Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1731085137.2e80709e60cc

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61d69fd12dc6614d0aa54ef78ef855be902d51719a8dbf3ac7586219e9ab9376
+size 200281

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 9.03 +/- 4.65
+      value: 10.08 +/- 4.73
       name: mean_reward
       verified: false
 ---

checkpoint_p0/checkpoint_000001170_4792320.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8bf8d1953200f4c9b03df6e83983ff09743018846a6007ee0d507d26be1a875
+size 34929669

checkpoint_p0/checkpoint_000001222_5005312.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2ab85adabc87a4269b7da336d2ef818960fbd2c72d3b8644025874330c6a9b5
+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 sha256:40d2dfc2b2026208e5d369ded478a5f88cd663281b01e1f3e25784057ed1725a
-size 17681182
+oid sha256:fc1a72d522d85f73e4290d12f99e9495540acc81138f66808c80f1ecdf639b96
+size 18474932

sf_log.txt

@@ -1215,3 +1215,831 @@ main_loop: 1093.0430
 [2024-11-08 16:55:52,702][00398] Avg episode rewards: #0: 21.129, true rewards: #0: 9.029
 [2024-11-08 16:55:52,704][00398] Avg episode reward: 21.129, avg true_objective: 9.029
 [2024-11-08 16:56:46,049][00398] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2024-11-08 16:56:50,249][00398] The model has been pushed to https://huggingface.co/Brumocas/rl_course_vizdoom_health_gathering_supreme
+[2024-11-08 16:58:57,579][00398] Environment doom_basic already registered, overwriting...
+[2024-11-08 16:58:57,581][00398] Environment doom_two_colors_easy already registered, overwriting...
+[2024-11-08 16:58:57,583][00398] Environment doom_two_colors_hard already registered, overwriting...
+[2024-11-08 16:58:57,585][00398] Environment doom_dm already registered, overwriting...
+[2024-11-08 16:58:57,588][00398] Environment doom_dwango5 already registered, overwriting...
+[2024-11-08 16:58:57,588][00398] Environment doom_my_way_home_flat_actions already registered, overwriting...
+[2024-11-08 16:58:57,589][00398] Environment doom_defend_the_center_flat_actions already registered, overwriting...
+[2024-11-08 16:58:57,590][00398] Environment doom_my_way_home already registered, overwriting...
+[2024-11-08 16:58:57,591][00398] Environment doom_deadly_corridor already registered, overwriting...
+[2024-11-08 16:58:57,592][00398] Environment doom_defend_the_center already registered, overwriting...
+[2024-11-08 16:58:57,593][00398] Environment doom_defend_the_line already registered, overwriting...
+[2024-11-08 16:58:57,595][00398] Environment doom_health_gathering already registered, overwriting...
+[2024-11-08 16:58:57,596][00398] Environment doom_health_gathering_supreme already registered, overwriting...
+[2024-11-08 16:58:57,597][00398] Environment doom_battle already registered, overwriting...
+[2024-11-08 16:58:57,598][00398] Environment doom_battle2 already registered, overwriting...
+[2024-11-08 16:58:57,599][00398] Environment doom_duel_bots already registered, overwriting...
+[2024-11-08 16:58:57,600][00398] Environment doom_deathmatch_bots already registered, overwriting...
+[2024-11-08 16:58:57,601][00398] Environment doom_duel already registered, overwriting...
+[2024-11-08 16:58:57,603][00398] Environment doom_deathmatch_full already registered, overwriting...
+[2024-11-08 16:58:57,604][00398] Environment doom_benchmark already registered, overwriting...
+[2024-11-08 16:58:57,605][00398] register_encoder_factory: <function make_vizdoom_encoder at 0x794ae9392320>
+[2024-11-08 16:58:57,628][00398] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-11-08 16:58:57,629][00398] Overriding arg 'train_for_env_steps' with value 5000000 passed from command line
+[2024-11-08 16:58:57,641][00398] Experiment dir /content/train_dir/default_experiment already exists!
+[2024-11-08 16:58:57,643][00398] Resuming existing experiment from /content/train_dir/default_experiment...
+[2024-11-08 16:58:57,645][00398] Weights and Biases integration disabled
+[2024-11-08 16:58:57,648][00398] Environment var CUDA_VISIBLE_DEVICES is 0
+
+[2024-11-08 16:59:00,305][00398] 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
+[2024-11-08 16:59:00,308][00398] Saving configuration to /content/train_dir/default_experiment/config.json...
+[2024-11-08 16:59:00,312][00398] Rollout worker 0 uses device cpu
+[2024-11-08 16:59:00,314][00398] Rollout worker 1 uses device cpu
+[2024-11-08 16:59:00,316][00398] Rollout worker 2 uses device cpu
+[2024-11-08 16:59:00,317][00398] Rollout worker 3 uses device cpu
+[2024-11-08 16:59:00,318][00398] Rollout worker 4 uses device cpu
+[2024-11-08 16:59:00,319][00398] Rollout worker 5 uses device cpu
+[2024-11-08 16:59:00,320][00398] Rollout worker 6 uses device cpu
+[2024-11-08 16:59:00,321][00398] Rollout worker 7 uses device cpu
+[2024-11-08 16:59:00,396][00398] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-11-08 16:59:00,398][00398] InferenceWorker_p0-w0: min num requests: 2
+[2024-11-08 16:59:00,430][00398] Starting all processes...
+[2024-11-08 16:59:00,431][00398] Starting process learner_proc0
+[2024-11-08 16:59:00,480][00398] Starting all processes...
+[2024-11-08 16:59:00,486][00398] Starting process inference_proc0-0
+[2024-11-08 16:59:00,486][00398] Starting process rollout_proc0
+[2024-11-08 16:59:00,488][00398] Starting process rollout_proc1
+[2024-11-08 16:59:00,488][00398] Starting process rollout_proc2
+[2024-11-08 16:59:00,488][00398] Starting process rollout_proc3
+[2024-11-08 16:59:00,488][00398] Starting process rollout_proc4
+[2024-11-08 16:59:00,488][00398] Starting process rollout_proc5
+[2024-11-08 16:59:00,488][00398] Starting process rollout_proc6
+[2024-11-08 16:59:00,488][00398] Starting process rollout_proc7
+[2024-11-08 16:59:17,014][17017] Worker 4 uses CPU cores [0]
+[2024-11-08 16:59:17,424][17014] Worker 2 uses CPU cores [0]
+[2024-11-08 16:59:17,600][16998] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-11-08 16:59:17,601][16998] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2024-11-08 16:59:17,607][17013] Worker 1 uses CPU cores [1]
+[2024-11-08 16:59:17,635][16998] Num visible devices: 1
+[2024-11-08 16:59:17,656][16998] Starting seed is not provided
+[2024-11-08 16:59:17,657][16998] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-11-08 16:59:17,658][16998] Initializing actor-critic model on device cuda:0
+[2024-11-08 16:59:17,659][16998] RunningMeanStd input shape: (3, 72, 128)
+[2024-11-08 16:59:17,660][16998] RunningMeanStd input shape: (1,)
+[2024-11-08 16:59:17,686][17015] Worker 3 uses CPU cores [1]
+[2024-11-08 16:59:17,693][17011] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-11-08 16:59:17,693][17011] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2024-11-08 16:59:17,702][16998] ConvEncoder: input_channels=3
+[2024-11-08 16:59:17,745][17018] Worker 5 uses CPU cores [1]
+[2024-11-08 16:59:17,770][17019] Worker 7 uses CPU cores [1]
+[2024-11-08 16:59:17,773][17016] Worker 6 uses CPU cores [0]
+[2024-11-08 16:59:17,776][17011] Num visible devices: 1
+[2024-11-08 16:59:17,789][17012] Worker 0 uses CPU cores [0]
+[2024-11-08 16:59:17,871][16998] Conv encoder output size: 512
+[2024-11-08 16:59:17,871][16998] Policy head output size: 512
+[2024-11-08 16:59:17,893][16998] Created Actor Critic model with architecture:
+[2024-11-08 16:59:17,894][16998] ActorCriticSharedWeights(
+  (obs_normalizer): ObservationNormalizer(
+    (running_mean_std): RunningMeanStdDictInPlace(
+      (running_mean_std): ModuleDict(
+        (obs): RunningMeanStdInPlace()
+      )
+    )
+  )
+  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
+  (encoder): VizdoomEncoder(
+    (basic_encoder): ConvEncoder(
+      (enc): RecursiveScriptModule(
+        original_name=ConvEncoderImpl
+        (conv_head): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Conv2d)
+          (1): RecursiveScriptModule(original_name=ELU)
+          (2): RecursiveScriptModule(original_name=Conv2d)
+          (3): RecursiveScriptModule(original_name=ELU)
+          (4): RecursiveScriptModule(original_name=Conv2d)
+          (5): RecursiveScriptModule(original_name=ELU)
+        )
+        (mlp_layers): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Linear)
+          (1): RecursiveScriptModule(original_name=ELU)
+        )
+      )
+    )
+  )
+  (core): ModelCoreRNN(
+    (core): GRU(512, 512)
+  )
+  (decoder): MlpDecoder(
+    (mlp): Identity()
+  )
+  (critic_linear): Linear(in_features=512, out_features=1, bias=True)
+  (action_parameterization): ActionParameterizationDefault(
+    (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
+  )
+)
+[2024-11-08 16:59:18,040][16998] Using optimizer <class 'torch.optim.adam.Adam'>
+[2024-11-08 16:59:18,862][16998] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-11-08 16:59:18,899][16998] Loading model from checkpoint
+[2024-11-08 16:59:18,901][16998] Loaded experiment state at self.train_step=978, self.env_steps=4005888
+[2024-11-08 16:59:18,902][16998] Initialized policy 0 weights for model version 978
+[2024-11-08 16:59:18,905][16998] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-11-08 16:59:18,915][16998] LearnerWorker_p0 finished initialization!
+[2024-11-08 16:59:19,021][17011] RunningMeanStd input shape: (3, 72, 128)
+[2024-11-08 16:59:19,023][17011] RunningMeanStd input shape: (1,)
+[2024-11-08 16:59:19,039][17011] ConvEncoder: input_channels=3
+[2024-11-08 16:59:19,147][17011] Conv encoder output size: 512
+[2024-11-08 16:59:19,148][17011] Policy head output size: 512
+[2024-11-08 16:59:19,203][00398] Inference worker 0-0 is ready!
+[2024-11-08 16:59:19,205][00398] All inference workers are ready! Signal rollout workers to start!
+[2024-11-08 16:59:19,449][17013] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-08 16:59:19,462][17012] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-08 16:59:19,470][17015] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-08 16:59:19,477][17019] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-08 16:59:19,530][17018] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-08 16:59:19,527][17014] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-08 16:59:19,568][17016] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-08 16:59:19,579][17017] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-08 16:59:20,388][00398] Heartbeat connected on Batcher_0
+[2024-11-08 16:59:20,394][00398] Heartbeat connected on LearnerWorker_p0
+[2024-11-08 16:59:20,433][00398] Heartbeat connected on InferenceWorker_p0-w0
+[2024-11-08 16:59:20,908][17012] Decorrelating experience for 0 frames...
+[2024-11-08 16:59:20,913][17014] Decorrelating experience for 0 frames...
+[2024-11-08 16:59:20,920][17016] Decorrelating experience for 0 frames...
+[2024-11-08 16:59:21,090][17013] Decorrelating experience for 0 frames...
+[2024-11-08 16:59:21,123][17015] Decorrelating experience for 0 frames...
+[2024-11-08 16:59:21,142][17019] Decorrelating experience for 0 frames...
+[2024-11-08 16:59:21,166][17018] Decorrelating experience for 0 frames...
+[2024-11-08 16:59:21,836][17016] Decorrelating experience for 32 frames...
+[2024-11-08 16:59:21,938][17012] Decorrelating experience for 32 frames...
+[2024-11-08 16:59:22,182][17013] Decorrelating experience for 32 frames...
+[2024-11-08 16:59:22,247][17015] Decorrelating experience for 32 frames...
+[2024-11-08 16:59:22,357][17019] Decorrelating experience for 32 frames...
+[2024-11-08 16:59:22,649][00398] 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)
+[2024-11-08 16:59:23,477][17014] Decorrelating experience for 32 frames...
+[2024-11-08 16:59:23,944][17016] Decorrelating experience for 64 frames...
+[2024-11-08 16:59:24,003][17018] Decorrelating experience for 32 frames...
+[2024-11-08 16:59:24,256][17012] Decorrelating experience for 64 frames...
+[2024-11-08 16:59:24,469][17013] Decorrelating experience for 64 frames...
+[2024-11-08 16:59:24,574][17015] Decorrelating experience for 64 frames...
+[2024-11-08 16:59:24,723][17019] Decorrelating experience for 64 frames...
+[2024-11-08 16:59:25,781][17017] Decorrelating experience for 0 frames...
+[2024-11-08 16:59:26,151][17013] Decorrelating experience for 96 frames...
+[2024-11-08 16:59:26,207][17016] Decorrelating experience for 96 frames...
+[2024-11-08 16:59:26,331][17015] Decorrelating experience for 96 frames...
+[2024-11-08 16:59:26,445][17012] Decorrelating experience for 96 frames...
+[2024-11-08 16:59:26,477][17014] Decorrelating experience for 64 frames...
+[2024-11-08 16:59:26,495][00398] Heartbeat connected on RolloutWorker_w1
+[2024-11-08 16:59:26,537][00398] Heartbeat connected on RolloutWorker_w6
+[2024-11-08 16:59:26,642][00398] Heartbeat connected on RolloutWorker_w3
+[2024-11-08 16:59:27,024][00398] Heartbeat connected on RolloutWorker_w0
+[2024-11-08 16:59:27,649][00398] 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)
+[2024-11-08 16:59:28,643][17018] Decorrelating experience for 64 frames...
+[2024-11-08 16:59:28,695][17017] Decorrelating experience for 32 frames...
+[2024-11-08 16:59:29,058][17019] Decorrelating experience for 96 frames...
+[2024-11-08 16:59:29,643][00398] Heartbeat connected on RolloutWorker_w7
+[2024-11-08 16:59:30,090][17014] Decorrelating experience for 96 frames...
+[2024-11-08 16:59:30,426][00398] Heartbeat connected on RolloutWorker_w2
+[2024-11-08 16:59:32,623][17018] Decorrelating experience for 96 frames...
+[2024-11-08 16:59:32,649][00398] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4005888. Throughput: 0: 180.2. Samples: 1802. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-11-08 16:59:32,655][00398] Avg episode reward: [(0, '4.423')]
+[2024-11-08 16:59:33,014][00398] Heartbeat connected on RolloutWorker_w5
+[2024-11-08 16:59:33,494][16998] Signal inference workers to stop experience collection...
+[2024-11-08 16:59:33,542][17011] InferenceWorker_p0-w0: stopping experience collection
+[2024-11-08 16:59:33,759][17017] Decorrelating experience for 64 frames...
+[2024-11-08 16:59:34,208][17017] Decorrelating experience for 96 frames...
+[2024-11-08 16:59:34,286][00398] Heartbeat connected on RolloutWorker_w4
+[2024-11-08 16:59:35,315][16998] Signal inference workers to resume experience collection...
+[2024-11-08 16:59:35,318][17011] InferenceWorker_p0-w0: resuming experience collection
+[2024-11-08 16:59:37,656][00398] Fps is (10 sec: 1637.1, 60 sec: 1091.7, 300 sec: 1091.7). Total num frames: 4022272. Throughput: 0: 326.1. Samples: 4894. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+[2024-11-08 16:59:37,659][00398] Avg episode reward: [(0, '8.044')]
+[2024-11-08 16:59:42,649][00398] Fps is (10 sec: 3276.7, 60 sec: 1638.4, 300 sec: 1638.4). Total num frames: 4038656. Throughput: 0: 376.5. Samples: 7530. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-11-08 16:59:42,652][00398] Avg episode reward: [(0, '11.289')]
+[2024-11-08 16:59:44,994][17011] Updated weights for policy 0, policy_version 988 (0.0042)
+[2024-11-08 16:59:47,649][00398] Fps is (10 sec: 3279.3, 60 sec: 1966.1, 300 sec: 1966.1). Total num frames: 4055040. Throughput: 0: 471.2. Samples: 11780. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-11-08 16:59:47,654][00398] Avg episode reward: [(0, '13.152')]
+[2024-11-08 16:59:52,649][00398] Fps is (10 sec: 3686.5, 60 sec: 2321.1, 300 sec: 2321.1). Total num frames: 4075520. Throughput: 0: 612.4. Samples: 18372. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-11-08 16:59:52,651][00398] Avg episode reward: [(0, '17.981')]
+[2024-11-08 16:59:54,675][17011] Updated weights for policy 0, policy_version 998 (0.0027)
+[2024-11-08 16:59:57,650][00398] Fps is (10 sec: 4505.0, 60 sec: 2691.6, 300 sec: 2691.6). Total num frames: 4100096. Throughput: 0: 622.7. Samples: 21796. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-11-08 16:59:57,652][00398] Avg episode reward: [(0, '20.430')]
+[2024-11-08 17:00:02,650][00398] Fps is (10 sec: 3685.8, 60 sec: 2662.3, 300 sec: 2662.3). Total num frames: 4112384. Throughput: 0: 670.3. Samples: 26812. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-11-08 17:00:02,653][00398] Avg episode reward: [(0, '19.891')]
+[2024-11-08 17:00:06,403][17011] Updated weights for policy 0, policy_version 1008 (0.0022)
+[2024-11-08 17:00:07,655][00398] Fps is (10 sec: 3275.2, 60 sec: 2821.3, 300 sec: 2821.3). Total num frames: 4132864. Throughput: 0: 713.2. Samples: 32100. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-11-08 17:00:07,657][00398] Avg episode reward: [(0, '23.205')]
+[2024-11-08 17:00:12,649][00398] Fps is (10 sec: 4096.5, 60 sec: 2949.1, 300 sec: 2949.1). Total num frames: 4153344. Throughput: 0: 788.4. Samples: 35478. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-11-08 17:00:12,651][00398] Avg episode reward: [(0, '22.991')]
+[2024-11-08 17:00:15,512][17011] Updated weights for policy 0, policy_version 1018 (0.0027)
+[2024-11-08 17:00:17,650][00398] Fps is (10 sec: 4097.8, 60 sec: 3053.3, 300 sec: 3053.3). Total num frames: 4173824. Throughput: 0: 891.5. Samples: 41922. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-11-08 17:00:17,655][00398] Avg episode reward: [(0, '23.155')]
+[2024-11-08 17:00:22,649][00398] Fps is (10 sec: 3686.5, 60 sec: 3072.0, 300 sec: 3072.0). Total num frames: 4190208. Throughput: 0: 920.5. Samples: 46310. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-11-08 17:00:22,650][00398] Avg episode reward: [(0, '21.656')]
+[2024-11-08 17:00:26,796][17011] Updated weights for policy 0, policy_version 1028 (0.0016)
+[2024-11-08 17:00:27,649][00398] Fps is (10 sec: 4096.5, 60 sec: 3481.6, 300 sec: 3213.8). Total num frames: 4214784. Throughput: 0: 941.8. Samples: 49910. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-11-08 17:00:27,653][00398] Avg episode reward: [(0, '21.554')]
+[2024-11-08 17:00:32,649][00398] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3276.8). Total num frames: 4235264. Throughput: 0: 1003.4. Samples: 56934. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-11-08 17:00:32,651][00398] Avg episode reward: [(0, '21.658')]
+[2024-11-08 17:00:37,509][17011] Updated weights for policy 0, policy_version 1038 (0.0017)
+[2024-11-08 17:00:37,649][00398] Fps is (10 sec: 3686.6, 60 sec: 3823.4, 300 sec: 3276.8). Total num frames: 4251648. Throughput: 0: 961.5. Samples: 61640. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-11-08 17:00:37,654][00398] Avg episode reward: [(0, '21.340')]
+[2024-11-08 17:00:42,649][00398] Fps is (10 sec: 3276.8, 60 sec: 3823.0, 300 sec: 3276.8). Total num frames: 4268032. Throughput: 0: 938.7. Samples: 64036. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-11-08 17:00:42,653][00398] Avg episode reward: [(0, '20.990')]
+[2024-11-08 17:00:47,082][17011] Updated weights for policy 0, policy_version 1048 (0.0019)
+[2024-11-08 17:00:47,649][00398] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3373.2). Total num frames: 4292608. Throughput: 0: 984.0. Samples: 71090. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-11-08 17:00:47,650][00398] Avg episode reward: [(0, '21.701')]
+[2024-11-08 17:00:52,649][00398] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3367.8). Total num frames: 4308992. Throughput: 0: 994.7. Samples: 76856. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-11-08 17:00:52,654][00398] Avg episode reward: [(0, '22.117')]
+[2024-11-08 17:00:57,649][00398] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3363.0). Total num frames: 4325376. Throughput: 0: 967.9. Samples: 79034. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-11-08 17:00:57,650][00398] Avg episode reward: [(0, '22.864')]
+[2024-11-08 17:00:57,663][16998] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001056_4325376.pth...
+[2024-11-08 17:00:57,816][16998] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000960_3932160.pth
+[2024-11-08 17:00:58,738][17011] Updated weights for policy 0, policy_version 1058 (0.0041)
+[2024-11-08 17:01:02,649][00398] Fps is (10 sec: 4096.0, 60 sec: 3959.6, 300 sec: 3440.6). Total num frames: 4349952. Throughput: 0: 968.1. Samples: 85484. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-11-08 17:01:02,651][00398] Avg episode reward: [(0, '23.136')]
+[2024-11-08 17:01:07,649][00398] Fps is (10 sec: 4505.6, 60 sec: 3959.9, 300 sec: 3471.8). Total num frames: 4370432. Throughput: 0: 1015.6. Samples: 92012. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-11-08 17:01:07,650][00398] Avg episode reward: [(0, '23.627')]
+[2024-11-08 17:01:08,118][17011] Updated weights for policy 0, policy_version 1068 (0.0021)
+[2024-11-08 17:01:12,649][00398] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3425.7). Total num frames: 4382720. Throughput: 0: 978.9. Samples: 93962. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-11-08 17:01:12,650][00398] Avg episode reward: [(0, '24.101')]
+[2024-11-08 17:01:17,649][00398] Fps is (10 sec: 3276.8, 60 sec: 3823.0, 300 sec: 3454.9). Total num frames: 4403200. Throughput: 0: 937.0. Samples: 99098. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-11-08 17:01:17,651][00398] Avg episode reward: [(0, '24.049')]
+[2024-11-08 17:01:19,597][17011] Updated weights for policy 0, policy_version 1078 (0.0015)
+[2024-11-08 17:01:22,649][00398] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3515.7). Total num frames: 4427776. Throughput: 0: 984.4. Samples: 105936. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-11-08 17:01:22,651][00398] Avg episode reward: [(0, '22.574')]
+[2024-11-08 17:01:27,649][00398] Fps is (10 sec: 4095.9, 60 sec: 3823.0, 300 sec: 3506.2). Total num frames: 4444160. Throughput: 0: 994.1. Samples: 108772. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-11-08 17:01:27,651][00398] Avg episode reward: [(0, '22.065')]
+[2024-11-08 17:01:31,571][17011] Updated weights for policy 0, policy_version 1088 (0.0032)
+[2024-11-08 17:01:32,649][00398] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3497.4). Total num frames: 4460544. Throughput: 0: 930.0. Samples: 112938. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-11-08 17:01:32,651][00398] Avg episode reward: [(0, '21.502')]
+[2024-11-08 17:01:37,649][00398] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3549.9). Total num frames: 4485120. Throughput: 0: 962.6. Samples: 120172. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-11-08 17:01:37,654][00398] Avg episode reward: [(0, '20.608')]
+[2024-11-08 17:01:40,052][17011] Updated weights for policy 0, policy_version 1098 (0.0026)
+[2024-11-08 17:01:42,648][00398] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3569.4). Total num frames: 4505600. Throughput: 0: 991.1. Samples: 123632. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-11-08 17:01:42,654][00398] Avg episode reward: [(0, '21.205')]
+[2024-11-08 17:01:47,649][00398] Fps is (10 sec: 3276.9, 60 sec: 3754.7, 300 sec: 3531.0). Total num frames: 4517888. Throughput: 0: 949.7. Samples: 128220. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-11-08 17:01:47,653][00398] Avg episode reward: [(0, '21.930')]
+[2024-11-08 17:01:51,745][17011] Updated weights for policy 0, policy_version 1108 (0.0022)
+[2024-11-08 17:01:52,649][00398] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3549.9). Total num frames: 4538368. Throughput: 0: 938.0. Samples: 134220. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-11-08 17:01:52,655][00398] Avg episode reward: [(0, '21.777')]
+[2024-11-08 17:01:57,648][00398] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3593.9). Total num frames: 4562944. Throughput: 0: 974.1. Samples: 137798. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2024-11-08 17:01:57,651][00398] Avg episode reward: [(0, '21.218')]
+[2024-11-08 17:02:01,932][17011] Updated weights for policy 0, policy_version 1118 (0.0018)
+[2024-11-08 17:02:02,649][00398] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3584.0). Total num frames: 4579328. Throughput: 0: 989.1. Samples: 143606. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2024-11-08 17:02:02,654][00398] Avg episode reward: [(0, '21.211')]
+[2024-11-08 17:02:07,649][00398] Fps is (10 sec: 3686.3, 60 sec: 3822.9, 300 sec: 3599.5). Total num frames: 4599808. Throughput: 0: 951.1. Samples: 148738. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-11-08 17:02:07,652][00398] Avg episode reward: [(0, '21.582')]
+[2024-11-08 17:02:12,007][17011] Updated weights for policy 0, policy_version 1128 (0.0013)
+[2024-11-08 17:02:12,649][00398] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3614.1). Total num frames: 4620288. Throughput: 0: 966.5. Samples: 152266. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-11-08 17:02:12,651][00398] Avg episode reward: [(0, '19.963')]
+[2024-11-08 17:02:17,649][00398] Fps is (10 sec: 4096.1, 60 sec: 3959.5, 300 sec: 3627.9). Total num frames: 4640768. Throughput: 0: 1024.7. Samples: 159048. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-11-08 17:02:17,653][00398] Avg episode reward: [(0, '20.799')]
+[2024-11-08 17:02:22,649][00398] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3618.1). Total num frames: 4657152. Throughput: 0: 957.1. Samples: 163242. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-11-08 17:02:22,651][00398] Avg episode reward: [(0, '20.026')]
+[2024-11-08 17:02:23,444][17011] Updated weights for policy 0, policy_version 1138 (0.0023)
+[2024-11-08 17:02:27,649][00398] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3631.0). Total num frames: 4677632. Throughput: 0: 953.8. Samples: 166552. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-11-08 17:02:27,657][00398] Avg episode reward: [(0, '20.024')]
+[2024-11-08 17:02:32,144][17011] Updated weights for policy 0, policy_version 1148 (0.0031)
+[2024-11-08 17:02:32,649][00398] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3664.8). Total num frames: 4702208. Throughput: 0: 1008.0. Samples: 173580. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-11-08 17:02:32,651][00398] Avg episode reward: [(0, '21.018')]
+[2024-11-08 17:02:37,650][00398] Fps is (10 sec: 4095.6, 60 sec: 3891.1, 300 sec: 3654.9). Total num frames: 4718592. Throughput: 0: 987.5. Samples: 178658. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-11-08 17:02:37,654][00398] Avg episode reward: [(0, '22.114')]
+[2024-11-08 17:02:42,649][00398] Fps is (10 sec: 3276.7, 60 sec: 3822.9, 300 sec: 3645.4). Total num frames: 4734976. Throughput: 0: 957.8. Samples: 180900. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-11-08 17:02:42,651][00398] Avg episode reward: [(0, '21.602')]
+[2024-11-08 17:02:43,699][17011] Updated weights for policy 0, policy_version 1158 (0.0015)
+[2024-11-08 17:02:47,649][00398] Fps is (10 sec: 4096.4, 60 sec: 4027.7, 300 sec: 3676.4). Total num frames: 4759552. Throughput: 0: 980.9. Samples: 187748. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-11-08 17:02:47,654][00398] Avg episode reward: [(0, '23.197')]
+[2024-11-08 17:02:52,651][00398] Fps is (10 sec: 4095.3, 60 sec: 3959.3, 300 sec: 3666.9). Total num frames: 4775936. Throughput: 0: 998.1. Samples: 193654. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-11-08 17:02:52,654][00398] Avg episode reward: [(0, '24.019')]
+[2024-11-08 17:02:54,558][17011] Updated weights for policy 0, policy_version 1168 (0.0019)
+[2024-11-08 17:02:57,649][00398] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3657.8). Total num frames: 4792320. Throughput: 0: 963.5. Samples: 195624. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-11-08 17:02:57,651][00398] Avg episode reward: [(0, '22.606')]
+[2024-11-08 17:02:57,663][16998] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001170_4792320.pth...
+[2024-11-08 17:02:57,786][16998] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth
+[2024-11-08 17:03:02,648][00398] Fps is (10 sec: 3687.2, 60 sec: 3891.2, 300 sec: 3667.8). Total num frames: 4812800. Throughput: 0: 945.6. Samples: 201598. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-11-08 17:03:02,651][00398] Avg episode reward: [(0, '22.460')]
+[2024-11-08 17:03:04,419][17011] Updated weights for policy 0, policy_version 1178 (0.0017)
+[2024-11-08 17:03:07,649][00398] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3695.5). Total num frames: 4837376. Throughput: 0: 1013.3. Samples: 208840. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-11-08 17:03:07,653][00398] Avg episode reward: [(0, '23.119')]
+[2024-11-08 17:03:12,649][00398] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3686.4). Total num frames: 4853760. Throughput: 0: 988.6. Samples: 211038. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-11-08 17:03:12,651][00398] Avg episode reward: [(0, '22.357')]
+[2024-11-08 17:03:16,179][17011] Updated weights for policy 0, policy_version 1188 (0.0023)
+[2024-11-08 17:03:17,649][00398] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3677.7). Total num frames: 4870144. Throughput: 0: 935.6. Samples: 215684. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-11-08 17:03:17,655][00398] Avg episode reward: [(0, '23.086')]
+[2024-11-08 17:03:22,649][00398] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3703.5). Total num frames: 4894720. Throughput: 0: 974.7. Samples: 222518. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-11-08 17:03:22,655][00398] Avg episode reward: [(0, '22.647')]
+[2024-11-08 17:03:25,035][17011] Updated weights for policy 0, policy_version 1198 (0.0014)
+[2024-11-08 17:03:27,651][00398] Fps is (10 sec: 4095.2, 60 sec: 3891.1, 300 sec: 3694.7). Total num frames: 4911104. Throughput: 0: 999.0. Samples: 225856. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-11-08 17:03:27,656][00398] Avg episode reward: [(0, '21.628')]
+[2024-11-08 17:03:32,649][00398] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3686.4). Total num frames: 4927488. Throughput: 0: 942.6. Samples: 230164. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-11-08 17:03:32,655][00398] Avg episode reward: [(0, '21.779')]
+[2024-11-08 17:03:36,494][17011] Updated weights for policy 0, policy_version 1208 (0.0018)
+[2024-11-08 17:03:37,649][00398] Fps is (10 sec: 4096.8, 60 sec: 3891.3, 300 sec: 3710.5). Total num frames: 4952064. Throughput: 0: 962.0. Samples: 236944. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-11-08 17:03:37,651][00398] Avg episode reward: [(0, '21.072')]
+[2024-11-08 17:03:42,649][00398] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3717.9). Total num frames: 4972544. Throughput: 0: 996.1. Samples: 240450. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-11-08 17:03:42,655][00398] Avg episode reward: [(0, '20.331')]
+[2024-11-08 17:03:47,302][17011] Updated weights for policy 0, policy_version 1218 (0.0018)
+[2024-11-08 17:03:47,648][00398] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3709.6). Total num frames: 4988928. Throughput: 0: 978.0. Samples: 245608. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-11-08 17:03:47,654][00398] Avg episode reward: [(0, '21.012')]
+[2024-11-08 17:03:51,616][16998] Stopping Batcher_0...
+[2024-11-08 17:03:51,617][16998] Loop batcher_evt_loop terminating...
+[2024-11-08 17:03:51,618][00398] Component Batcher_0 stopped!
+[2024-11-08 17:03:51,621][16998] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001222_5005312.pth...
+[2024-11-08 17:03:51,668][17011] Weights refcount: 2 0
+[2024-11-08 17:03:51,672][00398] Component InferenceWorker_p0-w0 stopped!
+[2024-11-08 17:03:51,672][17011] Stopping InferenceWorker_p0-w0...
+[2024-11-08 17:03:51,677][17011] Loop inference_proc0-0_evt_loop terminating...
+[2024-11-08 17:03:51,767][16998] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001056_4325376.pth
+[2024-11-08 17:03:51,777][16998] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001222_5005312.pth...
+[2024-11-08 17:03:51,953][00398] Component LearnerWorker_p0 stopped!
+[2024-11-08 17:03:51,956][16998] Stopping LearnerWorker_p0...
+[2024-11-08 17:03:51,956][16998] Loop learner_proc0_evt_loop terminating...
+[2024-11-08 17:03:52,070][00398] Component RolloutWorker_w1 stopped!
+[2024-11-08 17:03:52,069][17013] Stopping RolloutWorker_w1...
+[2024-11-08 17:03:52,075][17013] Loop rollout_proc1_evt_loop terminating...
+[2024-11-08 17:03:52,087][17012] Stopping RolloutWorker_w0...
+[2024-11-08 17:03:52,087][00398] Component RolloutWorker_w0 stopped!
+[2024-11-08 17:03:52,092][17012] Loop rollout_proc0_evt_loop terminating...
+[2024-11-08 17:03:52,096][17015] Stopping RolloutWorker_w3...
+[2024-11-08 17:03:52,095][00398] Component RolloutWorker_w3 stopped!
+[2024-11-08 17:03:52,102][17016] Stopping RolloutWorker_w6...
+[2024-11-08 17:03:52,102][00398] Component RolloutWorker_w6 stopped!
+[2024-11-08 17:03:52,100][17015] Loop rollout_proc3_evt_loop terminating...
+[2024-11-08 17:03:52,116][17016] Loop rollout_proc6_evt_loop terminating...
+[2024-11-08 17:03:52,119][17017] Stopping RolloutWorker_w4...
+[2024-11-08 17:03:52,119][00398] Component RolloutWorker_w4 stopped!
+[2024-11-08 17:03:52,133][17014] Stopping RolloutWorker_w2...
+[2024-11-08 17:03:52,131][17017] Loop rollout_proc4_evt_loop terminating...
+[2024-11-08 17:03:52,134][00398] Component RolloutWorker_w2 stopped!
+[2024-11-08 17:03:52,148][17014] Loop rollout_proc2_evt_loop terminating...
+[2024-11-08 17:03:52,168][17018] Stopping RolloutWorker_w5...
+[2024-11-08 17:03:52,168][00398] Component RolloutWorker_w5 stopped!
+[2024-11-08 17:03:52,170][17018] Loop rollout_proc5_evt_loop terminating...
+[2024-11-08 17:03:52,186][00398] Component RolloutWorker_w7 stopped!
+[2024-11-08 17:03:52,187][17019] Stopping RolloutWorker_w7...
+[2024-11-08 17:03:52,194][00398] Waiting for process learner_proc0 to stop...
+[2024-11-08 17:03:52,199][17019] Loop rollout_proc7_evt_loop terminating...
+[2024-11-08 17:03:53,675][00398] Waiting for process inference_proc0-0 to join...
+[2024-11-08 17:03:53,683][00398] Waiting for process rollout_proc0 to join...
+[2024-11-08 17:03:55,692][00398] Waiting for process rollout_proc1 to join...
+[2024-11-08 17:03:55,696][00398] Waiting for process rollout_proc2 to join...
+[2024-11-08 17:03:55,699][00398] Waiting for process rollout_proc3 to join...
+[2024-11-08 17:03:55,702][00398] Waiting for process rollout_proc4 to join...
+[2024-11-08 17:03:55,704][00398] Waiting for process rollout_proc5 to join...
+[2024-11-08 17:03:55,705][00398] Waiting for process rollout_proc6 to join...
+[2024-11-08 17:03:55,707][00398] Waiting for process rollout_proc7 to join...
+[2024-11-08 17:03:55,709][00398] Batcher 0 profile tree view:
+batching: 7.2792, releasing_batches: 0.0312
+[2024-11-08 17:03:55,711][00398] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0024
+  wait_policy_total: 109.3784
+update_model: 2.1380
+  weight_update: 0.0019
+one_step: 0.0024
+  handle_policy_step: 148.1923
+    deserialize: 3.6286, stack: 0.8147, obs_to_device_normalize: 31.7240, forward: 74.9819, send_messages: 7.2755
+    prepare_outputs: 22.4408
+      to_cpu: 13.8446
+[2024-11-08 17:03:55,713][00398] Learner 0 profile tree view:
+misc: 0.0015, prepare_batch: 4.6403
+train: 21.1580
+  epoch_init: 0.0014, minibatch_init: 0.0032, losses_postprocess: 0.1867, kl_divergence: 0.1733, after_optimizer: 0.9612
+  calculate_losses: 7.7968
+    losses_init: 0.0152, forward_head: 0.6687, bptt_initial: 5.1506, tail: 0.3464, advantages_returns: 0.0790, losses: 0.9821
+    bptt: 0.4830
+      bptt_forward_core: 0.4663
+  update: 11.8912
+    clip: 0.2475
+[2024-11-08 17:03:55,714][00398] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.0673, enqueue_policy_requests: 25.7625, env_step: 206.2125, overhead: 3.2194, complete_rollouts: 1.7571
+save_policy_outputs: 5.2639
+  split_output_tensors: 2.0946
+[2024-11-08 17:03:55,715][00398] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.0747, enqueue_policy_requests: 24.8768, env_step: 203.8205, overhead: 3.3080, complete_rollouts: 1.7814
+save_policy_outputs: 5.4304
+  split_output_tensors: 2.0578
+[2024-11-08 17:03:55,717][00398] Loop Runner_EvtLoop terminating...
+[2024-11-08 17:03:55,718][00398] Runner profile tree view:
+main_loop: 295.2884
+[2024-11-08 17:03:55,719][00398] Collected {0: 5005312}, FPS: 3384.6
+[2024-11-08 17:03:55,753][00398] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-11-08 17:03:55,755][00398] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-11-08 17:03:55,756][00398] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-11-08 17:03:55,758][00398] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-11-08 17:03:55,759][00398] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-11-08 17:03:55,760][00398] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-11-08 17:03:55,762][00398] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2024-11-08 17:03:55,764][00398] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-11-08 17:03:55,765][00398] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2024-11-08 17:03:55,767][00398] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2024-11-08 17:03:55,769][00398] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-11-08 17:03:55,770][00398] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-11-08 17:03:55,772][00398] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-11-08 17:03:55,774][00398] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-11-08 17:03:55,775][00398] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-11-08 17:03:55,816][00398] RunningMeanStd input shape: (3, 72, 128)
+[2024-11-08 17:03:55,820][00398] RunningMeanStd input shape: (1,)
+[2024-11-08 17:03:55,833][00398] ConvEncoder: input_channels=3
+[2024-11-08 17:03:55,870][00398] Conv encoder output size: 512
+[2024-11-08 17:03:55,871][00398] Policy head output size: 512
+[2024-11-08 17:03:55,890][00398] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001222_5005312.pth...
+[2024-11-08 17:03:56,334][00398] Num frames 100...
+[2024-11-08 17:03:56,468][00398] Num frames 200...
+[2024-11-08 17:03:56,603][00398] Num frames 300...
+[2024-11-08 17:03:56,751][00398] Num frames 400...
+[2024-11-08 17:03:56,872][00398] Num frames 500...
+[2024-11-08 17:03:56,993][00398] Num frames 600...
+[2024-11-08 17:03:57,116][00398] Num frames 700...
+[2024-11-08 17:03:57,240][00398] Num frames 800...
+[2024-11-08 17:03:57,359][00398] Num frames 900...
+[2024-11-08 17:03:57,495][00398] Num frames 1000...
+[2024-11-08 17:03:57,629][00398] Num frames 1100...
+[2024-11-08 17:03:57,759][00398] Num frames 1200...
+[2024-11-08 17:03:57,880][00398] Num frames 1300...
+[2024-11-08 17:03:58,000][00398] Num frames 1400...
+[2024-11-08 17:03:58,124][00398] Num frames 1500...
+[2024-11-08 17:03:58,257][00398] Num frames 1600...
+[2024-11-08 17:03:58,361][00398] Avg episode rewards: #0: 40.399, true rewards: #0: 16.400
+[2024-11-08 17:03:58,364][00398] Avg episode reward: 40.399, avg true_objective: 16.400
+[2024-11-08 17:03:58,441][00398] Num frames 1700...
+[2024-11-08 17:03:58,569][00398] Num frames 1800...
+[2024-11-08 17:03:58,693][00398] Num frames 1900...
+[2024-11-08 17:03:58,817][00398] Num frames 2000...
+[2024-11-08 17:03:58,939][00398] Num frames 2100...
+[2024-11-08 17:03:59,060][00398] Num frames 2200...
+[2024-11-08 17:03:59,196][00398] Num frames 2300...
+[2024-11-08 17:03:59,319][00398] Num frames 2400...
+[2024-11-08 17:03:59,444][00398] Num frames 2500...
+[2024-11-08 17:03:59,597][00398] Num frames 2600...
+[2024-11-08 17:03:59,773][00398] Num frames 2700...
+[2024-11-08 17:03:59,937][00398] Num frames 2800...
+[2024-11-08 17:04:00,110][00398] Num frames 2900...
+[2024-11-08 17:04:00,233][00398] Avg episode rewards: #0: 36.700, true rewards: #0: 14.700
+[2024-11-08 17:04:00,235][00398] Avg episode reward: 36.700, avg true_objective: 14.700
+[2024-11-08 17:04:00,345][00398] Num frames 3000...
+[2024-11-08 17:04:00,519][00398] Num frames 3100...
+[2024-11-08 17:04:00,684][00398] Num frames 3200...
+[2024-11-08 17:04:00,854][00398] Num frames 3300...
+[2024-11-08 17:04:01,029][00398] Num frames 3400...
+[2024-11-08 17:04:01,203][00398] Num frames 3500...
+[2024-11-08 17:04:01,388][00398] Num frames 3600...
+[2024-11-08 17:04:01,579][00398] Num frames 3700...
+[2024-11-08 17:04:01,758][00398] Num frames 3800...
+[2024-11-08 17:04:01,948][00398] Num frames 3900...
+[2024-11-08 17:04:02,130][00398] Num frames 4000...
+[2024-11-08 17:04:02,277][00398] Num frames 4100...
+[2024-11-08 17:04:02,399][00398] Num frames 4200...
+[2024-11-08 17:04:02,554][00398] Avg episode rewards: #0: 34.947, true rewards: #0: 14.280
+[2024-11-08 17:04:02,556][00398] Avg episode reward: 34.947, avg true_objective: 14.280
+[2024-11-08 17:04:02,590][00398] Num frames 4300...
+[2024-11-08 17:04:02,722][00398] Num frames 4400...
+[2024-11-08 17:04:02,842][00398] Num frames 4500...
+[2024-11-08 17:04:02,963][00398] Num frames 4600...
+[2024-11-08 17:04:03,090][00398] Num frames 4700...
+[2024-11-08 17:04:03,208][00398] Num frames 4800...
+[2024-11-08 17:04:03,335][00398] Num frames 4900...
+[2024-11-08 17:04:03,456][00398] Num frames 5000...
+[2024-11-08 17:04:03,585][00398] Num frames 5100...
+[2024-11-08 17:04:03,716][00398] Num frames 5200...
+[2024-11-08 17:04:03,841][00398] Num frames 5300...
+[2024-11-08 17:04:03,962][00398] Num frames 5400...
+[2024-11-08 17:04:04,086][00398] Num frames 5500...
+[2024-11-08 17:04:04,207][00398] Num frames 5600...
+[2024-11-08 17:04:04,333][00398] Num frames 5700...
+[2024-11-08 17:04:04,493][00398] Avg episode rewards: #0: 36.220, true rewards: #0: 14.470
+[2024-11-08 17:04:04,495][00398] Avg episode reward: 36.220, avg true_objective: 14.470
+[2024-11-08 17:04:04,514][00398] Num frames 5800...
+[2024-11-08 17:04:04,653][00398] Num frames 5900...
+[2024-11-08 17:04:04,772][00398] Num frames 6000...
+[2024-11-08 17:04:04,898][00398] Num frames 6100...
+[2024-11-08 17:04:05,016][00398] Num frames 6200...
+[2024-11-08 17:04:05,139][00398] Num frames 6300...
+[2024-11-08 17:04:05,261][00398] Num frames 6400...
+[2024-11-08 17:04:05,384][00398] Num frames 6500...
+[2024-11-08 17:04:05,505][00398] Num frames 6600...
+[2024-11-08 17:04:05,573][00398] Avg episode rewards: #0: 32.420, true rewards: #0: 13.220
+[2024-11-08 17:04:05,576][00398] Avg episode reward: 32.420, avg true_objective: 13.220
+[2024-11-08 17:04:05,696][00398] Num frames 6700...
+[2024-11-08 17:04:05,817][00398] Num frames 6800...
+[2024-11-08 17:04:05,939][00398] Num frames 6900...
+[2024-11-08 17:04:06,060][00398] Num frames 7000...
+[2024-11-08 17:04:06,186][00398] Num frames 7100...
+[2024-11-08 17:04:06,306][00398] Num frames 7200...
+[2024-11-08 17:04:06,432][00398] Num frames 7300...
+[2024-11-08 17:04:06,555][00398] Num frames 7400...
+[2024-11-08 17:04:06,706][00398] Avg episode rewards: #0: 29.623, true rewards: #0: 12.457
+[2024-11-08 17:04:06,708][00398] Avg episode reward: 29.623, avg true_objective: 12.457
+[2024-11-08 17:04:06,742][00398] Num frames 7500...
+[2024-11-08 17:04:06,863][00398] Num frames 7600...
+[2024-11-08 17:04:06,987][00398] Num frames 7700...
+[2024-11-08 17:04:07,107][00398] Num frames 7800...
+[2024-11-08 17:04:07,229][00398] Num frames 7900...
+[2024-11-08 17:04:07,351][00398] Num frames 8000...
+[2024-11-08 17:04:07,477][00398] Num frames 8100...
+[2024-11-08 17:04:07,610][00398] Num frames 8200...
+[2024-11-08 17:04:07,738][00398] Num frames 8300...
+[2024-11-08 17:04:07,813][00398] Avg episode rewards: #0: 27.877, true rewards: #0: 11.877
+[2024-11-08 17:04:07,815][00398] Avg episode reward: 27.877, avg true_objective: 11.877
+[2024-11-08 17:04:07,919][00398] Num frames 8400...
+[2024-11-08 17:04:08,037][00398] Num frames 8500...
+[2024-11-08 17:04:08,160][00398] Num frames 8600...
+[2024-11-08 17:04:08,282][00398] Num frames 8700...
+[2024-11-08 17:04:08,405][00398] Num frames 8800...
+[2024-11-08 17:04:08,526][00398] Num frames 8900...
+[2024-11-08 17:04:08,663][00398] Num frames 9000...
+[2024-11-08 17:04:08,828][00398] Avg episode rewards: #0: 25.977, true rewards: #0: 11.352
+[2024-11-08 17:04:08,830][00398] Avg episode reward: 25.977, avg true_objective: 11.352
+[2024-11-08 17:04:08,857][00398] Num frames 9100...
+[2024-11-08 17:04:08,981][00398] Num frames 9200...
+[2024-11-08 17:04:09,107][00398] Num frames 9300...
+[2024-11-08 17:04:09,230][00398] Num frames 9400...
+[2024-11-08 17:04:09,365][00398] Num frames 9500...
+[2024-11-08 17:04:09,489][00398] Num frames 9600...
+[2024-11-08 17:04:09,617][00398] Num frames 9700...
+[2024-11-08 17:04:09,740][00398] Num frames 9800...
+[2024-11-08 17:04:09,866][00398] Num frames 9900...
+[2024-11-08 17:04:09,991][00398] Num frames 10000...
+[2024-11-08 17:04:10,111][00398] Num frames 10100...
+[2024-11-08 17:04:10,215][00398] Avg episode rewards: #0: 25.709, true rewards: #0: 11.264
+[2024-11-08 17:04:10,216][00398] Avg episode reward: 25.709, avg true_objective: 11.264
+[2024-11-08 17:04:10,294][00398] Num frames 10200...
+[2024-11-08 17:04:10,415][00398] Num frames 10300...
+[2024-11-08 17:04:10,537][00398] Num frames 10400...
+[2024-11-08 17:04:10,664][00398] Num frames 10500...
+[2024-11-08 17:04:10,789][00398] Num frames 10600...
+[2024-11-08 17:04:10,914][00398] Num frames 10700...
+[2024-11-08 17:04:11,031][00398] Num frames 10800...
+[2024-11-08 17:04:11,151][00398] Num frames 10900...
+[2024-11-08 17:04:11,273][00398] Num frames 11000...
+[2024-11-08 17:04:11,394][00398] Num frames 11100...
+[2024-11-08 17:04:11,518][00398] Num frames 11200...
+[2024-11-08 17:04:11,647][00398] Num frames 11300...
+[2024-11-08 17:04:11,811][00398] Avg episode rewards: #0: 25.886, true rewards: #0: 11.386
+[2024-11-08 17:04:11,813][00398] Avg episode reward: 25.886, avg true_objective: 11.386
+[2024-11-08 17:05:19,322][00398] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2024-11-08 17:05:20,038][00398] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-11-08 17:05:20,043][00398] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-11-08 17:05:20,045][00398] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-11-08 17:05:20,047][00398] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-11-08 17:05:20,049][00398] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-11-08 17:05:20,054][00398] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-11-08 17:05:20,055][00398] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2024-11-08 17:05:20,058][00398] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-11-08 17:05:20,059][00398] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2024-11-08 17:05:20,062][00398] Adding new argument 'hf_repository'='Brumocas/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2024-11-08 17:05:20,063][00398] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-11-08 17:05:20,064][00398] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-11-08 17:05:20,065][00398] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-11-08 17:05:20,066][00398] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-11-08 17:05:20,067][00398] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-11-08 17:05:20,124][00398] RunningMeanStd input shape: (3, 72, 128)
+[2024-11-08 17:05:20,126][00398] RunningMeanStd input shape: (1,)
+[2024-11-08 17:05:20,144][00398] ConvEncoder: input_channels=3
+[2024-11-08 17:05:20,204][00398] Conv encoder output size: 512
+[2024-11-08 17:05:20,206][00398] Policy head output size: 512
+[2024-11-08 17:05:20,241][00398] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001222_5005312.pth...
+[2024-11-08 17:05:21,071][00398] Num frames 100...
+[2024-11-08 17:05:21,241][00398] Num frames 200...
+[2024-11-08 17:05:21,410][00398] Num frames 300...
+[2024-11-08 17:05:21,611][00398] Num frames 400...
+[2024-11-08 17:05:21,837][00398] Num frames 500...
+[2024-11-08 17:05:22,038][00398] Num frames 600...
+[2024-11-08 17:05:22,213][00398] Num frames 700...
+[2024-11-08 17:05:22,372][00398] Num frames 800...
+[2024-11-08 17:05:22,542][00398] Num frames 900...
+[2024-11-08 17:05:22,689][00398] Avg episode rewards: #0: 20.530, true rewards: #0: 9.530
+[2024-11-08 17:05:22,691][00398] Avg episode reward: 20.530, avg true_objective: 9.530
+[2024-11-08 17:05:22,767][00398] Num frames 1000...
+[2024-11-08 17:05:22,922][00398] Num frames 1100...
+[2024-11-08 17:05:23,080][00398] Num frames 1200...
+[2024-11-08 17:05:23,237][00398] Num frames 1300...
+[2024-11-08 17:05:23,398][00398] Num frames 1400...
+[2024-11-08 17:05:23,568][00398] Num frames 1500...
+[2024-11-08 17:05:23,735][00398] Num frames 1600...
+[2024-11-08 17:05:23,899][00398] Num frames 1700...
+[2024-11-08 17:05:24,095][00398] Num frames 1800...
+[2024-11-08 17:05:24,258][00398] Num frames 1900...
+[2024-11-08 17:05:24,441][00398] Num frames 2000...
+[2024-11-08 17:05:24,639][00398] Num frames 2100...
+[2024-11-08 17:05:24,810][00398] Num frames 2200...
+[2024-11-08 17:05:24,984][00398] Num frames 2300...
+[2024-11-08 17:05:25,174][00398] Num frames 2400...
+[2024-11-08 17:05:25,377][00398] Num frames 2500...
+[2024-11-08 17:05:25,555][00398] Num frames 2600...
+[2024-11-08 17:05:25,766][00398] Num frames 2700...
+[2024-11-08 17:05:25,953][00398] Num frames 2800...
+[2024-11-08 17:05:26,087][00398] Avg episode rewards: #0: 35.205, true rewards: #0: 14.205
+[2024-11-08 17:05:26,089][00398] Avg episode reward: 35.205, avg true_objective: 14.205
+[2024-11-08 17:05:26,197][00398] Num frames 2900...
+[2024-11-08 17:05:26,383][00398] Num frames 3000...
+[2024-11-08 17:05:26,583][00398] Num frames 3100...
+[2024-11-08 17:05:26,780][00398] Num frames 3200...
+[2024-11-08 17:05:26,972][00398] Num frames 3300...
+[2024-11-08 17:05:27,150][00398] Num frames 3400...
+[2024-11-08 17:05:27,318][00398] Num frames 3500...
+[2024-11-08 17:05:27,478][00398] Num frames 3600...
+[2024-11-08 17:05:27,609][00398] Avg episode rewards: #0: 28.137, true rewards: #0: 12.137
+[2024-11-08 17:05:27,610][00398] Avg episode reward: 28.137, avg true_objective: 12.137
+[2024-11-08 17:05:27,707][00398] Num frames 3700...
+[2024-11-08 17:05:27,875][00398] Num frames 3800...
+[2024-11-08 17:05:27,995][00398] Num frames 3900...
+[2024-11-08 17:05:28,115][00398] Num frames 4000...
+[2024-11-08 17:05:28,236][00398] Num frames 4100...
+[2024-11-08 17:05:28,358][00398] Num frames 4200...
+[2024-11-08 17:05:28,478][00398] Num frames 4300...
+[2024-11-08 17:05:28,607][00398] Num frames 4400...
+[2024-11-08 17:05:28,729][00398] Num frames 4500...
+[2024-11-08 17:05:28,858][00398] Num frames 4600...
+[2024-11-08 17:05:28,979][00398] Num frames 4700...
+[2024-11-08 17:05:29,098][00398] Num frames 4800...
+[2024-11-08 17:05:29,223][00398] Num frames 4900...
+[2024-11-08 17:05:29,346][00398] Num frames 5000...
+[2024-11-08 17:05:29,466][00398] Num frames 5100...
+[2024-11-08 17:05:29,604][00398] Avg episode rewards: #0: 29.907, true rewards: #0: 12.907
+[2024-11-08 17:05:29,607][00398] Avg episode reward: 29.907, avg true_objective: 12.907
+[2024-11-08 17:05:29,654][00398] Num frames 5200...
+[2024-11-08 17:05:29,772][00398] Num frames 5300...
+[2024-11-08 17:05:29,899][00398] Num frames 5400...
+[2024-11-08 17:05:30,022][00398] Num frames 5500...
+[2024-11-08 17:05:30,142][00398] Num frames 5600...
+[2024-11-08 17:05:30,265][00398] Num frames 5700...
+[2024-11-08 17:05:30,386][00398] Num frames 5800...
+[2024-11-08 17:05:30,506][00398] Num frames 5900...
+[2024-11-08 17:05:30,638][00398] Num frames 6000...
+[2024-11-08 17:05:30,761][00398] Num frames 6100...
+[2024-11-08 17:05:30,887][00398] Num frames 6200...
+[2024-11-08 17:05:31,013][00398] Num frames 6300...
+[2024-11-08 17:05:31,133][00398] Num frames 6400...
+[2024-11-08 17:05:31,254][00398] Num frames 6500...
+[2024-11-08 17:05:31,375][00398] Num frames 6600...
+[2024-11-08 17:05:31,546][00398] Avg episode rewards: #0: 30.586, true rewards: #0: 13.386
+[2024-11-08 17:05:31,548][00398] Avg episode reward: 30.586, avg true_objective: 13.386
+[2024-11-08 17:05:31,561][00398] Num frames 6700...
+[2024-11-08 17:05:31,684][00398] Num frames 6800...
+[2024-11-08 17:05:31,803][00398] Num frames 6900...
+[2024-11-08 17:05:31,930][00398] Num frames 7000...
+[2024-11-08 17:05:32,048][00398] Num frames 7100...
+[2024-11-08 17:05:32,204][00398] Num frames 7200...
+[2024-11-08 17:05:32,272][00398] Avg episode rewards: #0: 27.008, true rewards: #0: 12.008
+[2024-11-08 17:05:32,274][00398] Avg episode reward: 27.008, avg true_objective: 12.008
+[2024-11-08 17:05:32,434][00398] Num frames 7300...
+[2024-11-08 17:05:32,617][00398] Num frames 7400...
+[2024-11-08 17:05:32,777][00398] Num frames 7500...
+[2024-11-08 17:05:32,943][00398] Num frames 7600...
+[2024-11-08 17:05:33,112][00398] Num frames 7700...
+[2024-11-08 17:05:33,279][00398] Num frames 7800...
+[2024-11-08 17:05:33,448][00398] Num frames 7900...
+[2024-11-08 17:05:33,636][00398] Num frames 8000...
+[2024-11-08 17:05:33,759][00398] Avg episode rewards: #0: 25.341, true rewards: #0: 11.484
+[2024-11-08 17:05:33,761][00398] Avg episode reward: 25.341, avg true_objective: 11.484
+[2024-11-08 17:05:33,871][00398] Num frames 8100...
+[2024-11-08 17:05:34,053][00398] Num frames 8200...
+[2024-11-08 17:05:34,232][00398] Num frames 8300...
+[2024-11-08 17:05:34,418][00398] Num frames 8400...
+[2024-11-08 17:05:34,656][00398] Avg episode rewards: #0: 23.109, true rewards: #0: 10.609
+[2024-11-08 17:05:34,659][00398] Avg episode reward: 23.109, avg true_objective: 10.609
+[2024-11-08 17:05:34,690][00398] Num frames 8500...
+[2024-11-08 17:05:34,815][00398] Num frames 8600...
+[2024-11-08 17:05:34,934][00398] Num frames 8700...
+[2024-11-08 17:05:35,066][00398] Num frames 8800...
+[2024-11-08 17:05:35,191][00398] Num frames 8900...
+[2024-11-08 17:05:35,315][00398] Num frames 9000...
+[2024-11-08 17:05:35,438][00398] Num frames 9100...
+[2024-11-08 17:05:35,565][00398] Num frames 9200...
+[2024-11-08 17:05:35,691][00398] Num frames 9300...
+[2024-11-08 17:05:35,813][00398] Num frames 9400...
+[2024-11-08 17:05:35,942][00398] Num frames 9500...
+[2024-11-08 17:05:36,128][00398] Avg episode rewards: #0: 23.664, true rewards: #0: 10.664
+[2024-11-08 17:05:36,130][00398] Avg episode reward: 23.664, avg true_objective: 10.664
+[2024-11-08 17:05:36,135][00398] Num frames 9600...
+[2024-11-08 17:05:36,256][00398] Num frames 9700...
+[2024-11-08 17:05:36,376][00398] Num frames 9800...
+[2024-11-08 17:05:36,492][00398] Num frames 9900...
+[2024-11-08 17:05:36,635][00398] Num frames 10000...
+[2024-11-08 17:05:36,783][00398] Avg episode rewards: #0: 21.978, true rewards: #0: 10.078
+[2024-11-08 17:05:36,786][00398] Avg episode reward: 21.978, avg true_objective: 10.078
+[2024-11-08 17:06:35,863][00398] Replay video saved to /content/train_dir/default_experiment/replay.mp4!