00111] Avg episode reward: [(0, '9.000')]
[2023-02-22 17:58:09,834][11389] Updated weights for policy 0, policy_version 320 (0.0018)
[2023-02-22 17:58:14,324][00111] Fps is (10 sec: 3686.2, 60 sec: 3413.4, 300 sec: 3443.4). Total num frames: 1323008. Throughput: 0: 817.4. Samples: 330768. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 17:58:14,326][00111] Avg episode reward: [(0, '8.740')]
[2023-02-22 17:58:19,324][00111] Fps is (10 sec: 2867.0, 60 sec: 3276.8, 300 sec: 3443.4). Total num frames: 1335296. Throughput: 0: 815.2. Samples: 332718. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:58:19,328][00111] Avg episode reward: [(0, '8.304')]
[2023-02-22 17:58:22,762][11389] Updated weights for policy 0, policy_version 330 (0.0019)
[2023-02-22 17:58:24,329][00111] Fps is (10 sec: 3274.9, 60 sec: 3276.4, 300 sec: 3457.2). Total num frames: 1355776. Throughput: 0: 827.4. Samples: 338120. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:58:24,334][00111] Avg episode reward: [(0, '8.402')]
[2023-02-22 17:58:29,324][00111] Fps is (10 sec: 4505.7, 60 sec: 3413.4, 300 sec: 3471.2). Total num frames: 1380352. Throughput: 0: 826.6. Samples: 344760. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:58:29,326][00111] Avg episode reward: [(0, '8.883')]
[2023-02-22 17:58:33,230][11389] Updated weights for policy 0, policy_version 340 (0.0012)
[2023-02-22 17:58:34,323][00111] Fps is (10 sec: 3688.8, 60 sec: 3413.3, 300 sec: 3443.4). Total num frames: 1392640. Throughput: 0: 817.7. Samples: 347408. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:58:34,328][00111] Avg episode reward: [(0, '9.755')]
[2023-02-22 17:58:34,334][11375] Saving new best policy, reward=9.755!
[2023-02-22 17:58:39,323][00111] Fps is (10 sec: 2457.7, 60 sec: 3276.8, 300 sec: 3443.5). Total num frames: 1404928. Throughput: 0: 828.9. Samples: 351542. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:58:39,331][00111] Avg episode reward: [(0, '10.201')]
[2023-02-22 17:58:39,345][11375] Saving new best policy, reward=10.201!
[2023-02-22 17:58:44,323][00111] Fps is (10 sec: 3686.3, 60 sec: 3345.1, 300 sec: 3471.2). Total num frames: 1429504. Throughput: 0: 873.2. Samples: 356952. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:58:44,328][00111] Avg episode reward: [(0, '10.810')]
[2023-02-22 17:58:44,333][11375] Saving new best policy, reward=10.810!
[2023-02-22 17:58:45,226][11389] Updated weights for policy 0, policy_version 350 (0.0017)
[2023-02-22 17:58:49,323][00111] Fps is (10 sec: 4505.6, 60 sec: 3413.3, 300 sec: 3471.2). Total num frames: 1449984. Throughput: 0: 901.2. Samples: 360260. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:58:49,326][00111] Avg episode reward: [(0, '10.951')]
[2023-02-22 17:58:49,335][11375] Saving new best policy, reward=10.951!
[2023-02-22 17:58:54,323][00111] Fps is (10 sec: 3686.5, 60 sec: 3481.8, 300 sec: 3457.3). Total num frames: 1466368. Throughput: 0: 892.4. Samples: 365908. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:58:54,332][00111] Avg episode reward: [(0, '10.194')]
[2023-02-22 17:58:57,053][11389] Updated weights for policy 0, policy_version 360 (0.0012)
[2023-02-22 17:58:59,325][00111] Fps is (10 sec: 2866.7, 60 sec: 3481.5, 300 sec: 3457.3). Total num frames: 1478656. Throughput: 0: 876.8. Samples: 370226. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:58:59,333][00111] Avg episode reward: [(0, '10.148')]
[2023-02-22 17:59:04,323][00111] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3485.1). Total num frames: 1499136. Throughput: 0: 891.7. Samples: 372842. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 17:59:04,326][00111] Avg episode reward: [(0, '9.842')]
[2023-02-22 17:59:07,181][11389] Updated weights for policy 0, policy_version 370 (0.0017)
[2023-02-22 17:59:09,323][00111] Fps is (10 sec: 4506.4, 60 sec: 3618.1, 300 sec: 3499.0). Total num frames: 1523712. Throughput: 0: 922.8. Samples: 379640. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:59:09,325][00111] Avg episode reward: [(0, '11.305')]
[2023-02-22 17:59:09,339][11375] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000372_1523712.pth...
[2023-02-22 17:59:09,460][11375] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000165_675840.pth
[2023-02-22 17:59:09,486][11375] Saving new best policy, reward=11.305!
[2023-02-22 17:59:14,323][00111] Fps is (10 sec: 4096.0, 60 sec: 3618.2, 300 sec: 3485.1). Total num frames: 1540096. Throughput: 0: 895.8. Samples: 385072. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:59:14,327][00111] Avg episode reward: [(0, '12.127')]
[2023-02-22 17:59:14,333][11375] Saving new best policy, reward=12.127!
[2023-02-22 17:59:19,325][00111] Fps is (10 sec: 2866.7, 60 sec: 3618.1, 300 sec: 3485.1). Total num frames: 1552384. Throughput: 0: 881.5. Samples: 387078. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:59:19,335][00111] Avg episode reward: [(0, '12.777')]
[2023-02-22 17:59:19,353][11375] Saving new best policy, reward=12.777!
[2023-02-22 17:59:20,157][11389] Updated weights for policy 0, policy_version 380 (0.0024)
[2023-02-22 17:59:24,323][00111] Fps is (10 sec: 3276.8, 60 sec: 3618.5, 300 sec: 3512.8). Total num frames: 1572864. Throughput: 0: 898.4. Samples: 391968. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:59:24,326][00111] Avg episode reward: [(0, '11.793')]
[2023-02-22 17:59:29,323][00111] Fps is (10 sec: 4096.8, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 1593344. Throughput: 0: 926.0. Samples: 398620. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:59:29,329][00111] Avg episode reward: [(0, '11.285')]
[2023-02-22 17:59:29,528][11389] Updated weights for policy 0, policy_version 390 (0.0012)
[2023-02-22 17:59:34,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3499.0). Total num frames: 1609728. Throughput: 0: 920.6. Samples: 401688. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-22 17:59:34,326][00111] Avg episode reward: [(0, '11.553')]
[2023-02-22 17:59:39,323][00111] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3499.0). Total num frames: 1626112. Throughput: 0: 887.2. Samples: 405832. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 17:59:39,330][00111] Avg episode reward: [(0, '11.643')]
[2023-02-22 17:59:42,590][11389] Updated weights for policy 0, policy_version 400 (0.0027)
[2023-02-22 17:59:44,323][00111] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 1642496. Throughput: 0: 907.8. Samples: 411074. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:59:44,330][00111] Avg episode reward: [(0, '12.618')]
[2023-02-22 17:59:49,323][00111] Fps is (10 sec: 4096.2, 60 sec: 3618.1, 300 sec: 3540.6). Total num frames: 1667072. Throughput: 0: 920.7. Samples: 414274. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:59:49,325][00111] Avg episode reward: [(0, '12.385')]
[2023-02-22 17:59:52,002][11389] Updated weights for policy 0, policy_version 410 (0.0023)
[2023-02-22 17:59:54,323][00111] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3526.8). Total num frames: 1683456. Throughput: 0: 911.8. Samples: 420670. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 17:59:54,327][00111] Avg episode reward: [(0, '13.095')]
[2023-02-22 17:59:54,335][11375] Saving new best policy, reward=13.095!
[2023-02-22 17:59:59,323][00111] Fps is (10 sec: 3276.8, 60 sec: 3686.5, 300 sec: 3526.7). Total num frames: 1699840. Throughput: 0: 886.2. Samples: 424950. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 17:59:59,330][00111] Avg episode reward: [(0, '12.960')]
[2023-02-22 18:00:04,323][00111] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 1716224. Throughput: 0: 890.0. Samples: 427128. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:00:04,328][00111] Avg episode reward: [(0, '13.544')]
[2023-02-22 18:00:04,335][11375] Saving new best policy, reward=13.544!
[2023-02-22 18:00:04,824][11389] Updated weights for policy 0, policy_version 420 (0.0016)
[2023-02-22 18:00:09,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3540.6). Total num frames: 1736704. Throughput: 0: 921.2. Samples: 433424. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:00:09,328][00111] Avg episode reward: [(0, '13.762')]
[2023-02-22 18:00:09,343][11375] Saving new best policy, reward=13.762!
[2023-02-22 18:00:14,323][00111] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3540.6). Total num frames: 1757184. Throughput: 0: 905.8. Samples: 439380. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:00:14,326][00111] Avg episode reward: [(0, '14.414')]
[2023-02-22 18:00:14,327][11375] Saving new best policy, reward=14.414!
[2023-02-22 18:00:15,750][11389] Updated weights for policy 0, policy_version 430 (0.0012)
[2023-02-22 18:00:19,323][00111] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3526.7). Total num frames: 1769472. Throughput: 0: 882.5. Samples: 441400. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:00:19,330][00111] Avg episode reward: [(0, '14.553')]
[2023-02-22 18:00:19,340][11375] Saving new best policy, reward=14.553!
[2023-02-22 18:00:24,323][00111] Fps is (10 sec: 2867.1, 60 sec: 3549.8, 300 sec: 3526.7). Total num frames: 1785856. Throughput: 0: 886.2. Samples: 445712. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:00:24,326][00111] Avg episode reward: [(0, '15.362')]
[2023-02-22 18:00:24,329][11375] Saving new best policy, reward=15.362!
[2023-02-22 18:00:27,400][11389] Updated weights for policy 0, policy_version 440 (0.0041)
[2023-02-22 18:00:29,323][00111] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 1810432. Throughput: 0: 917.2. Samples: 452346. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:00:29,329][00111] Avg episode reward: [(0, '15.337')]
[2023-02-22 18:00:34,323][00111] Fps is (10 sec: 4505.8, 60 sec: 3686.4, 300 sec: 3568.4). Total num frames: 1830912. Throughput: 0: 921.6. Samples: 455748. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:00:34,327][00111] Avg episode reward: [(0, '15.716')]
[2023-02-22 18:00:34,334][11375] Saving new best policy, reward=15.716!
[2023-02-22 18:00:38,601][11389] Updated weights for policy 0, policy_version 450 (0.0029)
[2023-02-22 18:00:39,326][00111] Fps is (10 sec: 3276.0, 60 sec: 3618.0, 300 sec: 3540.6). Total num frames: 1843200. Throughput: 0: 882.8. Samples: 460396. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 18:00:39,328][00111] Avg episode reward: [(0, '15.577')]
[2023-02-22 18:00:44,323][00111] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3554.5). Total num frames: 1859584. Throughput: 0: 888.9. Samples: 464950. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:00:44,331][00111] Avg episode reward: [(0, '15.535')]
[2023-02-22 18:00:49,323][00111] Fps is (10 sec: 3687.3, 60 sec: 3549.9, 300 sec: 3568.4). Total num frames: 1880064. Throughput: 0: 913.5. Samples: 468236. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-22 18:00:49,326][00111] Avg episode reward: [(0, '16.174')]
[2023-02-22 18:00:49,356][11375] Saving new best policy, reward=16.174!
[2023-02-22 18:00:49,364][11389] Updated weights for policy 0, policy_version 460 (0.0031)
[2023-02-22 18:00:54,323][00111] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 1900544. Throughput: 0: 922.7. Samples: 474944. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:00:54,328][00111] Avg episode reward: [(0, '16.486')]
[2023-02-22 18:00:54,331][11375] Saving new best policy, reward=16.486!
[2023-02-22 18:00:59,323][00111] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3540.6). Total num frames: 1912832. Throughput: 0: 871.6. Samples: 478602. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:00:59,327][00111] Avg episode reward: [(0, '15.767')]
[2023-02-22 18:01:03,313][11389] Updated weights for policy 0, policy_version 470 (0.0018)
[2023-02-22 18:01:04,323][00111] Fps is (10 sec: 2457.6, 60 sec: 3481.6, 300 sec: 3526.8). Total num frames: 1925120. Throughput: 0: 873.4. Samples: 480704. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
[2023-02-22 18:01:04,334][00111] Avg episode reward: [(0, '15.573')]
[2023-02-22 18:01:09,323][00111] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3540.6). Total num frames: 1941504. Throughput: 0: 865.8. Samples: 484674. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 18:01:09,325][00111] Avg episode reward: [(0, '17.678')]
[2023-02-22 18:01:09,344][11375] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000474_1941504.pth...
[2023-02-22 18:01:09,459][11375] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000270_1105920.pth
[2023-02-22 18:01:09,469][11375] Saving new best policy, reward=17.678!
[2023-02-22 18:01:14,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3526.7). Total num frames: 1961984. Throughput: 0: 853.6. Samples: 490760. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:01:14,329][00111] Avg episode reward: [(0, '18.562')]
[2023-02-22 18:01:14,334][11375] Saving new best policy, reward=18.562!
[2023-02-22 18:01:15,566][11389] Updated weights for policy 0, policy_version 480 (0.0012)
[2023-02-22 18:01:19,325][00111] Fps is (10 sec: 3276.1, 60 sec: 3413.2, 300 sec: 3485.1). Total num frames: 1974272. Throughput: 0: 820.8. Samples: 492686. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:01:19,328][00111] Avg episode reward: [(0, '18.777')]
[2023-02-22 18:01:19,346][11375] Saving new best policy, reward=18.777!
[2023-02-22 18:01:24,323][00111] Fps is (10 sec: 2867.2, 60 sec: 3413.4, 300 sec: 3499.0). Total num frames: 1990656. Throughput: 0: 811.1. Samples: 496894. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 18:01:24,331][00111] Avg episode reward: [(0, '18.665')]
[2023-02-22 18:01:27,590][11389] Updated weights for policy 0, policy_version 490 (0.0017)
[2023-02-22 18:01:29,323][00111] Fps is (10 sec: 3687.3, 60 sec: 3345.1, 300 sec: 3512.9). Total num frames: 2011136. Throughput: 0: 846.2. Samples: 503030. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
[2023-02-22 18:01:29,332][00111] Avg episode reward: [(0, '19.471')]
[2023-02-22 18:01:29,346][11375] Saving new best policy, reward=19.471!
[2023-02-22 18:01:34,325][00111] Fps is (10 sec: 4095.1, 60 sec: 3344.9, 300 sec: 3512.8). Total num frames: 2031616. Throughput: 0: 846.0. Samples: 506308. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:01:34,332][00111] Avg episode reward: [(0, '18.196')]
[2023-02-22 18:01:38,809][11389] Updated weights for policy 0, policy_version 500 (0.0016)
[2023-02-22 18:01:39,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3413.5, 300 sec: 3485.1). Total num frames: 2048000. Throughput: 0: 809.7. Samples: 511380. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 18:01:39,328][00111] Avg episode reward: [(0, '17.475')]
[2023-02-22 18:01:44,323][00111] Fps is (10 sec: 2867.8, 60 sec: 3345.1, 300 sec: 3485.1). Total num frames: 2060288. Throughput: 0: 825.7. Samples: 515758. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 18:01:44,326][00111] Avg episode reward: [(0, '18.237')]
[2023-02-22 18:01:49,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3526.7). Total num frames: 2084864. Throughput: 0: 847.0. Samples: 518818. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:01:49,325][00111] Avg episode reward: [(0, '18.578')]
[2023-02-22 18:01:49,938][11389] Updated weights for policy 0, policy_version 510 (0.0030)
[2023-02-22 18:01:54,324][00111] Fps is (10 sec: 4505.3, 60 sec: 3413.3, 300 sec: 3512.8). Total num frames: 2105344. Throughput: 0: 911.3. Samples: 525682. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:01:54,328][00111] Avg episode reward: [(0, '19.516')]
[2023-02-22 18:01:54,334][11375] Saving new best policy, reward=19.516!
[2023-02-22 18:01:59,323][00111] Fps is (10 sec: 3686.3, 60 sec: 3481.6, 300 sec: 3499.0). Total num frames: 2121728. Throughput: 0: 884.6. Samples: 530566. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:01:59,326][00111] Avg episode reward: [(0, '19.774')]
[2023-02-22 18:01:59,348][11375] Saving new best policy, reward=19.774!
[2023-02-22 18:02:02,167][11389] Updated weights for policy 0, policy_version 520 (0.0026)
[2023-02-22 18:02:04,323][00111] Fps is (10 sec: 2867.4, 60 sec: 3481.6, 300 sec: 3499.0). Total num frames: 2134016. Throughput: 0: 887.4. Samples: 532616. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:02:04,326][00111] Avg episode reward: [(0, '20.260')]
[2023-02-22 18:02:04,331][11375] Saving new best policy, reward=20.260!
[2023-02-22 18:02:09,323][00111] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3512.9). Total num frames: 2154496. Throughput: 0: 914.4. Samples: 538042. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 18:02:09,325][00111] Avg episode reward: [(0, '20.397')]
[2023-02-22 18:02:09,342][11375] Saving new best policy, reward=20.397!
[2023-02-22 18:02:12,047][11389] Updated weights for policy 0, policy_version 530 (0.0017)
[2023-02-22 18:02:14,323][00111] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 2179072. Throughput: 0: 929.2. Samples: 544844. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:02:14,329][00111] Avg episode reward: [(0, '19.509')]
[2023-02-22 18:02:19,324][00111] Fps is (10 sec: 3685.9, 60 sec: 3618.2, 300 sec: 3498.9). Total num frames: 2191360. Throughput: 0: 913.0. Samples: 547390. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 18:02:19,327][00111] Avg episode reward: [(0, '19.728')]
[2023-02-22 18:02:24,323][00111] Fps is (10 sec: 2867.1, 60 sec: 3618.1, 300 sec: 3499.0). Total num frames: 2207744. Throughput: 0: 892.2. Samples: 551528. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 18:02:24,329][00111] Avg episode reward: [(0, '19.705')]
[2023-02-22 18:02:25,133][11389] Updated weights for policy 0, policy_version 540 (0.0014)
[2023-02-22 18:02:29,323][00111] Fps is (10 sec: 3686.8, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 2228224. Throughput: 0: 920.2. Samples: 557168. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:02:29,326][00111] Avg episode reward: [(0, '19.551')]
[2023-02-22 18:02:34,329][00111] Fps is (10 sec: 4093.7, 60 sec: 3617.9, 300 sec: 3526.7). Total num frames: 2248704. Throughput: 0: 924.0. Samples: 560402. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:02:34,334][00111] Avg episode reward: [(0, '18.162')]
[2023-02-22 18:02:34,512][11389] Updated weights for policy 0, policy_version 550 (0.0021)
[2023-02-22 18:02:39,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3512.8). Total num frames: 2265088. Throughput: 0: 898.8. Samples: 566126. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:02:39,330][00111] Avg episode reward: [(0, '18.301')]
[2023-02-22 18:02:44,327][00111] Fps is (10 sec: 2867.7, 60 sec: 3617.9, 300 sec: 3498.9). Total num frames: 2277376. Throughput: 0: 863.3. Samples: 569420. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 18:02:44,329][00111] Avg episode reward: [(0, '19.141')]
[2023-02-22 18:02:49,323][00111] Fps is (10 sec: 2048.0, 60 sec: 3345.1, 300 sec: 3485.1). Total num frames: 2285568. Throughput: 0: 856.4. Samples: 571152. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 18:02:49,330][00111] Avg episode reward: [(0, '19.219')]
[2023-02-22 18:02:51,218][11389] Updated weights for policy 0, policy_version 560 (0.0038)
[2023-02-22 18:02:54,323][00111] Fps is (10 sec: 2868.4, 60 sec: 3345.1, 300 sec: 3512.8). Total num frames: 2306048. Throughput: 0: 823.2. Samples: 575086. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:02:54,326][00111] Avg episode reward: [(0, '19.827')]
[2023-02-22 18:02:59,323][00111] Fps is (10 sec: 4095.9, 60 sec: 3413.3, 300 sec: 3526.7). Total num frames: 2326528. Throughput: 0: 824.9. Samples: 581966. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:02:59,326][00111] Avg episode reward: [(0, '20.438')]
[2023-02-22 18:02:59,346][11375] Saving new best policy, reward=20.438!
[2023-02-22 18:03:00,968][11389] Updated weights for policy 0, policy_version 570 (0.0015)
[2023-02-22 18:03:04,323][00111] Fps is (10 sec: 3686.2, 60 sec: 3481.6, 300 sec: 3512.8). Total num frames: 2342912. Throughput: 0: 825.3. Samples: 584528. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:03:04,326][00111] Avg episode reward: [(0, '21.855')]
[2023-02-22 18:03:04,331][11375] Saving new best policy, reward=21.855!
[2023-02-22 18:03:09,323][00111] Fps is (10 sec: 2867.3, 60 sec: 3345.1, 300 sec: 3499.0). Total num frames: 2355200. Throughput: 0: 823.7. Samples: 588596. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:03:09,327][00111] Avg episode reward: [(0, '22.641')]
[2023-02-22 18:03:09,339][11375] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000575_2355200.pth...
[2023-02-22 18:03:09,554][11375] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000372_1523712.pth
[2023-02-22 18:03:09,575][11375] Saving new best policy, reward=22.641!
[2023-02-22 18:03:13,868][11389] Updated weights for policy 0, policy_version 580 (0.0025)
[2023-02-22 18:03:14,323][00111] Fps is (10 sec: 3276.9, 60 sec: 3276.8, 300 sec: 3526.7). Total num frames: 2375680. Throughput: 0: 818.7. Samples: 594008. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 18:03:14,326][00111] Avg episode reward: [(0, '22.196')]
[2023-02-22 18:03:19,323][00111] Fps is (10 sec: 4096.0, 60 sec: 3413.4, 300 sec: 3526.8). Total num frames: 2396160. Throughput: 0: 818.7. Samples: 597238. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:03:19,326][00111] Avg episode reward: [(0, '20.104')]
[2023-02-22 18:03:24,325][00111] Fps is (10 sec: 3685.6, 60 sec: 3413.2, 300 sec: 3498.9). Total num frames: 2412544. Throughput: 0: 814.8. Samples: 602796. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 18:03:24,328][00111] Avg episode reward: [(0, '19.824')]
[2023-02-22 18:03:25,244][11389] Updated weights for policy 0, policy_version 590 (0.0023)
[2023-02-22 18:03:29,323][00111] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3499.0). Total num frames: 2424832. Throughput: 0: 833.5. Samples: 606924. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:03:29,326][00111] Avg episode reward: [(0, '20.095')]
[2023-02-22 18:03:34,323][00111] Fps is (10 sec: 3277.5, 60 sec: 3277.1, 300 sec: 3526.7). Total num frames: 2445312. Throughput: 0: 849.9. Samples: 609396. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-22 18:03:34,325][00111] Avg episode reward: [(0, '19.651')]
[2023-02-22 18:03:36,779][11389] Updated weights for policy 0, policy_version 600 (0.0012)
[2023-02-22 18:03:39,323][00111] Fps is (10 sec: 4096.0, 60 sec: 3345.1, 300 sec: 3512.8). Total num frames: 2465792. Throughput: 0: 904.8. Samples: 615800. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 18:03:39,331][00111] Avg episode reward: [(0, '19.760')]
[2023-02-22 18:03:44,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3413.6, 300 sec: 3499.0). Total num frames: 2482176. Throughput: 0: 868.8. Samples: 621064. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:03:44,330][00111] Avg episode reward: [(0, '20.616')]
[2023-02-22 18:03:49,324][00111] Fps is (10 sec: 2866.9, 60 sec: 3481.6, 300 sec: 3485.1). Total num frames: 2494464. Throughput: 0: 855.8. Samples: 623040. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:03:49,331][00111] Avg episode reward: [(0, '20.850')]
[2023-02-22 18:03:49,557][11389] Updated weights for policy 0, policy_version 610 (0.0025)
[2023-02-22 18:03:54,323][00111] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3512.9). Total num frames: 2514944. Throughput: 0: 872.5. Samples: 627858. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:03:54,326][00111] Avg episode reward: [(0, '21.602')]
[2023-02-22 18:03:59,247][11389] Updated weights for policy 0, policy_version 620 (0.0015)
[2023-02-22 18:03:59,323][00111] Fps is (10 sec: 4506.0, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 2539520. Throughput: 0: 900.1. Samples: 634514. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:03:59,330][00111] Avg episode reward: [(0, '20.852')]
[2023-02-22 18:04:04,323][00111] Fps is (10 sec: 4095.9, 60 sec: 3549.9, 300 sec: 3499.0). Total num frames: 2555904. Throughput: 0: 897.9. Samples: 637642. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:04:04,332][00111] Avg episode reward: [(0, '21.849')]
[2023-02-22 18:04:09,323][00111] Fps is (10 sec: 2867.1, 60 sec: 3549.9, 300 sec: 3485.1). Total num frames: 2568192. Throughput: 0: 871.5. Samples: 642014. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 18:04:09,330][00111] Avg episode reward: [(0, '21.063')]
[2023-02-22 18:04:12,033][11389] Updated weights for policy 0, policy_version 630 (0.0046)
[2023-02-22 18:04:14,323][00111] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3512.9). Total num frames: 2588672. Throughput: 0: 897.8. Samples: 647326. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:04:14,326][00111] Avg episode reward: [(0, '21.915')]
[2023-02-22 18:04:19,323][00111] Fps is (10 sec: 4505.7, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 2613248. Throughput: 0: 918.5. Samples: 650728. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:04:19,331][00111] Avg episode reward: [(0, '21.226')]
[2023-02-22 18:04:21,121][11389] Updated weights for policy 0, policy_version 640 (0.0024)
[2023-02-22 18:04:24,323][00111] Fps is (10 sec: 4096.0, 60 sec: 3618.3, 300 sec: 3512.8). Total num frames: 2629632. Throughput: 0: 912.4. Samples: 656856. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:04:24,330][00111] Avg episode reward: [(0, '22.459')]
[2023-02-22 18:04:29,324][00111] Fps is (10 sec: 2867.1, 60 sec: 3618.1, 300 sec: 3499.0). Total num frames: 2641920. Throughput: 0: 884.4. Samples: 660864. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 18:04:29,331][00111] Avg episode reward: [(0, '23.109')]
[2023-02-22 18:04:29,346][11375] Saving new best policy, reward=23.109!
[2023-02-22 18:04:34,323][00111] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3499.0). Total num frames: 2658304. Throughput: 0: 885.4. Samples: 662882. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:04:34,331][00111] Avg episode reward: [(0, '22.585')]
[2023-02-22 18:04:34,368][11389] Updated weights for policy 0, policy_version 650 (0.0029)
[2023-02-22 18:04:39,323][00111] Fps is (10 sec: 4096.2, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 2682880. Throughput: 0: 924.3. Samples: 669452. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:04:39,332][00111] Avg episode reward: [(0, '24.347')]
[2023-02-22 18:04:39,345][11375] Saving new best policy, reward=24.347!
[2023-02-22 18:04:44,326][00111] Fps is (10 sec: 4094.7, 60 sec: 3617.9, 300 sec: 3498.9). Total num frames: 2699264. Throughput: 0: 907.7. Samples: 675362. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 18:04:44,329][00111] Avg episode reward: [(0, '24.148')]
[2023-02-22 18:04:44,951][11389] Updated weights for policy 0, policy_version 660 (0.0018)
[2023-02-22 18:04:49,323][00111] Fps is (10 sec: 2867.2, 60 sec: 3618.2, 300 sec: 3485.1). Total num frames: 2711552. Throughput: 0: 884.8. Samples: 677456. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:04:49,336][00111] Avg episode reward: [(0, '23.553')]
[2023-02-22 18:04:54,323][00111] Fps is (10 sec: 3277.8, 60 sec: 3618.1, 300 sec: 3499.0). Total num frames: 2732032. Throughput: 0: 884.3. Samples: 681806. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:04:54,325][00111] Avg episode reward: [(0, '23.753')]
[2023-02-22 18:04:56,792][11389] Updated weights for policy 0, policy_version 670 (0.0024)
[2023-02-22 18:04:59,323][00111] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 2752512. Throughput: 0: 915.6. Samples: 688526. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:04:59,325][00111] Avg episode reward: [(0, '23.003')]
[2023-02-22 18:05:04,324][00111] Fps is (10 sec: 4095.5, 60 sec: 3618.1, 300 sec: 3512.8). Total num frames: 2772992. Throughput: 0: 912.3. Samples: 691784. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:05:04,329][00111] Avg episode reward: [(0, '22.685')]
[2023-02-22 18:05:08,375][11389] Updated weights for policy 0, policy_version 680 (0.0018)
[2023-02-22 18:05:09,323][00111] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3485.1). Total num frames: 2785280. Throughput: 0: 873.6. Samples: 696168. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 18:05:09,330][00111] Avg episode reward: [(0, '22.001')]
[2023-02-22 18:05:09,353][11375] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000680_2785280.pth...
[2023-02-22 18:05:09,530][11375] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000474_1941504.pth
[2023-02-22 18:05:14,323][00111] Fps is (10 sec: 2867.6, 60 sec: 3549.9, 300 sec: 3499.0). Total num frames: 2801664. Throughput: 0: 884.4. Samples: 700662. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:05:14,326][00111] Avg episode reward: [(0, '21.594')]
[2023-02-22 18:05:19,274][11389] Updated weights for policy 0, policy_version 690 (0.0012)
[2023-02-22 18:05:19,323][00111] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 2826240. Throughput: 0: 913.2. Samples: 703974. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:05:19,326][00111] Avg episode reward: [(0, '22.300')]
[2023-02-22 18:05:24,323][00111] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3499.0). Total num frames: 2842624. Throughput: 0: 913.6. Samples: 710564. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:05:24,327][00111] Avg episode reward: [(0, '21.571')]
[2023-02-22 18:05:29,323][00111] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3485.1). Total num frames: 2859008. Throughput: 0: 875.1. Samples: 714740. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
[2023-02-22 18:05:29,329][00111] Avg episode reward: [(0, '22.099')]
[2023-02-22 18:05:32,175][11389] Updated weights for policy 0, policy_version 700 (0.0016)
[2023-02-22 18:05:34,323][00111] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3499.0). Total num frames: 2875392. Throughput: 0: 876.5. Samples: 716898. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:05:34,328][00111] Avg episode reward: [(0, '21.791')]
[2023-02-22 18:05:39,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 2895872. Throughput: 0: 917.2. Samples: 723082. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:05:39,325][00111] Avg episode reward: [(0, '21.792')]
[2023-02-22 18:05:41,514][11389] Updated weights for policy 0, policy_version 710 (0.0017)
[2023-02-22 18:05:44,323][00111] Fps is (10 sec: 4096.0, 60 sec: 3618.3, 300 sec: 3512.8). Total num frames: 2916352. Throughput: 0: 912.6. Samples: 729594. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:05:44,326][00111] Avg episode reward: [(0, '22.126')]
[2023-02-22 18:05:49,323][00111] Fps is (10 sec: 3276.7, 60 sec: 3618.1, 300 sec: 3485.1). Total num frames: 2928640. Throughput: 0: 885.5. Samples: 731630. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 18:05:49,326][00111] Avg episode reward: [(0, '21.779')]
[2023-02-22 18:05:54,323][00111] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3499.0). Total num frames: 2945024. Throughput: 0: 878.9. Samples: 735720. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:05:54,326][00111] Avg episode reward: [(0, '21.559')]
[2023-02-22 18:05:54,615][11389] Updated weights for policy 0, policy_version 720 (0.0023)
[2023-02-22 18:05:59,323][00111] Fps is (10 sec: 4096.1, 60 sec: 3618.1, 300 sec: 3540.6). Total num frames: 2969600. Throughput: 0: 920.1. Samples: 742066. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:05:59,331][00111] Avg episode reward: [(0, '21.216')]
[2023-02-22 18:06:03,746][11389] Updated weights for policy 0, policy_version 730 (0.0013)
[2023-02-22 18:06:04,326][00111] Fps is (10 sec: 4504.1, 60 sec: 3618.0, 300 sec: 3554.5). Total num frames: 2990080. Throughput: 0: 922.2. Samples: 745474. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:06:04,328][00111] Avg episode reward: [(0, '21.065')]
[2023-02-22 18:06:09,323][00111] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 3002368. Throughput: 0: 888.2. Samples: 750532. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2023-02-22 18:06:09,330][00111] Avg episode reward: [(0, '21.045')]
[2023-02-22 18:06:14,323][00111] Fps is (10 sec: 2868.2, 60 sec: 3618.1, 300 sec: 3540.6). Total num frames: 3018752. Throughput: 0: 891.0. Samples: 754834. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 18:06:14,325][00111] Avg episode reward: [(0, '21.704')]
[2023-02-22 18:06:16,463][11389] Updated weights for policy 0, policy_version 740 (0.0020)
[2023-02-22 18:06:19,323][00111] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 3043328. Throughput: 0: 917.8. Samples: 758198. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 18:06:19,325][00111] Avg episode reward: [(0, '22.554')]
[2023-02-22 18:06:24,330][00111] Fps is (10 sec: 4502.4, 60 sec: 3686.0, 300 sec: 3568.3). Total num frames: 3063808. Throughput: 0: 932.3. Samples: 765044. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:06:24,341][00111] Avg episode reward: [(0, '22.802')]
[2023-02-22 18:06:26,624][11389] Updated weights for policy 0, policy_version 750 (0.0016)
[2023-02-22 18:06:29,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3554.5). Total num frames: 3080192. Throughput: 0: 896.3. Samples: 769928. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 18:06:29,330][00111] Avg episode reward: [(0, '21.989')]
[2023-02-22 18:06:34,323][00111] Fps is (10 sec: 2869.3, 60 sec: 3618.1, 300 sec: 3540.6). Total num frames: 3092480. Throughput: 0: 898.6. Samples: 772068. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:06:34,329][00111] Avg episode reward: [(0, '22.901')]
[2023-02-22 18:06:38,110][11389] Updated weights for policy 0, policy_version 760 (0.0020)
[2023-02-22 18:06:39,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 3117056. Throughput: 0: 938.6. Samples: 777958. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:06:39,325][00111] Avg episode reward: [(0, '22.427')]
[2023-02-22 18:06:44,323][00111] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3568.4). Total num frames: 3137536. Throughput: 0: 947.0. Samples: 784682. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:06:44,330][00111] Avg episode reward: [(0, '22.082')]
[2023-02-22 18:06:49,330][00111] Fps is (10 sec: 3274.5, 60 sec: 3686.0, 300 sec: 3540.5). Total num frames: 3149824. Throughput: 0: 922.1. Samples: 786974. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:06:49,333][00111] Avg episode reward: [(0, '21.795')]
[2023-02-22 18:06:49,348][11389] Updated weights for policy 0, policy_version 770 (0.0016)
[2023-02-22 18:06:54,323][00111] Fps is (10 sec: 2867.1, 60 sec: 3686.4, 300 sec: 3540.6). Total num frames: 3166208. Throughput: 0: 904.5. Samples: 791236. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:06:54,327][00111] Avg episode reward: [(0, '21.240')]
[2023-02-22 18:06:59,323][00111] Fps is (10 sec: 3689.0, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 3186688. Throughput: 0: 942.8. Samples: 797262. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:06:59,326][00111] Avg episode reward: [(0, '20.788')]
[2023-02-22 18:07:00,201][11389] Updated weights for policy 0, policy_version 780 (0.0028)
[2023-02-22 18:07:04,327][00111] Fps is (10 sec: 4503.8, 60 sec: 3686.3, 300 sec: 3582.2). Total num frames: 3211264. Throughput: 0: 942.5. Samples: 800614. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 18:07:04,330][00111] Avg episode reward: [(0, '19.676')]
[2023-02-22 18:07:09,324][00111] Fps is (10 sec: 3685.9, 60 sec: 3686.3, 300 sec: 3540.6). Total num frames: 3223552. Throughput: 0: 910.8. Samples: 806026. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 18:07:09,329][00111] Avg episode reward: [(0, '18.951')]
[2023-02-22 18:07:09,346][11375] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000787_3223552.pth...
[2023-02-22 18:07:09,510][11375] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000575_2355200.pth
[2023-02-22 18:07:12,558][11389] Updated weights for policy 0, policy_version 790 (0.0018)
[2023-02-22 18:07:14,323][00111] Fps is (10 sec: 2868.4, 60 sec: 3686.4, 300 sec: 3554.5). Total num frames: 3239936. Throughput: 0: 895.2. Samples: 810214. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 18:07:14,332][00111] Avg episode reward: [(0, '19.549')]
[2023-02-22 18:07:19,323][00111] Fps is (10 sec: 3686.8, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 3260416. Throughput: 0: 913.7. Samples: 813186. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:07:19,326][00111] Avg episode reward: [(0, '19.622')]
[2023-02-22 18:07:22,343][11389] Updated weights for policy 0, policy_version 800 (0.0025)
[2023-02-22 18:07:24,323][00111] Fps is (10 sec: 4505.6, 60 sec: 3686.8, 300 sec: 3582.3). Total num frames: 3284992. Throughput: 0: 932.1. Samples: 819904. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:07:24,330][00111] Avg episode reward: [(0, '20.209')]
[2023-02-22 18:07:29,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3554.6). Total num frames: 3297280. Throughput: 0: 890.7. Samples: 824764. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:07:29,326][00111] Avg episode reward: [(0, '19.975')]
[2023-02-22 18:07:34,323][00111] Fps is (10 sec: 2457.6, 60 sec: 3618.1, 300 sec: 3540.6). Total num frames: 3309568. Throughput: 0: 876.8. Samples: 826426. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:07:34,331][00111] Avg episode reward: [(0, '20.666')]
[2023-02-22 18:07:37,669][11389] Updated weights for policy 0, policy_version 810 (0.0026)
[2023-02-22 18:07:39,323][00111] Fps is (10 sec: 2048.0, 60 sec: 3345.1, 300 sec: 3526.8). Total num frames: 3317760. Throughput: 0: 857.4. Samples: 829820. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:07:39,326][00111] Avg episode reward: [(0, '21.456')]
[2023-02-22 18:07:44,323][00111] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3568.4). Total num frames: 3338240. Throughput: 0: 835.1. Samples: 834842. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:07:44,326][00111] Avg episode reward: [(0, '21.197')]
[2023-02-22 18:07:48,259][11389] Updated weights for policy 0, policy_version 820 (0.0016)
[2023-02-22 18:07:49,329][00111] Fps is (10 sec: 4093.5, 60 sec: 3481.7, 300 sec: 3568.3). Total num frames: 3358720. Throughput: 0: 833.4. Samples: 838120. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:07:49,332][00111] Avg episode reward: [(0, '21.735')]
[2023-02-22 18:07:54,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3554.5). Total num frames: 3375104. Throughput: 0: 828.9. Samples: 843326. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:07:54,326][00111] Avg episode reward: [(0, '21.171')]
[2023-02-22 18:07:59,323][00111] Fps is (10 sec: 2869.0, 60 sec: 3345.1, 300 sec: 3540.6). Total num frames: 3387392. Throughput: 0: 826.7. Samples: 847416. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:07:59,331][00111] Avg episode reward: [(0, '22.272')]
[2023-02-22 18:08:01,400][11389] Updated weights for policy 0, policy_version 830 (0.0027)
[2023-02-22 18:08:04,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3345.3, 300 sec: 3582.3). Total num frames: 3411968. Throughput: 0: 829.5. Samples: 850514. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:08:04,326][00111] Avg episode reward: [(0, '21.672')]
[2023-02-22 18:08:09,323][00111] Fps is (10 sec: 4505.6, 60 sec: 3481.7, 300 sec: 3582.3). Total num frames: 3432448. Throughput: 0: 828.4. Samples: 857180. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:08:09,330][00111] Avg episode reward: [(0, '22.710')]
[2023-02-22 18:08:11,628][11389] Updated weights for policy 0, policy_version 840 (0.0022)
[2023-02-22 18:08:14,328][00111] Fps is (10 sec: 3275.1, 60 sec: 3413.0, 300 sec: 3554.4). Total num frames: 3444736. Throughput: 0: 828.8. Samples: 862064. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:08:14,331][00111] Avg episode reward: [(0, '21.156')]
[2023-02-22 18:08:19,323][00111] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3554.5). Total num frames: 3461120. Throughput: 0: 837.1. Samples: 864096. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:08:19,328][00111] Avg episode reward: [(0, '21.175')]
[2023-02-22 18:08:23,537][11389] Updated weights for policy 0, policy_version 850 (0.0014)
[2023-02-22 18:08:24,324][00111] Fps is (10 sec: 3688.2, 60 sec: 3276.8, 300 sec: 3582.3). Total num frames: 3481600. Throughput: 0: 882.4. Samples: 869530. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:08:24,327][00111] Avg episode reward: [(0, '20.992')]
[2023-02-22 18:08:29,323][00111] Fps is (10 sec: 4505.6, 60 sec: 3481.6, 300 sec: 3596.1). Total num frames: 3506176. Throughput: 0: 920.0. Samples: 876244. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:08:29,326][00111] Avg episode reward: [(0, '20.949')]
[2023-02-22 18:08:34,326][00111] Fps is (10 sec: 3685.3, 60 sec: 3481.4, 300 sec: 3568.3). Total num frames: 3518464. Throughput: 0: 904.6. Samples: 878826. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:08:34,329][00111] Avg episode reward: [(0, '20.959')]
[2023-02-22 18:08:34,774][11389] Updated weights for policy 0, policy_version 860 (0.0018)
[2023-02-22 18:08:39,325][00111] Fps is (10 sec: 2866.7, 60 sec: 3618.0, 300 sec: 3568.4). Total num frames: 3534848. Throughput: 0: 882.9. Samples: 883056. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:08:39,327][00111] Avg episode reward: [(0, '21.257')]
[2023-02-22 18:08:44,323][00111] Fps is (10 sec: 3687.6, 60 sec: 3618.1, 300 sec: 3596.2). Total num frames: 3555328. Throughput: 0: 924.1. Samples: 889002. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
[2023-02-22 18:08:44,326][00111] Avg episode reward: [(0, '21.204')]
[2023-02-22 18:08:45,438][11389] Updated weights for policy 0, policy_version 870 (0.0030)
[2023-02-22 18:08:49,323][00111] Fps is (10 sec: 4506.4, 60 sec: 3686.8, 300 sec: 3610.0). Total num frames: 3579904. Throughput: 0: 931.3. Samples: 892422. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:08:49,332][00111] Avg episode reward: [(0, '22.259')]
[2023-02-22 18:08:54,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 3592192. Throughput: 0: 908.0. Samples: 898042. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:08:54,331][00111] Avg episode reward: [(0, '21.753')]
[2023-02-22 18:08:57,304][11389] Updated weights for policy 0, policy_version 880 (0.0023)
[2023-02-22 18:08:59,323][00111] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3568.4). Total num frames: 3608576. Throughput: 0: 898.2. Samples: 902480. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:08:59,333][00111] Avg episode reward: [(0, '22.060')]
[2023-02-22 18:09:04,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3596.2). Total num frames: 3629056. Throughput: 0: 915.1. Samples: 905274. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:09:04,326][00111] Avg episode reward: [(0, '21.308')]
[2023-02-22 18:09:07,207][11389] Updated weights for policy 0, policy_version 890 (0.0042)
[2023-02-22 18:09:09,323][00111] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 3653632. Throughput: 0: 947.0. Samples: 912144. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 18:09:09,332][00111] Avg episode reward: [(0, '22.380')]
[2023-02-22 18:09:09,345][11375] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000892_3653632.pth...
[2023-02-22 18:09:09,464][11375] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000680_2785280.pth
[2023-02-22 18:09:14,327][00111] Fps is (10 sec: 4094.3, 60 sec: 3754.7, 300 sec: 3582.2). Total num frames: 3670016. Throughput: 0: 918.0. Samples: 917556. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 18:09:14,332][00111] Avg episode reward: [(0, '22.203')]
[2023-02-22 18:09:19,323][00111] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3568.4). Total num frames: 3682304. Throughput: 0: 905.3. Samples: 919562. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:09:19,332][00111] Avg episode reward: [(0, '22.367')]
[2023-02-22 18:09:20,107][11389] Updated weights for policy 0, policy_version 900 (0.0020)
[2023-02-22 18:09:24,323][00111] Fps is (10 sec: 3278.2, 60 sec: 3686.4, 300 sec: 3596.2). Total num frames: 3702784. Throughput: 0: 921.7. Samples: 924530. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:09:24,331][00111] Avg episode reward: [(0, '21.339')]
[2023-02-22 18:09:29,323][00111] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 3723264. Throughput: 0: 939.6. Samples: 931282. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:09:29,326][00111] Avg episode reward: [(0, '21.675')]
[2023-02-22 18:09:29,475][11389] Updated weights for policy 0, policy_version 910 (0.0012)
[2023-02-22 18:09:34,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3686.6, 300 sec: 3582.3). Total num frames: 3739648. Throughput: 0: 930.9. Samples: 934314. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:09:34,326][00111] Avg episode reward: [(0, '20.339')]
[2023-02-22 18:09:39,323][00111] Fps is (10 sec: 3276.8, 60 sec: 3686.5, 300 sec: 3582.3). Total num frames: 3756032. Throughput: 0: 903.0. Samples: 938678. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:09:39,327][00111] Avg episode reward: [(0, '19.391')]
[2023-02-22 18:09:41,959][11389] Updated weights for policy 0, policy_version 920 (0.0042)
[2023-02-22 18:09:44,323][00111] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 3776512. Throughput: 0: 930.6. Samples: 944356. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2023-02-22 18:09:44,330][00111] Avg episode reward: [(0, '19.006')]
[2023-02-22 18:09:49,323][00111] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 3801088. Throughput: 0: 943.9. Samples: 947750. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:09:49,326][00111] Avg episode reward: [(0, '20.233')]
[2023-02-22 18:09:51,104][11389] Updated weights for policy 0, policy_version 930 (0.0014)
[2023-02-22 18:09:54,323][00111] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3610.0). Total num frames: 3817472. Throughput: 0: 926.7. Samples: 953846. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2023-02-22 18:09:54,325][00111] Avg episode reward: [(0, '19.338')]
[2023-02-22 18:09:59,323][00111] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 3829760. Throughput: 0: 901.6. Samples: 958124. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2023-02-22 18:09:59,325][00111] Avg episode reward: [(0, '21.015')]
[2023-02-22 18:10:03,928][11389] Updated weights for policy 0, policy_version 940 (0.0014)
[2023-02-22 18:10:04,323][00111] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 3850240. Throughput: 0: 907.6. Samples: 960402. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 18:10:04,326][00111] Avg episode reward: [(0, '20.986')]
[2023-02-22 18:10:09,326][00111] Fps is (10 sec: 4094.7, 60 sec: 3617.9, 300 sec: 3623.9). Total num frames: 3870720. Throughput: 0: 948.4. Samples: 967212. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2023-02-22 18:10:09,335][00111] Avg episode reward: [(0, '22.475')]
[2023-02-22 18:10:13,918][11389] Updated weights for policy 0, policy_version 950 (0.0017)
[2023-02-22 18:10:14,323][00111] Fps is (10 sec: 4096.0, 60 sec: 3686.7, 300 sec: 3610.0). Total num frames: 3891200. Throughput: 0: 927.9. Samples: 973038. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
[2023-02-22 18:10:14,326][00111] Avg episode reward: [(0, '22.836')]
[2023-02-22 18:10:19,324][00111] Fps is (10 sec: 3277.6, 60 sec: 3686.4, 300 sec: 3596.1). Total num frames: 3903488. Throughput: 0: 905.8. Samples: 975076. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:10:19,331][00111] Avg episode reward: [(0, '22.902')]
[2023-02-22 18:10:24,323][00111] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 3923968. Throughput: 0: 912.3. Samples: 979730. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:10:24,325][00111] Avg episode reward: [(0, '22.415')]
[2023-02-22 18:10:25,820][11389] Updated weights for policy 0, policy_version 960 (0.0031)
[2023-02-22 18:10:29,323][00111] Fps is (10 sec: 4096.2, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 3944448. Throughput: 0: 937.1. Samples: 986526. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:10:29,333][00111] Avg episode reward: [(0, '22.236')]
[2023-02-22 18:10:34,323][00111] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3623.9). Total num frames: 3964928. Throughput: 0: 933.7. Samples: 989766. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:10:34,329][00111] Avg episode reward: [(0, '23.004')]
[2023-02-22 18:10:36,851][11389] Updated weights for policy 0, policy_version 970 (0.0020)
[2023-02-22 18:10:39,323][00111] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3596.1). Total num frames: 3977216. Throughput: 0: 896.8. Samples: 994204. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:10:39,326][00111] Avg episode reward: [(0, '22.068')]
[2023-02-22 18:10:44,323][00111] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 3997696. Throughput: 0: 915.4. Samples: 999316. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2023-02-22 18:10:44,333][00111] Avg episode reward: [(0, '22.073')]
[2023-02-22 18:10:45,600][11375] Stopping Batcher_0...
[2023-02-22 18:10:45,601][11375] Loop batcher_evt_loop terminating...
[2023-02-22 18:10:45,603][11375] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2023-02-22 18:10:45,600][00111] Component Batcher_0 stopped!
[2023-02-22 18:10:45,659][11389] Weights refcount: 2 0
[2023-02-22 18:10:45,664][00111] Component RolloutWorker_w7 stopped!
[2023-02-22 18:10:45,670][00111] Component RolloutWorker_w6 stopped!
[2023-02-22 18:10:45,676][11397] Stopping RolloutWorker_w7...
[2023-02-22 18:10:45,677][00111] Component InferenceWorker_p0-w0 stopped!
[2023-02-22 18:10:45,669][11395] Stopping RolloutWorker_w6...
[2023-02-22 18:10:45,683][11389] Stopping InferenceWorker_p0-w0...
[2023-02-22 18:10:45,683][11389] Loop inference_proc0-0_evt_loop terminating...
[2023-02-22 18:10:45,692][11390] Stopping RolloutWorker_w0...
[2023-02-22 18:10:45,692][00111] Component RolloutWorker_w1 stopped!
[2023-02-22 18:10:45,689][11395] Loop rollout_proc6_evt_loop terminating...
[2023-02-22 18:10:45,694][00111] Component RolloutWorker_w0 stopped!
[2023-02-22 18:10:45,700][11393] Stopping RolloutWorker_w4...
[2023-02-22 18:10:45,702][00111] Component RolloutWorker_w4 stopped!
[2023-02-22 18:10:45,693][11390] Loop rollout_proc0_evt_loop terminating...
[2023-02-22 18:10:45,700][11391] Stopping RolloutWorker_w1...
[2023-02-22 18:10:45,708][11397] Loop rollout_proc7_evt_loop terminating...
[2023-02-22 18:10:45,701][11393] Loop rollout_proc4_evt_loop terminating...
[2023-02-22 18:10:45,712][11391] Loop rollout_proc1_evt_loop terminating...
[2023-02-22 18:10:45,721][00111] Component RolloutWorker_w3 stopped!
[2023-02-22 18:10:45,724][11392] Stopping RolloutWorker_w2...
[2023-02-22 18:10:45,725][00111] Component RolloutWorker_w2 stopped!
[2023-02-22 18:10:45,728][11396] Stopping RolloutWorker_w3...
[2023-02-22 18:10:45,729][11396] Loop rollout_proc3_evt_loop terminating...
[2023-02-22 18:10:45,725][11392] Loop rollout_proc2_evt_loop terminating...
[2023-02-22 18:10:45,731][00111] Component RolloutWorker_w5 stopped!
[2023-02-22 18:10:45,734][11394] Stopping RolloutWorker_w5...
[2023-02-22 18:10:45,737][11394] Loop rollout_proc5_evt_loop terminating...
[2023-02-22 18:10:45,771][11375] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000787_3223552.pth
[2023-02-22 18:10:45,783][11375] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2023-02-22 18:10:45,961][00111] Component LearnerWorker_p0 stopped!
[2023-02-22 18:10:45,968][00111] Waiting for process learner_proc0 to stop...
[2023-02-22 18:10:45,973][11375] Stopping LearnerWorker_p0...
[2023-02-22 18:10:45,974][11375] Loop learner_proc0_evt_loop terminating...
[2023-02-22 18:10:47,780][00111] Waiting for process inference_proc0-0 to join...
[2023-02-22 18:10:48,136][00111] Waiting for process rollout_proc0 to join...
[2023-02-22 18:10:48,142][00111] Waiting for process rollout_proc1 to join...
[2023-02-22 18:10:48,513][00111] Waiting for process rollout_proc2 to join...
[2023-02-22 18:10:48,515][00111] Waiting for process rollout_proc3 to join...
[2023-02-22 18:10:48,519][00111] Waiting for process rollout_proc4 to join...
[2023-02-22 18:10:48,522][00111] Waiting for process rollout_proc5 to join...
[2023-02-22 18:10:48,524][00111] Waiting for process rollout_proc6 to join...
[2023-02-22 18:10:48,526][00111] Waiting for process rollout_proc7 to join...
[2023-02-22 18:10:48,533][00111] Batcher 0 profile tree view:
batching: 26.7104, releasing_batches: 0.0237
[2023-02-22 18:10:48,536][00111] InferenceWorker_p0-w0 profile tree view:
wait_policy: 0.0060
  wait_policy_total: 559.8201
update_model: 8.1053
  weight_update: 0.0014
one_step: 0.0022
  handle_policy_step: 540.1349
    deserialize: 14.8347, stack: 3.0253, obs_to_device_normalize: 116.3364, forward: 265.0926, send_messages: 26.1867
    prepare_outputs: 87.2192
      to_cpu: 54.1515
[2023-02-22 18:10:48,538][00111] Learner 0 profile tree view:
misc: 0.0063, prepare_batch: 16.9352
train: 76.2172
  epoch_init: 0.0245, minibatch_init: 0.0216, losses_postprocess: 0.5476, kl_divergence: 0.5181, after_optimizer: 32.7778
  calculate_losses: 27.1497
    losses_init: 0.0072, forward_head: 1.8201, bptt_initial: 17.8341, tail: 1.2145, advantages_returns: 0.3697, losses: 3.3134
    bptt: 2.2057
      bptt_forward_core: 2.1033
  update: 14.6318
    clip: 1.4694
[2023-02-22 18:10:48,543][00111] RolloutWorker_w0 profile tree view:
wait_for_trajectories: 0.3578, enqueue_policy_requests: 154.6390, env_step: 864.5143, overhead: 22.2457, complete_rollouts: 7.6812
save_policy_outputs: 22.0629
  split_output_tensors: 10.5934
[2023-02-22 18:10:48,547][00111] RolloutWorker_w7 profile tree view:
wait_for_trajectories: 0.2936, enqueue_policy_requests: 158.2592, env_step: 860.2373, overhead: 23.0392, complete_rollouts: 7.5876
save_policy_outputs: 20.7489
  split_output_tensors: 9.8976
[2023-02-22 18:10:48,550][00111] Loop Runner_EvtLoop terminating...
[2023-02-22 18:10:48,552][00111] Runner profile tree view:
main_loop: 1174.6657
[2023-02-22 18:10:48,553][00111] Collected {0: 4005888}, FPS: 3410.2
[2023-02-22 18:11:44,327][00111] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
[2023-02-22 18:11:44,329][00111] Overriding arg 'num_workers' with value 1 passed from command line
[2023-02-22 18:11:44,334][00111] Adding new argument 'no_render'=True that is not in the saved config file!
[2023-02-22 18:11:44,336][00111] Adding new argument 'save_video'=True that is not in the saved config file!
[2023-02-22 18:11:44,338][00111] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2023-02-22 18:11:44,340][00111] Adding new argument 'video_name'=None that is not in the saved config file!
[2023-02-22 18:11:44,343][00111] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
[2023-02-22 18:11:44,345][00111] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2023-02-22 18:11:44,347][00111] Adding new argument 'push_to_hub'=False that is not in the saved config file!
[2023-02-22 18:11:44,348][00111] Adding new argument 'hf_repository'=None that is not in the saved config file!
[2023-02-22 18:11:44,352][00111] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2023-02-22 18:11:44,354][00111] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2023-02-22 18:11:44,355][00111] Adding new argument 'train_script'=None that is not in the saved config file!
[2023-02-22 18:11:44,357][00111] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2023-02-22 18:11:44,359][00111] Using frameskip 1 and render_action_repeat=4 for evaluation
[2023-02-22 18:11:44,383][00111] Doom resolution: 160x120, resize resolution: (128, 72)
[2023-02-22 18:11:44,388][00111] RunningMeanStd input shape: (3, 72, 128)
[2023-02-22 18:11:44,390][00111] RunningMeanStd input shape: (1,)
[2023-02-22 18:11:44,406][00111] ConvEncoder: input_channels=3
[2023-02-22 18:11:45,089][00111] Conv encoder output size: 512
[2023-02-22 18:11:45,091][00111] Policy head output size: 512
[2023-02-22 18:11:47,349][00111] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2023-02-22 18:11:48,581][00111] Num frames 100...
[2023-02-22 18:11:48,690][00111] Num frames 200...
[2023-02-22 18:11:48,798][00111] Num frames 300...
[2023-02-22 18:11:48,908][00111] Num frames 400...
[2023-02-22 18:11:49,019][00111] Num frames 500...
[2023-02-22 18:11:49,128][00111] Num frames 600...
[2023-02-22 18:11:49,242][00111] Num frames 700...
[2023-02-22 18:11:49,351][00111] Num frames 800...
[2023-02-22 18:11:49,465][00111] Num frames 900...
[2023-02-22 18:11:49,579][00111] Num frames 1000...
[2023-02-22 18:11:49,718][00111] Avg episode rewards: #0: 21.740, true rewards: #0: 10.740
[2023-02-22 18:11:49,719][00111] Avg episode reward: 21.740, avg true_objective: 10.740
[2023-02-22 18:11:49,756][00111] Num frames 1100...
[2023-02-22 18:11:49,874][00111] Num frames 1200...
[2023-02-22 18:11:49,988][00111] Num frames 1300...
[2023-02-22 18:11:50,104][00111] Num frames 1400...
[2023-02-22 18:11:50,223][00111] Num frames 1500...
[2023-02-22 18:11:50,340][00111] Num frames 1600...
[2023-02-22 18:11:50,449][00111] Num frames 1700...
[2023-02-22 18:11:50,561][00111] Num frames 1800...
[2023-02-22 18:11:50,669][00111] Num frames 1900...
[2023-02-22 18:11:50,777][00111] Num frames 2000...
[2023-02-22 18:11:50,845][00111] Avg episode rewards: #0: 21.535, true rewards: #0: 10.035
[2023-02-22 18:11:50,846][00111] Avg episode reward: 21.535, avg true_objective: 10.035
[2023-02-22 18:11:50,954][00111] Num frames 2100...
[2023-02-22 18:11:51,069][00111] Num frames 2200...
[2023-02-22 18:11:51,192][00111] Num frames 2300...
[2023-02-22 18:11:51,303][00111] Num frames 2400...
[2023-02-22 18:11:51,415][00111] Num frames 2500...
[2023-02-22 18:11:51,531][00111] Num frames 2600...
[2023-02-22 18:11:51,645][00111] Num frames 2700...
[2023-02-22 18:11:51,770][00111] Num frames 2800...
[2023-02-22 18:11:51,880][00111] Num frames 2900...
[2023-02-22 18:11:51,989][00111] Num frames 3000...
[2023-02-22 18:11:52,101][00111] Num frames 3100...
[2023-02-22 18:11:52,214][00111] Num frames 3200...
[2023-02-22 18:11:52,323][00111] Num frames 3300...
[2023-02-22 18:11:52,435][00111] Avg episode rewards: #0: 24.837, true rewards: #0: 11.170
[2023-02-22 18:11:52,437][00111] Avg episode reward: 24.837, avg true_objective: 11.170
[2023-02-22 18:11:52,496][00111] Num frames 3400...
[2023-02-22 18:11:52,603][00111] Num frames 3500...
[2023-02-22 18:11:52,713][00111] Num frames 3600...
[2023-02-22 18:11:52,824][00111] Num frames 3700...
[2023-02-22 18:11:52,907][00111] Avg episode rewards: #0: 19.813, true rewards: #0: 9.312
[2023-02-22 18:11:52,909][00111] Avg episode reward: 19.813, avg true_objective: 9.312
[2023-02-22 18:11:52,997][00111] Num frames 3800...
[2023-02-22 18:11:53,112][00111] Num frames 3900...
[2023-02-22 18:11:53,259][00111] Num frames 4000...
[2023-02-22 18:11:53,412][00111] Num frames 4100...
[2023-02-22 18:11:53,568][00111] Num frames 4200...
[2023-02-22 18:11:53,721][00111] Num frames 4300...
[2023-02-22 18:11:53,873][00111] Num frames 4400...
[2023-02-22 18:11:54,028][00111] Num frames 4500...
[2023-02-22 18:11:54,195][00111] Num frames 4600...
[2023-02-22 18:11:54,361][00111] Num frames 4700...
[2023-02-22 18:11:54,519][00111] Num frames 4800...
[2023-02-22 18:11:54,718][00111] Avg episode rewards: #0: 20.582, true rewards: #0: 9.782
[2023-02-22 18:11:54,723][00111] Avg episode reward: 20.582, avg true_objective: 9.782
[2023-02-22 18:11:54,742][00111] Num frames 4900...
[2023-02-22 18:11:54,901][00111] Num frames 5000...
[2023-02-22 18:11:55,066][00111] Num frames 5100...
[2023-02-22 18:11:55,221][00111] Num frames 5200...
[2023-02-22 18:11:55,410][00111] Avg episode rewards: #0: 18.292, true rewards: #0: 8.792
[2023-02-22 18:11:55,412][00111] Avg episode reward: 18.292, avg true_objective: 8.792
[2023-02-22 18:11:55,453][00111] Num frames 5300...
[2023-02-22 18:11:55,613][00111] Num frames 5400...
[2023-02-22 18:11:55,772][00111] Num frames 5500...
[2023-02-22 18:11:55,929][00111] Num frames 5600...
[2023-02-22 18:11:56,084][00111] Num frames 5700...
[2023-02-22 18:11:56,247][00111] Num frames 5800...
[2023-02-22 18:11:56,412][00111] Num frames 5900...
[2023-02-22 18:11:56,581][00111] Num frames 6000...
[2023-02-22 18:11:56,734][00111] Num frames 6100...
[2023-02-22 18:11:56,847][00111] Num frames 6200...
[2023-02-22 18:11:56,956][00111] Num frames 6300...
[2023-02-22 18:11:57,067][00111] Num frames 6400...
[2023-02-22 18:11:57,185][00111] Num frames 6500...
[2023-02-22 18:11:57,295][00111] Num frames 6600...
[2023-02-22 18:11:57,410][00111] Num frames 6700...
[2023-02-22 18:11:57,515][00111] Avg episode rewards: #0: 20.349, true rewards: #0: 9.634
[2023-02-22 18:11:57,516][00111] Avg episode reward: 20.349, avg true_objective: 9.634
[2023-02-22 18:11:57,583][00111] Num frames 6800...
[2023-02-22 18:11:57,695][00111] Num frames 6900...
[2023-02-22 18:11:57,805][00111] Num frames 7000...
[2023-02-22 18:11:57,917][00111] Num frames 7100...
[2023-02-22 18:11:58,030][00111] Num frames 7200...
[2023-02-22 18:11:58,142][00111] Num frames 7300...
[2023-02-22 18:11:58,219][00111] Avg episode rewards: #0: 18.900, true rewards: #0: 9.150
[2023-02-22 18:11:58,220][00111] Avg episode reward: 18.900, avg true_objective: 9.150
[2023-02-22 18:11:58,323][00111] Num frames 7400...
[2023-02-22 18:11:58,437][00111] Num frames 7500...
[2023-02-22 18:11:58,549][00111] Num frames 7600...
[2023-02-22 18:11:58,658][00111] Num frames 7700...
[2023-02-22 18:11:58,768][00111] Num frames 7800...
[2023-02-22 18:11:58,878][00111] Num frames 7900...
[2023-02-22 18:11:58,991][00111] Num frames 8000...
[2023-02-22 18:11:59,103][00111] Num frames 8100...
[2023-02-22 18:11:59,218][00111] Num frames 8200...
[2023-02-22 18:11:59,330][00111] Num frames 8300...
[2023-02-22 18:11:59,448][00111] Num frames 8400...
[2023-02-22 18:11:59,561][00111] Num frames 8500...
[2023-02-22 18:11:59,687][00111] Num frames 8600...
[2023-02-22 18:11:59,748][00111] Avg episode rewards: #0: 20.782, true rewards: #0: 9.560
[2023-02-22 18:11:59,750][00111] Avg episode reward: 20.782, avg true_objective: 9.560
[2023-02-22 18:11:59,861][00111] Num frames 8700...
[2023-02-22 18:11:59,971][00111] Num frames 8800...
[2023-02-22 18:12:00,082][00111] Num frames 8900...
[2023-02-22 18:12:00,196][00111] Num frames 9000...
[2023-02-22 18:12:00,305][00111] Num frames 9100...
[2023-02-22 18:12:00,422][00111] Num frames 9200...
[2023-02-22 18:12:00,535][00111] Num frames 9300...
[2023-02-22 18:12:00,646][00111] Num frames 9400...
[2023-02-22 18:12:00,756][00111] Num frames 9500...
[2023-02-22 18:12:00,865][00111] Num frames 9600...
[2023-02-22 18:12:00,973][00111] Num frames 9700...
[2023-02-22 18:12:01,088][00111] Num frames 9800...
[2023-02-22 18:12:01,199][00111] Num frames 9900...
[2023-02-22 18:12:01,310][00111] Num frames 10000...
[2023-02-22 18:12:01,426][00111] Num frames 10100...
[2023-02-22 18:12:01,543][00111] Num frames 10200...
[2023-02-22 18:12:01,659][00111] Num frames 10300...
[2023-02-22 18:12:01,769][00111] Num frames 10400...
[2023-02-22 18:12:01,878][00111] Num frames 10500...
[2023-02-22 18:12:01,990][00111] Num frames 10600...
[2023-02-22 18:12:02,110][00111] Num frames 10700...
[2023-02-22 18:12:02,172][00111] Avg episode rewards: #0: 24.404, true rewards: #0: 10.704
[2023-02-22 18:12:02,175][00111] Avg episode reward: 24.404, avg true_objective: 10.704
[2023-02-22 18:13:10,398][00111] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
[2023-02-22 18:19:58,955][00111] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
[2023-02-22 18:19:58,959][00111] Overriding arg 'num_workers' with value 1 passed from command line
[2023-02-22 18:19:58,962][00111] Adding new argument 'no_render'=True that is not in the saved config file!
[2023-02-22 18:19:58,965][00111] Adding new argument 'save_video'=True that is not in the saved config file!
[2023-02-22 18:19:58,968][00111] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2023-02-22 18:19:58,970][00111] Adding new argument 'video_name'=None that is not in the saved config file!
[2023-02-22 18:19:58,972][00111] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
[2023-02-22 18:19:58,974][00111] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2023-02-22 18:19:58,976][00111] Adding new argument 'push_to_hub'=True that is not in the saved config file!
[2023-02-22 18:19:58,977][00111] Adding new argument 'hf_repository'='zlicastro/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
[2023-02-22 18:19:58,980][00111] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2023-02-22 18:19:58,981][00111] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2023-02-22 18:19:58,982][00111] Adding new argument 'train_script'=None that is not in the saved config file!
[2023-02-22 18:19:58,984][00111] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2023-02-22 18:19:58,985][00111] Using frameskip 1 and render_action_repeat=4 for evaluation
[2023-02-22 18:19:59,020][00111] RunningMeanStd input shape: (3, 72, 128)
[2023-02-22 18:19:59,024][00111] RunningMeanStd input shape: (1,)
[2023-02-22 18:19:59,042][00111] ConvEncoder: input_channels=3
[2023-02-22 18:19:59,103][00111] Conv encoder output size: 512
[2023-02-22 18:19:59,105][00111] Policy head output size: 512
[2023-02-22 18:19:59,134][00111] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2023-02-22 18:19:59,763][00111] Num frames 100...
[2023-02-22 18:19:59,908][00111] Num frames 200...
[2023-02-22 18:20:00,029][00111] Num frames 300...
[2023-02-22 18:20:00,147][00111] Num frames 400...
[2023-02-22 18:20:00,259][00111] Num frames 500...
[2023-02-22 18:20:00,372][00111] Num frames 600...
[2023-02-22 18:20:00,486][00111] Num frames 700...
[2023-02-22 18:20:00,597][00111] Num frames 800...
[2023-02-22 18:20:00,752][00111] Avg episode rewards: #0: 21.910, true rewards: #0: 8.910
[2023-02-22 18:20:00,754][00111] Avg episode reward: 21.910, avg true_objective: 8.910
[2023-02-22 18:20:00,769][00111] Num frames 900...
[2023-02-22 18:20:00,884][00111] Num frames 1000...
[2023-02-22 18:20:01,003][00111] Num frames 1100...
[2023-02-22 18:20:01,114][00111] Num frames 1200...
[2023-02-22 18:20:01,229][00111] Num frames 1300...
[2023-02-22 18:20:01,339][00111] Num frames 1400...
[2023-02-22 18:20:01,462][00111] Num frames 1500...
[2023-02-22 18:20:01,572][00111] Num frames 1600...
[2023-02-22 18:20:01,686][00111] Num frames 1700...
[2023-02-22 18:20:01,797][00111] Num frames 1800...
[2023-02-22 18:20:01,943][00111] Avg episode rewards: #0: 20.915, true rewards: #0: 9.415
[2023-02-22 18:20:01,945][00111] Avg episode reward: 20.915, avg true_objective: 9.415
[2023-02-22 18:20:01,974][00111] Num frames 1900...
[2023-02-22 18:20:02,098][00111] Num frames 2000...
[2023-02-22 18:20:02,209][00111] Num frames 2100...
[2023-02-22 18:20:02,320][00111] Num frames 2200...
[2023-02-22 18:20:02,432][00111] Num frames 2300...
[2023-02-22 18:20:02,546][00111] Num frames 2400...
[2023-02-22 18:20:02,656][00111] Num frames 2500...
[2023-02-22 18:20:02,782][00111] Num frames 2600...
[2023-02-22 18:20:02,897][00111] Num frames 2700...
[2023-02-22 18:20:03,014][00111] Num frames 2800...
[2023-02-22 18:20:03,129][00111] Num frames 2900...
[2023-02-22 18:20:03,242][00111] Num frames 3000...
[2023-02-22 18:20:03,353][00111] Num frames 3100...
[2023-02-22 18:20:03,475][00111] Num frames 3200...
[2023-02-22 18:20:03,593][00111] Num frames 3300...
[2023-02-22 18:20:03,706][00111] Num frames 3400...
[2023-02-22 18:20:03,819][00111] Num frames 3500...
[2023-02-22 18:20:03,935][00111] Num frames 3600...
[2023-02-22 18:20:04,065][00111] Num frames 3700...
[2023-02-22 18:20:04,180][00111] Num frames 3800...
[2023-02-22 18:20:04,293][00111] Num frames 3900...
[2023-02-22 18:20:04,446][00111] Avg episode rewards: #0: 31.943, true rewards: #0: 13.277
[2023-02-22 18:20:04,447][00111] Avg episode reward: 31.943, avg true_objective: 13.277
[2023-02-22 18:20:04,472][00111] Num frames 4000...
[2023-02-22 18:20:04,589][00111] Num frames 4100...
[2023-02-22 18:20:04,709][00111] Num frames 4200...
[2023-02-22 18:20:04,833][00111] Num frames 4300...
[2023-02-22 18:20:04,945][00111] Num frames 4400...
[2023-02-22 18:20:05,063][00111] Num frames 4500...
[2023-02-22 18:20:05,176][00111] Num frames 4600...
[2023-02-22 18:20:05,289][00111] Num frames 4700...
[2023-02-22 18:20:05,399][00111] Avg episode rewards: #0: 28.620, true rewards: #0: 11.870
[2023-02-22 18:20:05,400][00111] Avg episode reward: 28.620, avg true_objective: 11.870
[2023-02-22 18:20:05,466][00111] Num frames 4800...
[2023-02-22 18:20:05,589][00111] Num frames 4900...
[2023-02-22 18:20:05,710][00111] Num frames 5000...
[2023-02-22 18:20:05,837][00111] Num frames 5100...
[2023-02-22 18:20:05,891][00111] Avg episode rewards: #0: 24.400, true rewards: #0: 10.200
[2023-02-22 18:20:05,894][00111] Avg episode reward: 24.400, avg true_objective: 10.200
[2023-02-22 18:20:06,017][00111] Num frames 5200...
[2023-02-22 18:20:06,136][00111] Num frames 5300...
[2023-02-22 18:20:06,252][00111] Num frames 5400...
[2023-02-22 18:20:06,365][00111] Num frames 5500...
[2023-02-22 18:20:06,477][00111] Num frames 5600...
[2023-02-22 18:20:06,585][00111] Num frames 5700...
[2023-02-22 18:20:06,696][00111] Num frames 5800...
[2023-02-22 18:20:06,816][00111] Num frames 5900...
[2023-02-22 18:20:06,926][00111] Num frames 6000...
[2023-02-22 18:20:07,037][00111] Num frames 6100...
[2023-02-22 18:20:07,154][00111] Num frames 6200...
[2023-02-22 18:20:07,270][00111] Num frames 6300...
[2023-02-22 18:20:07,382][00111] Num frames 6400...
[2023-02-22 18:20:07,511][00111] Num frames 6500...
[2023-02-22 18:20:07,585][00111] Avg episode rewards: #0: 25.860, true rewards: #0: 10.860
[2023-02-22 18:20:07,587][00111] Avg episode reward: 25.860, avg true_objective: 10.860
[2023-02-22 18:20:07,684][00111] Num frames 6600...
[2023-02-22 18:20:07,795][00111] Num frames 6700...
[2023-02-22 18:20:07,907][00111] Num frames 6800...
[2023-02-22 18:20:08,019][00111] Num frames 6900...
[2023-02-22 18:20:08,140][00111] Num frames 7000...
[2023-02-22 18:20:08,253][00111] Num frames 7100...
[2023-02-22 18:20:08,377][00111] Num frames 7200...
[2023-02-22 18:20:08,490][00111] Num frames 7300...
[2023-02-22 18:20:08,601][00111] Num frames 7400...
[2023-02-22 18:20:08,714][00111] Num frames 7500...
[2023-02-22 18:20:08,830][00111] Num frames 7600...
[2023-02-22 18:20:08,941][00111] Num frames 7700...
[2023-02-22 18:20:09,075][00111] Num frames 7800...
[2023-02-22 18:20:09,207][00111] Num frames 7900...
[2023-02-22 18:20:09,326][00111] Num frames 8000...
[2023-02-22 18:20:09,437][00111] Num frames 8100...
[2023-02-22 18:20:09,556][00111] Num frames 8200...
[2023-02-22 18:20:09,679][00111] Avg episode rewards: #0: 28.517, true rewards: #0: 11.803
[2023-02-22 18:20:09,681][00111] Avg episode reward: 28.517, avg true_objective: 11.803
[2023-02-22 18:20:09,730][00111] Num frames 8300...
[2023-02-22 18:20:09,847][00111] Num frames 8400...
[2023-02-22 18:20:09,998][00111] Num frames 8500...
[2023-02-22 18:20:10,166][00111] Num frames 8600...
[2023-02-22 18:20:10,332][00111] Num frames 8700...
[2023-02-22 18:20:10,493][00111] Num frames 8800...
[2023-02-22 18:20:10,647][00111] Num frames 8900...
[2023-02-22 18:20:10,805][00111] Num frames 9000...
[2023-02-22 18:20:10,962][00111] Num frames 9100...
[2023-02-22 18:20:11,130][00111] Num frames 9200...
[2023-02-22 18:20:11,311][00111] Num frames 9300...
[2023-02-22 18:20:11,475][00111] Num frames 9400...
[2023-02-22 18:20:11,629][00111] Num frames 9500...
[2023-02-22 18:20:11,794][00111] Num frames 9600...
[2023-02-22 18:20:11,956][00111] Num frames 9700...
[2023-02-22 18:20:12,117][00111] Num frames 9800...
[2023-02-22 18:20:12,283][00111] Num frames 9900...
[2023-02-22 18:20:12,448][00111] Num frames 10000...
[2023-02-22 18:20:12,612][00111] Num frames 10100...
[2023-02-22 18:20:12,774][00111] Num frames 10200...
[2023-02-22 18:20:12,934][00111] Num frames 10300...
[2023-02-22 18:20:13,090][00111] Avg episode rewards: #0: 31.827, true rewards: #0: 12.953
[2023-02-22 18:20:13,092][00111] Avg episode reward: 31.827, avg true_objective: 12.953
[2023-02-22 18:20:13,160][00111] Num frames 10400...
[2023-02-22 18:20:13,324][00111] Num frames 10500...
[2023-02-22 18:20:13,487][00111] Num frames 10600...
[2023-02-22 18:20:13,620][00111] Num frames 10700...
[2023-02-22 18:20:13,731][00111] Num frames 10800...
[2023-02-22 18:20:13,843][00111] Num frames 10900...
[2023-02-22 18:20:13,952][00111] Num frames 11000...
[2023-02-22 18:20:14,063][00111] Num frames 11100...
[2023-02-22 18:20:14,177][00111] Num frames 11200...
[2023-02-22 18:20:14,293][00111] Num frames 11300...
[2023-02-22 18:20:14,375][00111] Avg episode rewards: #0: 30.469, true rewards: #0: 12.580
[2023-02-22 18:20:14,379][00111] Avg episode reward: 30.469, avg true_objective: 12.580
[2023-02-22 18:20:14,473][00111] Num frames 11400...
[2023-02-22 18:20:14,587][00111] Num frames 11500...
[2023-02-22 18:20:14,699][00111] Num frames 11600...
[2023-02-22 18:20:14,809][00111] Num frames 11700...
[2023-02-22 18:20:14,923][00111] Num frames 11800...
[2023-02-22 18:20:15,037][00111] Num frames 11900...
[2023-02-22 18:20:15,150][00111] Num frames 12000...
[2023-02-22 18:20:15,277][00111] Num frames 12100...
[2023-02-22 18:20:15,388][00111] Num frames 12200...
[2023-02-22 18:20:15,464][00111] Avg episode rewards: #0: 29.318, true rewards: #0: 12.218
[2023-02-22 18:20:15,466][00111] Avg episode reward: 29.318, avg true_objective: 12.218
[2023-02-22 18:21:33,495][00111] Replay video saved to /content/train_dir/default_experiment/replay.mp4!