Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1722513751.ea6709614f88

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1124f386aae3b52711033cca0081f5cb66442ca78626d91d9ed1449dd41d7cdd
+size 452605

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 5.60 +/- 1.38
+      value: 10.15 +/- 4.96
       name: mean_reward
       verified: false
 ---

checkpoint_p0/best_000000929_3805184_reward_22.984.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b820a60b5456f582f58ef205862d4fd2c97ac5d4f48a944bf720c60efabe3b7b
+size 34929243

checkpoint_p0/checkpoint_000000898_3678208.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e700719fa2e017844c2ab4daf38f797b684f5696fd09a753e34d93ad34e2a496
+size 34929669

checkpoint_p0/checkpoint_000000978_4005888.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7dc8fbf1c5b36b65e0825213a61508ff926f04e640ba12ac83a6928e996336b
+size 34929669

config.json

@@ -65,7 +65,7 @@
   "summaries_use_frameskip": true,
   "heartbeat_interval": 20,
   "heartbeat_reporting_interval": 600,
-  "train_for_env_steps": 2000000,
+  "train_for_env_steps": 4000000,
   "train_for_seconds": 10000000000,
   "save_every_sec": 120,
   "keep_checkpoints": 2,

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba09fdf676b9674ae9ae7089c2e9338c70ce5bf920a002ccbde8e36b573274ab
-size 9864889
+oid sha256:04d0aa7afcc208b9ff12043189c8ab1221af36bba574c4c184b07e07c3677cd4
+size 18994842

sf_log.txt

@@ -1899,3 +1899,970 @@ main_loop: 74.4915
 [2024-08-01 12:01:10,320][00719] Avg episode rewards: #0: 8.600, true rewards: #0: 5.600
 [2024-08-01 12:01:10,322][00719] Avg episode reward: 8.600, avg true_objective: 5.600
 [2024-08-01 12:01:40,769][00719] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2024-08-01 12:01:49,880][00719] The model has been pushed to https://huggingface.co/ThNaToS/rl_course_vizdoom_health_gathering_supreme
+[2024-08-01 12:02:31,800][00719] Environment doom_basic already registered, overwriting...
+[2024-08-01 12:02:31,801][00719] Environment doom_two_colors_easy already registered, overwriting...
+[2024-08-01 12:02:31,804][00719] Environment doom_two_colors_hard already registered, overwriting...
+[2024-08-01 12:02:31,805][00719] Environment doom_dm already registered, overwriting...
+[2024-08-01 12:02:31,807][00719] Environment doom_dwango5 already registered, overwriting...
+[2024-08-01 12:02:31,809][00719] Environment doom_my_way_home_flat_actions already registered, overwriting...
+[2024-08-01 12:02:31,810][00719] Environment doom_defend_the_center_flat_actions already registered, overwriting...
+[2024-08-01 12:02:31,812][00719] Environment doom_my_way_home already registered, overwriting...
+[2024-08-01 12:02:31,813][00719] Environment doom_deadly_corridor already registered, overwriting...
+[2024-08-01 12:02:31,814][00719] Environment doom_defend_the_center already registered, overwriting...
+[2024-08-01 12:02:31,816][00719] Environment doom_defend_the_line already registered, overwriting...
+[2024-08-01 12:02:31,818][00719] Environment doom_health_gathering already registered, overwriting...
+[2024-08-01 12:02:31,819][00719] Environment doom_health_gathering_supreme already registered, overwriting...
+[2024-08-01 12:02:31,820][00719] Environment doom_battle already registered, overwriting...
+[2024-08-01 12:02:31,822][00719] Environment doom_battle2 already registered, overwriting...
+[2024-08-01 12:02:31,823][00719] Environment doom_duel_bots already registered, overwriting...
+[2024-08-01 12:02:31,824][00719] Environment doom_deathmatch_bots already registered, overwriting...
+[2024-08-01 12:02:31,825][00719] Environment doom_duel already registered, overwriting...
+[2024-08-01 12:02:31,827][00719] Environment doom_deathmatch_full already registered, overwriting...
+[2024-08-01 12:02:31,828][00719] Environment doom_benchmark already registered, overwriting...
+[2024-08-01 12:02:31,829][00719] register_encoder_factory: <function make_vizdoom_encoder at 0x7e9b3fe57370>
+[2024-08-01 12:02:31,853][00719] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-08-01 12:02:31,854][00719] Overriding arg 'train_for_env_steps' with value 4000000 passed from command line
+[2024-08-01 12:02:31,861][00719] Experiment dir /content/train_dir/default_experiment already exists!
+[2024-08-01 12:02:31,862][00719] Resuming existing experiment from /content/train_dir/default_experiment...
+[2024-08-01 12:02:31,866][00719] Weights and Biases integration disabled
+[2024-08-01 12:02:31,869][00719] Environment var CUDA_VISIBLE_DEVICES is 0
+
+[2024-08-01 12:02:33,787][00719] Starting experiment with the following configuration:
+help=False
+algo=APPO
+env=doom_health_gathering_supreme
+experiment=default_experiment
+train_dir=/content/train_dir
+restart_behavior=resume
+device=gpu
+seed=None
+num_policies=1
+async_rl=True
+serial_mode=False
+batched_sampling=False
+num_batches_to_accumulate=2
+worker_num_splits=2
+policy_workers_per_policy=1
+max_policy_lag=1000
+num_workers=8
+num_envs_per_worker=4
+batch_size=1024
+num_batches_per_epoch=1
+num_epochs=1
+rollout=32
+recurrence=32
+shuffle_minibatches=False
+gamma=0.99
+reward_scale=1.0
+reward_clip=1000.0
+value_bootstrap=False
+normalize_returns=True
+exploration_loss_coeff=0.001
+value_loss_coeff=0.5
+kl_loss_coeff=0.0
+exploration_loss=symmetric_kl
+gae_lambda=0.95
+ppo_clip_ratio=0.1
+ppo_clip_value=0.2
+with_vtrace=False
+vtrace_rho=1.0
+vtrace_c=1.0
+optimizer=adam
+adam_eps=1e-06
+adam_beta1=0.9
+adam_beta2=0.999
+max_grad_norm=4.0
+learning_rate=0.0001
+lr_schedule=constant
+lr_schedule_kl_threshold=0.008
+lr_adaptive_min=1e-06
+lr_adaptive_max=0.01
+obs_subtract_mean=0.0
+obs_scale=255.0
+normalize_input=True
+normalize_input_keys=None
+decorrelate_experience_max_seconds=0
+decorrelate_envs_on_one_worker=True
+actor_worker_gpus=[]
+set_workers_cpu_affinity=True
+force_envs_single_thread=False
+default_niceness=0
+log_to_file=True
+experiment_summaries_interval=10
+flush_summaries_interval=30
+stats_avg=100
+summaries_use_frameskip=True
+heartbeat_interval=20
+heartbeat_reporting_interval=600
+train_for_env_steps=4000000
+train_for_seconds=10000000000
+save_every_sec=120
+keep_checkpoints=2
+load_checkpoint_kind=latest
+save_milestones_sec=-1
+save_best_every_sec=5
+save_best_metric=reward
+save_best_after=100000
+benchmark=False
+encoder_mlp_layers=[512, 512]
+encoder_conv_architecture=convnet_simple
+encoder_conv_mlp_layers=[512]
+use_rnn=True
+rnn_size=512
+rnn_type=gru
+rnn_num_layers=1
+decoder_mlp_layers=[]
+nonlinearity=elu
+policy_initialization=orthogonal
+policy_init_gain=1.0
+actor_critic_share_weights=True
+adaptive_stddev=True
+continuous_tanh_scale=0.0
+initial_stddev=1.0
+use_env_info_cache=False
+env_gpu_actions=False
+env_gpu_observations=True
+env_frameskip=4
+env_framestack=1
+pixel_format=CHW
+use_record_episode_statistics=False
+with_wandb=False
+wandb_user=None
+wandb_project=sample_factory
+wandb_group=None
+wandb_job_type=SF
+wandb_tags=[]
+with_pbt=False
+pbt_mix_policies_in_one_env=True
+pbt_period_env_steps=5000000
+pbt_start_mutation=20000000
+pbt_replace_fraction=0.3
+pbt_mutation_rate=0.15
+pbt_replace_reward_gap=0.1
+pbt_replace_reward_gap_absolute=1e-06
+pbt_optimize_gamma=False
+pbt_target_objective=true_objective
+pbt_perturb_min=1.1
+pbt_perturb_max=1.5
+num_agents=-1
+num_humans=0
+num_bots=-1
+start_bot_difficulty=None
+timelimit=None
+res_w=128
+res_h=72
+wide_aspect_ratio=False
+eval_env_frameskip=1
+fps=35
+command_line=--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=4000000
+cli_args={'env': 'doom_health_gathering_supreme', 'num_workers': 8, 'num_envs_per_worker': 4, 'train_for_env_steps': 4000000}
+git_hash=unknown
+git_repo_name=not a git repository
+[2024-08-01 12:02:33,792][00719] Saving configuration to /content/train_dir/default_experiment/config.json...
+[2024-08-01 12:02:33,795][00719] Rollout worker 0 uses device cpu
+[2024-08-01 12:02:33,796][00719] Rollout worker 1 uses device cpu
+[2024-08-01 12:02:33,797][00719] Rollout worker 2 uses device cpu
+[2024-08-01 12:02:33,798][00719] Rollout worker 3 uses device cpu
+[2024-08-01 12:02:33,800][00719] Rollout worker 4 uses device cpu
+[2024-08-01 12:02:33,801][00719] Rollout worker 5 uses device cpu
+[2024-08-01 12:02:33,802][00719] Rollout worker 6 uses device cpu
+[2024-08-01 12:02:33,804][00719] Rollout worker 7 uses device cpu
+[2024-08-01 12:02:33,890][00719] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-08-01 12:02:33,893][00719] InferenceWorker_p0-w0: min num requests: 2
+[2024-08-01 12:02:33,925][00719] Starting all processes...
+[2024-08-01 12:02:33,926][00719] Starting process learner_proc0
+[2024-08-01 12:02:33,975][00719] Starting all processes...
+[2024-08-01 12:02:33,986][00719] Starting process inference_proc0-0
+[2024-08-01 12:02:33,986][00719] Starting process rollout_proc0
+[2024-08-01 12:02:33,988][00719] Starting process rollout_proc1
+[2024-08-01 12:02:33,988][00719] Starting process rollout_proc2
+[2024-08-01 12:02:33,988][00719] Starting process rollout_proc3
+[2024-08-01 12:02:33,988][00719] Starting process rollout_proc4
+[2024-08-01 12:02:33,988][00719] Starting process rollout_proc5
+[2024-08-01 12:02:33,988][00719] Starting process rollout_proc6
+[2024-08-01 12:02:33,988][00719] Starting process rollout_proc7
+[2024-08-01 12:02:47,832][11824] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-08-01 12:02:47,832][11824] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2024-08-01 12:02:47,904][11824] Num visible devices: 1
+[2024-08-01 12:02:47,942][11824] Starting seed is not provided
+[2024-08-01 12:02:47,943][11824] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-08-01 12:02:47,943][11824] Initializing actor-critic model on device cuda:0
+[2024-08-01 12:02:47,943][11824] RunningMeanStd input shape: (3, 72, 128)
+[2024-08-01 12:02:47,944][11824] RunningMeanStd input shape: (1,)
+[2024-08-01 12:02:48,044][11824] ConvEncoder: input_channels=3
+[2024-08-01 12:02:48,365][11841] Worker 3 uses CPU cores [1]
+[2024-08-01 12:02:48,394][11840] Worker 2 uses CPU cores [0]
+[2024-08-01 12:02:48,498][11838] Worker 0 uses CPU cores [0]
+[2024-08-01 12:02:48,503][11842] Worker 4 uses CPU cores [0]
+[2024-08-01 12:02:48,593][11843] Worker 5 uses CPU cores [1]
+[2024-08-01 12:02:48,638][11839] Worker 1 uses CPU cores [1]
+[2024-08-01 12:02:48,661][11837] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-08-01 12:02:48,661][11837] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2024-08-01 12:02:48,680][11837] Num visible devices: 1
+[2024-08-01 12:02:48,688][11848] Worker 7 uses CPU cores [1]
+[2024-08-01 12:02:48,718][11849] Worker 6 uses CPU cores [0]
+[2024-08-01 12:02:48,731][11824] Conv encoder output size: 512
+[2024-08-01 12:02:48,732][11824] Policy head output size: 512
+[2024-08-01 12:02:48,747][11824] Created Actor Critic model with architecture:
+[2024-08-01 12:02:48,747][11824] ActorCriticSharedWeights(
+  (obs_normalizer): ObservationNormalizer(
+    (running_mean_std): RunningMeanStdDictInPlace(
+      (running_mean_std): ModuleDict(
+        (obs): RunningMeanStdInPlace()
+      )
+    )
+  )
+  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
+  (encoder): VizdoomEncoder(
+    (basic_encoder): ConvEncoder(
+      (enc): RecursiveScriptModule(
+        original_name=ConvEncoderImpl
+        (conv_head): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Conv2d)
+          (1): RecursiveScriptModule(original_name=ELU)
+          (2): RecursiveScriptModule(original_name=Conv2d)
+          (3): RecursiveScriptModule(original_name=ELU)
+          (4): RecursiveScriptModule(original_name=Conv2d)
+          (5): RecursiveScriptModule(original_name=ELU)
+        )
+        (mlp_layers): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Linear)
+          (1): RecursiveScriptModule(original_name=ELU)
+        )
+      )
+    )
+  )
+  (core): ModelCoreRNN(
+    (core): GRU(512, 512)
+  )
+  (decoder): MlpDecoder(
+    (mlp): Identity()
+  )
+  (critic_linear): Linear(in_features=512, out_features=1, bias=True)
+  (action_parameterization): ActionParameterizationDefault(
+    (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
+  )
+)
+[2024-08-01 12:02:49,006][11824] Using optimizer <class 'torch.optim.adam.Adam'>
+[2024-08-01 12:02:50,171][11824] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000490_2007040.pth...
+[2024-08-01 12:02:50,215][11824] Loading model from checkpoint
+[2024-08-01 12:02:50,218][11824] Loaded experiment state at self.train_step=490, self.env_steps=2007040
+[2024-08-01 12:02:50,219][11824] Initialized policy 0 weights for model version 490
+[2024-08-01 12:02:50,226][11824] LearnerWorker_p0 finished initialization!
+[2024-08-01 12:02:50,226][11824] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-08-01 12:02:50,460][11837] RunningMeanStd input shape: (3, 72, 128)
+[2024-08-01 12:02:50,461][11837] RunningMeanStd input shape: (1,)
+[2024-08-01 12:02:50,480][11837] ConvEncoder: input_channels=3
+[2024-08-01 12:02:50,638][11837] Conv encoder output size: 512
+[2024-08-01 12:02:50,639][11837] Policy head output size: 512
+[2024-08-01 12:02:50,722][00719] Inference worker 0-0 is ready!
+[2024-08-01 12:02:50,724][00719] All inference workers are ready! Signal rollout workers to start!
+[2024-08-01 12:02:50,958][11838] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-08-01 12:02:50,957][11849] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-08-01 12:02:50,960][11840] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-08-01 12:02:50,963][11842] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-08-01 12:02:51,044][11848] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-08-01 12:02:51,051][11843] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-08-01 12:02:51,049][11839] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-08-01 12:02:51,053][11841] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-08-01 12:02:51,874][00719] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 2007040. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-08-01 12:02:52,246][11840] Decorrelating experience for 0 frames...
+[2024-08-01 12:02:52,251][11849] Decorrelating experience for 0 frames...
+[2024-08-01 12:02:53,291][11839] Decorrelating experience for 0 frames...
+[2024-08-01 12:02:53,284][11843] Decorrelating experience for 0 frames...
+[2024-08-01 12:02:53,294][11840] Decorrelating experience for 32 frames...
+[2024-08-01 12:02:53,303][11848] Decorrelating experience for 0 frames...
+[2024-08-01 12:02:53,442][11838] Decorrelating experience for 0 frames...
+[2024-08-01 12:02:53,882][00719] Heartbeat connected on Batcher_0
+[2024-08-01 12:02:53,886][00719] Heartbeat connected on LearnerWorker_p0
+[2024-08-01 12:02:53,926][00719] Heartbeat connected on InferenceWorker_p0-w0
+[2024-08-01 12:02:54,058][11841] Decorrelating experience for 0 frames...
+[2024-08-01 12:02:54,314][11849] Decorrelating experience for 32 frames...
+[2024-08-01 12:02:54,582][11839] Decorrelating experience for 32 frames...
+[2024-08-01 12:02:54,586][11843] Decorrelating experience for 32 frames...
+[2024-08-01 12:02:54,840][11842] Decorrelating experience for 0 frames...
+[2024-08-01 12:02:55,330][11841] Decorrelating experience for 32 frames...
+[2024-08-01 12:02:55,466][11849] Decorrelating experience for 64 frames...
+[2024-08-01 12:02:55,852][11842] Decorrelating experience for 32 frames...
+[2024-08-01 12:02:55,867][11840] Decorrelating experience for 64 frames...
+[2024-08-01 12:02:55,892][11848] Decorrelating experience for 32 frames...
+[2024-08-01 12:02:56,213][11843] Decorrelating experience for 64 frames...
+[2024-08-01 12:02:56,562][11839] Decorrelating experience for 64 frames...
+[2024-08-01 12:02:56,870][00719] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 2007040. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-08-01 12:02:57,043][11848] Decorrelating experience for 64 frames...
+[2024-08-01 12:02:57,334][11838] Decorrelating experience for 32 frames...
+[2024-08-01 12:02:57,377][11840] Decorrelating experience for 96 frames...
+[2024-08-01 12:02:57,437][11839] Decorrelating experience for 96 frames...
+[2024-08-01 12:02:57,558][00719] Heartbeat connected on RolloutWorker_w1
+[2024-08-01 12:02:57,614][00719] Heartbeat connected on RolloutWorker_w2
+[2024-08-01 12:02:57,698][11842] Decorrelating experience for 64 frames...
+[2024-08-01 12:02:57,795][11849] Decorrelating experience for 96 frames...
+[2024-08-01 12:02:58,142][00719] Heartbeat connected on RolloutWorker_w6
+[2024-08-01 12:02:58,271][11848] Decorrelating experience for 96 frames...
+[2024-08-01 12:02:58,497][00719] Heartbeat connected on RolloutWorker_w7
+[2024-08-01 12:02:59,263][11838] Decorrelating experience for 64 frames...
+[2024-08-01 12:02:59,391][11842] Decorrelating experience for 96 frames...
+[2024-08-01 12:02:59,682][11843] Decorrelating experience for 96 frames...
+[2024-08-01 12:02:59,867][11841] Decorrelating experience for 64 frames...
+[2024-08-01 12:02:59,948][00719] Heartbeat connected on RolloutWorker_w4
+[2024-08-01 12:02:59,977][00719] Heartbeat connected on RolloutWorker_w5
+[2024-08-01 12:03:01,870][00719] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 2007040. Throughput: 0: 75.8. Samples: 758. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-08-01 12:03:01,872][00719] Avg episode reward: [(0, '3.108')]
+[2024-08-01 12:03:02,138][11838] Decorrelating experience for 96 frames...
+[2024-08-01 12:03:02,644][00719] Heartbeat connected on RolloutWorker_w0
+[2024-08-01 12:03:03,412][11824] Signal inference workers to stop experience collection...
+[2024-08-01 12:03:03,495][11837] InferenceWorker_p0-w0: stopping experience collection
+[2024-08-01 12:03:03,687][11841] Decorrelating experience for 96 frames...
+[2024-08-01 12:03:03,771][00719] Heartbeat connected on RolloutWorker_w3
+[2024-08-01 12:03:04,793][11824] Signal inference workers to resume experience collection...
+[2024-08-01 12:03:04,794][11837] InferenceWorker_p0-w0: resuming experience collection
+[2024-08-01 12:03:06,870][00719] Fps is (10 sec: 1228.8, 60 sec: 819.4, 300 sec: 819.4). Total num frames: 2019328. Throughput: 0: 212.3. Samples: 3184. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+[2024-08-01 12:03:06,879][00719] Avg episode reward: [(0, '4.088')]
+[2024-08-01 12:03:11,870][00719] Fps is (10 sec: 2867.2, 60 sec: 1433.9, 300 sec: 1433.9). Total num frames: 2035712. Throughput: 0: 393.5. Samples: 7868. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0)
+[2024-08-01 12:03:11,877][00719] Avg episode reward: [(0, '5.510')]
+[2024-08-01 12:03:14,116][11837] Updated weights for policy 0, policy_version 500 (0.0021)
+[2024-08-01 12:03:16,870][00719] Fps is (10 sec: 4096.0, 60 sec: 2130.2, 300 sec: 2130.2). Total num frames: 2060288. Throughput: 0: 453.9. Samples: 11346. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0)
+[2024-08-01 12:03:16,877][00719] Avg episode reward: [(0, '6.805')]
+[2024-08-01 12:03:21,870][00719] Fps is (10 sec: 4505.6, 60 sec: 2457.9, 300 sec: 2457.9). Total num frames: 2080768. Throughput: 0: 601.1. Samples: 18032. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2024-08-01 12:03:21,876][00719] Avg episode reward: [(0, '7.640')]
+[2024-08-01 12:03:25,257][11837] Updated weights for policy 0, policy_version 510 (0.0027)
+[2024-08-01 12:03:26,870][00719] Fps is (10 sec: 3276.8, 60 sec: 2457.9, 300 sec: 2457.9). Total num frames: 2093056. Throughput: 0: 624.9. Samples: 21868. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2024-08-01 12:03:26,878][00719] Avg episode reward: [(0, '7.773')]
+[2024-08-01 12:03:26,881][11824] Saving new best policy, reward=7.773!
+[2024-08-01 12:03:31,870][00719] Fps is (10 sec: 3276.8, 60 sec: 2662.7, 300 sec: 2662.7). Total num frames: 2113536. Throughput: 0: 613.2. Samples: 24526. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2024-08-01 12:03:31,877][00719] Avg episode reward: [(0, '7.471')]
+[2024-08-01 12:03:35,383][11837] Updated weights for policy 0, policy_version 520 (0.0023)
+[2024-08-01 12:03:36,870][00719] Fps is (10 sec: 4096.0, 60 sec: 2821.9, 300 sec: 2821.9). Total num frames: 2134016. Throughput: 0: 698.9. Samples: 31446. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2024-08-01 12:03:36,877][00719] Avg episode reward: [(0, '7.646')]
+[2024-08-01 12:03:41,870][00719] Fps is (10 sec: 3686.4, 60 sec: 2867.4, 300 sec: 2867.4). Total num frames: 2150400. Throughput: 0: 816.2. Samples: 36730. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:03:41,876][00719] Avg episode reward: [(0, '7.895')]
+[2024-08-01 12:03:41,885][11824] Saving new best policy, reward=7.895!
+[2024-08-01 12:03:46,870][00719] Fps is (10 sec: 3276.8, 60 sec: 2904.6, 300 sec: 2904.6). Total num frames: 2166784. Throughput: 0: 844.5. Samples: 38760. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:03:46,873][00719] Avg episode reward: [(0, '8.047')]
+[2024-08-01 12:03:46,880][11824] Saving new best policy, reward=8.047!
+[2024-08-01 12:03:47,549][11837] Updated weights for policy 0, policy_version 530 (0.0035)
+[2024-08-01 12:03:51,870][00719] Fps is (10 sec: 3686.4, 60 sec: 3003.9, 300 sec: 3003.9). Total num frames: 2187264. Throughput: 0: 932.8. Samples: 45160. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-08-01 12:03:51,872][00719] Avg episode reward: [(0, '9.277')]
+[2024-08-01 12:03:51,885][11824] Saving new best policy, reward=9.277!
+[2024-08-01 12:03:56,874][00719] Fps is (10 sec: 4094.1, 60 sec: 3344.8, 300 sec: 3087.7). Total num frames: 2207744. Throughput: 0: 961.5. Samples: 51140. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-08-01 12:03:56,877][00719] Avg episode reward: [(0, '8.553')]
+[2024-08-01 12:03:57,537][11837] Updated weights for policy 0, policy_version 540 (0.0023)
+[2024-08-01 12:04:01,870][00719] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3042.9). Total num frames: 2220032. Throughput: 0: 927.6. Samples: 53086. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-08-01 12:04:01,874][00719] Avg episode reward: [(0, '8.819')]
+[2024-08-01 12:04:06,870][00719] Fps is (10 sec: 3688.1, 60 sec: 3754.7, 300 sec: 3167.7). Total num frames: 2244608. Throughput: 0: 905.2. Samples: 58766. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:04:06,874][00719] Avg episode reward: [(0, '8.116')]
+[2024-08-01 12:04:08,753][11837] Updated weights for policy 0, policy_version 550 (0.0020)
+[2024-08-01 12:04:11,870][00719] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3225.8). Total num frames: 2265088. Throughput: 0: 970.6. Samples: 65544. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-08-01 12:04:11,877][00719] Avg episode reward: [(0, '9.217')]
+[2024-08-01 12:04:16,870][00719] Fps is (10 sec: 3686.3, 60 sec: 3686.4, 300 sec: 3228.8). Total num frames: 2281472. Throughput: 0: 967.1. Samples: 68044. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-08-01 12:04:16,876][00719] Avg episode reward: [(0, '9.031')]
+[2024-08-01 12:04:20,473][11837] Updated weights for policy 0, policy_version 560 (0.0024)
+[2024-08-01 12:04:21,870][00719] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3231.4). Total num frames: 2297856. Throughput: 0: 915.1. Samples: 72624. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-08-01 12:04:21,873][00719] Avg episode reward: [(0, '9.470')]
+[2024-08-01 12:04:21,883][11824] Saving new best policy, reward=9.470!
+[2024-08-01 12:04:26,870][00719] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3320.1). Total num frames: 2322432. Throughput: 0: 946.0. Samples: 79298. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-08-01 12:04:26,872][00719] Avg episode reward: [(0, '8.755')]
+[2024-08-01 12:04:29,589][11837] Updated weights for policy 0, policy_version 570 (0.0027)
+[2024-08-01 12:04:31,870][00719] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3317.9). Total num frames: 2338816. Throughput: 0: 976.8. Samples: 82718. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-08-01 12:04:31,875][00719] Avg episode reward: [(0, '9.244')]
+[2024-08-01 12:04:31,886][11824] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000571_2338816.pth...
+[2024-08-01 12:04:32,080][11824] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000455_1863680.pth
+[2024-08-01 12:04:36,873][00719] Fps is (10 sec: 3275.7, 60 sec: 3686.2, 300 sec: 3315.8). Total num frames: 2355200. Throughput: 0: 928.8. Samples: 86958. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-08-01 12:04:36,876][00719] Avg episode reward: [(0, '9.898')]
+[2024-08-01 12:04:36,877][11824] Saving new best policy, reward=9.898!
+[2024-08-01 12:04:41,239][11837] Updated weights for policy 0, policy_version 580 (0.0035)
+[2024-08-01 12:04:41,870][00719] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3351.4). Total num frames: 2375680. Throughput: 0: 938.4. Samples: 93364. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-08-01 12:04:41,876][00719] Avg episode reward: [(0, '9.922')]
+[2024-08-01 12:04:41,886][11824] Saving new best policy, reward=9.922!
+[2024-08-01 12:04:46,870][00719] Fps is (10 sec: 4507.1, 60 sec: 3891.2, 300 sec: 3419.4). Total num frames: 2400256. Throughput: 0: 969.0. Samples: 96690. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:04:46,874][00719] Avg episode reward: [(0, '10.710')]
+[2024-08-01 12:04:46,877][11824] Saving new best policy, reward=10.710!
+[2024-08-01 12:04:51,870][00719] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3379.3). Total num frames: 2412544. Throughput: 0: 953.6. Samples: 101676. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-08-01 12:04:51,872][00719] Avg episode reward: [(0, '10.308')]
+[2024-08-01 12:04:52,437][11837] Updated weights for policy 0, policy_version 590 (0.0019)
+[2024-08-01 12:04:56,870][00719] Fps is (10 sec: 2867.2, 60 sec: 3686.7, 300 sec: 3375.2). Total num frames: 2428928. Throughput: 0: 917.8. Samples: 106846. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-08-01 12:04:56,872][00719] Avg episode reward: [(0, '10.446')]
+[2024-08-01 12:05:01,870][00719] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3434.4). Total num frames: 2453504. Throughput: 0: 937.5. Samples: 110232. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:05:01,873][00719] Avg episode reward: [(0, '10.711')]
+[2024-08-01 12:05:02,338][11837] Updated weights for policy 0, policy_version 600 (0.0055)
+[2024-08-01 12:05:06,870][00719] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3428.6). Total num frames: 2469888. Throughput: 0: 973.5. Samples: 116430. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:05:06,877][00719] Avg episode reward: [(0, '10.704')]
+[2024-08-01 12:05:11,870][00719] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3423.2). Total num frames: 2486272. Throughput: 0: 913.3. Samples: 120396. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-08-01 12:05:11,874][00719] Avg episode reward: [(0, '10.919')]
+[2024-08-01 12:05:11,888][11824] Saving new best policy, reward=10.919!
+[2024-08-01 12:05:14,346][11837] Updated weights for policy 0, policy_version 610 (0.0027)
+[2024-08-01 12:05:16,870][00719] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3446.4). Total num frames: 2506752. Throughput: 0: 912.2. Samples: 123766. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:05:16,878][00719] Avg episode reward: [(0, '11.950')]
+[2024-08-01 12:05:16,881][11824] Saving new best policy, reward=11.950!
+[2024-08-01 12:05:21,870][00719] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3468.0). Total num frames: 2527232. Throughput: 0: 968.9. Samples: 130556. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
+[2024-08-01 12:05:21,877][00719] Avg episode reward: [(0, '12.216')]
+[2024-08-01 12:05:21,888][11824] Saving new best policy, reward=12.216!
+[2024-08-01 12:05:25,289][11837] Updated weights for policy 0, policy_version 620 (0.0020)
+[2024-08-01 12:05:26,874][00719] Fps is (10 sec: 3685.0, 60 sec: 3686.2, 300 sec: 3461.8). Total num frames: 2543616. Throughput: 0: 919.0. Samples: 134724. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-08-01 12:05:26,880][00719] Avg episode reward: [(0, '12.296')]
+[2024-08-01 12:05:26,883][11824] Saving new best policy, reward=12.296!
+[2024-08-01 12:05:31,870][00719] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3456.1). Total num frames: 2560000. Throughput: 0: 893.4. Samples: 136892. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-08-01 12:05:31,872][00719] Avg episode reward: [(0, '12.047')]
+[2024-08-01 12:05:36,154][11837] Updated weights for policy 0, policy_version 630 (0.0030)
+[2024-08-01 12:05:36,870][00719] Fps is (10 sec: 3687.8, 60 sec: 3754.9, 300 sec: 3475.5). Total num frames: 2580480. Throughput: 0: 932.2. Samples: 143626. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-08-01 12:05:36,876][00719] Avg episode reward: [(0, '12.265')]
+[2024-08-01 12:05:41,872][00719] Fps is (10 sec: 4095.1, 60 sec: 3754.5, 300 sec: 3493.7). Total num frames: 2600960. Throughput: 0: 940.3. Samples: 149160. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-08-01 12:05:41,874][00719] Avg episode reward: [(0, '11.543')]
+[2024-08-01 12:05:46,870][00719] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3464.1). Total num frames: 2613248. Throughput: 0: 908.2. Samples: 151100. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-08-01 12:05:46,872][00719] Avg episode reward: [(0, '12.319')]
+[2024-08-01 12:05:46,880][11824] Saving new best policy, reward=12.319!
+[2024-08-01 12:05:48,127][11837] Updated weights for policy 0, policy_version 640 (0.0023)
+[2024-08-01 12:05:51,870][00719] Fps is (10 sec: 3277.5, 60 sec: 3686.4, 300 sec: 3481.7). Total num frames: 2633728. Throughput: 0: 903.7. Samples: 157096. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-08-01 12:05:51,876][00719] Avg episode reward: [(0, '12.954')]
+[2024-08-01 12:05:51,891][11824] Saving new best policy, reward=12.954!
+[2024-08-01 12:05:56,870][00719] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3498.3). Total num frames: 2654208. Throughput: 0: 954.7. Samples: 163356. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-08-01 12:05:56,875][00719] Avg episode reward: [(0, '12.579')]
+[2024-08-01 12:05:58,454][11837] Updated weights for policy 0, policy_version 650 (0.0025)
+[2024-08-01 12:06:01,870][00719] Fps is (10 sec: 3686.2, 60 sec: 3618.1, 300 sec: 3492.4). Total num frames: 2670592. Throughput: 0: 924.3. Samples: 165358. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-08-01 12:06:01,873][00719] Avg episode reward: [(0, '12.936')]
+[2024-08-01 12:06:06,870][00719] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3486.9). Total num frames: 2686976. Throughput: 0: 882.8. Samples: 170282. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-08-01 12:06:06,877][00719] Avg episode reward: [(0, '13.393')]
+[2024-08-01 12:06:06,879][11824] Saving new best policy, reward=13.393!
+[2024-08-01 12:06:09,914][11837] Updated weights for policy 0, policy_version 660 (0.0026)
+[2024-08-01 12:06:11,870][00719] Fps is (10 sec: 4096.3, 60 sec: 3754.7, 300 sec: 3522.6). Total num frames: 2711552. Throughput: 0: 935.5. Samples: 176818. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-08-01 12:06:11,875][00719] Avg episode reward: [(0, '13.332')]
+[2024-08-01 12:06:16,870][00719] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3516.6). Total num frames: 2727936. Throughput: 0: 949.4. Samples: 179614. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-08-01 12:06:16,872][00719] Avg episode reward: [(0, '14.066')]
+[2024-08-01 12:06:16,874][11824] Saving new best policy, reward=14.066!
+[2024-08-01 12:06:21,870][00719] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3491.4). Total num frames: 2740224. Throughput: 0: 890.4. Samples: 183694. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-08-01 12:06:21,872][00719] Avg episode reward: [(0, '14.692')]
+[2024-08-01 12:06:21,898][11824] Saving new best policy, reward=14.692!
+[2024-08-01 12:06:21,902][11837] Updated weights for policy 0, policy_version 670 (0.0027)
+[2024-08-01 12:06:26,870][00719] Fps is (10 sec: 3686.4, 60 sec: 3686.6, 300 sec: 3524.5). Total num frames: 2764800. Throughput: 0: 911.1. Samples: 190158. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-08-01 12:06:26,872][00719] Avg episode reward: [(0, '14.051')]
+[2024-08-01 12:06:31,515][11837] Updated weights for policy 0, policy_version 680 (0.0020)
+[2024-08-01 12:06:31,870][00719] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3537.5). Total num frames: 2785280. Throughput: 0: 940.9. Samples: 193442. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-08-01 12:06:31,874][00719] Avg episode reward: [(0, '13.288')]
+[2024-08-01 12:06:31,889][11824] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000680_2785280.pth...
+[2024-08-01 12:06:32,064][11824] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000490_2007040.pth
+[2024-08-01 12:06:36,870][00719] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3513.5). Total num frames: 2797568. Throughput: 0: 901.1. Samples: 197644. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:06:36,875][00719] Avg episode reward: [(0, '12.283')]
+[2024-08-01 12:06:41,870][00719] Fps is (10 sec: 3276.8, 60 sec: 3618.3, 300 sec: 3526.2). Total num frames: 2818048. Throughput: 0: 892.8. Samples: 203534. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:06:41,872][00719] Avg episode reward: [(0, '12.177')]
+[2024-08-01 12:06:43,301][11837] Updated weights for policy 0, policy_version 690 (0.0026)
+[2024-08-01 12:06:46,870][00719] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3538.3). Total num frames: 2838528. Throughput: 0: 924.4. Samples: 206956. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-08-01 12:06:46,874][00719] Avg episode reward: [(0, '13.925')]
+[2024-08-01 12:06:51,870][00719] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3532.9). Total num frames: 2854912. Throughput: 0: 934.7. Samples: 212344. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-08-01 12:06:51,876][00719] Avg episode reward: [(0, '14.358')]
+[2024-08-01 12:06:55,459][11837] Updated weights for policy 0, policy_version 700 (0.0032)
+[2024-08-01 12:06:56,870][00719] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3527.6). Total num frames: 2871296. Throughput: 0: 889.1. Samples: 216828. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-08-01 12:06:56,875][00719] Avg episode reward: [(0, '14.279')]
+[2024-08-01 12:07:01,870][00719] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3539.0). Total num frames: 2891776. Throughput: 0: 901.9. Samples: 220200. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-08-01 12:07:01,872][00719] Avg episode reward: [(0, '14.994')]
+[2024-08-01 12:07:01,884][11824] Saving new best policy, reward=14.994!
+[2024-08-01 12:07:04,902][11837] Updated weights for policy 0, policy_version 710 (0.0026)
+[2024-08-01 12:07:06,871][00719] Fps is (10 sec: 4095.4, 60 sec: 3754.6, 300 sec: 3549.9). Total num frames: 2912256. Throughput: 0: 951.2. Samples: 226500. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:07:06,874][00719] Avg episode reward: [(0, '13.790')]
+[2024-08-01 12:07:11,870][00719] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3528.9). Total num frames: 2924544. Throughput: 0: 894.6. Samples: 230416. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:07:11,875][00719] Avg episode reward: [(0, '14.033')]
+[2024-08-01 12:07:16,870][00719] Fps is (10 sec: 3277.3, 60 sec: 3618.1, 300 sec: 3539.6). Total num frames: 2945024. Throughput: 0: 887.0. Samples: 233358. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-08-01 12:07:16,873][00719] Avg episode reward: [(0, '16.495')]
+[2024-08-01 12:07:16,875][11824] Saving new best policy, reward=16.495!
+[2024-08-01 12:07:17,181][11837] Updated weights for policy 0, policy_version 720 (0.0028)
+[2024-08-01 12:07:21,870][00719] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3565.1). Total num frames: 2969600. Throughput: 0: 942.4. Samples: 240054. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-08-01 12:07:21,881][00719] Avg episode reward: [(0, '17.297')]
+[2024-08-01 12:07:21,893][11824] Saving new best policy, reward=17.297!
+[2024-08-01 12:07:26,871][00719] Fps is (10 sec: 3685.8, 60 sec: 3618.0, 300 sec: 3544.9). Total num frames: 2981888. Throughput: 0: 908.9. Samples: 244438. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-08-01 12:07:26,874][00719] Avg episode reward: [(0, '16.998')]
+[2024-08-01 12:07:29,677][11837] Updated weights for policy 0, policy_version 730 (0.0017)
+[2024-08-01 12:07:31,870][00719] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3540.2). Total num frames: 2998272. Throughput: 0: 878.9. Samples: 246508. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-08-01 12:07:31,876][00719] Avg episode reward: [(0, '17.987')]
+[2024-08-01 12:07:31,885][11824] Saving new best policy, reward=17.987!
+[2024-08-01 12:07:36,870][00719] Fps is (10 sec: 3687.0, 60 sec: 3686.4, 300 sec: 3549.9). Total num frames: 3018752. Throughput: 0: 907.7. Samples: 253190. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-08-01 12:07:36,872][00719] Avg episode reward: [(0, '15.836')]
+[2024-08-01 12:07:38,634][11837] Updated weights for policy 0, policy_version 740 (0.0017)
+[2024-08-01 12:07:41,870][00719] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3559.3). Total num frames: 3039232. Throughput: 0: 937.8. Samples: 259028. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-08-01 12:07:41,872][00719] Avg episode reward: [(0, '15.651')]
+[2024-08-01 12:07:46,870][00719] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3540.7). Total num frames: 3051520. Throughput: 0: 907.6. Samples: 261042. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-08-01 12:07:46,873][00719] Avg episode reward: [(0, '15.549')]
+[2024-08-01 12:07:50,671][11837] Updated weights for policy 0, policy_version 750 (0.0019)
+[2024-08-01 12:07:51,870][00719] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 3076096. Throughput: 0: 899.4. Samples: 266972. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-08-01 12:07:51,877][00719] Avg episode reward: [(0, '14.995')]
+[2024-08-01 12:07:56,870][00719] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 3096576. Throughput: 0: 960.0. Samples: 273618. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-08-01 12:07:56,872][00719] Avg episode reward: [(0, '14.879')]
+[2024-08-01 12:08:01,691][11837] Updated weights for policy 0, policy_version 760 (0.0025)
+[2024-08-01 12:08:01,875][00719] Fps is (10 sec: 3684.3, 60 sec: 3686.1, 300 sec: 3707.2). Total num frames: 3112960. Throughput: 0: 939.1. Samples: 275622. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-08-01 12:08:01,878][00719] Avg episode reward: [(0, '15.911')]
+[2024-08-01 12:08:06,870][00719] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3707.2). Total num frames: 3129344. Throughput: 0: 900.2. Samples: 280562. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:08:06,872][00719] Avg episode reward: [(0, '16.049')]
+[2024-08-01 12:08:11,660][11837] Updated weights for policy 0, policy_version 770 (0.0029)
+[2024-08-01 12:08:11,870][00719] Fps is (10 sec: 4098.3, 60 sec: 3822.9, 300 sec: 3707.2). Total num frames: 3153920. Throughput: 0: 953.2. Samples: 287330. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:08:11,875][00719] Avg episode reward: [(0, '16.724')]
+[2024-08-01 12:08:16,872][00719] Fps is (10 sec: 4095.1, 60 sec: 3754.5, 300 sec: 3693.3). Total num frames: 3170304. Throughput: 0: 974.2. Samples: 290350. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-08-01 12:08:16,877][00719] Avg episode reward: [(0, '16.911')]
+[2024-08-01 12:08:21,870][00719] Fps is (10 sec: 2867.1, 60 sec: 3549.8, 300 sec: 3693.3). Total num frames: 3182592. Throughput: 0: 916.4. Samples: 294428. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-08-01 12:08:21,873][00719] Avg episode reward: [(0, '16.554')]
+[2024-08-01 12:08:23,691][11837] Updated weights for policy 0, policy_version 780 (0.0017)
+[2024-08-01 12:08:26,870][00719] Fps is (10 sec: 3687.2, 60 sec: 3754.8, 300 sec: 3707.2). Total num frames: 3207168. Throughput: 0: 936.1. Samples: 301154. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-08-01 12:08:26,874][00719] Avg episode reward: [(0, '16.407')]
+[2024-08-01 12:08:31,870][00719] Fps is (10 sec: 4505.8, 60 sec: 3822.9, 300 sec: 3707.2). Total num frames: 3227648. Throughput: 0: 964.1. Samples: 304428. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:08:31,872][00719] Avg episode reward: [(0, '17.116')]
+[2024-08-01 12:08:31,886][11824] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000788_3227648.pth...
+[2024-08-01 12:08:32,057][11824] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000571_2338816.pth
+[2024-08-01 12:08:34,083][11837] Updated weights for policy 0, policy_version 790 (0.0024)
+[2024-08-01 12:08:36,870][00719] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 3239936. Throughput: 0: 929.5. Samples: 308800. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:08:36,875][00719] Avg episode reward: [(0, '16.571')]
+[2024-08-01 12:08:41,870][00719] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 3260416. Throughput: 0: 912.8. Samples: 314692. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-08-01 12:08:41,872][00719] Avg episode reward: [(0, '18.520')]
+[2024-08-01 12:08:41,886][11824] Saving new best policy, reward=18.520!
+[2024-08-01 12:08:44,783][11837] Updated weights for policy 0, policy_version 800 (0.0023)
+[2024-08-01 12:08:46,870][00719] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3721.1). Total num frames: 3284992. Throughput: 0: 942.2. Samples: 318016. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-08-01 12:08:46,872][00719] Avg episode reward: [(0, '18.578')]
+[2024-08-01 12:08:46,878][11824] Saving new best policy, reward=18.578!
+[2024-08-01 12:08:51,870][00719] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3693.4). Total num frames: 3297280. Throughput: 0: 952.9. Samples: 323442. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:08:51,872][00719] Avg episode reward: [(0, '18.700')]
+[2024-08-01 12:08:51,941][11824] Saving new best policy, reward=18.700!
+[2024-08-01 12:08:56,813][11837] Updated weights for policy 0, policy_version 810 (0.0028)
+[2024-08-01 12:08:56,870][00719] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 3317760. Throughput: 0: 908.7. Samples: 328220. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:08:56,873][00719] Avg episode reward: [(0, '18.126')]
+[2024-08-01 12:09:01,870][00719] Fps is (10 sec: 4096.0, 60 sec: 3755.0, 300 sec: 3707.2). Total num frames: 3338240. Throughput: 0: 911.4. Samples: 331362. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-08-01 12:09:01,877][00719] Avg episode reward: [(0, '17.835')]
+[2024-08-01 12:09:06,539][11837] Updated weights for policy 0, policy_version 820 (0.0019)
+[2024-08-01 12:09:06,870][00719] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3707.2). Total num frames: 3358720. Throughput: 0: 962.9. Samples: 337758. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:09:06,875][00719] Avg episode reward: [(0, '18.048')]
+[2024-08-01 12:09:11,870][00719] Fps is (10 sec: 3276.6, 60 sec: 3618.1, 300 sec: 3693.3). Total num frames: 3371008. Throughput: 0: 905.3. Samples: 341894. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-08-01 12:09:11,873][00719] Avg episode reward: [(0, '18.645')]
+[2024-08-01 12:09:16,870][00719] Fps is (10 sec: 3276.8, 60 sec: 3686.5, 300 sec: 3707.2). Total num frames: 3391488. Throughput: 0: 901.9. Samples: 345014. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-08-01 12:09:16,873][00719] Avg episode reward: [(0, '21.383')]
+[2024-08-01 12:09:16,881][11824] Saving new best policy, reward=21.383!
+[2024-08-01 12:09:18,084][11837] Updated weights for policy 0, policy_version 830 (0.0037)
+[2024-08-01 12:09:21,870][00719] Fps is (10 sec: 4505.9, 60 sec: 3891.2, 300 sec: 3707.2). Total num frames: 3416064. Throughput: 0: 953.4. Samples: 351702. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-08-01 12:09:21,879][00719] Avg episode reward: [(0, '22.293')]
+[2024-08-01 12:09:21,889][11824] Saving new best policy, reward=22.293!
+[2024-08-01 12:09:26,870][00719] Fps is (10 sec: 3686.3, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 3428352. Throughput: 0: 926.3. Samples: 356378. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-08-01 12:09:26,876][00719] Avg episode reward: [(0, '22.552')]
+[2024-08-01 12:09:26,883][11824] Saving new best policy, reward=22.552!
+[2024-08-01 12:09:30,219][11837] Updated weights for policy 0, policy_version 840 (0.0029)
+[2024-08-01 12:09:31,872][00719] Fps is (10 sec: 2866.5, 60 sec: 3618.0, 300 sec: 3693.3). Total num frames: 3444736. Throughput: 0: 897.5. Samples: 358408. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-08-01 12:09:31,874][00719] Avg episode reward: [(0, '22.323')]
+[2024-08-01 12:09:36,870][00719] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3707.2). Total num frames: 3469312. Throughput: 0: 927.7. Samples: 365188. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-08-01 12:09:36,876][00719] Avg episode reward: [(0, '20.231')]
+[2024-08-01 12:09:39,377][11837] Updated weights for policy 0, policy_version 850 (0.0019)
+[2024-08-01 12:09:41,872][00719] Fps is (10 sec: 4096.1, 60 sec: 3754.5, 300 sec: 3679.4). Total num frames: 3485696. Throughput: 0: 950.4. Samples: 370990. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-08-01 12:09:41,876][00719] Avg episode reward: [(0, '18.581')]
+[2024-08-01 12:09:46,870][00719] Fps is (10 sec: 3276.7, 60 sec: 3618.1, 300 sec: 3693.3). Total num frames: 3502080. Throughput: 0: 925.0. Samples: 372988. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:09:46,877][00719] Avg episode reward: [(0, '19.255')]
+[2024-08-01 12:09:51,047][11837] Updated weights for policy 0, policy_version 860 (0.0024)
+[2024-08-01 12:09:51,870][00719] Fps is (10 sec: 3687.3, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 3522560. Throughput: 0: 919.4. Samples: 379132. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-08-01 12:09:51,872][00719] Avg episode reward: [(0, '18.368')]
+[2024-08-01 12:09:56,870][00719] Fps is (10 sec: 4505.7, 60 sec: 3822.9, 300 sec: 3707.2). Total num frames: 3547136. Throughput: 0: 976.1. Samples: 385820. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-08-01 12:09:56,872][00719] Avg episode reward: [(0, '19.757')]
+[2024-08-01 12:10:01,870][00719] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 3559424. Throughput: 0: 950.2. Samples: 387774. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-08-01 12:10:01,877][00719] Avg episode reward: [(0, '19.424')]
+[2024-08-01 12:10:02,656][11837] Updated weights for policy 0, policy_version 870 (0.0035)
+[2024-08-01 12:10:06,870][00719] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 3579904. Throughput: 0: 906.4. Samples: 392488. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:10:06,876][00719] Avg episode reward: [(0, '20.203')]
+[2024-08-01 12:10:11,870][00719] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 3707.2). Total num frames: 3600384. Throughput: 0: 953.0. Samples: 399264. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-08-01 12:10:11,874][00719] Avg episode reward: [(0, '19.456')]
+[2024-08-01 12:10:12,417][11837] Updated weights for policy 0, policy_version 880 (0.0031)
+[2024-08-01 12:10:16,870][00719] Fps is (10 sec: 3686.5, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 3616768. Throughput: 0: 973.9. Samples: 402232. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-08-01 12:10:16,872][00719] Avg episode reward: [(0, '20.500')]
+[2024-08-01 12:10:21,870][00719] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3693.4). Total num frames: 3633152. Throughput: 0: 912.0. Samples: 406226. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-08-01 12:10:21,872][00719] Avg episode reward: [(0, '20.083')]
+[2024-08-01 12:10:24,437][11837] Updated weights for policy 0, policy_version 890 (0.0025)
+[2024-08-01 12:10:26,870][00719] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 3653632. Throughput: 0: 930.4. Samples: 412856. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-08-01 12:10:26,875][00719] Avg episode reward: [(0, '20.061')]
+[2024-08-01 12:10:31,876][00719] Fps is (10 sec: 4093.3, 60 sec: 3822.7, 300 sec: 3707.1). Total num frames: 3674112. Throughput: 0: 961.7. Samples: 416270. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:10:31,882][00719] Avg episode reward: [(0, '20.380')]
+[2024-08-01 12:10:31,898][11824] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000898_3678208.pth...
+[2024-08-01 12:10:32,088][11824] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000680_2785280.pth
+[2024-08-01 12:10:35,101][11837] Updated weights for policy 0, policy_version 900 (0.0034)
+[2024-08-01 12:10:36,870][00719] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3693.4). Total num frames: 3690496. Throughput: 0: 924.4. Samples: 420730. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-08-01 12:10:36,875][00719] Avg episode reward: [(0, '20.253')]
+[2024-08-01 12:10:41,870][00719] Fps is (10 sec: 3279.0, 60 sec: 3686.5, 300 sec: 3707.2). Total num frames: 3706880. Throughput: 0: 900.9. Samples: 426360. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:10:41,879][00719] Avg episode reward: [(0, '20.686')]
+[2024-08-01 12:10:45,678][11837] Updated weights for policy 0, policy_version 910 (0.0019)
+[2024-08-01 12:10:46,870][00719] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 3721.1). Total num frames: 3731456. Throughput: 0: 931.8. Samples: 429704. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-08-01 12:10:46,872][00719] Avg episode reward: [(0, '22.407')]
+[2024-08-01 12:10:51,870][00719] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 3747840. Throughput: 0: 953.6. Samples: 435400. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-08-01 12:10:51,875][00719] Avg episode reward: [(0, '21.935')]
+[2024-08-01 12:10:56,870][00719] Fps is (10 sec: 3276.7, 60 sec: 3618.1, 300 sec: 3707.2). Total num frames: 3764224. Throughput: 0: 906.3. Samples: 440046. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-08-01 12:10:56,877][00719] Avg episode reward: [(0, '21.694')]
+[2024-08-01 12:10:57,428][11837] Updated weights for policy 0, policy_version 920 (0.0026)
+[2024-08-01 12:11:01,870][00719] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 3784704. Throughput: 0: 915.4. Samples: 443424. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:11:01,876][00719] Avg episode reward: [(0, '22.639')]
+[2024-08-01 12:11:01,884][11824] Saving new best policy, reward=22.639!
+[2024-08-01 12:11:06,870][00719] Fps is (10 sec: 4096.1, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 3805184. Throughput: 0: 961.8. Samples: 449506. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-08-01 12:11:06,876][00719] Avg episode reward: [(0, '22.984')]
+[2024-08-01 12:11:06,879][11824] Saving new best policy, reward=22.984!
+[2024-08-01 12:11:08,124][11837] Updated weights for policy 0, policy_version 930 (0.0020)
+[2024-08-01 12:11:11,870][00719] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3693.3). Total num frames: 3817472. Throughput: 0: 903.7. Samples: 453522. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-08-01 12:11:11,872][00719] Avg episode reward: [(0, '21.402')]
+[2024-08-01 12:11:16,870][00719] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 3837952. Throughput: 0: 892.6. Samples: 456432. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-08-01 12:11:16,873][00719] Avg episode reward: [(0, '20.302')]
+[2024-08-01 12:11:19,117][11837] Updated weights for policy 0, policy_version 940 (0.0029)
+[2024-08-01 12:11:21,870][00719] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 3858432. Throughput: 0: 943.2. Samples: 463172. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-08-01 12:11:21,872][00719] Avg episode reward: [(0, '20.968')]
+[2024-08-01 12:11:26,870][00719] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 3874816. Throughput: 0: 926.2. Samples: 468040. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-08-01 12:11:26,872][00719] Avg episode reward: [(0, '20.007')]
+[2024-08-01 12:11:31,401][11837] Updated weights for policy 0, policy_version 950 (0.0033)
+[2024-08-01 12:11:31,870][00719] Fps is (10 sec: 3276.6, 60 sec: 3618.5, 300 sec: 3707.2). Total num frames: 3891200. Throughput: 0: 897.3. Samples: 470084. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-08-01 12:11:31,878][00719] Avg episode reward: [(0, '18.805')]
+[2024-08-01 12:11:36,870][00719] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 3915776. Throughput: 0: 918.8. Samples: 476748. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:11:36,872][00719] Avg episode reward: [(0, '19.099')]
+[2024-08-01 12:11:40,105][11837] Updated weights for policy 0, policy_version 960 (0.0014)
+[2024-08-01 12:11:41,870][00719] Fps is (10 sec: 4505.9, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 3936256. Throughput: 0: 954.5. Samples: 482998. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:11:41,874][00719] Avg episode reward: [(0, '18.094')]
+[2024-08-01 12:11:46,870][00719] Fps is (10 sec: 3276.6, 60 sec: 3618.1, 300 sec: 3707.2). Total num frames: 3948544. Throughput: 0: 922.2. Samples: 484924. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:11:46,873][00719] Avg episode reward: [(0, '18.225')]
+[2024-08-01 12:11:51,636][11837] Updated weights for policy 0, policy_version 970 (0.0041)
+[2024-08-01 12:11:51,870][00719] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 3973120. Throughput: 0: 921.2. Samples: 490960. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-08-01 12:11:51,877][00719] Avg episode reward: [(0, '19.173')]
+[2024-08-01 12:11:56,870][00719] Fps is (10 sec: 4505.8, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 3993600. Throughput: 0: 988.8. Samples: 498020. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-08-01 12:11:56,873][00719] Avg episode reward: [(0, '18.431')]
+[2024-08-01 12:11:59,604][11824] Stopping Batcher_0...
+[2024-08-01 12:11:59,604][11824] Loop batcher_evt_loop terminating...
+[2024-08-01 12:11:59,604][00719] Component Batcher_0 stopped!
+[2024-08-01 12:11:59,620][11824] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-08-01 12:11:59,702][00719] Component RolloutWorker_w4 stopped!
+[2024-08-01 12:11:59,706][11842] Stopping RolloutWorker_w4...
+[2024-08-01 12:11:59,706][11842] Loop rollout_proc4_evt_loop terminating...
+[2024-08-01 12:11:59,721][00719] Component RolloutWorker_w6 stopped!
+[2024-08-01 12:11:59,726][11849] Stopping RolloutWorker_w6...
+[2024-08-01 12:11:59,726][11849] Loop rollout_proc6_evt_loop terminating...
+[2024-08-01 12:11:59,733][11843] Stopping RolloutWorker_w5...
+[2024-08-01 12:11:59,733][11843] Loop rollout_proc5_evt_loop terminating...
+[2024-08-01 12:11:59,733][00719] Component RolloutWorker_w5 stopped!
+[2024-08-01 12:11:59,745][00719] Component RolloutWorker_w1 stopped!
+[2024-08-01 12:11:59,750][11837] Weights refcount: 2 0
+[2024-08-01 12:11:59,745][11839] Stopping RolloutWorker_w1...
+[2024-08-01 12:11:59,753][11839] Loop rollout_proc1_evt_loop terminating...
+[2024-08-01 12:11:59,754][00719] Component RolloutWorker_w0 stopped!
+[2024-08-01 12:11:59,756][11838] Stopping RolloutWorker_w0...
+[2024-08-01 12:11:59,756][11838] Loop rollout_proc0_evt_loop terminating...
+[2024-08-01 12:11:59,771][00719] Component InferenceWorker_p0-w0 stopped!
+[2024-08-01 12:11:59,776][00719] Component RolloutWorker_w2 stopped!
+[2024-08-01 12:11:59,778][11840] Stopping RolloutWorker_w2...
+[2024-08-01 12:11:59,778][11840] Loop rollout_proc2_evt_loop terminating...
+[2024-08-01 12:11:59,781][11837] Stopping InferenceWorker_p0-w0...
+[2024-08-01 12:11:59,782][11837] Loop inference_proc0-0_evt_loop terminating...
+[2024-08-01 12:11:59,816][11841] Stopping RolloutWorker_w3...
+[2024-08-01 12:11:59,815][00719] Component RolloutWorker_w3 stopped!
+[2024-08-01 12:11:59,826][11841] Loop rollout_proc3_evt_loop terminating...
+[2024-08-01 12:11:59,825][00719] Component RolloutWorker_w7 stopped!
+[2024-08-01 12:11:59,826][11848] Stopping RolloutWorker_w7...
+[2024-08-01 12:11:59,835][11848] Loop rollout_proc7_evt_loop terminating...
+[2024-08-01 12:11:59,883][11824] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000788_3227648.pth
+[2024-08-01 12:11:59,923][11824] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-08-01 12:12:00,235][00719] Component LearnerWorker_p0 stopped!
+[2024-08-01 12:12:00,238][00719] Waiting for process learner_proc0 to stop...
+[2024-08-01 12:12:00,243][11824] Stopping LearnerWorker_p0...
+[2024-08-01 12:12:00,243][11824] Loop learner_proc0_evt_loop terminating...
+[2024-08-01 12:12:02,140][00719] Waiting for process inference_proc0-0 to join...
+[2024-08-01 12:12:02,242][00719] Waiting for process rollout_proc0 to join...
+[2024-08-01 12:12:04,440][00719] Waiting for process rollout_proc1 to join...
+[2024-08-01 12:12:04,445][00719] Waiting for process rollout_proc2 to join...
+[2024-08-01 12:12:04,448][00719] Waiting for process rollout_proc3 to join...
+[2024-08-01 12:12:04,451][00719] Waiting for process rollout_proc4 to join...
+[2024-08-01 12:12:04,454][00719] Waiting for process rollout_proc5 to join...
+[2024-08-01 12:12:04,458][00719] Waiting for process rollout_proc6 to join...
+[2024-08-01 12:12:04,461][00719] Waiting for process rollout_proc7 to join...
+[2024-08-01 12:12:04,464][00719] Batcher 0 profile tree view:
+batching: 14.2866, releasing_batches: 0.0414
+[2024-08-01 12:12:04,465][00719] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0000
+  wait_policy_total: 206.9662
+update_model: 4.6550
+  weight_update: 0.0019
+one_step: 0.0031
+  handle_policy_step: 313.0695
+    deserialize: 8.4927, stack: 1.6646, obs_to_device_normalize: 63.1328, forward: 168.1129, send_messages: 15.1628
+    prepare_outputs: 41.5703
+      to_cpu: 23.9472
+[2024-08-01 12:12:04,467][00719] Learner 0 profile tree view:
+misc: 0.0026, prepare_batch: 7.6723
+train: 39.1823
+  epoch_init: 0.0033, minibatch_init: 0.0032, losses_postprocess: 0.3232, kl_divergence: 0.4214, after_optimizer: 2.0595
+  calculate_losses: 13.8445
+    losses_init: 0.0018, forward_head: 0.7894, bptt_initial: 9.3296, tail: 0.6387, advantages_returns: 0.1402, losses: 1.8140
+    bptt: 0.9599
+      bptt_forward_core: 0.9218
+  update: 22.1558
+    clip: 0.4885
+[2024-08-01 12:12:04,470][00719] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.2294, enqueue_policy_requests: 50.7448, env_step: 417.6763, overhead: 7.5089, complete_rollouts: 3.6553
+save_policy_outputs: 11.0508
+  split_output_tensors: 4.4648
+[2024-08-01 12:12:04,471][00719] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.1597, enqueue_policy_requests: 52.2065, env_step: 420.3663, overhead: 7.2817, complete_rollouts: 3.4570
+save_policy_outputs: 11.0252
+  split_output_tensors: 4.3506
+[2024-08-01 12:12:04,473][00719] Loop Runner_EvtLoop terminating...
+[2024-08-01 12:12:04,475][00719] Runner profile tree view:
+main_loop: 570.5493
+[2024-08-01 12:12:04,476][00719] Collected {0: 4005888}, FPS: 3503.4
+[2024-08-01 12:12:04,506][00719] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-08-01 12:12:04,508][00719] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-08-01 12:12:04,510][00719] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-08-01 12:12:04,512][00719] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-08-01 12:12:04,513][00719] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-08-01 12:12:04,515][00719] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-08-01 12:12:04,516][00719] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2024-08-01 12:12:04,517][00719] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-08-01 12:12:04,518][00719] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2024-08-01 12:12:04,519][00719] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2024-08-01 12:12:04,520][00719] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-08-01 12:12:04,521][00719] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-08-01 12:12:04,522][00719] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-08-01 12:12:04,523][00719] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-08-01 12:12:04,524][00719] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-08-01 12:12:04,552][00719] RunningMeanStd input shape: (3, 72, 128)
+[2024-08-01 12:12:04,554][00719] RunningMeanStd input shape: (1,)
+[2024-08-01 12:12:04,567][00719] ConvEncoder: input_channels=3
+[2024-08-01 12:12:04,605][00719] Conv encoder output size: 512
+[2024-08-01 12:12:04,606][00719] Policy head output size: 512
+[2024-08-01 12:12:04,625][00719] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-08-01 12:12:05,081][00719] Num frames 100...
+[2024-08-01 12:12:05,206][00719] Num frames 200...
+[2024-08-01 12:12:05,332][00719] Num frames 300...
+[2024-08-01 12:12:05,452][00719] Num frames 400...
+[2024-08-01 12:12:05,571][00719] Num frames 500...
+[2024-08-01 12:12:05,689][00719] Num frames 600...
+[2024-08-01 12:12:05,811][00719] Num frames 700...
+[2024-08-01 12:12:05,944][00719] Num frames 800...
+[2024-08-01 12:12:05,997][00719] Avg episode rewards: #0: 14.000, true rewards: #0: 8.000
+[2024-08-01 12:12:05,999][00719] Avg episode reward: 14.000, avg true_objective: 8.000
+[2024-08-01 12:12:06,124][00719] Num frames 900...
+[2024-08-01 12:12:06,245][00719] Num frames 1000...
+[2024-08-01 12:12:06,370][00719] Num frames 1100...
+[2024-08-01 12:12:06,493][00719] Num frames 1200...
+[2024-08-01 12:12:06,622][00719] Num frames 1300...
+[2024-08-01 12:12:06,742][00719] Num frames 1400...
+[2024-08-01 12:12:06,867][00719] Num frames 1500...
+[2024-08-01 12:12:06,997][00719] Num frames 1600...
+[2024-08-01 12:12:07,123][00719] Num frames 1700...
+[2024-08-01 12:12:07,243][00719] Num frames 1800...
+[2024-08-01 12:12:07,363][00719] Num frames 1900...
+[2024-08-01 12:12:07,491][00719] Num frames 2000...
+[2024-08-01 12:12:07,613][00719] Num frames 2100...
+[2024-08-01 12:12:07,736][00719] Num frames 2200...
+[2024-08-01 12:12:07,864][00719] Num frames 2300...
+[2024-08-01 12:12:07,928][00719] Avg episode rewards: #0: 26.020, true rewards: #0: 11.520
+[2024-08-01 12:12:07,929][00719] Avg episode reward: 26.020, avg true_objective: 11.520
+[2024-08-01 12:12:08,057][00719] Num frames 2400...
+[2024-08-01 12:12:08,182][00719] Num frames 2500...
+[2024-08-01 12:12:08,309][00719] Num frames 2600...
+[2024-08-01 12:12:08,436][00719] Num frames 2700...
+[2024-08-01 12:12:08,558][00719] Num frames 2800...
+[2024-08-01 12:12:08,682][00719] Num frames 2900...
+[2024-08-01 12:12:08,813][00719] Num frames 3000...
+[2024-08-01 12:12:08,944][00719] Num frames 3100...
+[2024-08-01 12:12:09,074][00719] Num frames 3200...
+[2024-08-01 12:12:09,200][00719] Num frames 3300...
+[2024-08-01 12:12:09,320][00719] Num frames 3400...
+[2024-08-01 12:12:09,445][00719] Num frames 3500...
+[2024-08-01 12:12:09,563][00719] Avg episode rewards: #0: 27.840, true rewards: #0: 11.840
+[2024-08-01 12:12:09,565][00719] Avg episode reward: 27.840, avg true_objective: 11.840
+[2024-08-01 12:12:09,627][00719] Num frames 3600...
+[2024-08-01 12:12:09,746][00719] Num frames 3700...
+[2024-08-01 12:12:09,869][00719] Num frames 3800...
+[2024-08-01 12:12:09,991][00719] Num frames 3900...
+[2024-08-01 12:12:10,088][00719] Avg episode rewards: #0: 22.332, true rewards: #0: 9.832
+[2024-08-01 12:12:10,090][00719] Avg episode reward: 22.332, avg true_objective: 9.832
+[2024-08-01 12:12:10,172][00719] Num frames 4000...
+[2024-08-01 12:12:10,299][00719] Num frames 4100...
+[2024-08-01 12:12:10,419][00719] Num frames 4200...
+[2024-08-01 12:12:10,539][00719] Num frames 4300...
+[2024-08-01 12:12:10,667][00719] Avg episode rewards: #0: 19.524, true rewards: #0: 8.724
+[2024-08-01 12:12:10,668][00719] Avg episode reward: 19.524, avg true_objective: 8.724
+[2024-08-01 12:12:10,719][00719] Num frames 4400...
+[2024-08-01 12:12:10,841][00719] Num frames 4500...
+[2024-08-01 12:12:10,968][00719] Num frames 4600...
+[2024-08-01 12:12:11,093][00719] Num frames 4700...
+[2024-08-01 12:12:11,219][00719] Num frames 4800...
+[2024-08-01 12:12:11,337][00719] Num frames 4900...
+[2024-08-01 12:12:11,460][00719] Num frames 5000...
+[2024-08-01 12:12:11,581][00719] Num frames 5100...
+[2024-08-01 12:12:11,705][00719] Num frames 5200...
+[2024-08-01 12:12:11,830][00719] Num frames 5300...
+[2024-08-01 12:12:12,006][00719] Avg episode rewards: #0: 19.990, true rewards: #0: 8.990
+[2024-08-01 12:12:12,007][00719] Avg episode reward: 19.990, avg true_objective: 8.990
+[2024-08-01 12:12:12,019][00719] Num frames 5400...
+[2024-08-01 12:12:12,149][00719] Num frames 5500...
+[2024-08-01 12:12:12,271][00719] Num frames 5600...
+[2024-08-01 12:12:12,391][00719] Num frames 5700...
+[2024-08-01 12:12:12,510][00719] Num frames 5800...
+[2024-08-01 12:12:12,683][00719] Num frames 5900...
+[2024-08-01 12:12:12,855][00719] Num frames 6000...
+[2024-08-01 12:12:13,026][00719] Num frames 6100...
+[2024-08-01 12:12:13,125][00719] Avg episode rewards: #0: 18.890, true rewards: #0: 8.747
+[2024-08-01 12:12:13,127][00719] Avg episode reward: 18.890, avg true_objective: 8.747
+[2024-08-01 12:12:13,275][00719] Num frames 6200...
+[2024-08-01 12:12:13,439][00719] Num frames 6300...
+[2024-08-01 12:12:13,598][00719] Num frames 6400...
+[2024-08-01 12:12:13,768][00719] Num frames 6500...
+[2024-08-01 12:12:13,958][00719] Num frames 6600...
+[2024-08-01 12:12:14,126][00719] Num frames 6700...
+[2024-08-01 12:12:14,310][00719] Num frames 6800...
+[2024-08-01 12:12:14,488][00719] Num frames 6900...
+[2024-08-01 12:12:14,661][00719] Num frames 7000...
+[2024-08-01 12:12:14,841][00719] Num frames 7100...
+[2024-08-01 12:12:15,029][00719] Num frames 7200...
+[2024-08-01 12:12:15,154][00719] Num frames 7300...
+[2024-08-01 12:12:15,303][00719] Avg episode rewards: #0: 19.839, true rewards: #0: 9.214
+[2024-08-01 12:12:15,305][00719] Avg episode reward: 19.839, avg true_objective: 9.214
+[2024-08-01 12:12:15,345][00719] Num frames 7400...
+[2024-08-01 12:12:15,468][00719] Num frames 7500...
+[2024-08-01 12:12:15,590][00719] Num frames 7600...
+[2024-08-01 12:12:15,711][00719] Num frames 7700...
+[2024-08-01 12:12:15,834][00719] Num frames 7800...
+[2024-08-01 12:12:15,920][00719] Avg episode rewards: #0: 18.243, true rewards: #0: 8.688
+[2024-08-01 12:12:15,921][00719] Avg episode reward: 18.243, avg true_objective: 8.688
+[2024-08-01 12:12:16,020][00719] Num frames 7900...
+[2024-08-01 12:12:16,139][00719] Num frames 8000...
+[2024-08-01 12:12:16,266][00719] Num frames 8100...
+[2024-08-01 12:12:16,392][00719] Num frames 8200...
+[2024-08-01 12:12:16,490][00719] Avg episode rewards: #0: 16.935, true rewards: #0: 8.235
+[2024-08-01 12:12:16,491][00719] Avg episode reward: 16.935, avg true_objective: 8.235
+[2024-08-01 12:13:01,502][00719] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2024-08-01 12:13:01,540][00719] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-08-01 12:13:01,542][00719] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-08-01 12:13:01,544][00719] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-08-01 12:13:01,545][00719] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-08-01 12:13:01,549][00719] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-08-01 12:13:01,550][00719] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-08-01 12:13:01,552][00719] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2024-08-01 12:13:01,553][00719] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-08-01 12:13:01,554][00719] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2024-08-01 12:13:01,555][00719] Adding new argument 'hf_repository'='ThNaToS/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2024-08-01 12:13:01,556][00719] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-08-01 12:13:01,557][00719] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-08-01 12:13:01,558][00719] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-08-01 12:13:01,559][00719] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-08-01 12:13:01,560][00719] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-08-01 12:13:01,588][00719] RunningMeanStd input shape: (3, 72, 128)
+[2024-08-01 12:13:01,590][00719] RunningMeanStd input shape: (1,)
+[2024-08-01 12:13:01,603][00719] ConvEncoder: input_channels=3
+[2024-08-01 12:13:01,642][00719] Conv encoder output size: 512
+[2024-08-01 12:13:01,644][00719] Policy head output size: 512
+[2024-08-01 12:13:01,661][00719] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-08-01 12:13:02,112][00719] Num frames 100...
+[2024-08-01 12:13:02,252][00719] Num frames 200...
+[2024-08-01 12:13:02,385][00719] Avg episode rewards: #0: 2.560, true rewards: #0: 2.560
+[2024-08-01 12:13:02,386][00719] Avg episode reward: 2.560, avg true_objective: 2.560
+[2024-08-01 12:13:02,442][00719] Num frames 300...
+[2024-08-01 12:13:02,567][00719] Num frames 400...
+[2024-08-01 12:13:02,695][00719] Num frames 500...
+[2024-08-01 12:13:02,825][00719] Num frames 600...
+[2024-08-01 12:13:02,952][00719] Num frames 700...
+[2024-08-01 12:13:03,074][00719] Num frames 800...
+[2024-08-01 12:13:03,196][00719] Num frames 900...
+[2024-08-01 12:13:03,320][00719] Num frames 1000...
+[2024-08-01 12:13:03,446][00719] Num frames 1100...
+[2024-08-01 12:13:03,571][00719] Num frames 1200...
+[2024-08-01 12:13:03,695][00719] Num frames 1300...
+[2024-08-01 12:13:03,827][00719] Num frames 1400...
+[2024-08-01 12:13:03,961][00719] Num frames 1500...
+[2024-08-01 12:13:04,066][00719] Avg episode rewards: #0: 15.695, true rewards: #0: 7.695
+[2024-08-01 12:13:04,068][00719] Avg episode reward: 15.695, avg true_objective: 7.695
+[2024-08-01 12:13:04,144][00719] Num frames 1600...
+[2024-08-01 12:13:04,282][00719] Num frames 1700...
+[2024-08-01 12:13:04,460][00719] Num frames 1800...
+[2024-08-01 12:13:04,625][00719] Num frames 1900...
+[2024-08-01 12:13:04,791][00719] Num frames 2000...
+[2024-08-01 12:13:04,973][00719] Num frames 2100...
+[2024-08-01 12:13:05,144][00719] Num frames 2200...
+[2024-08-01 12:13:05,306][00719] Num frames 2300...
+[2024-08-01 12:13:05,475][00719] Num frames 2400...
+[2024-08-01 12:13:05,661][00719] Num frames 2500...
+[2024-08-01 12:13:05,832][00719] Num frames 2600...
+[2024-08-01 12:13:06,033][00719] Num frames 2700...
+[2024-08-01 12:13:06,214][00719] Num frames 2800...
+[2024-08-01 12:13:06,397][00719] Avg episode rewards: #0: 20.250, true rewards: #0: 9.583
+[2024-08-01 12:13:06,399][00719] Avg episode reward: 20.250, avg true_objective: 9.583
+[2024-08-01 12:13:06,445][00719] Num frames 2900...
+[2024-08-01 12:13:06,615][00719] Num frames 3000...
+[2024-08-01 12:13:06,770][00719] Num frames 3100...
+[2024-08-01 12:13:06,896][00719] Num frames 3200...
+[2024-08-01 12:13:07,026][00719] Num frames 3300...
+[2024-08-01 12:13:07,145][00719] Num frames 3400...
+[2024-08-01 12:13:07,269][00719] Num frames 3500...
+[2024-08-01 12:13:07,391][00719] Num frames 3600...
+[2024-08-01 12:13:07,512][00719] Num frames 3700...
+[2024-08-01 12:13:07,638][00719] Num frames 3800...
+[2024-08-01 12:13:07,764][00719] Num frames 3900...
+[2024-08-01 12:13:07,894][00719] Num frames 4000...
+[2024-08-01 12:13:08,026][00719] Num frames 4100...
+[2024-08-01 12:13:08,147][00719] Avg episode rewards: #0: 21.638, true rewards: #0: 10.387
+[2024-08-01 12:13:08,149][00719] Avg episode reward: 21.638, avg true_objective: 10.387
+[2024-08-01 12:13:08,206][00719] Num frames 4200...
+[2024-08-01 12:13:08,332][00719] Num frames 4300...
+[2024-08-01 12:13:08,456][00719] Num frames 4400...
+[2024-08-01 12:13:08,575][00719] Num frames 4500...
+[2024-08-01 12:13:08,695][00719] Num frames 4600...
+[2024-08-01 12:13:08,819][00719] Num frames 4700...
+[2024-08-01 12:13:08,946][00719] Num frames 4800...
+[2024-08-01 12:13:09,075][00719] Num frames 4900...
+[2024-08-01 12:13:09,159][00719] Avg episode rewards: #0: 19.846, true rewards: #0: 9.846
+[2024-08-01 12:13:09,160][00719] Avg episode reward: 19.846, avg true_objective: 9.846
+[2024-08-01 12:13:09,257][00719] Num frames 5000...
+[2024-08-01 12:13:09,376][00719] Num frames 5100...
+[2024-08-01 12:13:09,501][00719] Num frames 5200...
+[2024-08-01 12:13:09,621][00719] Num frames 5300...
+[2024-08-01 12:13:09,726][00719] Avg episode rewards: #0: 17.565, true rewards: #0: 8.898
+[2024-08-01 12:13:09,728][00719] Avg episode reward: 17.565, avg true_objective: 8.898
+[2024-08-01 12:13:09,806][00719] Num frames 5400...
+[2024-08-01 12:13:09,939][00719] Num frames 5500...
+[2024-08-01 12:13:10,071][00719] Num frames 5600...
+[2024-08-01 12:13:10,195][00719] Num frames 5700...
+[2024-08-01 12:13:10,318][00719] Num frames 5800...
+[2024-08-01 12:13:10,445][00719] Num frames 5900...
+[2024-08-01 12:13:10,569][00719] Num frames 6000...
+[2024-08-01 12:13:10,693][00719] Num frames 6100...
+[2024-08-01 12:13:10,822][00719] Num frames 6200...
+[2024-08-01 12:13:10,953][00719] Num frames 6300...
+[2024-08-01 12:13:11,082][00719] Num frames 6400...
+[2024-08-01 12:13:11,204][00719] Num frames 6500...
+[2024-08-01 12:13:11,327][00719] Num frames 6600...
+[2024-08-01 12:13:11,451][00719] Num frames 6700...
+[2024-08-01 12:13:11,576][00719] Num frames 6800...
+[2024-08-01 12:13:11,700][00719] Num frames 6900...
+[2024-08-01 12:13:11,826][00719] Num frames 7000...
+[2024-08-01 12:13:11,960][00719] Num frames 7100...
+[2024-08-01 12:13:12,092][00719] Num frames 7200...
+[2024-08-01 12:13:12,217][00719] Num frames 7300...
+[2024-08-01 12:13:12,295][00719] Avg episode rewards: #0: 21.596, true rewards: #0: 10.453
+[2024-08-01 12:13:12,297][00719] Avg episode reward: 21.596, avg true_objective: 10.453
+[2024-08-01 12:13:12,401][00719] Num frames 7400...
+[2024-08-01 12:13:12,526][00719] Num frames 7500...
+[2024-08-01 12:13:12,647][00719] Num frames 7600...
+[2024-08-01 12:13:12,768][00719] Num frames 7700...
+[2024-08-01 12:13:12,899][00719] Num frames 7800...
+[2024-08-01 12:13:13,024][00719] Num frames 7900...
+[2024-08-01 12:13:13,152][00719] Num frames 8000...
+[2024-08-01 12:13:13,257][00719] Avg episode rewards: #0: 20.675, true rewards: #0: 10.050
+[2024-08-01 12:13:13,259][00719] Avg episode reward: 20.675, avg true_objective: 10.050
+[2024-08-01 12:13:13,333][00719] Num frames 8100...
+[2024-08-01 12:13:13,456][00719] Num frames 8200...
+[2024-08-01 12:13:13,582][00719] Num frames 8300...
+[2024-08-01 12:13:13,702][00719] Num frames 8400...
+[2024-08-01 12:13:13,823][00719] Num frames 8500...
+[2024-08-01 12:13:13,951][00719] Num frames 8600...
+[2024-08-01 12:13:14,069][00719] Num frames 8700...
+[2024-08-01 12:13:14,198][00719] Num frames 8800...
+[2024-08-01 12:13:14,322][00719] Num frames 8900...
+[2024-08-01 12:13:14,445][00719] Num frames 9000...
+[2024-08-01 12:13:14,569][00719] Num frames 9100...
+[2024-08-01 12:13:14,700][00719] Num frames 9200...
+[2024-08-01 12:13:14,834][00719] Num frames 9300...
+[2024-08-01 12:13:14,964][00719] Num frames 9400...
+[2024-08-01 12:13:15,040][00719] Avg episode rewards: #0: 21.684, true rewards: #0: 10.462
+[2024-08-01 12:13:15,042][00719] Avg episode reward: 21.684, avg true_objective: 10.462
+[2024-08-01 12:13:15,154][00719] Num frames 9500...
+[2024-08-01 12:13:15,275][00719] Num frames 9600...
+[2024-08-01 12:13:15,395][00719] Num frames 9700...
+[2024-08-01 12:13:15,521][00719] Num frames 9800...
+[2024-08-01 12:13:15,642][00719] Num frames 9900...
+[2024-08-01 12:13:15,768][00719] Num frames 10000...
+[2024-08-01 12:13:15,899][00719] Num frames 10100...
+[2024-08-01 12:13:16,018][00719] Avg episode rewards: #0: 20.852, true rewards: #0: 10.152
+[2024-08-01 12:13:16,020][00719] Avg episode reward: 20.852, avg true_objective: 10.152
+[2024-08-01 12:14:12,911][00719] Replay video saved to /content/train_dir/default_experiment/replay.mp4!