Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1756512588.5b240b05f395

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a4bde4e30845d2a645a3cf0f76f47a0408a6a89659bd2d6b9f08bcddf74c163
+size 218586

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 4.00 +/- 0.50
+      value: 4.44 +/- 1.93
       name: mean_reward
       verified: false
 ---

checkpoint_p0/best_000000241_987136_reward_8.004.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2b3abbd3f202746bb3e4701ea5ef79646944fb7ec891253a39d7b99dd236c47
+size 34929516

checkpoint_p0/checkpoint_000000210_860160.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae71cc8d09a5811c617e87228169f91afd6bc7fe87147168ff032d1545919c0c
+size 34929954

checkpoint_p0/checkpoint_000000246_1007616.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3252ed55019ae81621a6060a8fc612a1c2968b555798de8c7f3186b6eee9ed8
+size 34929954

config.json

@@ -65,7 +65,7 @@
   "summaries_use_frameskip": true,
   "heartbeat_interval": 20,
   "heartbeat_reporting_interval": 600,
-  "train_for_env_steps": 100000,
+  "train_for_env_steps": 1000000,
   "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 sha256:89edb3c2cb0f3e40d436213a570e5b0d41a4d8329a4110add7f169fe88c05708
-size 6110498
+oid sha256:1d3e0bfbacf838ff96bf029cbbfbdc40680e09e95c64f961e4ee0a195e746aed
+size 7311680

sf_log.txt

@@ -395,3 +395,767 @@ Check the documentation of torch.load to learn more about types accepted by defa
 [2025-08-30 00:08:21,387][02133] Avg episode rewards: #0: 4.400, true rewards: #0: 4.000
 [2025-08-30 00:08:21,388][02133] Avg episode reward: 4.400, avg true_objective: 4.000
 [2025-08-30 00:08:41,723][02133] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2025-08-30 00:08:47,004][02133] The model has been pushed to https://huggingface.co/Priyam05/rl_course_vizdoom_health_gathering_supreme
+[2025-08-30 00:09:48,409][02133] Environment doom_basic already registered, overwriting...
+[2025-08-30 00:09:48,410][02133] Environment doom_two_colors_easy already registered, overwriting...
+[2025-08-30 00:09:48,411][02133] Environment doom_two_colors_hard already registered, overwriting...
+[2025-08-30 00:09:48,412][02133] Environment doom_dm already registered, overwriting...
+[2025-08-30 00:09:48,413][02133] Environment doom_dwango5 already registered, overwriting...
+[2025-08-30 00:09:48,415][02133] Environment doom_my_way_home_flat_actions already registered, overwriting...
+[2025-08-30 00:09:48,416][02133] Environment doom_defend_the_center_flat_actions already registered, overwriting...
+[2025-08-30 00:09:48,417][02133] Environment doom_my_way_home already registered, overwriting...
+[2025-08-30 00:09:48,418][02133] Environment doom_deadly_corridor already registered, overwriting...
+[2025-08-30 00:09:48,420][02133] Environment doom_defend_the_center already registered, overwriting...
+[2025-08-30 00:09:48,421][02133] Environment doom_defend_the_line already registered, overwriting...
+[2025-08-30 00:09:48,422][02133] Environment doom_health_gathering already registered, overwriting...
+[2025-08-30 00:09:48,423][02133] Environment doom_health_gathering_supreme already registered, overwriting...
+[2025-08-30 00:09:48,423][02133] Environment doom_battle already registered, overwriting...
+[2025-08-30 00:09:48,424][02133] Environment doom_battle2 already registered, overwriting...
+[2025-08-30 00:09:48,425][02133] Environment doom_duel_bots already registered, overwriting...
+[2025-08-30 00:09:48,426][02133] Environment doom_deathmatch_bots already registered, overwriting...
+[2025-08-30 00:09:48,426][02133] Environment doom_duel already registered, overwriting...
+[2025-08-30 00:09:48,427][02133] Environment doom_deathmatch_full already registered, overwriting...
+[2025-08-30 00:09:48,428][02133] Environment doom_benchmark already registered, overwriting...
+[2025-08-30 00:09:48,431][02133] register_encoder_factory: <function make_vizdoom_encoder at 0x7850c852dc60>
+[2025-08-30 00:09:48,445][02133] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2025-08-30 00:09:48,449][02133] Overriding arg 'train_for_env_steps' with value 1000000 passed from command line
+[2025-08-30 00:09:48,454][02133] Experiment dir /content/train_dir/default_experiment already exists!
+[2025-08-30 00:09:48,455][02133] Resuming existing experiment from /content/train_dir/default_experiment...
+[2025-08-30 00:09:48,456][02133] Weights and Biases integration disabled
+[2025-08-30 00:09:48,459][02133] Environment var CUDA_VISIBLE_DEVICES is 0
+
+[2025-08-30 00:09:50,778][02133] 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=1000000
+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=100000
+cli_args={'env': 'doom_health_gathering_supreme', 'num_workers': 8, 'num_envs_per_worker': 4, 'train_for_env_steps': 100000}
+git_hash=unknown
+git_repo_name=not a git repository
+[2025-08-30 00:09:50,779][02133] Saving configuration to /content/train_dir/default_experiment/config.json...
+[2025-08-30 00:09:50,781][02133] Rollout worker 0 uses device cpu
+[2025-08-30 00:09:50,782][02133] Rollout worker 1 uses device cpu
+[2025-08-30 00:09:50,783][02133] Rollout worker 2 uses device cpu
+[2025-08-30 00:09:50,784][02133] Rollout worker 3 uses device cpu
+[2025-08-30 00:09:50,784][02133] Rollout worker 4 uses device cpu
+[2025-08-30 00:09:50,785][02133] Rollout worker 5 uses device cpu
+[2025-08-30 00:09:50,786][02133] Rollout worker 6 uses device cpu
+[2025-08-30 00:09:50,787][02133] Rollout worker 7 uses device cpu
+[2025-08-30 00:09:50,853][02133] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-08-30 00:09:50,854][02133] InferenceWorker_p0-w0: min num requests: 2
+[2025-08-30 00:09:50,881][02133] Starting all processes...
+[2025-08-30 00:09:50,882][02133] Starting process learner_proc0
+[2025-08-30 00:09:50,943][02133] Starting all processes...
+[2025-08-30 00:09:50,947][02133] Starting process inference_proc0-0
+[2025-08-30 00:09:50,948][02133] Starting process rollout_proc0
+[2025-08-30 00:09:50,948][02133] Starting process rollout_proc1
+[2025-08-30 00:09:50,948][02133] Starting process rollout_proc2
+[2025-08-30 00:09:50,948][02133] Starting process rollout_proc3
+[2025-08-30 00:09:50,948][02133] Starting process rollout_proc4
+[2025-08-30 00:09:50,948][02133] Starting process rollout_proc5
+[2025-08-30 00:09:50,948][02133] Starting process rollout_proc6
+[2025-08-30 00:09:50,948][02133] Starting process rollout_proc7
+[2025-08-30 00:10:06,001][07555] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-08-30 00:10:06,001][07555] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2025-08-30 00:10:06,064][07555] Num visible devices: 1
+[2025-08-30 00:10:06,076][07555] Starting seed is not provided
+[2025-08-30 00:10:06,077][07555] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-08-30 00:10:06,077][07555] Initializing actor-critic model on device cuda:0
+[2025-08-30 00:10:06,078][07555] RunningMeanStd input shape: (3, 72, 128)
+[2025-08-30 00:10:06,080][07555] RunningMeanStd input shape: (1,)
+[2025-08-30 00:10:06,140][07568] Worker 2 uses CPU cores [0]
+[2025-08-30 00:10:06,157][07555] ConvEncoder: input_channels=3
+[2025-08-30 00:10:06,257][07573] Worker 6 uses CPU cores [0]
+[2025-08-30 00:10:06,432][07570] Worker 5 uses CPU cores [1]
+[2025-08-30 00:10:06,480][07569] Worker 4 uses CPU cores [0]
+[2025-08-30 00:10:06,489][07574] Worker 0 uses CPU cores [0]
+[2025-08-30 00:10:06,602][07572] Worker 7 uses CPU cores [1]
+[2025-08-30 00:10:06,626][07555] Conv encoder output size: 512
+[2025-08-30 00:10:06,627][07555] Policy head output size: 512
+[2025-08-30 00:10:06,648][07555] Created Actor Critic model with architecture:
+[2025-08-30 00:10:06,648][07555] 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)
+  )
+)
+[2025-08-30 00:10:06,785][07571] Worker 1 uses CPU cores [1]
+[2025-08-30 00:10:06,800][07575] Worker 3 uses CPU cores [1]
+[2025-08-30 00:10:06,871][07576] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-08-30 00:10:06,872][07576] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2025-08-30 00:10:06,890][07576] Num visible devices: 1
+[2025-08-30 00:10:06,899][07555] Using optimizer <class 'torch.optim.adam.Adam'>
+[2025-08-30 00:10:07,835][07555] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000026_106496.pth...
+[2025-08-30 00:10:07,838][07555] Could not load from checkpoint, attempt 0
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.12/dist-packages/sample_factory/algo/learning/learner.py", line 281, in load_checkpoint
+    checkpoint_dict = torch.load(latest_checkpoint, map_location=device)
+                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/usr/local/lib/python3.12/dist-packages/torch/serialization.py", line 1529, in load
+    raise pickle.UnpicklingError(_get_wo_message(str(e))) from None
+_pickle.UnpicklingError: Weights only load failed. This file can still be loaded, to do so you have two options, do those steps only if you trust the source of the checkpoint. 
+	(1) In PyTorch 2.6, we changed the default value of the `weights_only` argument in `torch.load` from `False` to `True`. Re-running `torch.load` with `weights_only` set to `False` will likely succeed, but it can result in arbitrary code execution. Do it only if you got the file from a trusted source.
+	(2) Alternatively, to load with `weights_only=True` please check the recommended steps in the following error message.
+	WeightsUnpickler error: Unsupported global: GLOBAL numpy.core.multiarray.scalar was not an allowed global by default. Please use `torch.serialization.add_safe_globals([numpy.core.multiarray.scalar])` or the `torch.serialization.safe_globals([numpy.core.multiarray.scalar])` context manager to allowlist this global if you trust this class/function.
+
+Check the documentation of torch.load to learn more about types accepted by default with weights_only https://pytorch.org/docs/stable/generated/torch.load.html.
+[2025-08-30 00:10:07,839][07555] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000026_106496.pth...
+[2025-08-30 00:10:07,840][07555] Could not load from checkpoint, attempt 1
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.12/dist-packages/sample_factory/algo/learning/learner.py", line 281, in load_checkpoint
+    checkpoint_dict = torch.load(latest_checkpoint, map_location=device)
+                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/usr/local/lib/python3.12/dist-packages/torch/serialization.py", line 1529, in load
+    raise pickle.UnpicklingError(_get_wo_message(str(e))) from None
+_pickle.UnpicklingError: Weights only load failed. This file can still be loaded, to do so you have two options, do those steps only if you trust the source of the checkpoint. 
+	(1) In PyTorch 2.6, we changed the default value of the `weights_only` argument in `torch.load` from `False` to `True`. Re-running `torch.load` with `weights_only` set to `False` will likely succeed, but it can result in arbitrary code execution. Do it only if you got the file from a trusted source.
+	(2) Alternatively, to load with `weights_only=True` please check the recommended steps in the following error message.
+	WeightsUnpickler error: Unsupported global: GLOBAL numpy.core.multiarray.scalar was not an allowed global by default. Please use `torch.serialization.add_safe_globals([numpy.core.multiarray.scalar])` or the `torch.serialization.safe_globals([numpy.core.multiarray.scalar])` context manager to allowlist this global if you trust this class/function.
+
+Check the documentation of torch.load to learn more about types accepted by default with weights_only https://pytorch.org/docs/stable/generated/torch.load.html.
+[2025-08-30 00:10:07,841][07555] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000026_106496.pth...
+[2025-08-30 00:10:07,841][07555] Could not load from checkpoint, attempt 2
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.12/dist-packages/sample_factory/algo/learning/learner.py", line 281, in load_checkpoint
+    checkpoint_dict = torch.load(latest_checkpoint, map_location=device)
+                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/usr/local/lib/python3.12/dist-packages/torch/serialization.py", line 1529, in load
+    raise pickle.UnpicklingError(_get_wo_message(str(e))) from None
+_pickle.UnpicklingError: Weights only load failed. This file can still be loaded, to do so you have two options, do those steps only if you trust the source of the checkpoint. 
+	(1) In PyTorch 2.6, we changed the default value of the `weights_only` argument in `torch.load` from `False` to `True`. Re-running `torch.load` with `weights_only` set to `False` will likely succeed, but it can result in arbitrary code execution. Do it only if you got the file from a trusted source.
+	(2) Alternatively, to load with `weights_only=True` please check the recommended steps in the following error message.
+	WeightsUnpickler error: Unsupported global: GLOBAL numpy.core.multiarray.scalar was not an allowed global by default. Please use `torch.serialization.add_safe_globals([numpy.core.multiarray.scalar])` or the `torch.serialization.safe_globals([numpy.core.multiarray.scalar])` context manager to allowlist this global if you trust this class/function.
+
+Check the documentation of torch.load to learn more about types accepted by default with weights_only https://pytorch.org/docs/stable/generated/torch.load.html.
+[2025-08-30 00:10:07,842][07555] Did not load from checkpoint, starting from scratch!
+[2025-08-30 00:10:07,842][07555] Initialized policy 0 weights for model version 0
+[2025-08-30 00:10:07,845][07555] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-08-30 00:10:07,851][07555] LearnerWorker_p0 finished initialization!
+[2025-08-30 00:10:08,049][07576] RunningMeanStd input shape: (3, 72, 128)
+[2025-08-30 00:10:08,050][07576] RunningMeanStd input shape: (1,)
+[2025-08-30 00:10:08,060][07576] ConvEncoder: input_channels=3
+[2025-08-30 00:10:08,151][07576] Conv encoder output size: 512
+[2025-08-30 00:10:08,151][07576] Policy head output size: 512
+[2025-08-30 00:10:08,187][02133] Inference worker 0-0 is ready!
+[2025-08-30 00:10:08,188][02133] All inference workers are ready! Signal rollout workers to start!
+[2025-08-30 00:10:08,368][07570] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-08-30 00:10:08,368][07569] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-08-30 00:10:08,370][07571] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-08-30 00:10:08,366][07568] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-08-30 00:10:08,372][07575] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-08-30 00:10:08,373][07572] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-08-30 00:10:08,369][07574] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-08-30 00:10:08,374][07573] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-08-30 00:10:08,459][02133] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2025-08-30 00:10:09,706][07572] Decorrelating experience for 0 frames...
+[2025-08-30 00:10:09,708][07571] Decorrelating experience for 0 frames...
+[2025-08-30 00:10:09,711][07575] Decorrelating experience for 0 frames...
+[2025-08-30 00:10:09,995][07568] Decorrelating experience for 0 frames...
+[2025-08-30 00:10:10,006][07573] Decorrelating experience for 0 frames...
+[2025-08-30 00:10:10,004][07569] Decorrelating experience for 0 frames...
+[2025-08-30 00:10:10,007][07574] Decorrelating experience for 0 frames...
+[2025-08-30 00:10:10,846][02133] Heartbeat connected on Batcher_0
+[2025-08-30 00:10:10,850][02133] Heartbeat connected on LearnerWorker_p0
+[2025-08-30 00:10:10,857][07572] Decorrelating experience for 32 frames...
+[2025-08-30 00:10:10,858][07571] Decorrelating experience for 32 frames...
+[2025-08-30 00:10:10,904][02133] Heartbeat connected on InferenceWorker_p0-w0
+[2025-08-30 00:10:11,182][07574] Decorrelating experience for 32 frames...
+[2025-08-30 00:10:11,195][07573] Decorrelating experience for 32 frames...
+[2025-08-30 00:10:11,200][07568] Decorrelating experience for 32 frames...
+[2025-08-30 00:10:11,445][07570] Decorrelating experience for 0 frames...
+[2025-08-30 00:10:11,448][07575] Decorrelating experience for 32 frames...
+[2025-08-30 00:10:12,475][07569] Decorrelating experience for 32 frames...
+[2025-08-30 00:10:12,544][07572] Decorrelating experience for 64 frames...
+[2025-08-30 00:10:12,849][07570] Decorrelating experience for 32 frames...
+[2025-08-30 00:10:13,262][07575] Decorrelating experience for 64 frames...
+[2025-08-30 00:10:13,459][02133] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2025-08-30 00:10:13,483][07574] Decorrelating experience for 64 frames...
+[2025-08-30 00:10:13,494][07568] Decorrelating experience for 64 frames...
+[2025-08-30 00:10:13,501][07573] Decorrelating experience for 64 frames...
+[2025-08-30 00:10:14,544][07571] Decorrelating experience for 64 frames...
+[2025-08-30 00:10:14,673][07569] Decorrelating experience for 64 frames...
+[2025-08-30 00:10:15,469][07573] Decorrelating experience for 96 frames...
+[2025-08-30 00:10:15,839][07575] Decorrelating experience for 96 frames...
+[2025-08-30 00:10:15,883][02133] Heartbeat connected on RolloutWorker_w6
+[2025-08-30 00:10:16,073][07572] Decorrelating experience for 96 frames...
+[2025-08-30 00:10:16,086][07570] Decorrelating experience for 64 frames...
+[2025-08-30 00:10:16,533][02133] Heartbeat connected on RolloutWorker_w3
+[2025-08-30 00:10:16,763][02133] Heartbeat connected on RolloutWorker_w7
+[2025-08-30 00:10:17,156][07571] Decorrelating experience for 96 frames...
+[2025-08-30 00:10:17,742][02133] Heartbeat connected on RolloutWorker_w1
+[2025-08-30 00:10:17,978][07568] Decorrelating experience for 96 frames...
+[2025-08-30 00:10:18,159][07574] Decorrelating experience for 96 frames...
+[2025-08-30 00:10:18,459][02133] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 2.8. Samples: 28. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2025-08-30 00:10:18,461][02133] Avg episode reward: [(0, '1.067')]
+[2025-08-30 00:10:18,473][07569] Decorrelating experience for 96 frames...
+[2025-08-30 00:10:18,495][02133] Heartbeat connected on RolloutWorker_w2
+[2025-08-30 00:10:18,768][02133] Heartbeat connected on RolloutWorker_w0
+[2025-08-30 00:10:18,780][07570] Decorrelating experience for 96 frames...
+[2025-08-30 00:10:19,058][02133] Heartbeat connected on RolloutWorker_w4
+[2025-08-30 00:10:19,079][02133] Heartbeat connected on RolloutWorker_w5
+[2025-08-30 00:10:20,881][07555] Signal inference workers to stop experience collection...
+[2025-08-30 00:10:20,894][07576] InferenceWorker_p0-w0: stopping experience collection
+[2025-08-30 00:10:22,382][07555] Signal inference workers to resume experience collection...
+[2025-08-30 00:10:22,384][07576] InferenceWorker_p0-w0: resuming experience collection
+[2025-08-30 00:10:23,459][02133] Fps is (10 sec: 1228.8, 60 sec: 819.2, 300 sec: 819.2). Total num frames: 12288. Throughput: 0: 220.3. Samples: 3304. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+[2025-08-30 00:10:23,462][02133] Avg episode reward: [(0, '2.552')]
+[2025-08-30 00:10:28,459][02133] Fps is (10 sec: 3276.8, 60 sec: 1638.4, 300 sec: 1638.4). Total num frames: 32768. Throughput: 0: 345.2. Samples: 6904. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-08-30 00:10:28,460][02133] Avg episode reward: [(0, '3.840')]
+[2025-08-30 00:10:30,042][07576] Updated weights for policy 0, policy_version 10 (0.0095)
+[2025-08-30 00:10:33,459][02133] Fps is (10 sec: 3686.4, 60 sec: 1966.1, 300 sec: 1966.1). Total num frames: 49152. Throughput: 0: 502.7. Samples: 12568. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-08-30 00:10:33,460][02133] Avg episode reward: [(0, '4.421')]
+[2025-08-30 00:10:38,459][02133] Fps is (10 sec: 4096.0, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 73728. Throughput: 0: 641.7. Samples: 19250. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-08-30 00:10:38,463][02133] Avg episode reward: [(0, '4.386')]
+[2025-08-30 00:10:39,670][07576] Updated weights for policy 0, policy_version 20 (0.0023)
+[2025-08-30 00:10:43,459][02133] Fps is (10 sec: 4915.2, 60 sec: 2808.7, 300 sec: 2808.7). Total num frames: 98304. Throughput: 0: 655.6. Samples: 22946. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-08-30 00:10:43,463][02133] Avg episode reward: [(0, '4.373')]
+[2025-08-30 00:10:48,459][02133] Fps is (10 sec: 3686.4, 60 sec: 2764.8, 300 sec: 2764.8). Total num frames: 110592. Throughput: 0: 704.9. Samples: 28196. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-08-30 00:10:48,461][02133] Avg episode reward: [(0, '4.323')]
+[2025-08-30 00:10:48,466][07555] Saving new best policy, reward=4.323!
+[2025-08-30 00:10:50,391][07576] Updated weights for policy 0, policy_version 30 (0.0031)
+[2025-08-30 00:10:53,459][02133] Fps is (10 sec: 3686.4, 60 sec: 3003.7, 300 sec: 3003.7). Total num frames: 135168. Throughput: 0: 774.2. Samples: 34838. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-08-30 00:10:53,463][02133] Avg episode reward: [(0, '4.347')]
+[2025-08-30 00:10:53,467][07555] Saving new best policy, reward=4.347!
+[2025-08-30 00:10:58,459][02133] Fps is (10 sec: 4915.2, 60 sec: 3194.9, 300 sec: 3194.9). Total num frames: 159744. Throughput: 0: 854.3. Samples: 38442. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-08-30 00:10:58,460][02133] Avg episode reward: [(0, '4.387')]
+[2025-08-30 00:10:58,466][07555] Saving new best policy, reward=4.387!
+[2025-08-30 00:10:59,068][07576] Updated weights for policy 0, policy_version 40 (0.0016)
+[2025-08-30 00:11:03,459][02133] Fps is (10 sec: 4096.0, 60 sec: 3202.3, 300 sec: 3202.3). Total num frames: 176128. Throughput: 0: 973.0. Samples: 43814. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-08-30 00:11:03,463][02133] Avg episode reward: [(0, '4.307')]
+[2025-08-30 00:11:08,459][02133] Fps is (10 sec: 4096.0, 60 sec: 3345.1, 300 sec: 3345.1). Total num frames: 200704. Throughput: 0: 1054.3. Samples: 50746. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-08-30 00:11:08,460][02133] Avg episode reward: [(0, '4.405')]
+[2025-08-30 00:11:08,464][07555] Saving new best policy, reward=4.405!
+[2025-08-30 00:11:09,147][07576] Updated weights for policy 0, policy_version 50 (0.0028)
+[2025-08-30 00:11:13,459][02133] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3402.8). Total num frames: 221184. Throughput: 0: 1053.6. Samples: 54316. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-08-30 00:11:13,463][02133] Avg episode reward: [(0, '4.508')]
+[2025-08-30 00:11:13,476][07555] Saving new best policy, reward=4.508!
+[2025-08-30 00:11:18,459][02133] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3393.8). Total num frames: 237568. Throughput: 0: 1045.8. Samples: 59628. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2025-08-30 00:11:18,466][02133] Avg episode reward: [(0, '4.578')]
+[2025-08-30 00:11:18,475][07555] Saving new best policy, reward=4.578!
+[2025-08-30 00:11:19,490][07576] Updated weights for policy 0, policy_version 60 (0.0016)
+[2025-08-30 00:11:23,459][02133] Fps is (10 sec: 4096.0, 60 sec: 4164.3, 300 sec: 3495.3). Total num frames: 262144. Throughput: 0: 1048.6. Samples: 66438. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-08-30 00:11:23,463][02133] Avg episode reward: [(0, '4.495')]
+[2025-08-30 00:11:28,113][07576] Updated weights for policy 0, policy_version 70 (0.0022)
+[2025-08-30 00:11:28,459][02133] Fps is (10 sec: 4915.1, 60 sec: 4232.5, 300 sec: 3584.0). Total num frames: 286720. Throughput: 0: 1049.0. Samples: 70150. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-08-30 00:11:28,465][02133] Avg episode reward: [(0, '4.637')]
+[2025-08-30 00:11:28,471][07555] Saving new best policy, reward=4.637!
+[2025-08-30 00:11:33,459][02133] Fps is (10 sec: 4096.0, 60 sec: 4232.5, 300 sec: 3565.9). Total num frames: 303104. Throughput: 0: 1045.6. Samples: 75246. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-08-30 00:11:33,464][02133] Avg episode reward: [(0, '4.447')]
+[2025-08-30 00:11:38,353][07576] Updated weights for policy 0, policy_version 80 (0.0011)
+[2025-08-30 00:11:38,459][02133] Fps is (10 sec: 4096.1, 60 sec: 4232.5, 300 sec: 3640.9). Total num frames: 327680. Throughput: 0: 1056.9. Samples: 82400. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-08-30 00:11:38,461][02133] Avg episode reward: [(0, '4.378')]
+[2025-08-30 00:11:43,461][02133] Fps is (10 sec: 4505.4, 60 sec: 4164.2, 300 sec: 3664.8). Total num frames: 348160. Throughput: 0: 1056.3. Samples: 85974. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-08-30 00:11:43,464][02133] Avg episode reward: [(0, '4.573')]
+[2025-08-30 00:11:48,459][02133] Fps is (10 sec: 3686.4, 60 sec: 4232.5, 300 sec: 3645.4). Total num frames: 364544. Throughput: 0: 1048.1. Samples: 90980. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2025-08-30 00:11:48,462][02133] Avg episode reward: [(0, '4.632')]
+[2025-08-30 00:11:48,467][07555] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000089_364544.pth...
+[2025-08-30 00:11:48,832][07576] Updated weights for policy 0, policy_version 90 (0.0028)
+[2025-08-30 00:11:53,459][02133] Fps is (10 sec: 4096.2, 60 sec: 4232.5, 300 sec: 3705.9). Total num frames: 389120. Throughput: 0: 1050.3. Samples: 98010. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-08-30 00:11:53,463][02133] Avg episode reward: [(0, '4.556')]
+[2025-08-30 00:11:57,374][07576] Updated weights for policy 0, policy_version 100 (0.0014)
+[2025-08-30 00:11:58,461][02133] Fps is (10 sec: 4504.8, 60 sec: 4164.1, 300 sec: 3723.6). Total num frames: 409600. Throughput: 0: 1052.8. Samples: 101694. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2025-08-30 00:11:58,462][02133] Avg episode reward: [(0, '4.577')]
+[2025-08-30 00:12:03,460][02133] Fps is (10 sec: 4095.7, 60 sec: 4232.5, 300 sec: 3739.8). Total num frames: 430080. Throughput: 0: 1045.8. Samples: 106690. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-08-30 00:12:03,464][02133] Avg episode reward: [(0, '4.485')]
+[2025-08-30 00:12:07,741][07576] Updated weights for policy 0, policy_version 110 (0.0016)
+[2025-08-30 00:12:08,459][02133] Fps is (10 sec: 4096.7, 60 sec: 4164.3, 300 sec: 3754.7). Total num frames: 450560. Throughput: 0: 1054.0. Samples: 113866. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-08-30 00:12:08,466][02133] Avg episode reward: [(0, '4.489')]
+[2025-08-30 00:12:13,461][02133] Fps is (10 sec: 4504.9, 60 sec: 4232.4, 300 sec: 3801.0). Total num frames: 475136. Throughput: 0: 1052.2. Samples: 117502. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2025-08-30 00:12:13,463][02133] Avg episode reward: [(0, '4.714')]
+[2025-08-30 00:12:13,471][07555] Saving new best policy, reward=4.714!
+[2025-08-30 00:12:18,053][07576] Updated weights for policy 0, policy_version 120 (0.0024)
+[2025-08-30 00:12:18,459][02133] Fps is (10 sec: 4096.0, 60 sec: 4232.5, 300 sec: 3780.9). Total num frames: 491520. Throughput: 0: 1048.9. Samples: 122446. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-08-30 00:12:18,460][02133] Avg episode reward: [(0, '4.611')]
+[2025-08-30 00:12:23,459][02133] Fps is (10 sec: 4097.0, 60 sec: 4232.5, 300 sec: 3822.9). Total num frames: 516096. Throughput: 0: 1049.8. Samples: 129640. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-08-30 00:12:23,463][02133] Avg episode reward: [(0, '4.557')]
+[2025-08-30 00:12:26,671][07576] Updated weights for policy 0, policy_version 130 (0.0021)
+[2025-08-30 00:12:28,459][02133] Fps is (10 sec: 4505.6, 60 sec: 4164.3, 300 sec: 3832.7). Total num frames: 536576. Throughput: 0: 1047.5. Samples: 133110. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-08-30 00:12:28,468][02133] Avg episode reward: [(0, '4.613')]
+[2025-08-30 00:12:33,459][02133] Fps is (10 sec: 3686.4, 60 sec: 4164.3, 300 sec: 3813.5). Total num frames: 552960. Throughput: 0: 1046.0. Samples: 138048. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-08-30 00:12:33,463][02133] Avg episode reward: [(0, '4.702')]
+[2025-08-30 00:12:37,311][07576] Updated weights for policy 0, policy_version 140 (0.0018)
+[2025-08-30 00:12:38,459][02133] Fps is (10 sec: 4096.0, 60 sec: 4164.3, 300 sec: 3850.2). Total num frames: 577536. Throughput: 0: 1042.1. Samples: 144904. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2025-08-30 00:12:38,465][02133] Avg episode reward: [(0, '5.077')]
+[2025-08-30 00:12:38,474][07555] Saving new best policy, reward=5.077!
+[2025-08-30 00:12:43,459][02133] Fps is (10 sec: 4505.7, 60 sec: 4164.3, 300 sec: 3858.2). Total num frames: 598016. Throughput: 0: 1033.3. Samples: 148190. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-08-30 00:12:43,462][02133] Avg episode reward: [(0, '4.964')]
+[2025-08-30 00:12:48,460][02133] Fps is (10 sec: 3276.5, 60 sec: 4095.9, 300 sec: 3814.4). Total num frames: 610304. Throughput: 0: 1021.6. Samples: 152660. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2025-08-30 00:12:48,465][02133] Avg episode reward: [(0, '4.715')]
+[2025-08-30 00:12:48,488][07576] Updated weights for policy 0, policy_version 150 (0.0020)
+[2025-08-30 00:12:53,459][02133] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 3847.8). Total num frames: 634880. Throughput: 0: 1013.3. Samples: 159466. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2025-08-30 00:12:53,464][02133] Avg episode reward: [(0, '4.849')]
+[2025-08-30 00:12:57,336][07576] Updated weights for policy 0, policy_version 160 (0.0018)
+[2025-08-30 00:12:58,459][02133] Fps is (10 sec: 4505.9, 60 sec: 4096.1, 300 sec: 3855.1). Total num frames: 655360. Throughput: 0: 1012.1. Samples: 163044. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2025-08-30 00:12:58,463][02133] Avg episode reward: [(0, '4.868')]
+[2025-08-30 00:13:03,459][02133] Fps is (10 sec: 3686.4, 60 sec: 4027.8, 300 sec: 3838.5). Total num frames: 671744. Throughput: 0: 1009.6. Samples: 167876. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2025-08-30 00:13:03,463][02133] Avg episode reward: [(0, '4.680')]
+[2025-08-30 00:13:07,855][07576] Updated weights for policy 0, policy_version 170 (0.0013)
+[2025-08-30 00:13:08,459][02133] Fps is (10 sec: 4096.1, 60 sec: 4096.0, 300 sec: 3868.4). Total num frames: 696320. Throughput: 0: 1009.0. Samples: 175046. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-08-30 00:13:08,463][02133] Avg episode reward: [(0, '4.664')]
+[2025-08-30 00:13:13,459][02133] Fps is (10 sec: 4915.2, 60 sec: 4096.2, 300 sec: 3896.7). Total num frames: 720896. Throughput: 0: 1012.9. Samples: 178690. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-08-30 00:13:13,460][02133] Avg episode reward: [(0, '4.963')]
+[2025-08-30 00:13:18,315][07576] Updated weights for policy 0, policy_version 180 (0.0022)
+[2025-08-30 00:13:18,459][02133] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 3880.4). Total num frames: 737280. Throughput: 0: 1012.6. Samples: 183614. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-08-30 00:13:18,460][02133] Avg episode reward: [(0, '5.224')]
+[2025-08-30 00:13:18,467][07555] Saving new best policy, reward=5.224!
+[2025-08-30 00:13:23,459][02133] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3886.0). Total num frames: 757760. Throughput: 0: 1016.9. Samples: 190666. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-08-30 00:13:23,463][02133] Avg episode reward: [(0, '5.501')]
+[2025-08-30 00:13:23,546][07555] Saving new best policy, reward=5.501!
+[2025-08-30 00:13:27,376][07576] Updated weights for policy 0, policy_version 190 (0.0018)
+[2025-08-30 00:13:28,460][02133] Fps is (10 sec: 4095.7, 60 sec: 4027.7, 300 sec: 3891.2). Total num frames: 778240. Throughput: 0: 1021.8. Samples: 194170. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-08-30 00:13:28,464][02133] Avg episode reward: [(0, '5.684')]
+[2025-08-30 00:13:28,476][07555] Saving new best policy, reward=5.684!
+[2025-08-30 00:13:33,459][02133] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 3896.2). Total num frames: 798720. Throughput: 0: 1032.9. Samples: 199140. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-08-30 00:13:33,464][02133] Avg episode reward: [(0, '5.653')]
+[2025-08-30 00:13:37,372][07576] Updated weights for policy 0, policy_version 200 (0.0023)
+[2025-08-30 00:13:38,459][02133] Fps is (10 sec: 4505.9, 60 sec: 4096.0, 300 sec: 3920.5). Total num frames: 823296. Throughput: 0: 1042.9. Samples: 206398. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-08-30 00:13:38,463][02133] Avg episode reward: [(0, '5.665')]
+[2025-08-30 00:13:43,460][02133] Fps is (10 sec: 4505.2, 60 sec: 4095.9, 300 sec: 3924.5). Total num frames: 843776. Throughput: 0: 1044.0. Samples: 210024. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-08-30 00:13:43,464][02133] Avg episode reward: [(0, '5.705')]
+[2025-08-30 00:13:43,465][07555] Saving new best policy, reward=5.705!
+[2025-08-30 00:13:47,677][07576] Updated weights for policy 0, policy_version 210 (0.0012)
+[2025-08-30 00:13:48,459][02133] Fps is (10 sec: 3686.5, 60 sec: 4164.3, 300 sec: 3909.8). Total num frames: 860160. Throughput: 0: 1045.1. Samples: 214906. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-08-30 00:13:48,462][02133] Avg episode reward: [(0, '5.644')]
+[2025-08-30 00:13:48,468][07555] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000210_860160.pth...
+[2025-08-30 00:13:48,592][07555] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000026_106496.pth
+[2025-08-30 00:13:53,459][02133] Fps is (10 sec: 4096.4, 60 sec: 4164.3, 300 sec: 3932.2). Total num frames: 884736. Throughput: 0: 1042.7. Samples: 221966. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-08-30 00:13:53,463][02133] Avg episode reward: [(0, '5.383')]
+[2025-08-30 00:13:56,361][07576] Updated weights for policy 0, policy_version 220 (0.0016)
+[2025-08-30 00:13:58,459][02133] Fps is (10 sec: 4505.6, 60 sec: 4164.3, 300 sec: 3935.7). Total num frames: 905216. Throughput: 0: 1041.5. Samples: 225558. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2025-08-30 00:13:58,465][02133] Avg episode reward: [(0, '6.183')]
+[2025-08-30 00:13:58,471][07555] Saving new best policy, reward=6.183!
+[2025-08-30 00:14:03,459][02133] Fps is (10 sec: 4096.0, 60 sec: 4232.5, 300 sec: 3939.1). Total num frames: 925696. Throughput: 0: 1042.1. Samples: 230510. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2025-08-30 00:14:03,463][02133] Avg episode reward: [(0, '6.369')]
+[2025-08-30 00:14:03,467][07555] Saving new best policy, reward=6.369!
+[2025-08-30 00:14:06,935][07576] Updated weights for policy 0, policy_version 230 (0.0015)
+[2025-08-30 00:14:08,459][02133] Fps is (10 sec: 4096.0, 60 sec: 4164.3, 300 sec: 3942.4). Total num frames: 946176. Throughput: 0: 1041.7. Samples: 237544. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-08-30 00:14:08,463][02133] Avg episode reward: [(0, '6.839')]
+[2025-08-30 00:14:08,470][07555] Saving new best policy, reward=6.839!
+[2025-08-30 00:14:13,463][02133] Fps is (10 sec: 4095.0, 60 sec: 4095.8, 300 sec: 3945.5). Total num frames: 966656. Throughput: 0: 1041.3. Samples: 241032. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-08-30 00:14:13,468][02133] Avg episode reward: [(0, '7.071')]
+[2025-08-30 00:14:13,470][07555] Saving new best policy, reward=7.071!
+[2025-08-30 00:14:17,488][07576] Updated weights for policy 0, policy_version 240 (0.0027)
+[2025-08-30 00:14:18,459][02133] Fps is (10 sec: 4096.0, 60 sec: 4164.3, 300 sec: 3948.5). Total num frames: 987136. Throughput: 0: 1043.1. Samples: 246078. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-08-30 00:14:18,463][02133] Avg episode reward: [(0, '8.004')]
+[2025-08-30 00:14:18,469][07555] Saving new best policy, reward=8.004!
+[2025-08-30 00:14:22,764][07555] Stopping Batcher_0...
+[2025-08-30 00:14:22,764][07555] Loop batcher_evt_loop terminating...
+[2025-08-30 00:14:22,765][02133] Component Batcher_0 stopped!
+[2025-08-30 00:14:22,768][07555] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000246_1007616.pth...
+[2025-08-30 00:14:22,897][07555] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000089_364544.pth
+[2025-08-30 00:14:22,909][07555] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000246_1007616.pth...
+[2025-08-30 00:14:22,913][07576] Weights refcount: 2 0
+[2025-08-30 00:14:22,930][02133] Component InferenceWorker_p0-w0 stopped!
+[2025-08-30 00:14:22,931][07576] Stopping InferenceWorker_p0-w0...
+[2025-08-30 00:14:22,934][07576] Loop inference_proc0-0_evt_loop terminating...
+[2025-08-30 00:14:23,115][02133] Component LearnerWorker_p0 stopped!
+[2025-08-30 00:14:23,119][07555] Stopping LearnerWorker_p0...
+[2025-08-30 00:14:23,119][07555] Loop learner_proc0_evt_loop terminating...
+[2025-08-30 00:14:23,565][02133] Component RolloutWorker_w6 stopped!
+[2025-08-30 00:14:23,568][07573] Stopping RolloutWorker_w6...
+[2025-08-30 00:14:23,575][07573] Loop rollout_proc6_evt_loop terminating...
+[2025-08-30 00:14:23,593][07571] Stopping RolloutWorker_w1...
+[2025-08-30 00:14:23,594][07571] Loop rollout_proc1_evt_loop terminating...
+[2025-08-30 00:14:23,593][02133] Component RolloutWorker_w1 stopped!
+[2025-08-30 00:14:23,601][07572] Stopping RolloutWorker_w7...
+[2025-08-30 00:14:23,601][02133] Component RolloutWorker_w7 stopped!
+[2025-08-30 00:14:23,603][07572] Loop rollout_proc7_evt_loop terminating...
+[2025-08-30 00:14:23,622][07575] Stopping RolloutWorker_w3...
+[2025-08-30 00:14:23,622][02133] Component RolloutWorker_w3 stopped!
+[2025-08-30 00:14:23,633][07570] Stopping RolloutWorker_w5...
+[2025-08-30 00:14:23,633][02133] Component RolloutWorker_w5 stopped!
+[2025-08-30 00:14:23,623][07575] Loop rollout_proc3_evt_loop terminating...
+[2025-08-30 00:14:23,634][07570] Loop rollout_proc5_evt_loop terminating...
+[2025-08-30 00:14:23,648][02133] Component RolloutWorker_w4 stopped!
+[2025-08-30 00:14:23,649][07569] Stopping RolloutWorker_w4...
+[2025-08-30 00:14:23,650][07569] Loop rollout_proc4_evt_loop terminating...
+[2025-08-30 00:14:23,663][02133] Component RolloutWorker_w0 stopped!
+[2025-08-30 00:14:23,664][07574] Stopping RolloutWorker_w0...
+[2025-08-30 00:14:23,665][07574] Loop rollout_proc0_evt_loop terminating...
+[2025-08-30 00:14:23,724][02133] Component RolloutWorker_w2 stopped!
+[2025-08-30 00:14:23,727][02133] Waiting for process learner_proc0 to stop...
+[2025-08-30 00:14:23,730][07568] Stopping RolloutWorker_w2...
+[2025-08-30 00:14:23,741][07568] Loop rollout_proc2_evt_loop terminating...
+[2025-08-30 00:14:25,085][02133] Waiting for process inference_proc0-0 to join...
+[2025-08-30 00:14:25,090][02133] Waiting for process rollout_proc0 to join...
+[2025-08-30 00:14:27,614][02133] Waiting for process rollout_proc1 to join...
+[2025-08-30 00:14:27,918][02133] Waiting for process rollout_proc2 to join...
+[2025-08-30 00:14:27,920][02133] Waiting for process rollout_proc3 to join...
+[2025-08-30 00:14:27,921][02133] Waiting for process rollout_proc4 to join...
+[2025-08-30 00:14:27,922][02133] Waiting for process rollout_proc5 to join...
+[2025-08-30 00:14:27,923][02133] Waiting for process rollout_proc6 to join...
+[2025-08-30 00:14:27,924][02133] Waiting for process rollout_proc7 to join...
+[2025-08-30 00:14:27,925][02133] Batcher 0 profile tree view:
+batching: 6.2551, releasing_batches: 0.0077
+[2025-08-30 00:14:27,927][02133] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0000
+  wait_policy_total: 107.8726
+update_model: 1.9901
+  weight_update: 0.0026
+one_step: 0.0192
+  handle_policy_step: 134.6821
+    deserialize: 3.4461, stack: 0.7702, obs_to_device_normalize: 28.2248, forward: 69.2912, send_messages: 6.8835
+    prepare_outputs: 20.1651
+      to_cpu: 12.5958
+[2025-08-30 00:14:27,928][02133] Learner 0 profile tree view:
+misc: 0.0009, prepare_batch: 4.1257
+train: 19.1130
+  epoch_init: 0.0010, minibatch_init: 0.0016, losses_postprocess: 0.1870, kl_divergence: 0.1665, after_optimizer: 8.3136
+  calculate_losses: 6.6074
+    losses_init: 0.0009, forward_head: 0.6567, bptt_initial: 4.1140, tail: 0.2923, advantages_returns: 0.0716, losses: 0.9097
+    bptt: 0.4920
+      bptt_forward_core: 0.4440
+  update: 3.7163
+    clip: 0.2445
+[2025-08-30 00:14:27,930][02133] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.0546, enqueue_policy_requests: 26.2367, env_step: 191.6451, overhead: 2.9250, complete_rollouts: 1.6959
+save_policy_outputs: 4.3974
+  split_output_tensors: 1.7725
+[2025-08-30 00:14:27,931][02133] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.0872, enqueue_policy_requests: 26.4995, env_step: 191.5837, overhead: 3.0973, complete_rollouts: 1.5555
+save_policy_outputs: 4.6519
+  split_output_tensors: 1.9002
+[2025-08-30 00:14:27,932][02133] Loop Runner_EvtLoop terminating...
+[2025-08-30 00:14:27,935][02133] Runner profile tree view:
+main_loop: 277.0532
+[2025-08-30 00:14:27,936][02133] Collected {0: 1007616}, FPS: 3636.9
+[2025-08-30 00:14:46,367][02133] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2025-08-30 00:14:46,368][02133] Overriding arg 'num_workers' with value 1 passed from command line
+[2025-08-30 00:14:46,369][02133] Adding new argument 'no_render'=True that is not in the saved config file!
+[2025-08-30 00:14:46,370][02133] Adding new argument 'save_video'=True that is not in the saved config file!
+[2025-08-30 00:14:46,371][02133] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2025-08-30 00:14:46,372][02133] Adding new argument 'video_name'=None that is not in the saved config file!
+[2025-08-30 00:14:46,373][02133] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2025-08-30 00:14:46,374][02133] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2025-08-30 00:14:46,375][02133] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2025-08-30 00:14:46,376][02133] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2025-08-30 00:14:46,376][02133] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2025-08-30 00:14:46,377][02133] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2025-08-30 00:14:46,378][02133] Adding new argument 'train_script'=None that is not in the saved config file!
+[2025-08-30 00:14:46,379][02133] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2025-08-30 00:14:46,380][02133] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2025-08-30 00:14:46,415][02133] RunningMeanStd input shape: (3, 72, 128)
+[2025-08-30 00:14:46,416][02133] RunningMeanStd input shape: (1,)
+[2025-08-30 00:14:46,427][02133] ConvEncoder: input_channels=3
+[2025-08-30 00:14:46,458][02133] Conv encoder output size: 512
+[2025-08-30 00:14:46,459][02133] Policy head output size: 512
+[2025-08-30 00:14:46,477][02133] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000246_1007616.pth...
+[2025-08-30 00:14:46,904][02133] Num frames 100...
+[2025-08-30 00:14:47,024][02133] Num frames 200...
+[2025-08-30 00:14:47,145][02133] Num frames 300...
+[2025-08-30 00:14:47,301][02133] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
+[2025-08-30 00:14:47,302][02133] Avg episode reward: 3.840, avg true_objective: 3.840
+[2025-08-30 00:14:47,326][02133] Num frames 400...
+[2025-08-30 00:14:47,451][02133] Num frames 500...
+[2025-08-30 00:14:47,575][02133] Num frames 600...
+[2025-08-30 00:14:47,698][02133] Num frames 700...
+[2025-08-30 00:14:47,823][02133] Num frames 800...
+[2025-08-30 00:14:47,958][02133] Num frames 900...
+[2025-08-30 00:14:48,089][02133] Num frames 1000...
+[2025-08-30 00:14:48,247][02133] Avg episode rewards: #0: 7.440, true rewards: #0: 5.440
+[2025-08-30 00:14:48,248][02133] Avg episode reward: 7.440, avg true_objective: 5.440
+[2025-08-30 00:14:48,267][02133] Num frames 1100...
+[2025-08-30 00:14:48,388][02133] Num frames 1200...
+[2025-08-30 00:14:48,512][02133] Num frames 1300...
+[2025-08-30 00:14:48,642][02133] Num frames 1400...
+[2025-08-30 00:14:48,771][02133] Num frames 1500...
+[2025-08-30 00:14:48,904][02133] Num frames 1600...
+[2025-08-30 00:14:49,030][02133] Num frames 1700...
+[2025-08-30 00:14:49,154][02133] Num frames 1800...
+[2025-08-30 00:14:49,312][02133] Avg episode rewards: #0: 10.280, true rewards: #0: 6.280
+[2025-08-30 00:14:49,312][02133] Avg episode reward: 10.280, avg true_objective: 6.280
+[2025-08-30 00:14:49,336][02133] Num frames 1900...
+[2025-08-30 00:14:49,457][02133] Num frames 2000...
+[2025-08-30 00:14:49,577][02133] Num frames 2100...
+[2025-08-30 00:14:49,698][02133] Num frames 2200...
+[2025-08-30 00:14:49,832][02133] Num frames 2300...
+[2025-08-30 00:14:49,884][02133] Avg episode rewards: #0: 9.250, true rewards: #0: 5.750
+[2025-08-30 00:14:49,885][02133] Avg episode reward: 9.250, avg true_objective: 5.750
+[2025-08-30 00:14:50,079][02133] Num frames 2400...
+[2025-08-30 00:14:50,254][02133] Num frames 2500...
+[2025-08-30 00:14:50,433][02133] Num frames 2600...
+[2025-08-30 00:14:50,609][02133] Num frames 2700...
+[2025-08-30 00:14:50,747][02133] Avg episode rewards: #0: 8.496, true rewards: #0: 5.496
+[2025-08-30 00:14:50,750][02133] Avg episode reward: 8.496, avg true_objective: 5.496
+[2025-08-30 00:14:50,845][02133] Num frames 2800...
+[2025-08-30 00:14:51,020][02133] Num frames 2900...
+[2025-08-30 00:14:51,191][02133] Num frames 3000...
+[2025-08-30 00:14:51,367][02133] Num frames 3100...
+[2025-08-30 00:14:51,547][02133] Num frames 3200...
+[2025-08-30 00:14:51,718][02133] Num frames 3300...
+[2025-08-30 00:14:51,818][02133] Avg episode rewards: #0: 8.707, true rewards: #0: 5.540
+[2025-08-30 00:14:51,820][02133] Avg episode reward: 8.707, avg true_objective: 5.540
+[2025-08-30 00:14:51,956][02133] Num frames 3400...
+[2025-08-30 00:14:52,144][02133] Num frames 3500...
+[2025-08-30 00:14:52,281][02133] Num frames 3600...
+[2025-08-30 00:14:52,405][02133] Num frames 3700...
+[2025-08-30 00:14:52,549][02133] Avg episode rewards: #0: 8.246, true rewards: #0: 5.389
+[2025-08-30 00:14:52,550][02133] Avg episode reward: 8.246, avg true_objective: 5.389
+[2025-08-30 00:14:52,587][02133] Num frames 3800...
+[2025-08-30 00:14:52,710][02133] Num frames 3900...
+[2025-08-30 00:14:52,837][02133] Num frames 4000...
+[2025-08-30 00:14:52,960][02133] Num frames 4100...
+[2025-08-30 00:14:53,089][02133] Num frames 4200...
+[2025-08-30 00:14:53,222][02133] Num frames 4300...
+[2025-08-30 00:14:53,342][02133] Avg episode rewards: #0: 8.435, true rewards: #0: 5.435
+[2025-08-30 00:14:53,343][02133] Avg episode reward: 8.435, avg true_objective: 5.435
+[2025-08-30 00:14:53,408][02133] Num frames 4400...
+[2025-08-30 00:14:53,532][02133] Num frames 4500...
+[2025-08-30 00:14:53,656][02133] Num frames 4600...
+[2025-08-30 00:14:53,784][02133] Num frames 4700...
+[2025-08-30 00:14:53,835][02133] Avg episode rewards: #0: 8.111, true rewards: #0: 5.222
+[2025-08-30 00:14:53,836][02133] Avg episode reward: 8.111, avg true_objective: 5.222
+[2025-08-30 00:14:53,965][02133] Num frames 4800...
+[2025-08-30 00:14:54,092][02133] Num frames 4900...
+[2025-08-30 00:14:54,226][02133] Num frames 5000...
+[2025-08-30 00:14:54,346][02133] Num frames 5100...
+[2025-08-30 00:14:54,469][02133] Num frames 5200...
+[2025-08-30 00:14:54,589][02133] Num frames 5300...
+[2025-08-30 00:14:54,710][02133] Num frames 5400...
+[2025-08-30 00:14:54,849][02133] Avg episode rewards: #0: 8.568, true rewards: #0: 5.468
+[2025-08-30 00:14:54,850][02133] Avg episode reward: 8.568, avg true_objective: 5.468
+[2025-08-30 00:15:24,708][02133] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2025-08-30 00:15:57,391][02133] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2025-08-30 00:15:57,392][02133] Overriding arg 'num_workers' with value 1 passed from command line
+[2025-08-30 00:15:57,393][02133] Adding new argument 'no_render'=True that is not in the saved config file!
+[2025-08-30 00:15:57,394][02133] Adding new argument 'save_video'=True that is not in the saved config file!
+[2025-08-30 00:15:57,395][02133] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2025-08-30 00:15:57,396][02133] Adding new argument 'video_name'=None that is not in the saved config file!
+[2025-08-30 00:15:57,397][02133] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2025-08-30 00:15:57,397][02133] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2025-08-30 00:15:57,398][02133] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2025-08-30 00:15:57,399][02133] Adding new argument 'hf_repository'='Priyam05/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2025-08-30 00:15:57,400][02133] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2025-08-30 00:15:57,401][02133] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2025-08-30 00:15:57,402][02133] Adding new argument 'train_script'=None that is not in the saved config file!
+[2025-08-30 00:15:57,403][02133] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2025-08-30 00:15:57,404][02133] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2025-08-30 00:15:57,428][02133] RunningMeanStd input shape: (3, 72, 128)
+[2025-08-30 00:15:57,563][02133] RunningMeanStd input shape: (1,)
+[2025-08-30 00:15:57,572][02133] ConvEncoder: input_channels=3
+[2025-08-30 00:15:57,603][02133] Conv encoder output size: 512
+[2025-08-30 00:15:57,603][02133] Policy head output size: 512
+[2025-08-30 00:15:57,619][02133] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000246_1007616.pth...
+[2025-08-30 00:15:58,009][02133] Num frames 100...
+[2025-08-30 00:15:58,130][02133] Num frames 200...
+[2025-08-30 00:15:58,262][02133] Num frames 300...
+[2025-08-30 00:15:58,423][02133] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
+[2025-08-30 00:15:58,424][02133] Avg episode reward: 3.840, avg true_objective: 3.840
+[2025-08-30 00:15:58,446][02133] Num frames 400...
+[2025-08-30 00:15:58,564][02133] Num frames 500...
+[2025-08-30 00:15:58,681][02133] Num frames 600...
+[2025-08-30 00:15:58,782][02133] Avg episode rewards: #0: 3.200, true rewards: #0: 3.200
+[2025-08-30 00:15:58,783][02133] Avg episode reward: 3.200, avg true_objective: 3.200
+[2025-08-30 00:15:58,855][02133] Num frames 700...
+[2025-08-30 00:15:58,975][02133] Num frames 800...
+[2025-08-30 00:15:59,096][02133] Num frames 900...
+[2025-08-30 00:15:59,229][02133] Num frames 1000...
+[2025-08-30 00:15:59,316][02133] Avg episode rewards: #0: 3.413, true rewards: #0: 3.413
+[2025-08-30 00:15:59,316][02133] Avg episode reward: 3.413, avg true_objective: 3.413
+[2025-08-30 00:15:59,408][02133] Num frames 1100...
+[2025-08-30 00:15:59,528][02133] Num frames 1200...
+[2025-08-30 00:15:59,648][02133] Num frames 1300...
+[2025-08-30 00:15:59,815][02133] Avg episode rewards: #0: 3.740, true rewards: #0: 3.490
+[2025-08-30 00:15:59,816][02133] Avg episode reward: 3.740, avg true_objective: 3.490
+[2025-08-30 00:15:59,824][02133] Num frames 1400...
+[2025-08-30 00:15:59,943][02133] Num frames 1500...
+[2025-08-30 00:16:00,060][02133] Num frames 1600...
+[2025-08-30 00:16:00,202][02133] Num frames 1700...
+[2025-08-30 00:16:00,363][02133] Avg episode rewards: #0: 3.760, true rewards: #0: 3.560
+[2025-08-30 00:16:00,364][02133] Avg episode reward: 3.760, avg true_objective: 3.560
+[2025-08-30 00:16:00,390][02133] Num frames 1800...
+[2025-08-30 00:16:00,510][02133] Num frames 1900...
+[2025-08-30 00:16:00,631][02133] Num frames 2000...
+[2025-08-30 00:16:00,758][02133] Num frames 2100...
+[2025-08-30 00:16:00,878][02133] Num frames 2200...
+[2025-08-30 00:16:00,998][02133] Num frames 2300...
+[2025-08-30 00:16:01,121][02133] Num frames 2400...
+[2025-08-30 00:16:01,245][02133] Num frames 2500...
+[2025-08-30 00:16:01,375][02133] Num frames 2600...
+[2025-08-30 00:16:01,494][02133] Num frames 2700...
+[2025-08-30 00:16:01,559][02133] Avg episode rewards: #0: 5.847, true rewards: #0: 4.513
+[2025-08-30 00:16:01,559][02133] Avg episode reward: 5.847, avg true_objective: 4.513
+[2025-08-30 00:16:01,671][02133] Num frames 2800...
+[2025-08-30 00:16:01,790][02133] Num frames 2900...
+[2025-08-30 00:16:01,925][02133] Num frames 3000...
+[2025-08-30 00:16:02,032][02133] Avg episode rewards: #0: 5.611, true rewards: #0: 4.326
+[2025-08-30 00:16:02,033][02133] Avg episode reward: 5.611, avg true_objective: 4.326
+[2025-08-30 00:16:02,156][02133] Num frames 3100...
+[2025-08-30 00:16:02,336][02133] Num frames 3200...
+[2025-08-30 00:16:02,534][02133] Avg episode rewards: #0: 5.230, true rewards: #0: 4.105
+[2025-08-30 00:16:02,535][02133] Avg episode reward: 5.230, avg true_objective: 4.105
+[2025-08-30 00:16:02,565][02133] Num frames 3300...
+[2025-08-30 00:16:02,735][02133] Num frames 3400...
+[2025-08-30 00:16:02,903][02133] Num frames 3500...
+[2025-08-30 00:16:03,069][02133] Num frames 3600...
+[2025-08-30 00:16:03,239][02133] Num frames 3700...
+[2025-08-30 00:16:03,422][02133] Num frames 3800...
+[2025-08-30 00:16:03,638][02133] Avg episode rewards: #0: 5.658, true rewards: #0: 4.324
+[2025-08-30 00:16:03,639][02133] Avg episode reward: 5.658, avg true_objective: 4.324
+[2025-08-30 00:16:03,655][02133] Num frames 3900...
+[2025-08-30 00:16:03,831][02133] Num frames 4000...
+[2025-08-30 00:16:04,011][02133] Num frames 4100...
+[2025-08-30 00:16:04,160][02133] Num frames 4200...
+[2025-08-30 00:16:04,286][02133] Num frames 4300...
+[2025-08-30 00:16:04,420][02133] Num frames 4400...
+[2025-08-30 00:16:04,521][02133] Avg episode rewards: #0: 5.836, true rewards: #0: 4.436
+[2025-08-30 00:16:04,521][02133] Avg episode reward: 5.836, avg true_objective: 4.436
+[2025-08-30 00:16:27,557][02133] Replay video saved to /content/train_dir/default_experiment/replay.mp4!