Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1739519280.aa19c74a8cf4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a09c858348ab343e70da7be86efdda16e7e7af721596e6f602377e1d06b9f388
+size 192893

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 9.44 +/- 4.58
+      value: 11.94 +/- 5.03
       name: mean_reward
       verified: false
 ---

checkpoint_p0/best_000001210_4956160_reward_29.554.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a65f556b44715eff601c370ac38110d08eeaaa07abe6b5e8ffa79cd58c76bd3a
+size 34929243

checkpoint_p0/checkpoint_000001180_4833280.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dda48ade5117adad6d1284ff811afcfda5d3d8dbc998a127db452956ea14b1d4
+size 34929669

checkpoint_p0/checkpoint_000001222_5005312.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13123f6b62115d0efeb7a078d61fafd767e094579923a0cdd0a12558a54a669b
+size 34929669

config.json

@@ -65,7 +65,7 @@
   "summaries_use_frameskip": true,
   "heartbeat_interval": 20,
   "heartbeat_reporting_interval": 600,
-  "train_for_env_steps": 4000000,
+  "train_for_env_steps": 5000000,
   "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:faa5d7fc9add684655501f42e9e3e1401ee1437f9a1fd9ce0d37e303964b6f57
-size 17960113
+oid sha256:894fe29a891f802a279687a7ee5c9977efa14e2fb32442e454b45a53242947c8
+size 23102686

sf_log.txt

@@ -1070,3 +1070,838 @@ main_loop: 1042.0112
 [2025-02-14 07:43:43,685][00436] Avg episode rewards: #0: 21.437, true rewards: #0: 9.437
 [2025-02-14 07:43:43,686][00436] Avg episode reward: 21.437, avg true_objective: 9.437
 [2025-02-14 07:44:38,128][00436] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2025-02-14 07:44:42,755][00436] The model has been pushed to https://huggingface.co/gyaan/rl_course_vizdoom_health_gathering_supreme
+[2025-02-14 07:48:00,387][00436] Environment doom_basic already registered, overwriting...
+[2025-02-14 07:48:00,389][00436] Environment doom_two_colors_easy already registered, overwriting...
+[2025-02-14 07:48:00,391][00436] Environment doom_two_colors_hard already registered, overwriting...
+[2025-02-14 07:48:00,393][00436] Environment doom_dm already registered, overwriting...
+[2025-02-14 07:48:00,398][00436] Environment doom_dwango5 already registered, overwriting...
+[2025-02-14 07:48:00,399][00436] Environment doom_my_way_home_flat_actions already registered, overwriting...
+[2025-02-14 07:48:00,400][00436] Environment doom_defend_the_center_flat_actions already registered, overwriting...
+[2025-02-14 07:48:00,401][00436] Environment doom_my_way_home already registered, overwriting...
+[2025-02-14 07:48:00,405][00436] Environment doom_deadly_corridor already registered, overwriting...
+[2025-02-14 07:48:00,406][00436] Environment doom_defend_the_center already registered, overwriting...
+[2025-02-14 07:48:00,407][00436] Environment doom_defend_the_line already registered, overwriting...
+[2025-02-14 07:48:00,408][00436] Environment doom_health_gathering already registered, overwriting...
+[2025-02-14 07:48:00,409][00436] Environment doom_health_gathering_supreme already registered, overwriting...
+[2025-02-14 07:48:00,413][00436] Environment doom_battle already registered, overwriting...
+[2025-02-14 07:48:00,414][00436] Environment doom_battle2 already registered, overwriting...
+[2025-02-14 07:48:00,415][00436] Environment doom_duel_bots already registered, overwriting...
+[2025-02-14 07:48:00,416][00436] Environment doom_deathmatch_bots already registered, overwriting...
+[2025-02-14 07:48:00,417][00436] Environment doom_duel already registered, overwriting...
+[2025-02-14 07:48:00,417][00436] Environment doom_deathmatch_full already registered, overwriting...
+[2025-02-14 07:48:00,418][00436] Environment doom_benchmark already registered, overwriting...
+[2025-02-14 07:48:00,419][00436] register_encoder_factory: <function make_vizdoom_encoder at 0x790af59fec00>
+[2025-02-14 07:48:00,444][00436] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2025-02-14 07:48:00,453][00436] Overriding arg 'train_for_env_steps' with value 5000000 passed from command line
+[2025-02-14 07:48:00,465][00436] Experiment dir /content/train_dir/default_experiment already exists!
+[2025-02-14 07:48:00,467][00436] Resuming existing experiment from /content/train_dir/default_experiment...
+[2025-02-14 07:48:00,468][00436] Weights and Biases integration disabled
+[2025-02-14 07:48:00,473][00436] Environment var CUDA_VISIBLE_DEVICES is 0
+
+[2025-02-14 07:48:03,692][00436] 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=5000000
+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
+[2025-02-14 07:48:03,694][00436] Saving configuration to /content/train_dir/default_experiment/config.json...
+[2025-02-14 07:48:03,696][00436] Rollout worker 0 uses device cpu
+[2025-02-14 07:48:03,699][00436] Rollout worker 1 uses device cpu
+[2025-02-14 07:48:03,701][00436] Rollout worker 2 uses device cpu
+[2025-02-14 07:48:03,702][00436] Rollout worker 3 uses device cpu
+[2025-02-14 07:48:03,703][00436] Rollout worker 4 uses device cpu
+[2025-02-14 07:48:03,710][00436] Rollout worker 5 uses device cpu
+[2025-02-14 07:48:03,712][00436] Rollout worker 6 uses device cpu
+[2025-02-14 07:48:03,713][00436] Rollout worker 7 uses device cpu
+[2025-02-14 07:48:03,787][00436] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-02-14 07:48:03,790][00436] InferenceWorker_p0-w0: min num requests: 2
+[2025-02-14 07:48:03,821][00436] Starting all processes...
+[2025-02-14 07:48:03,822][00436] Starting process learner_proc0
+[2025-02-14 07:48:03,886][00436] Starting all processes...
+[2025-02-14 07:48:03,898][00436] Starting process inference_proc0-0
+[2025-02-14 07:48:03,898][00436] Starting process rollout_proc0
+[2025-02-14 07:48:03,899][00436] Starting process rollout_proc1
+[2025-02-14 07:48:03,899][00436] Starting process rollout_proc2
+[2025-02-14 07:48:03,900][00436] Starting process rollout_proc3
+[2025-02-14 07:48:03,900][00436] Starting process rollout_proc4
+[2025-02-14 07:48:03,901][00436] Starting process rollout_proc5
+[2025-02-14 07:48:03,903][00436] Starting process rollout_proc6
+[2025-02-14 07:48:03,903][00436] Starting process rollout_proc7
+[2025-02-14 07:48:19,194][13629] Worker 4 uses CPU cores [0]
+[2025-02-14 07:48:19,300][13627] Worker 2 uses CPU cores [0]
+[2025-02-14 07:48:19,403][13631] Worker 6 uses CPU cores [0]
+[2025-02-14 07:48:19,410][13630] Worker 5 uses CPU cores [1]
+[2025-02-14 07:48:19,419][13626] Worker 1 uses CPU cores [1]
+[2025-02-14 07:48:19,511][13607] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-02-14 07:48:19,512][13607] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2025-02-14 07:48:19,524][13632] Worker 7 uses CPU cores [1]
+[2025-02-14 07:48:19,540][13624] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-02-14 07:48:19,541][13624] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2025-02-14 07:48:19,565][13624] Num visible devices: 1
+[2025-02-14 07:48:19,566][13607] Num visible devices: 1
+[2025-02-14 07:48:19,575][13628] Worker 3 uses CPU cores [1]
+[2025-02-14 07:48:19,579][13607] Starting seed is not provided
+[2025-02-14 07:48:19,579][13607] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-02-14 07:48:19,579][13607] Initializing actor-critic model on device cuda:0
+[2025-02-14 07:48:19,580][13607] RunningMeanStd input shape: (3, 72, 128)
+[2025-02-14 07:48:19,581][13607] RunningMeanStd input shape: (1,)
+[2025-02-14 07:48:19,592][13625] Worker 0 uses CPU cores [0]
+[2025-02-14 07:48:19,600][13607] ConvEncoder: input_channels=3
+[2025-02-14 07:48:19,718][13607] Conv encoder output size: 512
+[2025-02-14 07:48:19,718][13607] Policy head output size: 512
+[2025-02-14 07:48:19,734][13607] Created Actor Critic model with architecture:
+[2025-02-14 07:48:19,734][13607] 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)
+  )
+)
+[2025-02-14 07:48:19,858][13607] Using optimizer <class 'torch.optim.adam.Adam'>
+[2025-02-14 07:48:21,021][13607] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2025-02-14 07:48:21,059][13607] Loading model from checkpoint
+[2025-02-14 07:48:21,061][13607] Loaded experiment state at self.train_step=978, self.env_steps=4005888
+[2025-02-14 07:48:21,061][13607] Initialized policy 0 weights for model version 978
+[2025-02-14 07:48:21,063][13607] LearnerWorker_p0 finished initialization!
+[2025-02-14 07:48:21,064][13607] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-02-14 07:48:21,190][13624] RunningMeanStd input shape: (3, 72, 128)
+[2025-02-14 07:48:21,192][13624] RunningMeanStd input shape: (1,)
+[2025-02-14 07:48:21,204][13624] ConvEncoder: input_channels=3
+[2025-02-14 07:48:21,305][13624] Conv encoder output size: 512
+[2025-02-14 07:48:21,305][13624] Policy head output size: 512
+[2025-02-14 07:48:21,343][00436] Inference worker 0-0 is ready!
+[2025-02-14 07:48:21,344][00436] All inference workers are ready! Signal rollout workers to start!
+[2025-02-14 07:48:21,595][13629] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-02-14 07:48:21,670][13631] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-02-14 07:48:21,668][13628] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-02-14 07:48:21,675][13632] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-02-14 07:48:21,697][13625] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-02-14 07:48:21,723][13630] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-02-14 07:48:21,740][13627] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-02-14 07:48:21,774][13626] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-02-14 07:48:23,118][13628] Decorrelating experience for 0 frames...
+[2025-02-14 07:48:23,114][13632] Decorrelating experience for 0 frames...
+[2025-02-14 07:48:23,593][13629] Decorrelating experience for 0 frames...
+[2025-02-14 07:48:23,632][13631] Decorrelating experience for 0 frames...
+[2025-02-14 07:48:23,653][13625] Decorrelating experience for 0 frames...
+[2025-02-14 07:48:23,673][13627] Decorrelating experience for 0 frames...
+[2025-02-14 07:48:23,779][00436] Heartbeat connected on Batcher_0
+[2025-02-14 07:48:23,784][00436] Heartbeat connected on LearnerWorker_p0
+[2025-02-14 07:48:23,814][00436] Heartbeat connected on InferenceWorker_p0-w0
+[2025-02-14 07:48:24,111][13632] Decorrelating experience for 32 frames...
+[2025-02-14 07:48:24,201][13630] Decorrelating experience for 0 frames...
+[2025-02-14 07:48:24,527][13631] Decorrelating experience for 32 frames...
+[2025-02-14 07:48:24,597][13627] Decorrelating experience for 32 frames...
+[2025-02-14 07:48:24,801][13628] Decorrelating experience for 32 frames...
+[2025-02-14 07:48:25,297][13625] Decorrelating experience for 32 frames...
+[2025-02-14 07:48:25,301][13626] Decorrelating experience for 0 frames...
+[2025-02-14 07:48:25,473][00436] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 4005888. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2025-02-14 07:48:26,119][13630] Decorrelating experience for 32 frames...
+[2025-02-14 07:48:26,149][13631] Decorrelating experience for 64 frames...
+[2025-02-14 07:48:26,748][13628] Decorrelating experience for 64 frames...
+[2025-02-14 07:48:26,998][13632] Decorrelating experience for 64 frames...
+[2025-02-14 07:48:27,257][13629] Decorrelating experience for 32 frames...
+[2025-02-14 07:48:27,730][13625] Decorrelating experience for 64 frames...
+[2025-02-14 07:48:28,211][13630] Decorrelating experience for 64 frames...
+[2025-02-14 07:48:28,218][13627] Decorrelating experience for 64 frames...
+[2025-02-14 07:48:28,639][13628] Decorrelating experience for 96 frames...
+[2025-02-14 07:48:29,022][00436] Heartbeat connected on RolloutWorker_w3
+[2025-02-14 07:48:29,138][13631] Decorrelating experience for 96 frames...
+[2025-02-14 07:48:29,793][00436] Heartbeat connected on RolloutWorker_w6
+[2025-02-14 07:48:30,180][13629] Decorrelating experience for 64 frames...
+[2025-02-14 07:48:30,291][13632] Decorrelating experience for 96 frames...
+[2025-02-14 07:48:30,301][13626] Decorrelating experience for 32 frames...
+[2025-02-14 07:48:30,421][13625] Decorrelating experience for 96 frames...
+[2025-02-14 07:48:30,473][00436] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4005888. Throughput: 0: 12.0. Samples: 60. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2025-02-14 07:48:30,600][00436] Heartbeat connected on RolloutWorker_w7
+[2025-02-14 07:48:30,889][00436] Heartbeat connected on RolloutWorker_w0
+[2025-02-14 07:48:31,876][13627] Decorrelating experience for 96 frames...
+[2025-02-14 07:48:32,485][00436] Heartbeat connected on RolloutWorker_w2
+[2025-02-14 07:48:32,744][13630] Decorrelating experience for 96 frames...
+[2025-02-14 07:48:33,274][00436] Heartbeat connected on RolloutWorker_w5
+[2025-02-14 07:48:33,899][13626] Decorrelating experience for 64 frames...
+[2025-02-14 07:48:34,563][13607] Signal inference workers to stop experience collection...
+[2025-02-14 07:48:34,588][13624] InferenceWorker_p0-w0: stopping experience collection
+[2025-02-14 07:48:35,005][13626] Decorrelating experience for 96 frames...
+[2025-02-14 07:48:35,045][13629] Decorrelating experience for 96 frames...
+[2025-02-14 07:48:35,127][00436] Heartbeat connected on RolloutWorker_w4
+[2025-02-14 07:48:35,173][00436] Heartbeat connected on RolloutWorker_w1
+[2025-02-14 07:48:35,473][00436] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4005888. Throughput: 0: 179.2. Samples: 1792. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2025-02-14 07:48:35,485][00436] Avg episode reward: [(0, '5.519')]
+[2025-02-14 07:48:35,556][13607] Signal inference workers to resume experience collection...
+[2025-02-14 07:48:35,557][13624] InferenceWorker_p0-w0: resuming experience collection
+[2025-02-14 07:48:40,474][00436] Fps is (10 sec: 2457.5, 60 sec: 1638.4, 300 sec: 1638.4). Total num frames: 4030464. Throughput: 0: 439.6. Samples: 6594. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-02-14 07:48:40,476][00436] Avg episode reward: [(0, '10.389')]
+[2025-02-14 07:48:45,001][13624] Updated weights for policy 0, policy_version 988 (0.0027)
+[2025-02-14 07:48:45,473][00436] Fps is (10 sec: 4096.0, 60 sec: 2048.0, 300 sec: 2048.0). Total num frames: 4046848. Throughput: 0: 561.5. Samples: 11230. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2025-02-14 07:48:45,480][00436] Avg episode reward: [(0, '14.393')]
+[2025-02-14 07:48:50,473][00436] Fps is (10 sec: 4096.1, 60 sec: 2621.4, 300 sec: 2621.4). Total num frames: 4071424. Throughput: 0: 590.2. Samples: 14756. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-02-14 07:48:50,478][00436] Avg episode reward: [(0, '16.854')]
+[2025-02-14 07:48:54,104][13624] Updated weights for policy 0, policy_version 998 (0.0029)
+[2025-02-14 07:48:55,474][00436] Fps is (10 sec: 4505.4, 60 sec: 2867.2, 300 sec: 2867.2). Total num frames: 4091904. Throughput: 0: 706.3. Samples: 21188. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-02-14 07:48:55,478][00436] Avg episode reward: [(0, '17.677')]
+[2025-02-14 07:49:00,473][00436] Fps is (10 sec: 3276.8, 60 sec: 2808.7, 300 sec: 2808.7). Total num frames: 4104192. Throughput: 0: 737.3. Samples: 25804. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2025-02-14 07:49:00,478][00436] Avg episode reward: [(0, '19.975')]
+[2025-02-14 07:49:05,091][13624] Updated weights for policy 0, policy_version 1008 (0.0021)
+[2025-02-14 07:49:05,473][00436] Fps is (10 sec: 3686.6, 60 sec: 3072.0, 300 sec: 3072.0). Total num frames: 4128768. Throughput: 0: 731.0. Samples: 29238. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2025-02-14 07:49:05,479][00436] Avg episode reward: [(0, '22.568')]
+[2025-02-14 07:49:10,473][00436] Fps is (10 sec: 4505.6, 60 sec: 3185.8, 300 sec: 3185.8). Total num frames: 4149248. Throughput: 0: 804.5. Samples: 36204. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-02-14 07:49:10,477][00436] Avg episode reward: [(0, '25.940')]
+[2025-02-14 07:49:15,473][00436] Fps is (10 sec: 3686.4, 60 sec: 3194.9, 300 sec: 3194.9). Total num frames: 4165632. Throughput: 0: 907.2. Samples: 40886. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-02-14 07:49:15,480][00436] Avg episode reward: [(0, '26.159')]
+[2025-02-14 07:49:16,080][13624] Updated weights for policy 0, policy_version 1018 (0.0026)
+[2025-02-14 07:49:20,473][00436] Fps is (10 sec: 4096.0, 60 sec: 3351.3, 300 sec: 3351.3). Total num frames: 4190208. Throughput: 0: 946.0. Samples: 44364. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-02-14 07:49:20,482][00436] Avg episode reward: [(0, '28.399')]
+[2025-02-14 07:49:20,489][13607] Saving new best policy, reward=28.399!
+[2025-02-14 07:49:24,782][13624] Updated weights for policy 0, policy_version 1028 (0.0015)
+[2025-02-14 07:49:25,476][00436] Fps is (10 sec: 4504.4, 60 sec: 3413.2, 300 sec: 3413.2). Total num frames: 4210688. Throughput: 0: 993.7. Samples: 51312. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-02-14 07:49:25,484][00436] Avg episode reward: [(0, '29.158')]
+[2025-02-14 07:49:25,486][13607] Saving new best policy, reward=29.158!
+[2025-02-14 07:49:30,473][00436] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3339.8). Total num frames: 4222976. Throughput: 0: 987.0. Samples: 55646. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-02-14 07:49:30,475][00436] Avg episode reward: [(0, '27.438')]
+[2025-02-14 07:49:35,473][00436] Fps is (10 sec: 3687.4, 60 sec: 4027.7, 300 sec: 3452.3). Total num frames: 4247552. Throughput: 0: 983.4. Samples: 59008. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-02-14 07:49:35,480][00436] Avg episode reward: [(0, '26.877')]
+[2025-02-14 07:49:35,970][13624] Updated weights for policy 0, policy_version 1038 (0.0012)
+[2025-02-14 07:49:40,474][00436] Fps is (10 sec: 4505.4, 60 sec: 3959.5, 300 sec: 3495.2). Total num frames: 4268032. Throughput: 0: 993.6. Samples: 65898. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-02-14 07:49:40,476][00436] Avg episode reward: [(0, '25.331')]
+[2025-02-14 07:49:45,473][00436] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3481.6). Total num frames: 4284416. Throughput: 0: 993.7. Samples: 70522. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-02-14 07:49:45,476][00436] Avg episode reward: [(0, '25.188')]
+[2025-02-14 07:49:46,752][13624] Updated weights for policy 0, policy_version 1048 (0.0015)
+[2025-02-14 07:49:50,473][00436] Fps is (10 sec: 4096.2, 60 sec: 3959.5, 300 sec: 3565.9). Total num frames: 4308992. Throughput: 0: 996.2. Samples: 74068. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2025-02-14 07:49:50,478][00436] Avg episode reward: [(0, '24.083')]
+[2025-02-14 07:49:55,476][00436] Fps is (10 sec: 4504.5, 60 sec: 3959.3, 300 sec: 3595.3). Total num frames: 4329472. Throughput: 0: 998.6. Samples: 81144. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2025-02-14 07:49:55,480][00436] Avg episode reward: [(0, '25.341')]
+[2025-02-14 07:49:56,023][13624] Updated weights for policy 0, policy_version 1058 (0.0014)
+[2025-02-14 07:50:00,477][00436] Fps is (10 sec: 3685.1, 60 sec: 4027.5, 300 sec: 3578.5). Total num frames: 4345856. Throughput: 0: 992.5. Samples: 85552. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-02-14 07:50:00,486][00436] Avg episode reward: [(0, '25.838')]
+[2025-02-14 07:50:00,498][13607] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001061_4345856.pth...
+[2025-02-14 07:50:00,627][13607] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000894_3661824.pth
+[2025-02-14 07:50:05,473][00436] Fps is (10 sec: 3687.3, 60 sec: 3959.5, 300 sec: 3604.5). Total num frames: 4366336. Throughput: 0: 989.3. Samples: 88882. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-02-14 07:50:05,480][00436] Avg episode reward: [(0, '25.862')]
+[2025-02-14 07:50:06,789][13624] Updated weights for policy 0, policy_version 1068 (0.0016)
+[2025-02-14 07:50:10,475][00436] Fps is (10 sec: 4506.4, 60 sec: 4027.6, 300 sec: 3666.8). Total num frames: 4390912. Throughput: 0: 987.1. Samples: 95732. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-02-14 07:50:10,478][00436] Avg episode reward: [(0, '27.260')]
+[2025-02-14 07:50:15,473][00436] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3611.9). Total num frames: 4403200. Throughput: 0: 994.1. Samples: 100382. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-02-14 07:50:15,480][00436] Avg episode reward: [(0, '26.786')]
+[2025-02-14 07:50:17,519][13624] Updated weights for policy 0, policy_version 1078 (0.0023)
+[2025-02-14 07:50:20,473][00436] Fps is (10 sec: 3687.0, 60 sec: 3959.5, 300 sec: 3668.6). Total num frames: 4427776. Throughput: 0: 997.2. Samples: 103884. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-02-14 07:50:20,478][00436] Avg episode reward: [(0, '26.185')]
+[2025-02-14 07:50:25,473][00436] Fps is (10 sec: 4505.6, 60 sec: 3959.6, 300 sec: 3686.4). Total num frames: 4448256. Throughput: 0: 996.1. Samples: 110720. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-02-14 07:50:25,479][00436] Avg episode reward: [(0, '25.814')]
+[2025-02-14 07:50:27,557][13624] Updated weights for policy 0, policy_version 1088 (0.0013)
+[2025-02-14 07:50:30,473][00436] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3637.2). Total num frames: 4460544. Throughput: 0: 991.2. Samples: 115124. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-02-14 07:50:30,476][00436] Avg episode reward: [(0, '25.918')]
+[2025-02-14 07:50:35,473][00436] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3686.4). Total num frames: 4485120. Throughput: 0: 985.7. Samples: 118424. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-02-14 07:50:35,476][00436] Avg episode reward: [(0, '24.770')]
+[2025-02-14 07:50:37,525][13624] Updated weights for policy 0, policy_version 1098 (0.0015)
+[2025-02-14 07:50:40,473][00436] Fps is (10 sec: 4915.2, 60 sec: 4027.8, 300 sec: 3731.9). Total num frames: 4509696. Throughput: 0: 986.2. Samples: 125520. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-02-14 07:50:40,476][00436] Avg episode reward: [(0, '24.364')]
+[2025-02-14 07:50:45,474][00436] Fps is (10 sec: 3686.3, 60 sec: 3959.4, 300 sec: 3686.4). Total num frames: 4521984. Throughput: 0: 997.4. Samples: 130434. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-02-14 07:50:45,482][00436] Avg episode reward: [(0, '24.075')]
+[2025-02-14 07:50:48,142][13624] Updated weights for policy 0, policy_version 1108 (0.0026)
+[2025-02-14 07:50:50,473][00436] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3728.8). Total num frames: 4546560. Throughput: 0: 999.6. Samples: 133866. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2025-02-14 07:50:50,475][00436] Avg episode reward: [(0, '23.896')]
+[2025-02-14 07:50:55,473][00436] Fps is (10 sec: 4915.4, 60 sec: 4027.9, 300 sec: 3768.3). Total num frames: 4571136. Throughput: 0: 1006.4. Samples: 141018. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-02-14 07:50:55,478][00436] Avg episode reward: [(0, '24.519')]
+[2025-02-14 07:50:57,741][13624] Updated weights for policy 0, policy_version 1118 (0.0015)
+[2025-02-14 07:51:00,475][00436] Fps is (10 sec: 3685.9, 60 sec: 3959.6, 300 sec: 3726.0). Total num frames: 4583424. Throughput: 0: 1009.6. Samples: 145816. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-02-14 07:51:00,482][00436] Avg episode reward: [(0, '25.762')]
+[2025-02-14 07:51:05,473][00436] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3763.2). Total num frames: 4608000. Throughput: 0: 1009.6. Samples: 149316. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2025-02-14 07:51:05,476][00436] Avg episode reward: [(0, '26.854')]
+[2025-02-14 07:51:07,433][13624] Updated weights for policy 0, policy_version 1128 (0.0021)
+[2025-02-14 07:51:10,473][00436] Fps is (10 sec: 4915.9, 60 sec: 4027.8, 300 sec: 3798.1). Total num frames: 4632576. Throughput: 0: 1016.5. Samples: 156464. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-02-14 07:51:10,475][00436] Avg episode reward: [(0, '26.332')]
+[2025-02-14 07:51:15,473][00436] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3758.7). Total num frames: 4644864. Throughput: 0: 1027.6. Samples: 161368. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-02-14 07:51:15,476][00436] Avg episode reward: [(0, '25.744')]
+[2025-02-14 07:51:18,084][13624] Updated weights for policy 0, policy_version 1138 (0.0020)
+[2025-02-14 07:51:20,474][00436] Fps is (10 sec: 3686.3, 60 sec: 4027.7, 300 sec: 3791.7). Total num frames: 4669440. Throughput: 0: 1031.1. Samples: 164824. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-02-14 07:51:20,478][00436] Avg episode reward: [(0, '26.056')]
+[2025-02-14 07:51:25,473][00436] Fps is (10 sec: 4915.2, 60 sec: 4096.0, 300 sec: 3822.9). Total num frames: 4694016. Throughput: 0: 1032.4. Samples: 171980. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-02-14 07:51:25,475][00436] Avg episode reward: [(0, '24.355')]
+[2025-02-14 07:51:27,589][13624] Updated weights for policy 0, policy_version 1148 (0.0018)
+[2025-02-14 07:51:30,477][00436] Fps is (10 sec: 3685.2, 60 sec: 4095.8, 300 sec: 3786.0). Total num frames: 4706304. Throughput: 0: 1028.2. Samples: 176708. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-02-14 07:51:30,482][00436] Avg episode reward: [(0, '24.539')]
+[2025-02-14 07:51:35,473][00436] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 3815.7). Total num frames: 4730880. Throughput: 0: 1027.6. Samples: 180106. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-02-14 07:51:35,476][00436] Avg episode reward: [(0, '24.743')]
+[2025-02-14 07:51:37,471][13624] Updated weights for policy 0, policy_version 1158 (0.0018)
+[2025-02-14 07:51:40,474][00436] Fps is (10 sec: 4916.7, 60 sec: 4096.0, 300 sec: 3843.9). Total num frames: 4755456. Throughput: 0: 1028.2. Samples: 187286. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-02-14 07:51:40,477][00436] Avg episode reward: [(0, '26.191')]
+[2025-02-14 07:51:45,473][00436] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 3809.3). Total num frames: 4767744. Throughput: 0: 1028.9. Samples: 192116. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-02-14 07:51:45,476][00436] Avg episode reward: [(0, '26.387')]
+[2025-02-14 07:51:48,010][13624] Updated weights for policy 0, policy_version 1168 (0.0017)
+[2025-02-14 07:51:50,473][00436] Fps is (10 sec: 3686.6, 60 sec: 4096.0, 300 sec: 3836.3). Total num frames: 4792320. Throughput: 0: 1029.6. Samples: 195648. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-02-14 07:51:50,476][00436] Avg episode reward: [(0, '26.799')]
+[2025-02-14 07:51:55,473][00436] Fps is (10 sec: 4915.2, 60 sec: 4096.0, 300 sec: 3861.9). Total num frames: 4816896. Throughput: 0: 1028.6. Samples: 202750. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2025-02-14 07:51:55,477][00436] Avg episode reward: [(0, '26.529')]
+[2025-02-14 07:51:57,355][13624] Updated weights for policy 0, policy_version 1178 (0.0024)
+[2025-02-14 07:52:00,473][00436] Fps is (10 sec: 3686.4, 60 sec: 4096.1, 300 sec: 3829.3). Total num frames: 4829184. Throughput: 0: 1025.3. Samples: 207506. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-02-14 07:52:00,478][00436] Avg episode reward: [(0, '27.132')]
+[2025-02-14 07:52:00,518][13607] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001180_4833280.pth...
+[2025-02-14 07:52:00,666][13607] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth
+[2025-02-14 07:52:05,473][00436] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 3854.0). Total num frames: 4853760. Throughput: 0: 1021.8. Samples: 210804. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-02-14 07:52:05,476][00436] Avg episode reward: [(0, '27.476')]
+[2025-02-14 07:52:07,449][13624] Updated weights for policy 0, policy_version 1188 (0.0027)
+[2025-02-14 07:52:10,473][00436] Fps is (10 sec: 4915.2, 60 sec: 4096.0, 300 sec: 3877.5). Total num frames: 4878336. Throughput: 0: 1019.9. Samples: 217874. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-02-14 07:52:10,476][00436] Avg episode reward: [(0, '27.026')]
+[2025-02-14 07:52:15,473][00436] Fps is (10 sec: 4096.0, 60 sec: 4164.3, 300 sec: 3864.5). Total num frames: 4894720. Throughput: 0: 1020.7. Samples: 222634. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2025-02-14 07:52:15,477][00436] Avg episode reward: [(0, '26.811')]
+[2025-02-14 07:52:18,001][13624] Updated weights for policy 0, policy_version 1198 (0.0015)
+[2025-02-14 07:52:20,473][00436] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 3869.4). Total num frames: 4915200. Throughput: 0: 1023.9. Samples: 226182. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2025-02-14 07:52:20,483][00436] Avg episode reward: [(0, '28.712')]
+[2025-02-14 07:52:25,475][00436] Fps is (10 sec: 4504.7, 60 sec: 4095.9, 300 sec: 3891.2). Total num frames: 4939776. Throughput: 0: 1023.5. Samples: 233344. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2025-02-14 07:52:25,482][00436] Avg episode reward: [(0, '29.438')]
+[2025-02-14 07:52:25,487][13607] Saving new best policy, reward=29.438!
+[2025-02-14 07:52:27,425][13624] Updated weights for policy 0, policy_version 1208 (0.0013)
+[2025-02-14 07:52:30,473][00436] Fps is (10 sec: 4096.0, 60 sec: 4164.5, 300 sec: 3878.7). Total num frames: 4956160. Throughput: 0: 1018.7. Samples: 237956. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2025-02-14 07:52:30,479][00436] Avg episode reward: [(0, '29.554')]
+[2025-02-14 07:52:30,492][13607] Saving new best policy, reward=29.554!
+[2025-02-14 07:52:35,473][00436] Fps is (10 sec: 3687.1, 60 sec: 4096.0, 300 sec: 3883.0). Total num frames: 4976640. Throughput: 0: 1014.8. Samples: 241316. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-02-14 07:52:35,480][00436] Avg episode reward: [(0, '29.219')]
+[2025-02-14 07:52:37,506][13624] Updated weights for policy 0, policy_version 1218 (0.0022)
+[2025-02-14 07:52:40,473][00436] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 3903.2). Total num frames: 5001216. Throughput: 0: 1016.5. Samples: 248492. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-02-14 07:52:40,476][00436] Avg episode reward: [(0, '28.054')]
+[2025-02-14 07:52:41,361][13607] Stopping Batcher_0...
+[2025-02-14 07:52:41,365][00436] Component Batcher_0 stopped!
+[2025-02-14 07:52:41,367][13607] Loop batcher_evt_loop terminating...
+[2025-02-14 07:52:41,373][13607] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001222_5005312.pth...
+[2025-02-14 07:52:41,467][13624] Weights refcount: 2 0
+[2025-02-14 07:52:41,479][00436] Component InferenceWorker_p0-w0 stopped!
+[2025-02-14 07:52:41,483][13624] Stopping InferenceWorker_p0-w0...
+[2025-02-14 07:52:41,483][13624] Loop inference_proc0-0_evt_loop terminating...
+[2025-02-14 07:52:41,548][13607] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001061_4345856.pth
+[2025-02-14 07:52:41,575][13607] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001222_5005312.pth...
+[2025-02-14 07:52:41,827][00436] Component LearnerWorker_p0 stopped!
+[2025-02-14 07:52:41,833][13607] Stopping LearnerWorker_p0...
+[2025-02-14 07:52:41,833][13607] Loop learner_proc0_evt_loop terminating...
+[2025-02-14 07:52:42,072][00436] Component RolloutWorker_w5 stopped!
+[2025-02-14 07:52:42,078][13630] Stopping RolloutWorker_w5...
+[2025-02-14 07:52:42,083][00436] Component RolloutWorker_w7 stopped!
+[2025-02-14 07:52:42,087][13632] Stopping RolloutWorker_w7...
+[2025-02-14 07:52:42,094][00436] Component RolloutWorker_w3 stopped!
+[2025-02-14 07:52:42,098][13628] Stopping RolloutWorker_w3...
+[2025-02-14 07:52:42,099][13628] Loop rollout_proc3_evt_loop terminating...
+[2025-02-14 07:52:42,100][13630] Loop rollout_proc5_evt_loop terminating...
+[2025-02-14 07:52:42,112][00436] Component RolloutWorker_w1 stopped!
+[2025-02-14 07:52:42,115][13626] Stopping RolloutWorker_w1...
+[2025-02-14 07:52:42,116][13626] Loop rollout_proc1_evt_loop terminating...
+[2025-02-14 07:52:42,107][13632] Loop rollout_proc7_evt_loop terminating...
+[2025-02-14 07:52:42,270][00436] Component RolloutWorker_w0 stopped!
+[2025-02-14 07:52:42,270][13625] Stopping RolloutWorker_w0...
+[2025-02-14 07:52:42,276][13625] Loop rollout_proc0_evt_loop terminating...
+[2025-02-14 07:52:42,326][00436] Component RolloutWorker_w2 stopped!
+[2025-02-14 07:52:42,334][13627] Stopping RolloutWorker_w2...
+[2025-02-14 07:52:42,335][13627] Loop rollout_proc2_evt_loop terminating...
+[2025-02-14 07:52:42,437][13631] Stopping RolloutWorker_w6...
+[2025-02-14 07:52:42,437][00436] Component RolloutWorker_w6 stopped!
+[2025-02-14 07:52:42,443][13629] Stopping RolloutWorker_w4...
+[2025-02-14 07:52:42,443][13629] Loop rollout_proc4_evt_loop terminating...
+[2025-02-14 07:52:42,443][00436] Component RolloutWorker_w4 stopped!
+[2025-02-14 07:52:42,446][00436] Waiting for process learner_proc0 to stop...
+[2025-02-14 07:52:42,449][13631] Loop rollout_proc6_evt_loop terminating...
+[2025-02-14 07:52:44,115][00436] Waiting for process inference_proc0-0 to join...
+[2025-02-14 07:52:44,174][00436] Waiting for process rollout_proc0 to join...
+[2025-02-14 07:52:46,466][00436] Waiting for process rollout_proc1 to join...
+[2025-02-14 07:52:46,506][00436] Waiting for process rollout_proc2 to join...
+[2025-02-14 07:52:46,509][00436] Waiting for process rollout_proc3 to join...
+[2025-02-14 07:52:46,511][00436] Waiting for process rollout_proc4 to join...
+[2025-02-14 07:52:46,515][00436] Waiting for process rollout_proc5 to join...
+[2025-02-14 07:52:46,516][00436] Waiting for process rollout_proc6 to join...
+[2025-02-14 07:52:46,518][00436] Waiting for process rollout_proc7 to join...
+[2025-02-14 07:52:46,522][00436] Batcher 0 profile tree view:
+batching: 6.1311, releasing_batches: 0.0063
+[2025-02-14 07:52:46,523][00436] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0000
+  wait_policy_total: 103.2326
+update_model: 2.0046
+  weight_update: 0.0022
+one_step: 0.0104
+  handle_policy_step: 144.4081
+    deserialize: 3.4548, stack: 0.7423, obs_to_device_normalize: 30.3564, forward: 74.6529, send_messages: 7.1637
+    prepare_outputs: 22.0848
+      to_cpu: 13.6550
+[2025-02-14 07:52:46,524][00436] Learner 0 profile tree view:
+misc: 0.0009, prepare_batch: 4.2370
+train: 20.0195
+  epoch_init: 0.0012, minibatch_init: 0.0014, losses_postprocess: 0.1660, kl_divergence: 0.1880, after_optimizer: 0.8447
+  calculate_losses: 6.5899
+    losses_init: 0.0008, forward_head: 0.6238, bptt_initial: 4.1340, tail: 0.3297, advantages_returns: 0.0705, losses: 0.8757
+    bptt: 0.4848
+      bptt_forward_core: 0.4517
+  update: 12.0735
+    clip: 0.2249
+[2025-02-14 07:52:46,526][00436] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.0736, enqueue_policy_requests: 22.8663, env_step: 200.0027, overhead: 2.9398, complete_rollouts: 2.0251
+save_policy_outputs: 4.4570
+  split_output_tensors: 1.7724
+[2025-02-14 07:52:46,527][00436] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.0737, enqueue_policy_requests: 24.7789, env_step: 198.5096, overhead: 2.8235, complete_rollouts: 1.8543
+save_policy_outputs: 4.2478
+  split_output_tensors: 1.7220
+[2025-02-14 07:52:46,528][00436] Loop Runner_EvtLoop terminating...
+[2025-02-14 07:52:46,530][00436] Runner profile tree view:
+main_loop: 282.7091
+[2025-02-14 07:52:46,531][00436] Collected {0: 5005312}, FPS: 3535.2
+[2025-02-14 07:54:33,274][00436] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2025-02-14 07:54:33,276][00436] Overriding arg 'num_workers' with value 1 passed from command line
+[2025-02-14 07:54:33,278][00436] Adding new argument 'no_render'=True that is not in the saved config file!
+[2025-02-14 07:54:33,279][00436] Adding new argument 'save_video'=True that is not in the saved config file!
+[2025-02-14 07:54:33,281][00436] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2025-02-14 07:54:33,283][00436] Adding new argument 'video_name'=None that is not in the saved config file!
+[2025-02-14 07:54:33,284][00436] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2025-02-14 07:54:33,285][00436] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2025-02-14 07:54:33,288][00436] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2025-02-14 07:54:33,290][00436] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2025-02-14 07:54:33,291][00436] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2025-02-14 07:54:33,292][00436] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2025-02-14 07:54:33,293][00436] Adding new argument 'train_script'=None that is not in the saved config file!
+[2025-02-14 07:54:33,296][00436] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2025-02-14 07:54:33,298][00436] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2025-02-14 07:54:33,335][00436] RunningMeanStd input shape: (3, 72, 128)
+[2025-02-14 07:54:33,337][00436] RunningMeanStd input shape: (1,)
+[2025-02-14 07:54:33,354][00436] ConvEncoder: input_channels=3
+[2025-02-14 07:54:33,391][00436] Conv encoder output size: 512
+[2025-02-14 07:54:33,392][00436] Policy head output size: 512
+[2025-02-14 07:54:33,413][00436] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001222_5005312.pth...
+[2025-02-14 07:54:33,841][00436] Num frames 100...
+[2025-02-14 07:54:33,977][00436] Num frames 200...
+[2025-02-14 07:54:34,108][00436] Num frames 300...
+[2025-02-14 07:54:34,257][00436] Num frames 400...
+[2025-02-14 07:54:34,401][00436] Num frames 500...
+[2025-02-14 07:54:34,559][00436] Avg episode rewards: #0: 9.760, true rewards: #0: 5.760
+[2025-02-14 07:54:34,561][00436] Avg episode reward: 9.760, avg true_objective: 5.760
+[2025-02-14 07:54:34,597][00436] Num frames 600...
+[2025-02-14 07:54:34,738][00436] Num frames 700...
+[2025-02-14 07:54:34,873][00436] Num frames 800...
+[2025-02-14 07:54:35,004][00436] Num frames 900...
+[2025-02-14 07:54:35,137][00436] Num frames 1000...
+[2025-02-14 07:54:35,277][00436] Num frames 1100...
+[2025-02-14 07:54:35,409][00436] Num frames 1200...
+[2025-02-14 07:54:35,548][00436] Num frames 1300...
+[2025-02-14 07:54:35,687][00436] Num frames 1400...
+[2025-02-14 07:54:35,825][00436] Num frames 1500...
+[2025-02-14 07:54:35,957][00436] Num frames 1600...
+[2025-02-14 07:54:36,097][00436] Num frames 1700...
+[2025-02-14 07:54:36,191][00436] Avg episode rewards: #0: 19.640, true rewards: #0: 8.640
+[2025-02-14 07:54:36,193][00436] Avg episode reward: 19.640, avg true_objective: 8.640
+[2025-02-14 07:54:36,299][00436] Num frames 1800...
+[2025-02-14 07:54:36,435][00436] Num frames 1900...
+[2025-02-14 07:54:36,565][00436] Num frames 2000...
+[2025-02-14 07:54:36,721][00436] Num frames 2100...
+[2025-02-14 07:54:36,915][00436] Num frames 2200...
+[2025-02-14 07:54:37,096][00436] Num frames 2300...
+[2025-02-14 07:54:37,281][00436] Num frames 2400...
+[2025-02-14 07:54:37,452][00436] Num frames 2500...
+[2025-02-14 07:54:37,630][00436] Num frames 2600...
+[2025-02-14 07:54:37,760][00436] Avg episode rewards: #0: 20.807, true rewards: #0: 8.807
+[2025-02-14 07:54:37,762][00436] Avg episode reward: 20.807, avg true_objective: 8.807
+[2025-02-14 07:54:37,870][00436] Num frames 2700...
+[2025-02-14 07:54:38,039][00436] Num frames 2800...
+[2025-02-14 07:54:38,232][00436] Num frames 2900...
+[2025-02-14 07:54:38,424][00436] Num frames 3000...
+[2025-02-14 07:54:38,609][00436] Num frames 3100...
+[2025-02-14 07:54:38,793][00436] Num frames 3200...
+[2025-02-14 07:54:38,986][00436] Num frames 3300...
+[2025-02-14 07:54:39,130][00436] Num frames 3400...
+[2025-02-14 07:54:39,268][00436] Num frames 3500...
+[2025-02-14 07:54:39,403][00436] Num frames 3600...
+[2025-02-14 07:54:39,531][00436] Num frames 3700...
+[2025-02-14 07:54:39,665][00436] Num frames 3800...
+[2025-02-14 07:54:39,766][00436] Avg episode rewards: #0: 22.330, true rewards: #0: 9.580
+[2025-02-14 07:54:39,767][00436] Avg episode reward: 22.330, avg true_objective: 9.580
+[2025-02-14 07:54:39,864][00436] Num frames 3900...
+[2025-02-14 07:54:39,993][00436] Num frames 4000...
+[2025-02-14 07:54:40,125][00436] Num frames 4100...
+[2025-02-14 07:54:40,264][00436] Num frames 4200...
+[2025-02-14 07:54:40,400][00436] Num frames 4300...
+[2025-02-14 07:54:40,530][00436] Num frames 4400...
+[2025-02-14 07:54:40,598][00436] Avg episode rewards: #0: 19.816, true rewards: #0: 8.816
+[2025-02-14 07:54:40,599][00436] Avg episode reward: 19.816, avg true_objective: 8.816
+[2025-02-14 07:54:40,727][00436] Num frames 4500...
+[2025-02-14 07:54:40,865][00436] Num frames 4600...
+[2025-02-14 07:54:41,002][00436] Num frames 4700...
+[2025-02-14 07:54:41,131][00436] Num frames 4800...
+[2025-02-14 07:54:41,269][00436] Num frames 4900...
+[2025-02-14 07:54:41,401][00436] Num frames 5000...
+[2025-02-14 07:54:41,530][00436] Num frames 5100...
+[2025-02-14 07:54:41,661][00436] Num frames 5200...
+[2025-02-14 07:54:41,793][00436] Num frames 5300...
+[2025-02-14 07:54:41,854][00436] Avg episode rewards: #0: 19.840, true rewards: #0: 8.840
+[2025-02-14 07:54:41,856][00436] Avg episode reward: 19.840, avg true_objective: 8.840
+[2025-02-14 07:54:41,991][00436] Num frames 5400...
+[2025-02-14 07:54:42,124][00436] Num frames 5500...
+[2025-02-14 07:54:42,265][00436] Num frames 5600...
+[2025-02-14 07:54:42,400][00436] Num frames 5700...
+[2025-02-14 07:54:42,535][00436] Num frames 5800...
+[2025-02-14 07:54:42,667][00436] Num frames 5900...
+[2025-02-14 07:54:42,797][00436] Num frames 6000...
+[2025-02-14 07:54:42,932][00436] Num frames 6100...
+[2025-02-14 07:54:43,073][00436] Num frames 6200...
+[2025-02-14 07:54:43,212][00436] Num frames 6300...
+[2025-02-14 07:54:43,343][00436] Num frames 6400...
+[2025-02-14 07:54:43,431][00436] Avg episode rewards: #0: 21.034, true rewards: #0: 9.177
+[2025-02-14 07:54:43,432][00436] Avg episode reward: 21.034, avg true_objective: 9.177
+[2025-02-14 07:54:43,531][00436] Num frames 6500...
+[2025-02-14 07:54:43,660][00436] Num frames 6600...
+[2025-02-14 07:54:43,788][00436] Num frames 6700...
+[2025-02-14 07:54:43,920][00436] Num frames 6800...
+[2025-02-14 07:54:44,059][00436] Num frames 6900...
+[2025-02-14 07:54:44,198][00436] Num frames 7000...
+[2025-02-14 07:54:44,329][00436] Num frames 7100...
+[2025-02-14 07:54:44,459][00436] Num frames 7200...
+[2025-02-14 07:54:44,589][00436] Num frames 7300...
+[2025-02-14 07:54:44,718][00436] Num frames 7400...
+[2025-02-14 07:54:44,848][00436] Num frames 7500...
+[2025-02-14 07:54:44,983][00436] Num frames 7600...
+[2025-02-14 07:54:45,136][00436] Avg episode rewards: #0: 21.340, true rewards: #0: 9.590
+[2025-02-14 07:54:45,137][00436] Avg episode reward: 21.340, avg true_objective: 9.590
+[2025-02-14 07:54:45,180][00436] Num frames 7700...
+[2025-02-14 07:54:45,316][00436] Num frames 7800...
+[2025-02-14 07:54:45,456][00436] Num frames 7900...
+[2025-02-14 07:54:45,593][00436] Num frames 8000...
+[2025-02-14 07:54:45,728][00436] Num frames 8100...
+[2025-02-14 07:54:45,860][00436] Num frames 8200...
+[2025-02-14 07:54:45,992][00436] Num frames 8300...
+[2025-02-14 07:54:46,130][00436] Num frames 8400...
+[2025-02-14 07:54:46,270][00436] Num frames 8500...
+[2025-02-14 07:54:46,404][00436] Num frames 8600...
+[2025-02-14 07:54:46,536][00436] Num frames 8700...
+[2025-02-14 07:54:46,672][00436] Avg episode rewards: #0: 21.622, true rewards: #0: 9.733
+[2025-02-14 07:54:46,674][00436] Avg episode reward: 21.622, avg true_objective: 9.733
+[2025-02-14 07:54:46,731][00436] Num frames 8800...
+[2025-02-14 07:54:46,865][00436] Num frames 8900...
+[2025-02-14 07:54:47,000][00436] Num frames 9000...
+[2025-02-14 07:54:47,140][00436] Num frames 9100...
+[2025-02-14 07:54:47,281][00436] Num frames 9200...
+[2025-02-14 07:54:47,421][00436] Num frames 9300...
+[2025-02-14 07:54:47,555][00436] Num frames 9400...
+[2025-02-14 07:54:47,686][00436] Num frames 9500...
+[2025-02-14 07:54:47,823][00436] Num frames 9600...
+[2025-02-14 07:54:47,959][00436] Num frames 9700...
+[2025-02-14 07:54:48,100][00436] Num frames 9800...
+[2025-02-14 07:54:48,244][00436] Num frames 9900...
+[2025-02-14 07:54:48,387][00436] Num frames 10000...
+[2025-02-14 07:54:48,527][00436] Num frames 10100...
+[2025-02-14 07:54:48,591][00436] Avg episode rewards: #0: 22.404, true rewards: #0: 10.104
+[2025-02-14 07:54:48,594][00436] Avg episode reward: 22.404, avg true_objective: 10.104
+[2025-02-14 07:55:49,275][00436] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2025-02-14 07:56:08,753][00436] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2025-02-14 07:56:08,755][00436] Overriding arg 'num_workers' with value 1 passed from command line
+[2025-02-14 07:56:08,757][00436] Adding new argument 'no_render'=True that is not in the saved config file!
+[2025-02-14 07:56:08,758][00436] Adding new argument 'save_video'=True that is not in the saved config file!
+[2025-02-14 07:56:08,761][00436] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2025-02-14 07:56:08,763][00436] Adding new argument 'video_name'=None that is not in the saved config file!
+[2025-02-14 07:56:08,764][00436] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2025-02-14 07:56:08,768][00436] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2025-02-14 07:56:08,769][00436] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2025-02-14 07:56:08,770][00436] Adding new argument 'hf_repository'='gyaan/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2025-02-14 07:56:08,771][00436] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2025-02-14 07:56:08,775][00436] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2025-02-14 07:56:08,777][00436] Adding new argument 'train_script'=None that is not in the saved config file!
+[2025-02-14 07:56:08,778][00436] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2025-02-14 07:56:08,779][00436] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2025-02-14 07:56:08,813][00436] RunningMeanStd input shape: (3, 72, 128)
+[2025-02-14 07:56:08,815][00436] RunningMeanStd input shape: (1,)
+[2025-02-14 07:56:08,828][00436] ConvEncoder: input_channels=3
+[2025-02-14 07:56:08,864][00436] Conv encoder output size: 512
+[2025-02-14 07:56:08,865][00436] Policy head output size: 512
+[2025-02-14 07:56:08,883][00436] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001222_5005312.pth...
+[2025-02-14 07:56:09,360][00436] Num frames 100...
+[2025-02-14 07:56:09,497][00436] Num frames 200...
+[2025-02-14 07:56:09,624][00436] Num frames 300...
+[2025-02-14 07:56:09,761][00436] Num frames 400...
+[2025-02-14 07:56:09,899][00436] Num frames 500...
+[2025-02-14 07:56:10,028][00436] Num frames 600...
+[2025-02-14 07:56:10,169][00436] Num frames 700...
+[2025-02-14 07:56:10,310][00436] Num frames 800...
+[2025-02-14 07:56:10,441][00436] Num frames 900...
+[2025-02-14 07:56:10,571][00436] Num frames 1000...
+[2025-02-14 07:56:10,705][00436] Num frames 1100...
+[2025-02-14 07:56:10,854][00436] Num frames 1200...
+[2025-02-14 07:56:10,986][00436] Num frames 1300...
+[2025-02-14 07:56:11,114][00436] Num frames 1400...
+[2025-02-14 07:56:11,249][00436] Num frames 1500...
+[2025-02-14 07:56:11,386][00436] Num frames 1600...
+[2025-02-14 07:56:11,439][00436] Avg episode rewards: #0: 45.000, true rewards: #0: 16.000
+[2025-02-14 07:56:11,440][00436] Avg episode reward: 45.000, avg true_objective: 16.000
+[2025-02-14 07:56:11,570][00436] Num frames 1700...
+[2025-02-14 07:56:11,699][00436] Num frames 1800...
+[2025-02-14 07:56:11,827][00436] Num frames 1900...
+[2025-02-14 07:56:11,973][00436] Num frames 2000...
+[2025-02-14 07:56:12,051][00436] Avg episode rewards: #0: 25.580, true rewards: #0: 10.080
+[2025-02-14 07:56:12,052][00436] Avg episode reward: 25.580, avg true_objective: 10.080
+[2025-02-14 07:56:12,171][00436] Num frames 2100...
+[2025-02-14 07:56:12,309][00436] Num frames 2200...
+[2025-02-14 07:56:12,439][00436] Num frames 2300...
+[2025-02-14 07:56:12,571][00436] Num frames 2400...
+[2025-02-14 07:56:12,704][00436] Num frames 2500...
+[2025-02-14 07:56:12,840][00436] Num frames 2600...
+[2025-02-14 07:56:12,979][00436] Num frames 2700...
+[2025-02-14 07:56:13,112][00436] Num frames 2800...
+[2025-02-14 07:56:13,252][00436] Num frames 2900...
+[2025-02-14 07:56:13,386][00436] Num frames 3000...
+[2025-02-14 07:56:13,518][00436] Num frames 3100...
+[2025-02-14 07:56:13,649][00436] Num frames 3200...
+[2025-02-14 07:56:13,784][00436] Num frames 3300...
+[2025-02-14 07:56:13,928][00436] Num frames 3400...
+[2025-02-14 07:56:14,061][00436] Num frames 3500...
+[2025-02-14 07:56:14,198][00436] Num frames 3600...
+[2025-02-14 07:56:14,331][00436] Num frames 3700...
+[2025-02-14 07:56:14,462][00436] Num frames 3800...
+[2025-02-14 07:56:14,596][00436] Num frames 3900...
+[2025-02-14 07:56:14,727][00436] Num frames 4000...
+[2025-02-14 07:56:14,857][00436] Num frames 4100...
+[2025-02-14 07:56:14,933][00436] Avg episode rewards: #0: 36.053, true rewards: #0: 13.720
+[2025-02-14 07:56:14,935][00436] Avg episode reward: 36.053, avg true_objective: 13.720
+[2025-02-14 07:56:15,042][00436] Num frames 4200...
+[2025-02-14 07:56:15,177][00436] Num frames 4300...
+[2025-02-14 07:56:15,315][00436] Num frames 4400...
+[2025-02-14 07:56:15,445][00436] Num frames 4500...
+[2025-02-14 07:56:15,590][00436] Num frames 4600...
+[2025-02-14 07:56:15,724][00436] Num frames 4700...
+[2025-02-14 07:56:15,854][00436] Num frames 4800...
+[2025-02-14 07:56:15,937][00436] Avg episode rewards: #0: 30.550, true rewards: #0: 12.050
+[2025-02-14 07:56:15,939][00436] Avg episode reward: 30.550, avg true_objective: 12.050
+[2025-02-14 07:56:16,077][00436] Num frames 4900...
+[2025-02-14 07:56:16,266][00436] Num frames 5000...
+[2025-02-14 07:56:16,437][00436] Num frames 5100...
+[2025-02-14 07:56:16,613][00436] Num frames 5200...
+[2025-02-14 07:56:16,781][00436] Num frames 5300...
+[2025-02-14 07:56:17,006][00436] Avg episode rewards: #0: 26.392, true rewards: #0: 10.792
+[2025-02-14 07:56:17,008][00436] Avg episode reward: 26.392, avg true_objective: 10.792
+[2025-02-14 07:56:17,021][00436] Num frames 5400...
+[2025-02-14 07:56:17,192][00436] Num frames 5500...
+[2025-02-14 07:56:17,363][00436] Num frames 5600...
+[2025-02-14 07:56:17,544][00436] Num frames 5700...
+[2025-02-14 07:56:17,733][00436] Num frames 5800...
+[2025-02-14 07:56:17,914][00436] Num frames 5900...
+[2025-02-14 07:56:18,102][00436] Num frames 6000...
+[2025-02-14 07:56:18,289][00436] Num frames 6100...
+[2025-02-14 07:56:18,424][00436] Num frames 6200...
+[2025-02-14 07:56:18,555][00436] Num frames 6300...
+[2025-02-14 07:56:18,687][00436] Num frames 6400...
+[2025-02-14 07:56:18,822][00436] Num frames 6500...
+[2025-02-14 07:56:18,955][00436] Num frames 6600...
+[2025-02-14 07:56:19,095][00436] Num frames 6700...
+[2025-02-14 07:56:19,236][00436] Num frames 6800...
+[2025-02-14 07:56:19,298][00436] Avg episode rewards: #0: 28.173, true rewards: #0: 11.340
+[2025-02-14 07:56:19,299][00436] Avg episode reward: 28.173, avg true_objective: 11.340
+[2025-02-14 07:56:19,425][00436] Num frames 6900...
+[2025-02-14 07:56:19,553][00436] Num frames 7000...
+[2025-02-14 07:56:19,684][00436] Num frames 7100...
+[2025-02-14 07:56:19,815][00436] Num frames 7200...
+[2025-02-14 07:56:19,957][00436] Num frames 7300...
+[2025-02-14 07:56:20,104][00436] Num frames 7400...
+[2025-02-14 07:56:20,243][00436] Num frames 7500...
+[2025-02-14 07:56:20,374][00436] Num frames 7600...
+[2025-02-14 07:56:20,512][00436] Num frames 7700...
+[2025-02-14 07:56:20,647][00436] Num frames 7800...
+[2025-02-14 07:56:20,780][00436] Num frames 7900...
+[2025-02-14 07:56:20,913][00436] Num frames 8000...
+[2025-02-14 07:56:20,983][00436] Avg episode rewards: #0: 27.871, true rewards: #0: 11.443
+[2025-02-14 07:56:20,985][00436] Avg episode reward: 27.871, avg true_objective: 11.443
+[2025-02-14 07:56:21,112][00436] Num frames 8100...
+[2025-02-14 07:56:21,249][00436] Num frames 8200...
+[2025-02-14 07:56:21,380][00436] Num frames 8300...
+[2025-02-14 07:56:21,515][00436] Num frames 8400...
+[2025-02-14 07:56:21,649][00436] Num frames 8500...
+[2025-02-14 07:56:21,779][00436] Num frames 8600...
+[2025-02-14 07:56:21,912][00436] Num frames 8700...
+[2025-02-14 07:56:22,046][00436] Num frames 8800...
+[2025-02-14 07:56:22,194][00436] Num frames 8900...
+[2025-02-14 07:56:22,327][00436] Num frames 9000...
+[2025-02-14 07:56:22,505][00436] Avg episode rewards: #0: 28.237, true rewards: #0: 11.362
+[2025-02-14 07:56:22,507][00436] Avg episode reward: 28.237, avg true_objective: 11.362
+[2025-02-14 07:56:22,525][00436] Num frames 9100...
+[2025-02-14 07:56:22,656][00436] Num frames 9200...
+[2025-02-14 07:56:22,788][00436] Num frames 9300...
+[2025-02-14 07:56:22,925][00436] Num frames 9400...
+[2025-02-14 07:56:23,055][00436] Num frames 9500...
+[2025-02-14 07:56:23,203][00436] Num frames 9600...
+[2025-02-14 07:56:23,335][00436] Num frames 9700...
+[2025-02-14 07:56:23,468][00436] Num frames 9800...
+[2025-02-14 07:56:23,599][00436] Num frames 9900...
+[2025-02-14 07:56:23,731][00436] Num frames 10000...
+[2025-02-14 07:56:23,862][00436] Num frames 10100...
+[2025-02-14 07:56:23,994][00436] Num frames 10200...
+[2025-02-14 07:56:24,105][00436] Avg episode rewards: #0: 27.935, true rewards: #0: 11.380
+[2025-02-14 07:56:24,107][00436] Avg episode reward: 27.935, avg true_objective: 11.380
+[2025-02-14 07:56:24,194][00436] Num frames 10300...
+[2025-02-14 07:56:24,330][00436] Num frames 10400...
+[2025-02-14 07:56:24,462][00436] Num frames 10500...
+[2025-02-14 07:56:24,591][00436] Num frames 10600...
+[2025-02-14 07:56:24,722][00436] Num frames 10700...
+[2025-02-14 07:56:24,857][00436] Num frames 10800...
+[2025-02-14 07:56:24,990][00436] Num frames 10900...
+[2025-02-14 07:56:25,126][00436] Num frames 11000...
+[2025-02-14 07:56:25,279][00436] Num frames 11100...
+[2025-02-14 07:56:25,413][00436] Num frames 11200...
+[2025-02-14 07:56:25,548][00436] Num frames 11300...
+[2025-02-14 07:56:25,685][00436] Num frames 11400...
+[2025-02-14 07:56:25,816][00436] Num frames 11500...
+[2025-02-14 07:56:25,949][00436] Num frames 11600...
+[2025-02-14 07:56:26,076][00436] Num frames 11700...
+[2025-02-14 07:56:26,216][00436] Num frames 11800...
+[2025-02-14 07:56:26,357][00436] Num frames 11900...
+[2025-02-14 07:56:26,463][00436] Avg episode rewards: #0: 29.138, true rewards: #0: 11.938
+[2025-02-14 07:56:26,466][00436] Avg episode reward: 29.138, avg true_objective: 11.938
+[2025-02-14 07:57:38,965][00436] Replay video saved to /content/train_dir/default_experiment/replay.mp4!