Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1725528160.127c6a122c23

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a464cc5a64cff7c18cea400e888d3d513c3b53add4bdd6e92c6453aa8fecaf4
+size 2343

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 9.01 +/- 4.95
+      value: 8.82 +/- 4.53
       name: mean_reward
       verified: false
 ---

checkpoint_p0/checkpoint_000000980_4014080.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:777fd6fe6dbb7a22137209fcc6278d58c46615fbb6a67735ff2f3d9aff1223b1
+size 34929669

checkpoint_p0/checkpoint_000000981_4018176.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff674e218a767ea35fa36f2da2416975c0e2cf5cc6d4234ddcf8e9024cc33f4d
+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": 2000000,
   "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:eebb3c9aa2933def16ae77a57c61d99637293404657219d0cab103665411d960
-size 17360340
+oid sha256:3d5564e1e0ab2416fc2c7e391e458095d91777008bcfd9aa5c402c3041f3c663
+size 16920056

sf_log.txt

@@ -1128,3 +1128,657 @@ main_loop: 1104.8237
 [2024-09-05 09:18:59,172][00556] Avg episode rewards: #0: 19.908, true rewards: #0: 9.008
 [2024-09-05 09:18:59,173][00556] Avg episode reward: 19.908, avg true_objective: 9.008
 [2024-09-05 09:19:58,814][00556] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2024-09-05 09:20:05,980][00556] The model has been pushed to https://huggingface.co/neeldevenshah/rl_course_vizdoom_health_gathering_supreme
+[2024-09-05 09:22:40,327][00556] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-09-05 09:22:40,329][00556] Overriding arg 'train_for_env_steps' with value 2000000 passed from command line
+[2024-09-05 09:22:40,340][00556] Experiment dir /content/train_dir/default_experiment already exists!
+[2024-09-05 09:22:40,342][00556] Resuming existing experiment from /content/train_dir/default_experiment...
+[2024-09-05 09:22:40,346][00556] Weights and Biases integration disabled
+[2024-09-05 09:22:40,352][00556] Environment var CUDA_VISIBLE_DEVICES is 0
+
+[2024-09-05 09:22:42,659][00556] 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=2000000
+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
+[2024-09-05 09:22:42,661][00556] Saving configuration to /content/train_dir/default_experiment/config.json...
+[2024-09-05 09:22:42,665][00556] Rollout worker 0 uses device cpu
+[2024-09-05 09:22:42,668][00556] Rollout worker 1 uses device cpu
+[2024-09-05 09:22:42,670][00556] Rollout worker 2 uses device cpu
+[2024-09-05 09:22:42,672][00556] Rollout worker 3 uses device cpu
+[2024-09-05 09:22:42,673][00556] Rollout worker 4 uses device cpu
+[2024-09-05 09:22:42,674][00556] Rollout worker 5 uses device cpu
+[2024-09-05 09:22:42,675][00556] Rollout worker 6 uses device cpu
+[2024-09-05 09:22:42,676][00556] Rollout worker 7 uses device cpu
+[2024-09-05 09:22:42,751][00556] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-09-05 09:22:42,752][00556] InferenceWorker_p0-w0: min num requests: 2
+[2024-09-05 09:22:42,918][00556] Starting all processes...
+[2024-09-05 09:22:42,921][00556] Starting process learner_proc0
+[2024-09-05 09:22:42,968][00556] Starting all processes...
+[2024-09-05 09:22:42,973][00556] Starting process inference_proc0-0
+[2024-09-05 09:22:42,974][00556] Starting process rollout_proc0
+[2024-09-05 09:22:42,976][00556] Starting process rollout_proc1
+[2024-09-05 09:22:42,976][00556] Starting process rollout_proc2
+[2024-09-05 09:22:42,976][00556] Starting process rollout_proc3
+[2024-09-05 09:22:42,976][00556] Starting process rollout_proc4
+[2024-09-05 09:22:42,976][00556] Starting process rollout_proc5
+[2024-09-05 09:22:42,976][00556] Starting process rollout_proc6
+[2024-09-05 09:22:42,976][00556] Starting process rollout_proc7
+[2024-09-05 09:22:59,230][13525] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-09-05 09:22:59,231][13525] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2024-09-05 09:22:59,317][13525] Num visible devices: 1
+[2024-09-05 09:22:59,345][13525] Starting seed is not provided
+[2024-09-05 09:22:59,346][13525] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-09-05 09:22:59,347][13525] Initializing actor-critic model on device cuda:0
+[2024-09-05 09:22:59,348][13525] RunningMeanStd input shape: (3, 72, 128)
+[2024-09-05 09:22:59,349][13525] RunningMeanStd input shape: (1,)
+[2024-09-05 09:22:59,419][13525] ConvEncoder: input_channels=3
+[2024-09-05 09:22:59,581][13541] Worker 1 uses CPU cores [1]
+[2024-09-05 09:22:59,601][13540] Worker 2 uses CPU cores [0]
+[2024-09-05 09:22:59,607][13545] Worker 5 uses CPU cores [1]
+[2024-09-05 09:22:59,667][13539] Worker 0 uses CPU cores [0]
+[2024-09-05 09:22:59,687][13543] Worker 4 uses CPU cores [0]
+[2024-09-05 09:22:59,699][13542] Worker 3 uses CPU cores [1]
+[2024-09-05 09:22:59,707][13546] Worker 6 uses CPU cores [0]
+[2024-09-05 09:22:59,734][13538] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-09-05 09:22:59,735][13538] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2024-09-05 09:22:59,778][13538] Num visible devices: 1
+[2024-09-05 09:22:59,807][13544] Worker 7 uses CPU cores [1]
+[2024-09-05 09:22:59,844][13525] Conv encoder output size: 512
+[2024-09-05 09:22:59,844][13525] Policy head output size: 512
+[2024-09-05 09:22:59,861][13525] Created Actor Critic model with architecture:
+[2024-09-05 09:22:59,861][13525] 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)
+  )
+)
+[2024-09-05 09:22:59,992][13525] Using optimizer <class 'torch.optim.adam.Adam'>
+[2024-09-05 09:23:00,592][13525] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-09-05 09:23:00,628][13525] Loading model from checkpoint
+[2024-09-05 09:23:00,630][13525] Loaded experiment state at self.train_step=978, self.env_steps=4005888
+[2024-09-05 09:23:00,630][13525] Initialized policy 0 weights for model version 978
+[2024-09-05 09:23:00,634][13525] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-09-05 09:23:00,643][13525] LearnerWorker_p0 finished initialization!
+[2024-09-05 09:23:00,772][13538] RunningMeanStd input shape: (3, 72, 128)
+[2024-09-05 09:23:00,774][13538] RunningMeanStd input shape: (1,)
+[2024-09-05 09:23:00,797][13538] ConvEncoder: input_channels=3
+[2024-09-05 09:23:00,902][13538] Conv encoder output size: 512
+[2024-09-05 09:23:00,903][13538] Policy head output size: 512
+[2024-09-05 09:23:00,956][00556] Inference worker 0-0 is ready!
+[2024-09-05 09:23:00,958][00556] All inference workers are ready! Signal rollout workers to start!
+[2024-09-05 09:23:01,269][13540] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-05 09:23:01,280][13544] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-05 09:23:01,285][13546] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-05 09:23:01,287][13545] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-05 09:23:01,287][13539] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-05 09:23:01,290][13541] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-05 09:23:01,292][13543] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-05 09:23:01,413][13542] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-05 09:23:02,350][13544] Decorrelating experience for 0 frames...
+[2024-09-05 09:23:02,349][13541] Decorrelating experience for 0 frames...
+[2024-09-05 09:23:02,742][00556] Heartbeat connected on Batcher_0
+[2024-09-05 09:23:02,747][00556] Heartbeat connected on LearnerWorker_p0
+[2024-09-05 09:23:02,778][00556] Heartbeat connected on InferenceWorker_p0-w0
+[2024-09-05 09:23:03,046][13540] Decorrelating experience for 0 frames...
+[2024-09-05 09:23:03,058][13546] Decorrelating experience for 0 frames...
+[2024-09-05 09:23:03,064][13539] Decorrelating experience for 0 frames...
+[2024-09-05 09:23:03,072][13543] Decorrelating experience for 0 frames...
+[2024-09-05 09:23:03,115][13541] Decorrelating experience for 32 frames...
+[2024-09-05 09:23:03,296][13542] Decorrelating experience for 0 frames...
+[2024-09-05 09:23:04,066][13544] Decorrelating experience for 32 frames...
+[2024-09-05 09:23:04,144][13545] Decorrelating experience for 0 frames...
+[2024-09-05 09:23:04,523][13546] Decorrelating experience for 32 frames...
+[2024-09-05 09:23:04,526][13539] Decorrelating experience for 32 frames...
+[2024-09-05 09:23:04,634][13540] Decorrelating experience for 32 frames...
+[2024-09-05 09:23:05,099][13543] Decorrelating experience for 32 frames...
+[2024-09-05 09:23:05,356][00556] 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)
+[2024-09-05 09:23:05,493][13542] Decorrelating experience for 32 frames...
+[2024-09-05 09:23:05,676][13545] Decorrelating experience for 32 frames...
+[2024-09-05 09:23:06,764][13541] Decorrelating experience for 64 frames...
+[2024-09-05 09:23:07,325][13546] Decorrelating experience for 64 frames...
+[2024-09-05 09:23:07,343][13544] Decorrelating experience for 64 frames...
+[2024-09-05 09:23:07,467][13540] Decorrelating experience for 64 frames...
+[2024-09-05 09:23:07,888][13543] Decorrelating experience for 64 frames...
+[2024-09-05 09:23:08,078][13539] Decorrelating experience for 64 frames...
+[2024-09-05 09:23:08,111][13542] Decorrelating experience for 64 frames...
+[2024-09-05 09:23:08,779][13545] Decorrelating experience for 64 frames...
+[2024-09-05 09:23:09,261][13546] Decorrelating experience for 96 frames...
+[2024-09-05 09:23:09,361][13540] Decorrelating experience for 96 frames...
+[2024-09-05 09:23:09,562][00556] Heartbeat connected on RolloutWorker_w6
+[2024-09-05 09:23:09,818][00556] Heartbeat connected on RolloutWorker_w2
+[2024-09-05 09:23:10,166][13539] Decorrelating experience for 96 frames...
+[2024-09-05 09:23:10,355][00556] 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)
+[2024-09-05 09:23:10,607][00556] Heartbeat connected on RolloutWorker_w0
+[2024-09-05 09:23:10,671][13541] Decorrelating experience for 96 frames...
+[2024-09-05 09:23:11,046][13542] Decorrelating experience for 96 frames...
+[2024-09-05 09:23:11,122][00556] Heartbeat connected on RolloutWorker_w1
+[2024-09-05 09:23:11,396][00556] Heartbeat connected on RolloutWorker_w3
+[2024-09-05 09:23:11,696][13544] Decorrelating experience for 96 frames...
+[2024-09-05 09:23:11,833][13543] Decorrelating experience for 96 frames...
+[2024-09-05 09:23:12,278][00556] Heartbeat connected on RolloutWorker_w7
+[2024-09-05 09:23:12,492][00556] Heartbeat connected on RolloutWorker_w4
+[2024-09-05 09:23:13,407][13545] Decorrelating experience for 96 frames...
+[2024-09-05 09:23:14,057][00556] Heartbeat connected on RolloutWorker_w5
+[2024-09-05 09:23:15,353][00556] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4005888. Throughput: 0: 119.0. Samples: 1190. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-09-05 09:23:15,355][00556] Avg episode reward: [(0, '4.190')]
+[2024-09-05 09:23:16,207][13525] Signal inference workers to stop experience collection...
+[2024-09-05 09:23:16,227][13538] InferenceWorker_p0-w0: stopping experience collection
+[2024-09-05 09:23:17,702][13525] Signal inference workers to resume experience collection...
+[2024-09-05 09:23:17,726][00556] Component Batcher_0 stopped!
+[2024-09-05 09:23:17,733][13525] Stopping Batcher_0...
+[2024-09-05 09:23:17,734][13525] Loop batcher_evt_loop terminating...
+[2024-09-05 09:23:17,771][13538] Weights refcount: 2 0
+[2024-09-05 09:23:17,775][00556] Component InferenceWorker_p0-w0 stopped!
+[2024-09-05 09:23:17,780][13538] Stopping InferenceWorker_p0-w0...
+[2024-09-05 09:23:17,781][13538] Loop inference_proc0-0_evt_loop terminating...
+[2024-09-05 09:23:18,026][00556] Component RolloutWorker_w3 stopped!
+[2024-09-05 09:23:18,032][13542] Stopping RolloutWorker_w3...
+[2024-09-05 09:23:18,034][13542] Loop rollout_proc3_evt_loop terminating...
+[2024-09-05 09:23:18,051][00556] Component RolloutWorker_w1 stopped!
+[2024-09-05 09:23:18,055][13541] Stopping RolloutWorker_w1...
+[2024-09-05 09:23:18,057][13541] Loop rollout_proc1_evt_loop terminating...
+[2024-09-05 09:23:18,066][00556] Component RolloutWorker_w7 stopped!
+[2024-09-05 09:23:18,070][13544] Stopping RolloutWorker_w7...
+[2024-09-05 09:23:18,075][13544] Loop rollout_proc7_evt_loop terminating...
+[2024-09-05 09:23:18,090][00556] Component RolloutWorker_w5 stopped!
+[2024-09-05 09:23:18,095][13545] Stopping RolloutWorker_w5...
+[2024-09-05 09:23:18,096][13545] Loop rollout_proc5_evt_loop terminating...
+[2024-09-05 09:23:18,163][13539] Stopping RolloutWorker_w0...
+[2024-09-05 09:23:18,163][13539] Loop rollout_proc0_evt_loop terminating...
+[2024-09-05 09:23:18,166][13543] Stopping RolloutWorker_w4...
+[2024-09-05 09:23:18,170][13543] Loop rollout_proc4_evt_loop terminating...
+[2024-09-05 09:23:18,163][00556] Component RolloutWorker_w0 stopped!
+[2024-09-05 09:23:18,171][00556] Component RolloutWorker_w4 stopped!
+[2024-09-05 09:23:18,205][13546] Stopping RolloutWorker_w6...
+[2024-09-05 09:23:18,206][13546] Loop rollout_proc6_evt_loop terminating...
+[2024-09-05 09:23:18,205][00556] Component RolloutWorker_w6 stopped!
+[2024-09-05 09:23:18,211][13540] Stopping RolloutWorker_w2...
+[2024-09-05 09:23:18,211][13540] Loop rollout_proc2_evt_loop terminating...
+[2024-09-05 09:23:18,211][00556] Component RolloutWorker_w2 stopped!
+[2024-09-05 09:23:18,583][13525] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000980_4014080.pth...
+[2024-09-05 09:23:18,725][13525] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000950_3891200.pth
+[2024-09-05 09:23:18,813][13525] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000981_4018176.pth...
+[2024-09-05 09:23:18,994][13525] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth
+[2024-09-05 09:23:19,030][13525] Stopping LearnerWorker_p0...
+[2024-09-05 09:23:19,031][13525] Loop learner_proc0_evt_loop terminating...
+[2024-09-05 09:23:19,032][00556] Component LearnerWorker_p0 stopped!
+[2024-09-05 09:23:19,035][00556] Waiting for process learner_proc0 to stop...
+[2024-09-05 09:23:20,461][00556] Waiting for process inference_proc0-0 to join...
+[2024-09-05 09:23:20,464][00556] Waiting for process rollout_proc0 to join...
+[2024-09-05 09:23:22,069][00556] Waiting for process rollout_proc1 to join...
+[2024-09-05 09:23:22,076][00556] Waiting for process rollout_proc2 to join...
+[2024-09-05 09:23:22,077][00556] Waiting for process rollout_proc3 to join...
+[2024-09-05 09:23:22,079][00556] Waiting for process rollout_proc4 to join...
+[2024-09-05 09:23:22,082][00556] Waiting for process rollout_proc5 to join...
+[2024-09-05 09:23:22,084][00556] Waiting for process rollout_proc6 to join...
+[2024-09-05 09:23:22,085][00556] Waiting for process rollout_proc7 to join...
+[2024-09-05 09:23:22,087][00556] Batcher 0 profile tree view:
+batching: 0.8961, releasing_batches: 0.0236
+[2024-09-05 09:23:22,088][00556] InferenceWorker_p0-w0 profile tree view:
+update_model: 0.0191
+wait_policy: 0.0053
+  wait_policy_total: 10.7084
+one_step: 0.0030
+  handle_policy_step: 4.1885
+    deserialize: 0.0672, stack: 0.0200, obs_to_device_normalize: 0.7834, forward: 2.7947, send_messages: 0.1187
+    prepare_outputs: 0.2949
+      to_cpu: 0.1654
+[2024-09-05 09:23:22,090][00556] Learner 0 profile tree view:
+misc: 0.0000, prepare_batch: 2.5375
+train: 2.8481
+  epoch_init: 0.0000, minibatch_init: 0.0000, losses_postprocess: 0.0005, kl_divergence: 0.0105, after_optimizer: 0.0580
+  calculate_losses: 1.4088
+    losses_init: 0.0000, forward_head: 0.4098, bptt_initial: 0.8584, tail: 0.0752, advantages_returns: 0.0011, losses: 0.0453
+    bptt: 0.0081
+      bptt_forward_core: 0.0079
+  update: 1.3689
+    clip: 0.0561
+[2024-09-05 09:23:22,091][00556] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.0009, enqueue_policy_requests: 0.5479, env_step: 3.3452, overhead: 0.0306, complete_rollouts: 0.0128
+save_policy_outputs: 0.0620
+  split_output_tensors: 0.0194
+[2024-09-05 09:23:22,093][00556] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.0011, enqueue_policy_requests: 0.4878, env_step: 2.5696, overhead: 0.0508, complete_rollouts: 0.0444
+save_policy_outputs: 0.0733
+  split_output_tensors: 0.0311
+[2024-09-05 09:23:22,095][00556] Loop Runner_EvtLoop terminating...
+[2024-09-05 09:23:22,097][00556] Runner profile tree view:
+main_loop: 39.1793
+[2024-09-05 09:23:22,099][00556] Collected {0: 4018176}, FPS: 313.6
+[2024-09-05 09:23:22,118][00556] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-09-05 09:23:22,129][00556] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-09-05 09:23:22,131][00556] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-09-05 09:23:22,132][00556] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-09-05 09:23:22,133][00556] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-09-05 09:23:22,136][00556] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-09-05 09:23:22,137][00556] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2024-09-05 09:23:22,139][00556] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-09-05 09:23:22,140][00556] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2024-09-05 09:23:22,141][00556] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2024-09-05 09:23:22,143][00556] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-09-05 09:23:22,144][00556] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-09-05 09:23:22,145][00556] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-09-05 09:23:22,146][00556] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-09-05 09:23:22,147][00556] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-09-05 09:23:22,179][00556] RunningMeanStd input shape: (3, 72, 128)
+[2024-09-05 09:23:22,180][00556] RunningMeanStd input shape: (1,)
+[2024-09-05 09:23:22,193][00556] ConvEncoder: input_channels=3
+[2024-09-05 09:23:22,231][00556] Conv encoder output size: 512
+[2024-09-05 09:23:22,232][00556] Policy head output size: 512
+[2024-09-05 09:23:22,255][00556] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000981_4018176.pth...
+[2024-09-05 09:23:22,914][00556] Num frames 100...
+[2024-09-05 09:23:23,082][00556] Num frames 200...
+[2024-09-05 09:23:23,252][00556] Num frames 300...
+[2024-09-05 09:23:23,421][00556] Num frames 400...
+[2024-09-05 09:23:23,589][00556] Num frames 500...
+[2024-09-05 09:23:23,771][00556] Num frames 600...
+[2024-09-05 09:23:24,002][00556] Avg episode rewards: #0: 14.880, true rewards: #0: 6.880
+[2024-09-05 09:23:24,004][00556] Avg episode reward: 14.880, avg true_objective: 6.880
+[2024-09-05 09:23:24,031][00556] Num frames 700...
+[2024-09-05 09:23:24,204][00556] Num frames 800...
+[2024-09-05 09:23:24,381][00556] Num frames 900...
+[2024-09-05 09:23:24,575][00556] Num frames 1000...
+[2024-09-05 09:23:24,759][00556] Num frames 1100...
+[2024-09-05 09:23:24,941][00556] Num frames 1200...
+[2024-09-05 09:23:25,104][00556] Num frames 1300...
+[2024-09-05 09:23:25,228][00556] Num frames 1400...
+[2024-09-05 09:23:25,355][00556] Num frames 1500...
+[2024-09-05 09:23:25,475][00556] Num frames 1600...
+[2024-09-05 09:23:25,600][00556] Num frames 1700...
+[2024-09-05 09:23:25,732][00556] Num frames 1800...
+[2024-09-05 09:23:25,864][00556] Num frames 1900...
+[2024-09-05 09:23:25,995][00556] Num frames 2000...
+[2024-09-05 09:23:26,118][00556] Num frames 2100...
+[2024-09-05 09:23:26,245][00556] Num frames 2200...
+[2024-09-05 09:23:26,379][00556] Num frames 2300...
+[2024-09-05 09:23:26,507][00556] Num frames 2400...
+[2024-09-05 09:23:26,632][00556] Num frames 2500...
+[2024-09-05 09:23:26,763][00556] Num frames 2600...
+[2024-09-05 09:23:26,898][00556] Num frames 2700...
+[2024-09-05 09:23:27,069][00556] Avg episode rewards: #0: 35.440, true rewards: #0: 13.940
+[2024-09-05 09:23:27,070][00556] Avg episode reward: 35.440, avg true_objective: 13.940
+[2024-09-05 09:23:27,088][00556] Num frames 2800...
+[2024-09-05 09:23:27,210][00556] Num frames 2900...
+[2024-09-05 09:23:27,337][00556] Num frames 3000...
+[2024-09-05 09:23:27,460][00556] Num frames 3100...
+[2024-09-05 09:23:27,589][00556] Num frames 3200...
+[2024-09-05 09:23:27,726][00556] Num frames 3300...
+[2024-09-05 09:23:27,849][00556] Num frames 3400...
+[2024-09-05 09:23:27,983][00556] Num frames 3500...
+[2024-09-05 09:23:28,106][00556] Avg episode rewards: #0: 29.853, true rewards: #0: 11.853
+[2024-09-05 09:23:28,108][00556] Avg episode reward: 29.853, avg true_objective: 11.853
+[2024-09-05 09:23:28,163][00556] Num frames 3600...
+[2024-09-05 09:23:28,290][00556] Num frames 3700...
+[2024-09-05 09:23:28,415][00556] Num frames 3800...
+[2024-09-05 09:23:28,540][00556] Num frames 3900...
+[2024-09-05 09:23:28,668][00556] Num frames 4000...
+[2024-09-05 09:23:28,792][00556] Num frames 4100...
+[2024-09-05 09:23:28,916][00556] Num frames 4200...
+[2024-09-05 09:23:29,048][00556] Num frames 4300...
+[2024-09-05 09:23:29,173][00556] Num frames 4400...
+[2024-09-05 09:23:29,324][00556] Num frames 4500...
+[2024-09-05 09:23:29,452][00556] Num frames 4600...
+[2024-09-05 09:23:29,580][00556] Num frames 4700...
+[2024-09-05 09:23:29,712][00556] Num frames 4800...
+[2024-09-05 09:23:29,837][00556] Num frames 4900...
+[2024-09-05 09:23:29,889][00556] Avg episode rewards: #0: 29.750, true rewards: #0: 12.250
+[2024-09-05 09:23:29,891][00556] Avg episode reward: 29.750, avg true_objective: 12.250
+[2024-09-05 09:23:30,024][00556] Num frames 5000...
+[2024-09-05 09:23:30,149][00556] Num frames 5100...
+[2024-09-05 09:23:30,272][00556] Num frames 5200...
+[2024-09-05 09:23:30,400][00556] Num frames 5300...
+[2024-09-05 09:23:30,524][00556] Num frames 5400...
+[2024-09-05 09:23:30,654][00556] Num frames 5500...
+[2024-09-05 09:23:30,783][00556] Num frames 5600...
+[2024-09-05 09:23:30,844][00556] Avg episode rewards: #0: 27.008, true rewards: #0: 11.208
+[2024-09-05 09:23:30,845][00556] Avg episode reward: 27.008, avg true_objective: 11.208
+[2024-09-05 09:23:30,968][00556] Num frames 5700...
+[2024-09-05 09:23:31,101][00556] Num frames 5800...
+[2024-09-05 09:23:31,228][00556] Num frames 5900...
+[2024-09-05 09:23:31,353][00556] Num frames 6000...
+[2024-09-05 09:23:31,480][00556] Num frames 6100...
+[2024-09-05 09:23:31,603][00556] Num frames 6200...
+[2024-09-05 09:23:31,738][00556] Num frames 6300...
+[2024-09-05 09:23:31,863][00556] Num frames 6400...
+[2024-09-05 09:23:31,938][00556] Avg episode rewards: #0: 25.858, true rewards: #0: 10.692
+[2024-09-05 09:23:31,939][00556] Avg episode reward: 25.858, avg true_objective: 10.692
+[2024-09-05 09:23:32,054][00556] Num frames 6500...
+[2024-09-05 09:23:32,185][00556] Num frames 6600...
+[2024-09-05 09:23:32,312][00556] Num frames 6700...
+[2024-09-05 09:23:32,435][00556] Num frames 6800...
+[2024-09-05 09:23:32,560][00556] Num frames 6900...
+[2024-09-05 09:23:32,690][00556] Num frames 7000...
+[2024-09-05 09:23:32,812][00556] Num frames 7100...
+[2024-09-05 09:23:32,969][00556] Avg episode rewards: #0: 24.261, true rewards: #0: 10.261
+[2024-09-05 09:23:32,971][00556] Avg episode reward: 24.261, avg true_objective: 10.261
+[2024-09-05 09:23:32,995][00556] Num frames 7200...
+[2024-09-05 09:23:33,128][00556] Num frames 7300...
+[2024-09-05 09:23:33,249][00556] Num frames 7400...
+[2024-09-05 09:23:33,376][00556] Num frames 7500...
+[2024-09-05 09:23:33,500][00556] Num frames 7600...
+[2024-09-05 09:23:33,622][00556] Num frames 7700...
+[2024-09-05 09:23:33,755][00556] Num frames 7800...
+[2024-09-05 09:23:33,877][00556] Num frames 7900...
+[2024-09-05 09:23:33,999][00556] Num frames 8000...
+[2024-09-05 09:23:34,132][00556] Num frames 8100...
+[2024-09-05 09:23:34,257][00556] Num frames 8200...
+[2024-09-05 09:23:34,382][00556] Num frames 8300...
+[2024-09-05 09:23:34,509][00556] Num frames 8400...
+[2024-09-05 09:23:34,648][00556] Avg episode rewards: #0: 24.704, true rewards: #0: 10.579
+[2024-09-05 09:23:34,650][00556] Avg episode reward: 24.704, avg true_objective: 10.579
+[2024-09-05 09:23:34,704][00556] Num frames 8500...
+[2024-09-05 09:23:34,828][00556] Num frames 8600...
+[2024-09-05 09:23:34,951][00556] Num frames 8700...
+[2024-09-05 09:23:35,083][00556] Num frames 8800...
+[2024-09-05 09:23:35,262][00556] Num frames 8900...
+[2024-09-05 09:23:35,440][00556] Num frames 9000...
+[2024-09-05 09:23:35,608][00556] Num frames 9100...
+[2024-09-05 09:23:35,786][00556] Num frames 9200...
+[2024-09-05 09:23:35,959][00556] Num frames 9300...
+[2024-09-05 09:23:36,131][00556] Num frames 9400...
+[2024-09-05 09:23:36,318][00556] Num frames 9500...
+[2024-09-05 09:23:36,493][00556] Num frames 9600...
+[2024-09-05 09:23:36,675][00556] Num frames 9700...
+[2024-09-05 09:23:36,804][00556] Avg episode rewards: #0: 25.270, true rewards: #0: 10.826
+[2024-09-05 09:23:36,807][00556] Avg episode reward: 25.270, avg true_objective: 10.826
+[2024-09-05 09:23:36,910][00556] Num frames 9800...
+[2024-09-05 09:23:37,091][00556] Num frames 9900...
+[2024-09-05 09:23:37,273][00556] Num frames 10000...
+[2024-09-05 09:23:37,455][00556] Num frames 10100...
+[2024-09-05 09:23:37,633][00556] Num frames 10200...
+[2024-09-05 09:23:37,777][00556] Num frames 10300...
+[2024-09-05 09:23:37,856][00556] Avg episode rewards: #0: 23.719, true rewards: #0: 10.319
+[2024-09-05 09:23:37,858][00556] Avg episode reward: 23.719, avg true_objective: 10.319
+[2024-09-05 09:24:46,467][00556] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2024-09-05 09:24:46,948][00556] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-09-05 09:24:46,950][00556] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-09-05 09:24:46,952][00556] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-09-05 09:24:46,954][00556] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-09-05 09:24:46,956][00556] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-09-05 09:24:46,958][00556] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-09-05 09:24:46,960][00556] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2024-09-05 09:24:46,961][00556] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-09-05 09:24:46,962][00556] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2024-09-05 09:24:46,964][00556] Adding new argument 'hf_repository'='neeldevenshah/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2024-09-05 09:24:46,965][00556] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-09-05 09:24:46,966][00556] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-09-05 09:24:46,967][00556] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-09-05 09:24:46,968][00556] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-09-05 09:24:46,969][00556] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-09-05 09:24:47,009][00556] RunningMeanStd input shape: (3, 72, 128)
+[2024-09-05 09:24:47,012][00556] RunningMeanStd input shape: (1,)
+[2024-09-05 09:24:47,032][00556] ConvEncoder: input_channels=3
+[2024-09-05 09:24:47,101][00556] Conv encoder output size: 512
+[2024-09-05 09:24:47,103][00556] Policy head output size: 512
+[2024-09-05 09:24:47,130][00556] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000981_4018176.pth...
+[2024-09-05 09:24:47,796][00556] Num frames 100...
+[2024-09-05 09:24:47,962][00556] Num frames 200...
+[2024-09-05 09:24:48,132][00556] Num frames 300...
+[2024-09-05 09:24:48,299][00556] Num frames 400...
+[2024-09-05 09:24:48,468][00556] Num frames 500...
+[2024-09-05 09:24:48,630][00556] Num frames 600...
+[2024-09-05 09:24:48,798][00556] Num frames 700...
+[2024-09-05 09:24:48,956][00556] Num frames 800...
+[2024-09-05 09:24:49,119][00556] Num frames 900...
+[2024-09-05 09:24:49,294][00556] Num frames 1000...
+[2024-09-05 09:24:49,465][00556] Num frames 1100...
+[2024-09-05 09:24:49,630][00556] Num frames 1200...
+[2024-09-05 09:24:49,798][00556] Num frames 1300...
+[2024-09-05 09:24:49,970][00556] Num frames 1400...
+[2024-09-05 09:24:50,147][00556] Num frames 1500...
+[2024-09-05 09:24:50,321][00556] Num frames 1600...
+[2024-09-05 09:24:50,516][00556] Num frames 1700...
+[2024-09-05 09:24:50,697][00556] Num frames 1800...
+[2024-09-05 09:24:50,811][00556] Avg episode rewards: #0: 42.329, true rewards: #0: 18.330
+[2024-09-05 09:24:50,814][00556] Avg episode reward: 42.329, avg true_objective: 18.330
+[2024-09-05 09:24:50,935][00556] Num frames 1900...
+[2024-09-05 09:24:51,117][00556] Num frames 2000...
+[2024-09-05 09:24:51,343][00556] Num frames 2100...
+[2024-09-05 09:24:51,564][00556] Num frames 2200...
+[2024-09-05 09:24:51,746][00556] Num frames 2300...
+[2024-09-05 09:24:51,930][00556] Num frames 2400...
+[2024-09-05 09:24:52,128][00556] Num frames 2500...
+[2024-09-05 09:24:52,359][00556] Num frames 2600...
+[2024-09-05 09:24:52,562][00556] Num frames 2700...
+[2024-09-05 09:24:52,746][00556] Num frames 2800...
+[2024-09-05 09:24:52,931][00556] Num frames 2900...
+[2024-09-05 09:24:53,107][00556] Num frames 3000...
+[2024-09-05 09:24:53,275][00556] Num frames 3100...
+[2024-09-05 09:24:53,457][00556] Num frames 3200...
+[2024-09-05 09:24:53,630][00556] Num frames 3300...
+[2024-09-05 09:24:53,798][00556] Num frames 3400...
+[2024-09-05 09:24:53,953][00556] Avg episode rewards: #0: 40.874, true rewards: #0: 17.375
+[2024-09-05 09:24:53,955][00556] Avg episode reward: 40.874, avg true_objective: 17.375
+[2024-09-05 09:24:53,989][00556] Num frames 3500...
+[2024-09-05 09:24:54,109][00556] Num frames 3600...
+[2024-09-05 09:24:54,234][00556] Num frames 3700...
+[2024-09-05 09:24:54,358][00556] Num frames 3800...
+[2024-09-05 09:24:54,491][00556] Num frames 3900...
+[2024-09-05 09:24:54,616][00556] Num frames 4000...
+[2024-09-05 09:24:54,748][00556] Num frames 4100...
+[2024-09-05 09:24:54,861][00556] Avg episode rewards: #0: 31.823, true rewards: #0: 13.823
+[2024-09-05 09:24:54,862][00556] Avg episode reward: 31.823, avg true_objective: 13.823
+[2024-09-05 09:24:54,964][00556] Num frames 4200...
+[2024-09-05 09:24:55,144][00556] Num frames 4300...
+[2024-09-05 09:24:55,309][00556] Num frames 4400...
+[2024-09-05 09:24:55,484][00556] Num frames 4500...
+[2024-09-05 09:24:55,671][00556] Num frames 4600...
+[2024-09-05 09:24:55,846][00556] Num frames 4700...
+[2024-09-05 09:24:56,011][00556] Num frames 4800...
+[2024-09-05 09:24:56,182][00556] Num frames 4900...
+[2024-09-05 09:24:56,267][00556] Avg episode rewards: #0: 27.287, true rewards: #0: 12.287
+[2024-09-05 09:24:56,269][00556] Avg episode reward: 27.287, avg true_objective: 12.287
+[2024-09-05 09:24:56,427][00556] Num frames 5000...
+[2024-09-05 09:24:56,605][00556] Num frames 5100...
+[2024-09-05 09:24:56,802][00556] Num frames 5200...
+[2024-09-05 09:24:56,984][00556] Num frames 5300...
+[2024-09-05 09:24:57,165][00556] Num frames 5400...
+[2024-09-05 09:24:57,342][00556] Num frames 5500...
+[2024-09-05 09:24:57,519][00556] Num frames 5600...
+[2024-09-05 09:24:57,599][00556] Avg episode rewards: #0: 24.438, true rewards: #0: 11.238
+[2024-09-05 09:24:57,601][00556] Avg episode reward: 24.438, avg true_objective: 11.238
+[2024-09-05 09:24:57,712][00556] Num frames 5700...
+[2024-09-05 09:24:57,836][00556] Num frames 5800...
+[2024-09-05 09:24:57,962][00556] Num frames 5900...
+[2024-09-05 09:24:58,088][00556] Num frames 6000...
+[2024-09-05 09:24:58,213][00556] Num frames 6100...
+[2024-09-05 09:24:58,358][00556] Avg episode rewards: #0: 22.288, true rewards: #0: 10.288
+[2024-09-05 09:24:58,360][00556] Avg episode reward: 22.288, avg true_objective: 10.288
+[2024-09-05 09:24:58,397][00556] Num frames 6200...
+[2024-09-05 09:24:58,525][00556] Num frames 6300...
+[2024-09-05 09:24:58,664][00556] Num frames 6400...
+[2024-09-05 09:24:58,791][00556] Num frames 6500...
+[2024-09-05 09:24:58,892][00556] Avg episode rewards: #0: 19.908, true rewards: #0: 9.337
+[2024-09-05 09:24:58,893][00556] Avg episode reward: 19.908, avg true_objective: 9.337
+[2024-09-05 09:24:58,975][00556] Num frames 6600...
+[2024-09-05 09:24:59,097][00556] Num frames 6700...
+[2024-09-05 09:24:59,219][00556] Num frames 6800...
+[2024-09-05 09:24:59,344][00556] Num frames 6900...
+[2024-09-05 09:24:59,471][00556] Num frames 7000...
+[2024-09-05 09:24:59,599][00556] Num frames 7100...
+[2024-09-05 09:24:59,675][00556] Avg episode rewards: #0: 18.640, true rewards: #0: 8.890
+[2024-09-05 09:24:59,677][00556] Avg episode reward: 18.640, avg true_objective: 8.890
+[2024-09-05 09:24:59,792][00556] Num frames 7200...
+[2024-09-05 09:24:59,914][00556] Num frames 7300...
+[2024-09-05 09:25:00,042][00556] Num frames 7400...
+[2024-09-05 09:25:00,176][00556] Num frames 7500...
+[2024-09-05 09:25:00,300][00556] Num frames 7600...
+[2024-09-05 09:25:00,424][00556] Num frames 7700...
+[2024-09-05 09:25:00,549][00556] Num frames 7800...
+[2024-09-05 09:25:00,686][00556] Num frames 7900...
+[2024-09-05 09:25:00,810][00556] Num frames 8000...
+[2024-09-05 09:25:00,890][00556] Avg episode rewards: #0: 18.467, true rewards: #0: 8.911
+[2024-09-05 09:25:00,891][00556] Avg episode reward: 18.467, avg true_objective: 8.911
+[2024-09-05 09:25:00,994][00556] Num frames 8100...
+[2024-09-05 09:25:01,118][00556] Num frames 8200...
+[2024-09-05 09:25:01,266][00556] Num frames 8300...
+[2024-09-05 09:25:01,391][00556] Num frames 8400...
+[2024-09-05 09:25:01,516][00556] Num frames 8500...
+[2024-09-05 09:25:01,641][00556] Num frames 8600...
+[2024-09-05 09:25:01,782][00556] Num frames 8700...
+[2024-09-05 09:25:01,919][00556] Num frames 8800...
+[2024-09-05 09:25:02,001][00556] Avg episode rewards: #0: 18.120, true rewards: #0: 8.820
+[2024-09-05 09:25:02,002][00556] Avg episode reward: 18.120, avg true_objective: 8.820
+[2024-09-05 09:25:58,542][00556] Replay video saved to /content/train_dir/default_experiment/replay.mp4!