Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1741685575.58c6eccd5343

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5967de1eb6b4fb3e8de52dc222281017b0ab3ceb916b2d10efe9b18a7b61ce5
+size 192624

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 9.45 +/- 4.65
+      value: 9.69 +/- 4.55
       name: mean_reward
       verified: false
 ---

checkpoint_p0/best_000001077_4411392_reward_29.362.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eccac242858ffd706cf79d62dc95fab382b2904915cd50e39cfbbe443de7f473
+size 34929243

checkpoint_p0/checkpoint_000001180_4833280.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19e0bc8ab4b1549eb622781caf4e788f07526a4725c7c4d6b25f3bd65d484589
+size 34929669

checkpoint_p0/checkpoint_000001222_5005312.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:880715179abc52649cb84d05e676e960b7305ab19d34d482d43e0ecf7ab5c74d
+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 sha256:2213a985462be2654f1fcb5739a9191306ba7dac2e989064872c98087b78a2ba
-size 18776142
+oid sha256:cb2b60f48e3b9f6c51076117c170c9009f4ac5e93eeccff797ccea01543a7df9
+size 18477134

sf_log.txt

@@ -1069,3 +1069,834 @@ main_loop: 1085.5647
 [2025-03-11 09:30:26,421][01034] Avg episode rewards: #0: 21.954, true rewards: #0: 9.454
 [2025-03-11 09:30:26,422][01034] Avg episode reward: 21.954, avg true_objective: 9.454
 [2025-03-11 09:31:19,097][01034] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2025-03-11 09:31:25,046][01034] The model has been pushed to https://huggingface.co/so7en/Doom_unit8_2
+[2025-03-11 09:32:55,246][01034] Environment doom_basic already registered, overwriting...
+[2025-03-11 09:32:55,247][01034] Environment doom_two_colors_easy already registered, overwriting...
+[2025-03-11 09:32:55,253][01034] Environment doom_two_colors_hard already registered, overwriting...
+[2025-03-11 09:32:55,254][01034] Environment doom_dm already registered, overwriting...
+[2025-03-11 09:32:55,255][01034] Environment doom_dwango5 already registered, overwriting...
+[2025-03-11 09:32:55,256][01034] Environment doom_my_way_home_flat_actions already registered, overwriting...
+[2025-03-11 09:32:55,260][01034] Environment doom_defend_the_center_flat_actions already registered, overwriting...
+[2025-03-11 09:32:55,261][01034] Environment doom_my_way_home already registered, overwriting...
+[2025-03-11 09:32:55,264][01034] Environment doom_deadly_corridor already registered, overwriting...
+[2025-03-11 09:32:55,268][01034] Environment doom_defend_the_center already registered, overwriting...
+[2025-03-11 09:32:55,271][01034] Environment doom_defend_the_line already registered, overwriting...
+[2025-03-11 09:32:55,272][01034] Environment doom_health_gathering already registered, overwriting...
+[2025-03-11 09:32:55,274][01034] Environment doom_health_gathering_supreme already registered, overwriting...
+[2025-03-11 09:32:55,278][01034] Environment doom_battle already registered, overwriting...
+[2025-03-11 09:32:55,279][01034] Environment doom_battle2 already registered, overwriting...
+[2025-03-11 09:32:55,283][01034] Environment doom_duel_bots already registered, overwriting...
+[2025-03-11 09:32:55,284][01034] Environment doom_deathmatch_bots already registered, overwriting...
+[2025-03-11 09:32:55,289][01034] Environment doom_duel already registered, overwriting...
+[2025-03-11 09:32:55,290][01034] Environment doom_deathmatch_full already registered, overwriting...
+[2025-03-11 09:32:55,290][01034] Environment doom_benchmark already registered, overwriting...
+[2025-03-11 09:32:55,296][01034] register_encoder_factory: <function make_vizdoom_encoder at 0x79692d1f59e0>
+[2025-03-11 09:32:55,330][01034] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2025-03-11 09:32:55,338][01034] Overriding arg 'train_for_env_steps' with value 5000000 passed from command line
+[2025-03-11 09:32:55,350][01034] Experiment dir /content/train_dir/default_experiment already exists!
+[2025-03-11 09:32:55,353][01034] Resuming existing experiment from /content/train_dir/default_experiment...
+[2025-03-11 09:32:55,357][01034] Weights and Biases integration disabled
+[2025-03-11 09:32:55,361][01034] Environment var CUDA_VISIBLE_DEVICES is 0
+
+[2025-03-11 09:32:59,335][01034] 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
+[2025-03-11 09:32:59,337][01034] Saving configuration to /content/train_dir/default_experiment/config.json...
+[2025-03-11 09:32:59,339][01034] Rollout worker 0 uses device cpu
+[2025-03-11 09:32:59,339][01034] Rollout worker 1 uses device cpu
+[2025-03-11 09:32:59,342][01034] Rollout worker 2 uses device cpu
+[2025-03-11 09:32:59,345][01034] Rollout worker 3 uses device cpu
+[2025-03-11 09:32:59,345][01034] Rollout worker 4 uses device cpu
+[2025-03-11 09:32:59,346][01034] Rollout worker 5 uses device cpu
+[2025-03-11 09:32:59,347][01034] Rollout worker 6 uses device cpu
+[2025-03-11 09:32:59,348][01034] Rollout worker 7 uses device cpu
+[2025-03-11 09:32:59,427][01034] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-03-11 09:32:59,427][01034] InferenceWorker_p0-w0: min num requests: 2
+[2025-03-11 09:32:59,462][01034] Starting all processes...
+[2025-03-11 09:32:59,463][01034] Starting process learner_proc0
+[2025-03-11 09:32:59,513][01034] Starting all processes...
+[2025-03-11 09:32:59,519][01034] Starting process inference_proc0-0
+[2025-03-11 09:32:59,524][01034] Starting process rollout_proc0
+[2025-03-11 09:32:59,524][01034] Starting process rollout_proc1
+[2025-03-11 09:32:59,524][01034] Starting process rollout_proc2
+[2025-03-11 09:32:59,524][01034] Starting process rollout_proc3
+[2025-03-11 09:32:59,524][01034] Starting process rollout_proc4
+[2025-03-11 09:32:59,524][01034] Starting process rollout_proc5
+[2025-03-11 09:32:59,524][01034] Starting process rollout_proc6
+[2025-03-11 09:32:59,524][01034] Starting process rollout_proc7
+[2025-03-11 09:33:14,431][11994] Worker 5 uses CPU cores [1]
+[2025-03-11 09:33:14,697][11975] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-03-11 09:33:14,698][11975] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2025-03-11 09:33:14,762][11975] Num visible devices: 1
+[2025-03-11 09:33:14,804][11988] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-03-11 09:33:14,805][11988] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2025-03-11 09:33:14,808][11975] Starting seed is not provided
+[2025-03-11 09:33:14,809][11975] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-03-11 09:33:14,810][11975] Initializing actor-critic model on device cuda:0
+[2025-03-11 09:33:14,811][11975] RunningMeanStd input shape: (3, 72, 128)
+[2025-03-11 09:33:14,813][11975] RunningMeanStd input shape: (1,)
+[2025-03-11 09:33:14,839][11993] Worker 4 uses CPU cores [0]
+[2025-03-11 09:33:14,860][11975] ConvEncoder: input_channels=3
+[2025-03-11 09:33:14,904][11988] Num visible devices: 1
+[2025-03-11 09:33:14,965][11992] Worker 3 uses CPU cores [1]
+[2025-03-11 09:33:14,966][11995] Worker 7 uses CPU cores [1]
+[2025-03-11 09:33:15,098][11991] Worker 2 uses CPU cores [0]
+[2025-03-11 09:33:15,104][11989] Worker 0 uses CPU cores [0]
+[2025-03-11 09:33:15,127][11990] Worker 1 uses CPU cores [1]
+[2025-03-11 09:33:15,175][11996] Worker 6 uses CPU cores [0]
+[2025-03-11 09:33:15,204][11975] Conv encoder output size: 512
+[2025-03-11 09:33:15,204][11975] Policy head output size: 512
+[2025-03-11 09:33:15,221][11975] Created Actor Critic model with architecture:
+[2025-03-11 09:33:15,221][11975] 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)
+  )
+)
+[2025-03-11 09:33:15,464][11975] Using optimizer <class 'torch.optim.adam.Adam'>
+[2025-03-11 09:33:16,398][11975] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2025-03-11 09:33:16,441][11975] Loading model from checkpoint
+[2025-03-11 09:33:16,444][11975] Loaded experiment state at self.train_step=978, self.env_steps=4005888
+[2025-03-11 09:33:16,444][11975] Initialized policy 0 weights for model version 978
+[2025-03-11 09:33:16,447][11975] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-03-11 09:33:16,450][11975] LearnerWorker_p0 finished initialization!
+[2025-03-11 09:33:16,707][11988] RunningMeanStd input shape: (3, 72, 128)
+[2025-03-11 09:33:16,708][11988] RunningMeanStd input shape: (1,)
+[2025-03-11 09:33:16,720][11988] ConvEncoder: input_channels=3
+[2025-03-11 09:33:16,820][11988] Conv encoder output size: 512
+[2025-03-11 09:33:16,820][11988] Policy head output size: 512
+[2025-03-11 09:33:16,855][01034] Inference worker 0-0 is ready!
+[2025-03-11 09:33:16,858][01034] All inference workers are ready! Signal rollout workers to start!
+[2025-03-11 09:33:17,136][11993] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-03-11 09:33:17,152][11995] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-03-11 09:33:17,153][11990] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-03-11 09:33:17,161][11991] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-03-11 09:33:17,170][11989] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-03-11 09:33:17,168][11996] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-03-11 09:33:17,180][11994] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-03-11 09:33:17,244][11992] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-03-11 09:33:18,192][11993] Decorrelating experience for 0 frames...
+[2025-03-11 09:33:18,200][11991] Decorrelating experience for 0 frames...
+[2025-03-11 09:33:18,492][11990] Decorrelating experience for 0 frames...
+[2025-03-11 09:33:18,491][11995] Decorrelating experience for 0 frames...
+[2025-03-11 09:33:18,523][11994] Decorrelating experience for 0 frames...
+[2025-03-11 09:33:19,418][01034] Heartbeat connected on Batcher_0
+[2025-03-11 09:33:19,424][01034] Heartbeat connected on LearnerWorker_p0
+[2025-03-11 09:33:19,466][01034] Heartbeat connected on InferenceWorker_p0-w0
+[2025-03-11 09:33:19,525][11993] Decorrelating experience for 32 frames...
+[2025-03-11 09:33:19,563][11991] Decorrelating experience for 32 frames...
+[2025-03-11 09:33:19,607][11989] Decorrelating experience for 0 frames...
+[2025-03-11 09:33:20,362][01034] 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)
+[2025-03-11 09:33:20,559][11995] Decorrelating experience for 32 frames...
+[2025-03-11 09:33:20,571][11990] Decorrelating experience for 32 frames...
+[2025-03-11 09:33:20,589][11992] Decorrelating experience for 0 frames...
+[2025-03-11 09:33:20,643][11994] Decorrelating experience for 32 frames...
+[2025-03-11 09:33:22,090][11996] Decorrelating experience for 0 frames...
+[2025-03-11 09:33:22,135][11989] Decorrelating experience for 32 frames...
+[2025-03-11 09:33:22,684][11993] Decorrelating experience for 64 frames...
+[2025-03-11 09:33:22,728][11991] Decorrelating experience for 64 frames...
+[2025-03-11 09:33:22,903][11990] Decorrelating experience for 64 frames...
+[2025-03-11 09:33:22,951][11994] Decorrelating experience for 64 frames...
+[2025-03-11 09:33:23,783][11995] Decorrelating experience for 64 frames...
+[2025-03-11 09:33:24,073][11996] Decorrelating experience for 32 frames...
+[2025-03-11 09:33:24,580][11990] Decorrelating experience for 96 frames...
+[2025-03-11 09:33:24,617][11989] Decorrelating experience for 64 frames...
+[2025-03-11 09:33:24,669][11993] Decorrelating experience for 96 frames...
+[2025-03-11 09:33:24,706][11991] Decorrelating experience for 96 frames...
+[2025-03-11 09:33:24,731][01034] Heartbeat connected on RolloutWorker_w1
+[2025-03-11 09:33:24,934][01034] Heartbeat connected on RolloutWorker_w4
+[2025-03-11 09:33:24,959][01034] Heartbeat connected on RolloutWorker_w2
+[2025-03-11 09:33:25,178][11992] Decorrelating experience for 32 frames...
+[2025-03-11 09:33:25,363][01034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4005888. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2025-03-11 09:33:26,132][11995] Decorrelating experience for 96 frames...
+[2025-03-11 09:33:26,385][01034] Heartbeat connected on RolloutWorker_w7
+[2025-03-11 09:33:27,002][11996] Decorrelating experience for 64 frames...
+[2025-03-11 09:33:27,316][11992] Decorrelating experience for 64 frames...
+[2025-03-11 09:33:28,643][11994] Decorrelating experience for 96 frames...
+[2025-03-11 09:33:29,174][01034] Heartbeat connected on RolloutWorker_w5
+[2025-03-11 09:33:29,331][11975] Signal inference workers to stop experience collection...
+[2025-03-11 09:33:29,348][11988] InferenceWorker_p0-w0: stopping experience collection
+[2025-03-11 09:33:29,617][11992] Decorrelating experience for 96 frames...
+[2025-03-11 09:33:29,725][01034] Heartbeat connected on RolloutWorker_w3
+[2025-03-11 09:33:29,861][11996] Decorrelating experience for 96 frames...
+[2025-03-11 09:33:29,982][01034] Heartbeat connected on RolloutWorker_w6
+[2025-03-11 09:33:30,098][11989] Decorrelating experience for 96 frames...
+[2025-03-11 09:33:30,179][01034] Heartbeat connected on RolloutWorker_w0
+[2025-03-11 09:33:30,362][01034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4005888. Throughput: 0: 197.8. Samples: 1978. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2025-03-11 09:33:30,363][01034] Avg episode reward: [(0, '3.446')]
+[2025-03-11 09:33:30,528][11975] Signal inference workers to resume experience collection...
+[2025-03-11 09:33:30,529][11988] InferenceWorker_p0-w0: resuming experience collection
+[2025-03-11 09:33:35,367][01034] Fps is (10 sec: 2456.7, 60 sec: 1637.8, 300 sec: 1637.8). Total num frames: 4030464. Throughput: 0: 465.6. Samples: 6986. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2025-03-11 09:33:35,370][01034] Avg episode reward: [(0, '9.019')]
+[2025-03-11 09:33:40,068][11988] Updated weights for policy 0, policy_version 988 (0.0013)
+[2025-03-11 09:33:40,362][01034] Fps is (10 sec: 4095.9, 60 sec: 2048.0, 300 sec: 2048.0). Total num frames: 4046848. Throughput: 0: 447.7. Samples: 8954. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-03-11 09:33:40,367][01034] Avg episode reward: [(0, '12.408')]
+[2025-03-11 09:33:45,362][01034] Fps is (10 sec: 4098.2, 60 sec: 2621.4, 300 sec: 2621.4). Total num frames: 4071424. Throughput: 0: 620.9. Samples: 15522. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2025-03-11 09:33:45,366][01034] Avg episode reward: [(0, '15.496')]
+[2025-03-11 09:33:48,882][11988] Updated weights for policy 0, policy_version 998 (0.0021)
+[2025-03-11 09:33:50,362][01034] Fps is (10 sec: 4505.7, 60 sec: 2867.2, 300 sec: 2867.2). Total num frames: 4091904. Throughput: 0: 733.2. Samples: 21996. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2025-03-11 09:33:50,363][01034] Avg episode reward: [(0, '16.786')]
+[2025-03-11 09:33:55,362][01034] Fps is (10 sec: 3276.8, 60 sec: 2808.7, 300 sec: 2808.7). Total num frames: 4104192. Throughput: 0: 688.9. Samples: 24112. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2025-03-11 09:33:55,363][01034] Avg episode reward: [(0, '18.035')]
+[2025-03-11 09:33:59,613][11988] Updated weights for policy 0, policy_version 1008 (0.0014)
+[2025-03-11 09:34:00,362][01034] Fps is (10 sec: 3686.4, 60 sec: 3072.0, 300 sec: 3072.0). Total num frames: 4128768. Throughput: 0: 756.0. Samples: 30240. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2025-03-11 09:34:00,363][01034] Avg episode reward: [(0, '21.810')]
+[2025-03-11 09:34:05,362][01034] Fps is (10 sec: 4915.2, 60 sec: 3276.8, 300 sec: 3276.8). Total num frames: 4153344. Throughput: 0: 832.1. Samples: 37446. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2025-03-11 09:34:05,365][01034] Avg episode reward: [(0, '22.686')]
+[2025-03-11 09:34:10,125][11988] Updated weights for policy 0, policy_version 1018 (0.0017)
+[2025-03-11 09:34:10,362][01034] Fps is (10 sec: 4096.0, 60 sec: 3276.8, 300 sec: 3276.8). Total num frames: 4169728. Throughput: 0: 882.4. Samples: 39708. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-03-11 09:34:10,363][01034] Avg episode reward: [(0, '23.657')]
+[2025-03-11 09:34:15,362][01034] Fps is (10 sec: 4096.0, 60 sec: 3425.7, 300 sec: 3425.7). Total num frames: 4194304. Throughput: 0: 982.0. Samples: 46168. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-03-11 09:34:15,363][01034] Avg episode reward: [(0, '25.134')]
+[2025-03-11 09:34:18,601][11988] Updated weights for policy 0, policy_version 1028 (0.0017)
+[2025-03-11 09:34:20,362][01034] Fps is (10 sec: 4505.5, 60 sec: 3481.6, 300 sec: 3481.6). Total num frames: 4214784. Throughput: 0: 1029.5. Samples: 53308. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-03-11 09:34:20,363][01034] Avg episode reward: [(0, '25.168')]
+[2025-03-11 09:34:25,362][01034] Fps is (10 sec: 3686.4, 60 sec: 3754.8, 300 sec: 3465.8). Total num frames: 4231168. Throughput: 0: 1034.4. Samples: 55500. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-03-11 09:34:25,363][01034] Avg episode reward: [(0, '25.489')]
+[2025-03-11 09:34:25,371][11975] Saving new best policy, reward=25.489!
+[2025-03-11 09:34:28,907][11988] Updated weights for policy 0, policy_version 1038 (0.0029)
+[2025-03-11 09:34:30,362][01034] Fps is (10 sec: 4096.1, 60 sec: 4164.3, 300 sec: 3569.4). Total num frames: 4255744. Throughput: 0: 1029.4. Samples: 61844. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2025-03-11 09:34:30,368][01034] Avg episode reward: [(0, '25.401')]
+[2025-03-11 09:34:35,362][01034] Fps is (10 sec: 3686.4, 60 sec: 3959.8, 300 sec: 3495.3). Total num frames: 4268032. Throughput: 0: 992.1. Samples: 66642. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2025-03-11 09:34:35,366][01034] Avg episode reward: [(0, '25.305')]
+[2025-03-11 09:34:40,362][01034] Fps is (10 sec: 2867.2, 60 sec: 3959.5, 300 sec: 3481.6). Total num frames: 4284416. Throughput: 0: 992.8. Samples: 68786. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2025-03-11 09:34:40,365][01034] Avg episode reward: [(0, '25.804')]
+[2025-03-11 09:34:40,369][11975] Saving new best policy, reward=25.804!
+[2025-03-11 09:34:41,484][11988] Updated weights for policy 0, policy_version 1048 (0.0018)
+[2025-03-11 09:34:45,362][01034] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3565.9). Total num frames: 4308992. Throughput: 0: 1001.5. Samples: 75306. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-03-11 09:34:45,365][01034] Avg episode reward: [(0, '26.943')]
+[2025-03-11 09:34:45,371][11975] Saving new best policy, reward=26.943!
+[2025-03-11 09:34:50,362][01034] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3595.4). Total num frames: 4329472. Throughput: 0: 993.6. Samples: 82158. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-03-11 09:34:50,367][01034] Avg episode reward: [(0, '26.996')]
+[2025-03-11 09:34:50,385][11975] Saving new best policy, reward=26.996!
+[2025-03-11 09:34:50,393][11988] Updated weights for policy 0, policy_version 1058 (0.0023)
+[2025-03-11 09:34:55,362][01034] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3578.6). Total num frames: 4345856. Throughput: 0: 991.2. Samples: 84314. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-03-11 09:34:55,364][01034] Avg episode reward: [(0, '27.098')]
+[2025-03-11 09:34:55,444][11975] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001062_4349952.pth...
+[2025-03-11 09:34:55,589][11975] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000970_3973120.pth
+[2025-03-11 09:34:55,603][11975] Saving new best policy, reward=27.098!
+[2025-03-11 09:35:00,362][01034] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3645.4). Total num frames: 4370432. Throughput: 0: 986.2. Samples: 90548. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-03-11 09:35:00,367][01034] Avg episode reward: [(0, '27.904')]
+[2025-03-11 09:35:00,372][11975] Saving new best policy, reward=27.904!
+[2025-03-11 09:35:00,612][11988] Updated weights for policy 0, policy_version 1068 (0.0048)
+[2025-03-11 09:35:05,362][01034] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3666.9). Total num frames: 4390912. Throughput: 0: 980.5. Samples: 97430. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-03-11 09:35:05,366][01034] Avg episode reward: [(0, '29.205')]
+[2025-03-11 09:35:05,372][11975] Saving new best policy, reward=29.205!
+[2025-03-11 09:35:10,362][01034] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3686.4). Total num frames: 4411392. Throughput: 0: 978.3. Samples: 99522. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-03-11 09:35:10,367][01034] Avg episode reward: [(0, '29.362')]
+[2025-03-11 09:35:10,370][11975] Saving new best policy, reward=29.362!
+[2025-03-11 09:35:11,248][11988] Updated weights for policy 0, policy_version 1078 (0.0022)
+[2025-03-11 09:35:15,362][01034] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3704.2). Total num frames: 4431872. Throughput: 0: 985.6. Samples: 106194. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-03-11 09:35:15,366][01034] Avg episode reward: [(0, '27.649')]
+[2025-03-11 09:35:20,292][11988] Updated weights for policy 0, policy_version 1088 (0.0020)
+[2025-03-11 09:35:20,364][01034] Fps is (10 sec: 4504.4, 60 sec: 4027.6, 300 sec: 3754.6). Total num frames: 4456448. Throughput: 0: 1024.1. Samples: 112730. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2025-03-11 09:35:20,367][01034] Avg episode reward: [(0, '26.766')]
+[2025-03-11 09:35:25,362][01034] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3735.6). Total num frames: 4472832. Throughput: 0: 1024.6. Samples: 114892. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2025-03-11 09:35:25,366][01034] Avg episode reward: [(0, '26.297')]
+[2025-03-11 09:35:30,362][01034] Fps is (10 sec: 3687.3, 60 sec: 3959.5, 300 sec: 3749.4). Total num frames: 4493312. Throughput: 0: 1024.0. Samples: 121386. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2025-03-11 09:35:30,363][01034] Avg episode reward: [(0, '24.421')]
+[2025-03-11 09:35:30,760][11988] Updated weights for policy 0, policy_version 1098 (0.0034)
+[2025-03-11 09:35:35,368][01034] Fps is (10 sec: 4093.3, 60 sec: 4095.6, 300 sec: 3762.1). Total num frames: 4513792. Throughput: 0: 1015.5. Samples: 127864. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2025-03-11 09:35:35,370][01034] Avg episode reward: [(0, '24.652')]
+[2025-03-11 09:35:40,362][01034] Fps is (10 sec: 4096.0, 60 sec: 4164.3, 300 sec: 3774.2). Total num frames: 4534272. Throughput: 0: 1016.6. Samples: 130060. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-03-11 09:35:40,365][01034] Avg episode reward: [(0, '23.710')]
+[2025-03-11 09:35:41,360][11988] Updated weights for policy 0, policy_version 1108 (0.0024)
+[2025-03-11 09:35:45,362][01034] Fps is (10 sec: 4098.7, 60 sec: 4096.0, 300 sec: 3785.3). Total num frames: 4554752. Throughput: 0: 1028.6. Samples: 136834. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-03-11 09:35:45,366][01034] Avg episode reward: [(0, '24.926')]
+[2025-03-11 09:35:50,362][01034] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 3795.6). Total num frames: 4575232. Throughput: 0: 1021.3. Samples: 143388. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2025-03-11 09:35:50,366][01034] Avg episode reward: [(0, '24.932')]
+[2025-03-11 09:35:50,596][11988] Updated weights for policy 0, policy_version 1118 (0.0018)
+[2025-03-11 09:35:55,362][01034] Fps is (10 sec: 4096.0, 60 sec: 4164.3, 300 sec: 3805.3). Total num frames: 4595712. Throughput: 0: 1021.7. Samples: 145500. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2025-03-11 09:35:55,368][01034] Avg episode reward: [(0, '24.212')]
+[2025-03-11 09:36:00,362][01034] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 3814.4). Total num frames: 4616192. Throughput: 0: 1022.8. Samples: 152220. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-03-11 09:36:00,367][01034] Avg episode reward: [(0, '24.105')]
+[2025-03-11 09:36:00,587][11988] Updated weights for policy 0, policy_version 1128 (0.0021)
+[2025-03-11 09:36:05,364][01034] Fps is (10 sec: 4095.2, 60 sec: 4095.9, 300 sec: 3822.9). Total num frames: 4636672. Throughput: 0: 1020.2. Samples: 158640. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-03-11 09:36:05,365][01034] Avg episode reward: [(0, '24.591')]
+[2025-03-11 09:36:10,362][01034] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3806.9). Total num frames: 4653056. Throughput: 0: 1018.2. Samples: 160712. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-03-11 09:36:10,364][01034] Avg episode reward: [(0, '25.626')]
+[2025-03-11 09:36:11,436][11988] Updated weights for policy 0, policy_version 1138 (0.0016)
+[2025-03-11 09:36:15,362][01034] Fps is (10 sec: 4096.8, 60 sec: 4096.0, 300 sec: 3838.5). Total num frames: 4677632. Throughput: 0: 1020.0. Samples: 167286. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-03-11 09:36:15,365][01034] Avg episode reward: [(0, '26.171')]
+[2025-03-11 09:36:20,364][01034] Fps is (10 sec: 4504.6, 60 sec: 4027.8, 300 sec: 3845.6). Total num frames: 4698112. Throughput: 0: 1011.0. Samples: 173354. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2025-03-11 09:36:20,365][01034] Avg episode reward: [(0, '27.801')]
+[2025-03-11 09:36:21,961][11988] Updated weights for policy 0, policy_version 1148 (0.0024)
+[2025-03-11 09:36:25,362][01034] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3830.3). Total num frames: 4714496. Throughput: 0: 1007.4. Samples: 175392. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-03-11 09:36:25,365][01034] Avg episode reward: [(0, '29.018')]
+[2025-03-11 09:36:30,362][01034] Fps is (10 sec: 4097.0, 60 sec: 4096.0, 300 sec: 3858.9). Total num frames: 4739072. Throughput: 0: 1007.9. Samples: 182188. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-03-11 09:36:30,363][01034] Avg episode reward: [(0, '27.383')]
+[2025-03-11 09:36:31,344][11988] Updated weights for policy 0, policy_version 1158 (0.0017)
+[2025-03-11 09:36:35,362][01034] Fps is (10 sec: 4095.8, 60 sec: 4028.1, 300 sec: 3843.9). Total num frames: 4755456. Throughput: 0: 997.2. Samples: 188262. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-03-11 09:36:35,364][01034] Avg episode reward: [(0, '26.201')]
+[2025-03-11 09:36:40,362][01034] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3850.2). Total num frames: 4775936. Throughput: 0: 995.5. Samples: 190296. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2025-03-11 09:36:40,363][01034] Avg episode reward: [(0, '25.372')]
+[2025-03-11 09:36:42,078][11988] Updated weights for policy 0, policy_version 1168 (0.0029)
+[2025-03-11 09:36:45,362][01034] Fps is (10 sec: 4096.2, 60 sec: 4027.7, 300 sec: 3856.2). Total num frames: 4796416. Throughput: 0: 1000.5. Samples: 197244. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2025-03-11 09:36:45,363][01034] Avg episode reward: [(0, '24.422')]
+[2025-03-11 09:36:50,363][01034] Fps is (10 sec: 4095.7, 60 sec: 4027.7, 300 sec: 3861.9). Total num frames: 4816896. Throughput: 0: 992.2. Samples: 203286. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2025-03-11 09:36:50,364][01034] Avg episode reward: [(0, '24.667')]
+[2025-03-11 09:36:52,769][11988] Updated weights for policy 0, policy_version 1178 (0.0017)
+[2025-03-11 09:36:55,362][01034] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3848.3). Total num frames: 4833280. Throughput: 0: 992.8. Samples: 205390. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2025-03-11 09:36:55,365][01034] Avg episode reward: [(0, '25.056')]
+[2025-03-11 09:36:55,375][11975] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001180_4833280.pth...
+[2025-03-11 09:36:55,572][11975] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth
+[2025-03-11 09:37:00,362][01034] Fps is (10 sec: 4096.4, 60 sec: 4027.7, 300 sec: 3872.6). Total num frames: 4857856. Throughput: 0: 996.9. Samples: 212146. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-03-11 09:37:00,367][01034] Avg episode reward: [(0, '26.580')]
+[2025-03-11 09:37:01,909][11988] Updated weights for policy 0, policy_version 1188 (0.0013)
+[2025-03-11 09:37:05,362][01034] Fps is (10 sec: 4096.0, 60 sec: 3959.6, 300 sec: 3859.3). Total num frames: 4874240. Throughput: 0: 993.3. Samples: 218050. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-03-11 09:37:05,369][01034] Avg episode reward: [(0, '26.225')]
+[2025-03-11 09:37:10,362][01034] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3864.5). Total num frames: 4894720. Throughput: 0: 997.3. Samples: 220272. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-03-11 09:37:10,365][01034] Avg episode reward: [(0, '25.605')]
+[2025-03-11 09:37:12,703][11988] Updated weights for policy 0, policy_version 1198 (0.0013)
+[2025-03-11 09:37:15,362][01034] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3886.8). Total num frames: 4919296. Throughput: 0: 1000.5. Samples: 227212. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2025-03-11 09:37:15,365][01034] Avg episode reward: [(0, '26.486')]
+[2025-03-11 09:37:20,364][01034] Fps is (10 sec: 4095.0, 60 sec: 3959.5, 300 sec: 3874.1). Total num frames: 4935680. Throughput: 0: 996.2. Samples: 233092. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-03-11 09:37:20,365][01034] Avg episode reward: [(0, '25.940')]
+[2025-03-11 09:37:23,538][11988] Updated weights for policy 0, policy_version 1208 (0.0034)
+[2025-03-11 09:37:25,362][01034] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3878.7). Total num frames: 4956160. Throughput: 0: 1000.9. Samples: 235336. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-03-11 09:37:25,365][01034] Avg episode reward: [(0, '26.098')]
+[2025-03-11 09:37:30,362][01034] Fps is (10 sec: 4097.0, 60 sec: 3959.5, 300 sec: 3883.0). Total num frames: 4976640. Throughput: 0: 1004.2. Samples: 242432. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-03-11 09:37:30,363][01034] Avg episode reward: [(0, '26.919')]
+[2025-03-11 09:37:32,059][11988] Updated weights for policy 0, policy_version 1218 (0.0021)
+[2025-03-11 09:37:35,362][01034] Fps is (10 sec: 4096.0, 60 sec: 4027.8, 300 sec: 3887.2). Total num frames: 4997120. Throughput: 0: 1004.7. Samples: 248496. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2025-03-11 09:37:35,365][01034] Avg episode reward: [(0, '27.347')]
+[2025-03-11 09:37:37,397][11975] Stopping Batcher_0...
+[2025-03-11 09:37:37,397][11975] Loop batcher_evt_loop terminating...
+[2025-03-11 09:37:37,397][01034] Component Batcher_0 stopped!
+[2025-03-11 09:37:37,399][11975] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001222_5005312.pth...
+[2025-03-11 09:37:37,458][11988] Weights refcount: 2 0
+[2025-03-11 09:37:37,463][01034] Component InferenceWorker_p0-w0 stopped!
+[2025-03-11 09:37:37,465][11988] Stopping InferenceWorker_p0-w0...
+[2025-03-11 09:37:37,467][11988] Loop inference_proc0-0_evt_loop terminating...
+[2025-03-11 09:37:37,521][11975] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001062_4349952.pth
+[2025-03-11 09:37:37,530][11975] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001222_5005312.pth...
+[2025-03-11 09:37:37,711][11975] Stopping LearnerWorker_p0...
+[2025-03-11 09:37:37,712][01034] Component LearnerWorker_p0 stopped!
+[2025-03-11 09:37:37,715][11975] Loop learner_proc0_evt_loop terminating...
+[2025-03-11 09:37:37,767][01034] Component RolloutWorker_w6 stopped!
+[2025-03-11 09:37:37,768][11996] Stopping RolloutWorker_w6...
+[2025-03-11 09:37:37,770][01034] Component RolloutWorker_w4 stopped!
+[2025-03-11 09:37:37,772][11993] Stopping RolloutWorker_w4...
+[2025-03-11 09:37:37,768][11996] Loop rollout_proc6_evt_loop terminating...
+[2025-03-11 09:37:37,772][11993] Loop rollout_proc4_evt_loop terminating...
+[2025-03-11 09:37:37,781][01034] Component RolloutWorker_w2 stopped!
+[2025-03-11 09:37:37,782][11991] Stopping RolloutWorker_w2...
+[2025-03-11 09:37:37,788][11991] Loop rollout_proc2_evt_loop terminating...
+[2025-03-11 09:37:37,808][01034] Component RolloutWorker_w0 stopped!
+[2025-03-11 09:37:37,808][11989] Stopping RolloutWorker_w0...
+[2025-03-11 09:37:37,811][11989] Loop rollout_proc0_evt_loop terminating...
+[2025-03-11 09:37:37,955][11994] Stopping RolloutWorker_w5...
+[2025-03-11 09:37:37,955][11994] Loop rollout_proc5_evt_loop terminating...
+[2025-03-11 09:37:37,963][11995] Stopping RolloutWorker_w7...
+[2025-03-11 09:37:37,963][11995] Loop rollout_proc7_evt_loop terminating...
+[2025-03-11 09:37:37,963][01034] Component RolloutWorker_w5 stopped!
+[2025-03-11 09:37:37,966][01034] Component RolloutWorker_w7 stopped!
+[2025-03-11 09:37:37,982][11992] Stopping RolloutWorker_w3...
+[2025-03-11 09:37:37,982][01034] Component RolloutWorker_w3 stopped!
+[2025-03-11 09:37:37,993][11992] Loop rollout_proc3_evt_loop terminating...
+[2025-03-11 09:37:38,023][11990] Stopping RolloutWorker_w1...
+[2025-03-11 09:37:38,026][11990] Loop rollout_proc1_evt_loop terminating...
+[2025-03-11 09:37:38,023][01034] Component RolloutWorker_w1 stopped!
+[2025-03-11 09:37:38,027][01034] Waiting for process learner_proc0 to stop...
+[2025-03-11 09:37:39,434][01034] Waiting for process inference_proc0-0 to join...
+[2025-03-11 09:37:39,435][01034] Waiting for process rollout_proc0 to join...
+[2025-03-11 09:37:41,580][01034] Waiting for process rollout_proc1 to join...
+[2025-03-11 09:37:41,604][01034] Waiting for process rollout_proc2 to join...
+[2025-03-11 09:37:41,608][01034] Waiting for process rollout_proc3 to join...
+[2025-03-11 09:37:41,610][01034] Waiting for process rollout_proc4 to join...
+[2025-03-11 09:37:41,612][01034] Waiting for process rollout_proc5 to join...
+[2025-03-11 09:37:41,613][01034] Waiting for process rollout_proc6 to join...
+[2025-03-11 09:37:41,614][01034] Waiting for process rollout_proc7 to join...
+[2025-03-11 09:37:41,616][01034] Batcher 0 profile tree view:
+batching: 6.6567, releasing_batches: 0.0064
+[2025-03-11 09:37:41,617][01034] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0000
+  wait_policy_total: 106.0202
+update_model: 2.0983
+  weight_update: 0.0023
+one_step: 0.0027
+  handle_policy_step: 142.7545
+    deserialize: 3.5692, stack: 0.7917, obs_to_device_normalize: 30.2719, forward: 73.4046, send_messages: 6.8078
+    prepare_outputs: 21.8253
+      to_cpu: 13.4822
+[2025-03-11 09:37:41,618][01034] Learner 0 profile tree view:
+misc: 0.0010, prepare_batch: 4.1704
+train: 20.0778
+  epoch_init: 0.0011, minibatch_init: 0.0014, losses_postprocess: 0.1680, kl_divergence: 0.1749, after_optimizer: 0.7446
+  calculate_losses: 6.6746
+    losses_init: 0.0008, forward_head: 0.6318, bptt_initial: 4.0933, tail: 0.3026, advantages_returns: 0.0758, losses: 0.9827
+    bptt: 0.5234
+      bptt_forward_core: 0.5085
+  update: 12.1652
+    clip: 0.2320
+[2025-03-11 09:37:41,619][01034] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.0540, enqueue_policy_requests: 23.6359, env_step: 197.9996, overhead: 2.9385, complete_rollouts: 1.6932
+save_policy_outputs: 4.2113
+  split_output_tensors: 1.5586
+[2025-03-11 09:37:41,621][01034] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.0829, enqueue_policy_requests: 25.4075, env_step: 197.3198, overhead: 3.0436, complete_rollouts: 1.7271
+save_policy_outputs: 4.7781
+  split_output_tensors: 1.9377
+[2025-03-11 09:37:41,623][01034] Loop Runner_EvtLoop terminating...
+[2025-03-11 09:37:41,624][01034] Runner profile tree view:
+main_loop: 282.1627
+[2025-03-11 09:37:41,625][01034] Collected {0: 5005312}, FPS: 3542.0
+[2025-03-11 09:38:17,617][01034] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2025-03-11 09:38:17,619][01034] Overriding arg 'num_workers' with value 1 passed from command line
+[2025-03-11 09:38:17,620][01034] Adding new argument 'no_render'=True that is not in the saved config file!
+[2025-03-11 09:38:17,621][01034] Adding new argument 'save_video'=True that is not in the saved config file!
+[2025-03-11 09:38:17,622][01034] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2025-03-11 09:38:17,623][01034] Adding new argument 'video_name'=None that is not in the saved config file!
+[2025-03-11 09:38:17,624][01034] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2025-03-11 09:38:17,625][01034] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2025-03-11 09:38:17,626][01034] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2025-03-11 09:38:17,626][01034] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2025-03-11 09:38:17,627][01034] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2025-03-11 09:38:17,628][01034] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2025-03-11 09:38:17,629][01034] Adding new argument 'train_script'=None that is not in the saved config file!
+[2025-03-11 09:38:17,629][01034] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2025-03-11 09:38:17,630][01034] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2025-03-11 09:38:17,669][01034] RunningMeanStd input shape: (3, 72, 128)
+[2025-03-11 09:38:17,671][01034] RunningMeanStd input shape: (1,)
+[2025-03-11 09:38:17,690][01034] ConvEncoder: input_channels=3
+[2025-03-11 09:38:17,728][01034] Conv encoder output size: 512
+[2025-03-11 09:38:17,729][01034] Policy head output size: 512
+[2025-03-11 09:38:17,748][01034] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001222_5005312.pth...
+[2025-03-11 09:38:18,162][01034] Num frames 100...
+[2025-03-11 09:38:18,290][01034] Num frames 200...
+[2025-03-11 09:38:18,425][01034] Num frames 300...
+[2025-03-11 09:38:18,570][01034] Num frames 400...
+[2025-03-11 09:38:18,705][01034] Num frames 500...
+[2025-03-11 09:38:18,842][01034] Num frames 600...
+[2025-03-11 09:38:18,973][01034] Num frames 700...
+[2025-03-11 09:38:19,104][01034] Num frames 800...
+[2025-03-11 09:38:19,233][01034] Num frames 900...
+[2025-03-11 09:38:19,362][01034] Num frames 1000...
+[2025-03-11 09:38:19,500][01034] Num frames 1100...
+[2025-03-11 09:38:19,636][01034] Num frames 1200...
+[2025-03-11 09:38:19,780][01034] Num frames 1300...
+[2025-03-11 09:38:19,912][01034] Num frames 1400...
+[2025-03-11 09:38:20,045][01034] Num frames 1500...
+[2025-03-11 09:38:20,175][01034] Num frames 1600...
+[2025-03-11 09:38:20,309][01034] Num frames 1700...
+[2025-03-11 09:38:20,453][01034] Num frames 1800...
+[2025-03-11 09:38:20,582][01034] Num frames 1900...
+[2025-03-11 09:38:20,716][01034] Num frames 2000...
+[2025-03-11 09:38:20,861][01034] Num frames 2100...
+[2025-03-11 09:38:20,913][01034] Avg episode rewards: #0: 63.999, true rewards: #0: 21.000
+[2025-03-11 09:38:20,914][01034] Avg episode reward: 63.999, avg true_objective: 21.000
+[2025-03-11 09:38:21,044][01034] Num frames 2200...
+[2025-03-11 09:38:21,174][01034] Num frames 2300...
+[2025-03-11 09:38:21,305][01034] Num frames 2400...
+[2025-03-11 09:38:21,490][01034] Num frames 2500...
+[2025-03-11 09:38:21,663][01034] Num frames 2600...
+[2025-03-11 09:38:21,767][01034] Avg episode rewards: #0: 37.129, true rewards: #0: 13.130
+[2025-03-11 09:38:21,768][01034] Avg episode reward: 37.129, avg true_objective: 13.130
+[2025-03-11 09:38:21,907][01034] Num frames 2700...
+[2025-03-11 09:38:22,076][01034] Num frames 2800...
+[2025-03-11 09:38:22,247][01034] Num frames 2900...
+[2025-03-11 09:38:22,421][01034] Num frames 3000...
+[2025-03-11 09:38:22,594][01034] Num frames 3100...
+[2025-03-11 09:38:22,768][01034] Num frames 3200...
+[2025-03-11 09:38:22,958][01034] Num frames 3300...
+[2025-03-11 09:38:23,139][01034] Num frames 3400...
+[2025-03-11 09:38:23,325][01034] Num frames 3500...
+[2025-03-11 09:38:23,524][01034] Num frames 3600...
+[2025-03-11 09:38:23,682][01034] Num frames 3700...
+[2025-03-11 09:38:23,813][01034] Num frames 3800...
+[2025-03-11 09:38:23,957][01034] Num frames 3900...
+[2025-03-11 09:38:24,088][01034] Num frames 4000...
+[2025-03-11 09:38:24,216][01034] Num frames 4100...
+[2025-03-11 09:38:24,348][01034] Num frames 4200...
+[2025-03-11 09:38:24,482][01034] Avg episode rewards: #0: 38.843, true rewards: #0: 14.177
+[2025-03-11 09:38:24,483][01034] Avg episode reward: 38.843, avg true_objective: 14.177
+[2025-03-11 09:38:24,544][01034] Num frames 4300...
+[2025-03-11 09:38:24,672][01034] Num frames 4400...
+[2025-03-11 09:38:24,811][01034] Num frames 4500...
+[2025-03-11 09:38:24,950][01034] Num frames 4600...
+[2025-03-11 09:38:25,088][01034] Num frames 4700...
+[2025-03-11 09:38:25,217][01034] Num frames 4800...
+[2025-03-11 09:38:25,347][01034] Num frames 4900...
+[2025-03-11 09:38:25,484][01034] Num frames 5000...
+[2025-03-11 09:38:25,615][01034] Num frames 5100...
+[2025-03-11 09:38:25,745][01034] Num frames 5200...
+[2025-03-11 09:38:25,903][01034] Num frames 5300...
+[2025-03-11 09:38:26,040][01034] Avg episode rewards: #0: 35.372, true rewards: #0: 13.372
+[2025-03-11 09:38:26,041][01034] Avg episode reward: 35.372, avg true_objective: 13.372
+[2025-03-11 09:38:26,109][01034] Num frames 5400...
+[2025-03-11 09:38:26,241][01034] Num frames 5500...
+[2025-03-11 09:38:26,372][01034] Num frames 5600...
+[2025-03-11 09:38:26,509][01034] Num frames 5700...
+[2025-03-11 09:38:26,635][01034] Num frames 5800...
+[2025-03-11 09:38:26,768][01034] Num frames 5900...
+[2025-03-11 09:38:26,871][01034] Avg episode rewards: #0: 30.472, true rewards: #0: 11.872
+[2025-03-11 09:38:26,871][01034] Avg episode reward: 30.472, avg true_objective: 11.872
+[2025-03-11 09:38:26,955][01034] Num frames 6000...
+[2025-03-11 09:38:27,093][01034] Num frames 6100...
+[2025-03-11 09:38:27,224][01034] Num frames 6200...
+[2025-03-11 09:38:27,352][01034] Num frames 6300...
+[2025-03-11 09:38:27,486][01034] Num frames 6400...
+[2025-03-11 09:38:27,616][01034] Num frames 6500...
+[2025-03-11 09:38:27,745][01034] Num frames 6600...
+[2025-03-11 09:38:27,811][01034] Avg episode rewards: #0: 27.513, true rewards: #0: 11.013
+[2025-03-11 09:38:27,812][01034] Avg episode reward: 27.513, avg true_objective: 11.013
+[2025-03-11 09:38:27,935][01034] Num frames 6700...
+[2025-03-11 09:38:28,075][01034] Num frames 6800...
+[2025-03-11 09:38:28,202][01034] Num frames 6900...
+[2025-03-11 09:38:28,333][01034] Num frames 7000...
+[2025-03-11 09:38:28,467][01034] Num frames 7100...
+[2025-03-11 09:38:28,596][01034] Num frames 7200...
+[2025-03-11 09:38:28,724][01034] Num frames 7300...
+[2025-03-11 09:38:28,857][01034] Num frames 7400...
+[2025-03-11 09:38:28,987][01034] Num frames 7500...
+[2025-03-11 09:38:29,126][01034] Num frames 7600...
+[2025-03-11 09:38:29,257][01034] Num frames 7700...
+[2025-03-11 09:38:29,429][01034] Avg episode rewards: #0: 27.417, true rewards: #0: 11.131
+[2025-03-11 09:38:29,430][01034] Avg episode reward: 27.417, avg true_objective: 11.131
+[2025-03-11 09:38:29,442][01034] Num frames 7800...
+[2025-03-11 09:38:29,570][01034] Num frames 7900...
+[2025-03-11 09:38:29,702][01034] Num frames 8000...
+[2025-03-11 09:38:29,834][01034] Num frames 8100...
+[2025-03-11 09:38:29,963][01034] Num frames 8200...
+[2025-03-11 09:38:30,102][01034] Num frames 8300...
+[2025-03-11 09:38:30,230][01034] Num frames 8400...
+[2025-03-11 09:38:30,357][01034] Num frames 8500...
+[2025-03-11 09:38:30,493][01034] Num frames 8600...
+[2025-03-11 09:38:30,623][01034] Num frames 8700...
+[2025-03-11 09:38:30,754][01034] Num frames 8800...
+[2025-03-11 09:38:30,884][01034] Num frames 8900...
+[2025-03-11 09:38:31,014][01034] Num frames 9000...
+[2025-03-11 09:38:31,155][01034] Num frames 9100...
+[2025-03-11 09:38:31,291][01034] Num frames 9200...
+[2025-03-11 09:38:31,429][01034] Num frames 9300...
+[2025-03-11 09:38:31,561][01034] Num frames 9400...
+[2025-03-11 09:38:31,693][01034] Num frames 9500...
+[2025-03-11 09:38:31,828][01034] Num frames 9600...
+[2025-03-11 09:38:31,966][01034] Num frames 9700...
+[2025-03-11 09:38:32,102][01034] Num frames 9800...
+[2025-03-11 09:38:32,247][01034] Avg episode rewards: #0: 30.826, true rewards: #0: 12.326
+[2025-03-11 09:38:32,248][01034] Avg episode reward: 30.826, avg true_objective: 12.326
+[2025-03-11 09:38:32,299][01034] Num frames 9900...
+[2025-03-11 09:38:32,437][01034] Num frames 10000...
+[2025-03-11 09:38:32,567][01034] Num frames 10100...
+[2025-03-11 09:38:32,725][01034] Num frames 10200...
+[2025-03-11 09:38:32,855][01034] Num frames 10300...
+[2025-03-11 09:38:32,987][01034] Num frames 10400...
+[2025-03-11 09:38:33,119][01034] Num frames 10500...
+[2025-03-11 09:38:33,264][01034] Num frames 10600...
+[2025-03-11 09:38:33,392][01034] Num frames 10700...
+[2025-03-11 09:38:33,535][01034] Num frames 10800...
+[2025-03-11 09:38:33,683][01034] Num frames 10900...
+[2025-03-11 09:38:33,864][01034] Num frames 11000...
+[2025-03-11 09:38:33,988][01034] Avg episode rewards: #0: 30.595, true rewards: #0: 12.262
+[2025-03-11 09:38:33,989][01034] Avg episode reward: 30.595, avg true_objective: 12.262
+[2025-03-11 09:38:34,105][01034] Num frames 11100...
+[2025-03-11 09:38:34,280][01034] Num frames 11200...
+[2025-03-11 09:38:34,451][01034] Num frames 11300...
+[2025-03-11 09:38:34,616][01034] Num frames 11400...
+[2025-03-11 09:38:34,783][01034] Num frames 11500...
+[2025-03-11 09:38:34,961][01034] Num frames 11600...
+[2025-03-11 09:38:35,040][01034] Avg episode rewards: #0: 28.912, true rewards: #0: 11.612
+[2025-03-11 09:38:35,041][01034] Avg episode reward: 28.912, avg true_objective: 11.612
+[2025-03-11 09:39:42,700][01034] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2025-03-11 09:40:02,896][01034] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2025-03-11 09:40:02,897][01034] Overriding arg 'num_workers' with value 1 passed from command line
+[2025-03-11 09:40:02,898][01034] Adding new argument 'no_render'=True that is not in the saved config file!
+[2025-03-11 09:40:02,901][01034] Adding new argument 'save_video'=True that is not in the saved config file!
+[2025-03-11 09:40:02,902][01034] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2025-03-11 09:40:02,903][01034] Adding new argument 'video_name'=None that is not in the saved config file!
+[2025-03-11 09:40:02,904][01034] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2025-03-11 09:40:02,904][01034] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2025-03-11 09:40:02,905][01034] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2025-03-11 09:40:02,909][01034] Adding new argument 'hf_repository'='so7en/Doom_unit8_2' that is not in the saved config file!
+[2025-03-11 09:40:02,910][01034] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2025-03-11 09:40:02,910][01034] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2025-03-11 09:40:02,911][01034] Adding new argument 'train_script'=None that is not in the saved config file!
+[2025-03-11 09:40:02,912][01034] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2025-03-11 09:40:02,913][01034] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2025-03-11 09:40:02,954][01034] RunningMeanStd input shape: (3, 72, 128)
+[2025-03-11 09:40:02,956][01034] RunningMeanStd input shape: (1,)
+[2025-03-11 09:40:02,970][01034] ConvEncoder: input_channels=3
+[2025-03-11 09:40:03,025][01034] Conv encoder output size: 512
+[2025-03-11 09:40:03,026][01034] Policy head output size: 512
+[2025-03-11 09:40:03,052][01034] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001222_5005312.pth...
+[2025-03-11 09:40:03,620][01034] Num frames 100...
+[2025-03-11 09:40:03,755][01034] Num frames 200...
+[2025-03-11 09:40:03,887][01034] Num frames 300...
+[2025-03-11 09:40:04,015][01034] Num frames 400...
+[2025-03-11 09:40:04,142][01034] Num frames 500...
+[2025-03-11 09:40:04,277][01034] Num frames 600...
+[2025-03-11 09:40:04,415][01034] Num frames 700...
+[2025-03-11 09:40:04,543][01034] Num frames 800...
+[2025-03-11 09:40:04,673][01034] Num frames 900...
+[2025-03-11 09:40:04,802][01034] Num frames 1000...
+[2025-03-11 09:40:04,926][01034] Num frames 1100...
+[2025-03-11 09:40:05,057][01034] Num frames 1200...
+[2025-03-11 09:40:05,189][01034] Num frames 1300...
+[2025-03-11 09:40:05,372][01034] Avg episode rewards: #0: 38.950, true rewards: #0: 13.950
+[2025-03-11 09:40:05,374][01034] Avg episode reward: 38.950, avg true_objective: 13.950
+[2025-03-11 09:40:05,383][01034] Num frames 1400...
+[2025-03-11 09:40:05,516][01034] Num frames 1500...
+[2025-03-11 09:40:05,648][01034] Num frames 1600...
+[2025-03-11 09:40:05,776][01034] Num frames 1700...
+[2025-03-11 09:40:05,846][01034] Avg episode rewards: #0: 22.055, true rewards: #0: 8.555
+[2025-03-11 09:40:05,846][01034] Avg episode reward: 22.055, avg true_objective: 8.555
+[2025-03-11 09:40:05,957][01034] Num frames 1800...
+[2025-03-11 09:40:06,092][01034] Num frames 1900...
+[2025-03-11 09:40:06,217][01034] Num frames 2000...
+[2025-03-11 09:40:06,356][01034] Num frames 2100...
+[2025-03-11 09:40:06,491][01034] Num frames 2200...
+[2025-03-11 09:40:06,624][01034] Num frames 2300...
+[2025-03-11 09:40:06,756][01034] Num frames 2400...
+[2025-03-11 09:40:06,883][01034] Num frames 2500...
+[2025-03-11 09:40:07,013][01034] Num frames 2600...
+[2025-03-11 09:40:07,142][01034] Num frames 2700...
+[2025-03-11 09:40:07,284][01034] Num frames 2800...
+[2025-03-11 09:40:07,420][01034] Num frames 2900...
+[2025-03-11 09:40:07,550][01034] Num frames 3000...
+[2025-03-11 09:40:07,679][01034] Num frames 3100...
+[2025-03-11 09:40:07,846][01034] Avg episode rewards: #0: 27.277, true rewards: #0: 10.610
+[2025-03-11 09:40:07,847][01034] Avg episode reward: 27.277, avg true_objective: 10.610
+[2025-03-11 09:40:07,870][01034] Num frames 3200...
+[2025-03-11 09:40:07,993][01034] Num frames 3300...
+[2025-03-11 09:40:08,120][01034] Num frames 3400...
+[2025-03-11 09:40:08,248][01034] Num frames 3500...
+[2025-03-11 09:40:08,383][01034] Num frames 3600...
+[2025-03-11 09:40:08,523][01034] Num frames 3700...
+[2025-03-11 09:40:08,650][01034] Num frames 3800...
+[2025-03-11 09:40:08,778][01034] Num frames 3900...
+[2025-03-11 09:40:08,907][01034] Num frames 4000...
+[2025-03-11 09:40:09,035][01034] Num frames 4100...
+[2025-03-11 09:40:09,197][01034] Avg episode rewards: #0: 26.195, true rewards: #0: 10.445
+[2025-03-11 09:40:09,198][01034] Avg episode reward: 26.195, avg true_objective: 10.445
+[2025-03-11 09:40:09,234][01034] Num frames 4200...
+[2025-03-11 09:40:09,378][01034] Num frames 4300...
+[2025-03-11 09:40:09,516][01034] Num frames 4400...
+[2025-03-11 09:40:09,641][01034] Num frames 4500...
+[2025-03-11 09:40:09,768][01034] Num frames 4600...
+[2025-03-11 09:40:09,897][01034] Num frames 4700...
+[2025-03-11 09:40:10,022][01034] Num frames 4800...
+[2025-03-11 09:40:10,150][01034] Num frames 4900...
+[2025-03-11 09:40:10,282][01034] Num frames 5000...
+[2025-03-11 09:40:10,430][01034] Num frames 5100...
+[2025-03-11 09:40:10,559][01034] Num frames 5200...
+[2025-03-11 09:40:10,684][01034] Num frames 5300...
+[2025-03-11 09:40:10,813][01034] Num frames 5400...
+[2025-03-11 09:40:10,941][01034] Num frames 5500...
+[2025-03-11 09:40:11,070][01034] Num frames 5600...
+[2025-03-11 09:40:11,195][01034] Num frames 5700...
+[2025-03-11 09:40:11,323][01034] Num frames 5800...
+[2025-03-11 09:40:11,483][01034] Num frames 5900...
+[2025-03-11 09:40:11,647][01034] Avg episode rewards: #0: 30.364, true rewards: #0: 11.964
+[2025-03-11 09:40:11,648][01034] Avg episode reward: 30.364, avg true_objective: 11.964
+[2025-03-11 09:40:11,674][01034] Num frames 6000...
+[2025-03-11 09:40:11,810][01034] Num frames 6100...
+[2025-03-11 09:40:11,938][01034] Num frames 6200...
+[2025-03-11 09:40:12,066][01034] Num frames 6300...
+[2025-03-11 09:40:12,246][01034] Avg episode rewards: #0: 26.497, true rewards: #0: 10.663
+[2025-03-11 09:40:12,247][01034] Avg episode reward: 26.497, avg true_objective: 10.663
+[2025-03-11 09:40:12,251][01034] Num frames 6400...
+[2025-03-11 09:40:12,378][01034] Num frames 6500...
+[2025-03-11 09:40:12,519][01034] Num frames 6600...
+[2025-03-11 09:40:12,649][01034] Num frames 6700...
+[2025-03-11 09:40:12,778][01034] Num frames 6800...
+[2025-03-11 09:40:12,906][01034] Num frames 6900...
+[2025-03-11 09:40:13,015][01034] Avg episode rewards: #0: 23.774, true rewards: #0: 9.917
+[2025-03-11 09:40:13,016][01034] Avg episode reward: 23.774, avg true_objective: 9.917
+[2025-03-11 09:40:13,092][01034] Num frames 7000...
+[2025-03-11 09:40:13,222][01034] Num frames 7100...
+[2025-03-11 09:40:13,368][01034] Num frames 7200...
+[2025-03-11 09:40:13,562][01034] Num frames 7300...
+[2025-03-11 09:40:13,733][01034] Num frames 7400...
+[2025-03-11 09:40:13,904][01034] Num frames 7500...
+[2025-03-11 09:40:14,074][01034] Num frames 7600...
+[2025-03-11 09:40:14,240][01034] Num frames 7700...
+[2025-03-11 09:40:14,410][01034] Num frames 7800...
+[2025-03-11 09:40:14,589][01034] Num frames 7900...
+[2025-03-11 09:40:14,705][01034] Avg episode rewards: #0: 23.042, true rewards: #0: 9.917
+[2025-03-11 09:40:14,707][01034] Avg episode reward: 23.042, avg true_objective: 9.917
+[2025-03-11 09:40:14,825][01034] Num frames 8000...
+[2025-03-11 09:40:14,999][01034] Num frames 8100...
+[2025-03-11 09:40:15,180][01034] Num frames 8200...
+[2025-03-11 09:40:15,362][01034] Num frames 8300...
+[2025-03-11 09:40:15,554][01034] Num frames 8400...
+[2025-03-11 09:40:15,698][01034] Num frames 8500...
+[2025-03-11 09:40:15,824][01034] Num frames 8600...
+[2025-03-11 09:40:15,956][01034] Num frames 8700...
+[2025-03-11 09:40:16,090][01034] Num frames 8800...
+[2025-03-11 09:40:16,225][01034] Avg episode rewards: #0: 22.847, true rewards: #0: 9.847
+[2025-03-11 09:40:16,225][01034] Avg episode reward: 22.847, avg true_objective: 9.847
+[2025-03-11 09:40:16,279][01034] Num frames 8900...
+[2025-03-11 09:40:16,415][01034] Num frames 9000...
+[2025-03-11 09:40:16,552][01034] Num frames 9100...
+[2025-03-11 09:40:16,683][01034] Num frames 9200...
+[2025-03-11 09:40:16,812][01034] Num frames 9300...
+[2025-03-11 09:40:16,943][01034] Num frames 9400...
+[2025-03-11 09:40:17,072][01034] Num frames 9500...
+[2025-03-11 09:40:17,203][01034] Num frames 9600...
+[2025-03-11 09:40:17,387][01034] Avg episode rewards: #0: 22.094, true rewards: #0: 9.694
+[2025-03-11 09:40:17,388][01034] Avg episode reward: 22.094, avg true_objective: 9.694
+[2025-03-11 09:41:11,174][01034] Replay video saved to /content/train_dir/default_experiment/replay.mp4!