Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1722101970.452e51389018

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef560d848d7f8a247dd895ee97c221c347b03473b060631feb3e946a961cbbe9
+size 112704

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 7.55 +/- 2.83
+      value: 11.54 +/- 5.62
       name: mean_reward
       verified: false
 ---

checkpoint_p0/best_000001055_4321280_reward_20.107.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac697f2b86e134b5fef67d10851888b81bc77f7705ee6a87f360a9258be05b28
+size 34929243

checkpoint_p0/checkpoint_000001050_4300800.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7f7cfe11c1d9401472bf49e8e725b28e03ab9d952b43615e7ea4e4e15d748ed
+size 34929669

checkpoint_p0/checkpoint_000001101_4509696.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9386383845359bcea6b2f1c4cd4e83dadd02ff34ecb39a2c6ac587fc1df467f2
+size 34929669

config.json

@@ -65,7 +65,7 @@
   "summaries_use_frameskip": true,
   "heartbeat_interval": 20,
   "heartbeat_reporting_interval": 600,
-  "train_for_env_steps": 4005000,
+  "train_for_env_steps": 4505000,
   "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:b9d49ee96c55273fb9e9dd3d536f78358012db7ae010f8fb20387fef2bd42957
-size 14078944
+oid sha256:cdbf3d4d8001af8ac65b08fafe13a97c1db1f4d63eb1d4ebaf4c10e9388271aa
+size 21793979

sf_log.txt

@@ -1963,3 +1963,792 @@ main_loop: 37.5755
 [2024-07-27 17:38:15,970][00473] Avg episode rewards: #0: 14.652, true rewards: #0: 7.552
 [2024-07-27 17:38:15,974][00473] Avg episode reward: 14.652, avg true_objective: 7.552
 [2024-07-27 17:39:03,628][00473] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2024-07-27 17:39:07,781][00473] The model has been pushed to https://huggingface.co/rishisim/rl_course_vizdoom_health_gathering_supreme
+[2024-07-27 17:39:30,317][00473] Environment doom_basic already registered, overwriting...
+[2024-07-27 17:39:30,320][00473] Environment doom_two_colors_easy already registered, overwriting...
+[2024-07-27 17:39:30,322][00473] Environment doom_two_colors_hard already registered, overwriting...
+[2024-07-27 17:39:30,325][00473] Environment doom_dm already registered, overwriting...
+[2024-07-27 17:39:30,329][00473] Environment doom_dwango5 already registered, overwriting...
+[2024-07-27 17:39:30,330][00473] Environment doom_my_way_home_flat_actions already registered, overwriting...
+[2024-07-27 17:39:30,331][00473] Environment doom_defend_the_center_flat_actions already registered, overwriting...
+[2024-07-27 17:39:30,332][00473] Environment doom_my_way_home already registered, overwriting...
+[2024-07-27 17:39:30,333][00473] Environment doom_deadly_corridor already registered, overwriting...
+[2024-07-27 17:39:30,334][00473] Environment doom_defend_the_center already registered, overwriting...
+[2024-07-27 17:39:30,342][00473] Environment doom_defend_the_line already registered, overwriting...
+[2024-07-27 17:39:30,344][00473] Environment doom_health_gathering already registered, overwriting...
+[2024-07-27 17:39:30,345][00473] Environment doom_health_gathering_supreme already registered, overwriting...
+[2024-07-27 17:39:30,347][00473] Environment doom_battle already registered, overwriting...
+[2024-07-27 17:39:30,349][00473] Environment doom_battle2 already registered, overwriting...
+[2024-07-27 17:39:30,351][00473] Environment doom_duel_bots already registered, overwriting...
+[2024-07-27 17:39:30,352][00473] Environment doom_deathmatch_bots already registered, overwriting...
+[2024-07-27 17:39:30,354][00473] Environment doom_duel already registered, overwriting...
+[2024-07-27 17:39:30,356][00473] Environment doom_deathmatch_full already registered, overwriting...
+[2024-07-27 17:39:30,357][00473] Environment doom_benchmark already registered, overwriting...
+[2024-07-27 17:39:30,359][00473] register_encoder_factory: <function make_vizdoom_encoder at 0x7f79f8ee35b0>
+[2024-07-27 17:39:30,381][00473] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-07-27 17:39:30,383][00473] Overriding arg 'train_for_env_steps' with value 4505000 passed from command line
+[2024-07-27 17:39:30,392][00473] Experiment dir /content/train_dir/default_experiment already exists!
+[2024-07-27 17:39:30,395][00473] Resuming existing experiment from /content/train_dir/default_experiment...
+[2024-07-27 17:39:30,397][00473] Weights and Biases integration disabled
+[2024-07-27 17:39:30,403][00473] Environment var CUDA_VISIBLE_DEVICES is 0
+
+[2024-07-27 17:39:32,519][00473] 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=4505000
+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
+[2024-07-27 17:39:32,521][00473] Saving configuration to /content/train_dir/default_experiment/config.json...
+[2024-07-27 17:39:32,525][00473] Rollout worker 0 uses device cpu
+[2024-07-27 17:39:32,526][00473] Rollout worker 1 uses device cpu
+[2024-07-27 17:39:32,528][00473] Rollout worker 2 uses device cpu
+[2024-07-27 17:39:32,530][00473] Rollout worker 3 uses device cpu
+[2024-07-27 17:39:32,531][00473] Rollout worker 4 uses device cpu
+[2024-07-27 17:39:32,532][00473] Rollout worker 5 uses device cpu
+[2024-07-27 17:39:32,534][00473] Rollout worker 6 uses device cpu
+[2024-07-27 17:39:32,535][00473] Rollout worker 7 uses device cpu
+[2024-07-27 17:39:32,635][00473] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-07-27 17:39:32,637][00473] InferenceWorker_p0-w0: min num requests: 2
+[2024-07-27 17:39:32,671][00473] Starting all processes...
+[2024-07-27 17:39:32,674][00473] Starting process learner_proc0
+[2024-07-27 17:39:32,721][00473] Starting all processes...
+[2024-07-27 17:39:32,729][00473] Starting process inference_proc0-0
+[2024-07-27 17:39:32,730][00473] Starting process rollout_proc0
+[2024-07-27 17:39:32,730][00473] Starting process rollout_proc1
+[2024-07-27 17:39:32,730][00473] Starting process rollout_proc2
+[2024-07-27 17:39:32,730][00473] Starting process rollout_proc3
+[2024-07-27 17:39:32,732][00473] Starting process rollout_proc4
+[2024-07-27 17:39:32,739][00473] Starting process rollout_proc5
+[2024-07-27 17:39:32,739][00473] Starting process rollout_proc6
+[2024-07-27 17:39:32,739][00473] Starting process rollout_proc7
+[2024-07-27 17:39:48,066][18884] Worker 6 uses CPU cores [0]
+[2024-07-27 17:39:48,151][18863] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-07-27 17:39:48,154][18863] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2024-07-27 17:39:48,204][18881] Worker 4 uses CPU cores [0]
+[2024-07-27 17:39:48,214][18863] Num visible devices: 1
+[2024-07-27 17:39:48,243][18863] Starting seed is not provided
+[2024-07-27 17:39:48,245][18863] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-07-27 17:39:48,245][18863] Initializing actor-critic model on device cuda:0
+[2024-07-27 17:39:48,246][18863] RunningMeanStd input shape: (3, 72, 128)
+[2024-07-27 17:39:48,248][18863] RunningMeanStd input shape: (1,)
+[2024-07-27 17:39:48,261][18883] Worker 7 uses CPU cores [1]
+[2024-07-27 17:39:48,285][18863] ConvEncoder: input_channels=3
+[2024-07-27 17:39:48,441][18876] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-07-27 17:39:48,445][18876] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2024-07-27 17:39:48,482][18879] Worker 2 uses CPU cores [0]
+[2024-07-27 17:39:48,495][18877] Worker 1 uses CPU cores [1]
+[2024-07-27 17:39:48,510][18876] Num visible devices: 1
+[2024-07-27 17:39:48,577][18882] Worker 5 uses CPU cores [1]
+[2024-07-27 17:39:48,630][18880] Worker 3 uses CPU cores [1]
+[2024-07-27 17:39:48,639][18878] Worker 0 uses CPU cores [0]
+[2024-07-27 17:39:48,678][18863] Conv encoder output size: 512
+[2024-07-27 17:39:48,679][18863] Policy head output size: 512
+[2024-07-27 17:39:48,694][18863] Created Actor Critic model with architecture:
+[2024-07-27 17:39:48,694][18863] 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)
+  )
+)
+[2024-07-27 17:39:48,850][18863] Using optimizer <class 'torch.optim.adam.Adam'>
+[2024-07-27 17:39:49,619][18863] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000980_4014080.pth...
+[2024-07-27 17:39:49,654][18863] Loading model from checkpoint
+[2024-07-27 17:39:49,656][18863] Loaded experiment state at self.train_step=980, self.env_steps=4014080
+[2024-07-27 17:39:49,657][18863] Initialized policy 0 weights for model version 980
+[2024-07-27 17:39:49,659][18863] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-07-27 17:39:49,666][18863] LearnerWorker_p0 finished initialization!
+[2024-07-27 17:39:49,767][18876] RunningMeanStd input shape: (3, 72, 128)
+[2024-07-27 17:39:49,768][18876] RunningMeanStd input shape: (1,)
+[2024-07-27 17:39:49,780][18876] ConvEncoder: input_channels=3
+[2024-07-27 17:39:49,886][18876] Conv encoder output size: 512
+[2024-07-27 17:39:49,887][18876] Policy head output size: 512
+[2024-07-27 17:39:49,942][00473] Inference worker 0-0 is ready!
+[2024-07-27 17:39:49,944][00473] All inference workers are ready! Signal rollout workers to start!
+[2024-07-27 17:39:50,170][18880] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-07-27 17:39:50,173][18877] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-07-27 17:39:50,174][18883] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-07-27 17:39:50,169][18882] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-07-27 17:39:50,181][18881] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-07-27 17:39:50,194][18879] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-07-27 17:39:50,195][18878] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-07-27 17:39:50,192][18884] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-07-27 17:39:50,403][00473] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 4014080. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-07-27 17:39:50,826][18878] Decorrelating experience for 0 frames...
+[2024-07-27 17:39:51,217][18878] Decorrelating experience for 32 frames...
+[2024-07-27 17:39:51,585][18883] Decorrelating experience for 0 frames...
+[2024-07-27 17:39:51,588][18877] Decorrelating experience for 0 frames...
+[2024-07-27 17:39:51,590][18880] Decorrelating experience for 0 frames...
+[2024-07-27 17:39:52,097][18878] Decorrelating experience for 64 frames...
+[2024-07-27 17:39:52,623][18881] Decorrelating experience for 0 frames...
+[2024-07-27 17:39:52,626][18884] Decorrelating experience for 0 frames...
+[2024-07-27 17:39:52,628][00473] Heartbeat connected on Batcher_0
+[2024-07-27 17:39:52,638][00473] Heartbeat connected on LearnerWorker_p0
+[2024-07-27 17:39:52,674][00473] Heartbeat connected on InferenceWorker_p0-w0
+[2024-07-27 17:39:53,133][18880] Decorrelating experience for 32 frames...
+[2024-07-27 17:39:53,135][18877] Decorrelating experience for 32 frames...
+[2024-07-27 17:39:53,137][18883] Decorrelating experience for 32 frames...
+[2024-07-27 17:39:53,198][18882] Decorrelating experience for 0 frames...
+[2024-07-27 17:39:54,076][18884] Decorrelating experience for 32 frames...
+[2024-07-27 17:39:54,079][18881] Decorrelating experience for 32 frames...
+[2024-07-27 17:39:54,081][18879] Decorrelating experience for 0 frames...
+[2024-07-27 17:39:54,288][18882] Decorrelating experience for 32 frames...
+[2024-07-27 17:39:54,934][18883] Decorrelating experience for 64 frames...
+[2024-07-27 17:39:54,971][18878] Decorrelating experience for 96 frames...
+[2024-07-27 17:39:55,345][00473] Heartbeat connected on RolloutWorker_w0
+[2024-07-27 17:39:55,406][00473] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4014080. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-07-27 17:39:56,651][18880] Decorrelating experience for 64 frames...
+[2024-07-27 17:39:56,744][18879] Decorrelating experience for 32 frames...
+[2024-07-27 17:39:57,140][18877] Decorrelating experience for 64 frames...
+[2024-07-27 17:39:57,686][18882] Decorrelating experience for 64 frames...
+[2024-07-27 17:39:57,938][18883] Decorrelating experience for 96 frames...
+[2024-07-27 17:39:58,470][00473] Heartbeat connected on RolloutWorker_w7
+[2024-07-27 17:39:59,430][18881] Decorrelating experience for 64 frames...
+[2024-07-27 17:39:59,624][18880] Decorrelating experience for 96 frames...
+[2024-07-27 17:39:59,864][18884] Decorrelating experience for 64 frames...
+[2024-07-27 17:40:00,058][00473] Heartbeat connected on RolloutWorker_w3
+[2024-07-27 17:40:00,403][00473] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4014080. Throughput: 0: 42.0. Samples: 420. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-07-27 17:40:00,407][00473] Avg episode reward: [(0, '2.560')]
+[2024-07-27 17:40:00,645][18877] Decorrelating experience for 96 frames...
+[2024-07-27 17:40:00,943][18882] Decorrelating experience for 96 frames...
+[2024-07-27 17:40:01,245][00473] Heartbeat connected on RolloutWorker_w1
+[2024-07-27 17:40:01,957][00473] Heartbeat connected on RolloutWorker_w5
+[2024-07-27 17:40:02,674][18879] Decorrelating experience for 64 frames...
+[2024-07-27 17:40:03,967][18884] Decorrelating experience for 96 frames...
+[2024-07-27 17:40:04,683][00473] Heartbeat connected on RolloutWorker_w6
+[2024-07-27 17:40:05,052][18863] Signal inference workers to stop experience collection...
+[2024-07-27 17:40:05,066][18876] InferenceWorker_p0-w0: stopping experience collection
+[2024-07-27 17:40:05,286][18881] Decorrelating experience for 96 frames...
+[2024-07-27 17:40:05,389][18879] Decorrelating experience for 96 frames...
+[2024-07-27 17:40:05,403][00473] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4014080. Throughput: 0: 160.1. Samples: 2402. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-07-27 17:40:05,407][00473] Avg episode reward: [(0, '5.740')]
+[2024-07-27 17:40:05,455][00473] Heartbeat connected on RolloutWorker_w4
+[2024-07-27 17:40:05,545][00473] Heartbeat connected on RolloutWorker_w2
+[2024-07-27 17:40:06,486][18863] Signal inference workers to resume experience collection...
+[2024-07-27 17:40:06,488][18876] InferenceWorker_p0-w0: resuming experience collection
+[2024-07-27 17:40:10,403][00473] Fps is (10 sec: 2048.1, 60 sec: 1024.0, 300 sec: 1024.0). Total num frames: 4034560. Throughput: 0: 171.6. Samples: 3432. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-07-27 17:40:10,408][00473] Avg episode reward: [(0, '8.034')]
+[2024-07-27 17:40:15,403][00473] Fps is (10 sec: 3686.4, 60 sec: 1474.6, 300 sec: 1474.6). Total num frames: 4050944. Throughput: 0: 367.2. Samples: 9180. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-07-27 17:40:15,406][00473] Avg episode reward: [(0, '10.297')]
+[2024-07-27 17:40:16,092][18876] Updated weights for policy 0, policy_version 990 (0.0219)
+[2024-07-27 17:40:20,403][00473] Fps is (10 sec: 2867.2, 60 sec: 1638.4, 300 sec: 1638.4). Total num frames: 4063232. Throughput: 0: 433.3. Samples: 13000. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0)
+[2024-07-27 17:40:20,410][00473] Avg episode reward: [(0, '12.401')]
+[2024-07-27 17:40:25,403][00473] Fps is (10 sec: 3276.8, 60 sec: 1989.5, 300 sec: 1989.5). Total num frames: 4083712. Throughput: 0: 452.9. Samples: 15850. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2024-07-27 17:40:25,406][00473] Avg episode reward: [(0, '14.255')]
+[2024-07-27 17:40:28,173][18876] Updated weights for policy 0, policy_version 1000 (0.0015)
+[2024-07-27 17:40:30,403][00473] Fps is (10 sec: 4096.0, 60 sec: 2252.8, 300 sec: 2252.8). Total num frames: 4104192. Throughput: 0: 544.3. Samples: 21770. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-07-27 17:40:30,407][00473] Avg episode reward: [(0, '15.281')]
+[2024-07-27 17:40:35,408][00473] Fps is (10 sec: 3275.3, 60 sec: 2275.3, 300 sec: 2275.3). Total num frames: 4116480. Throughput: 0: 583.3. Samples: 26252. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2024-07-27 17:40:35,410][00473] Avg episode reward: [(0, '16.210')]
+[2024-07-27 17:40:40,403][00473] Fps is (10 sec: 2867.1, 60 sec: 2375.7, 300 sec: 2375.7). Total num frames: 4132864. Throughput: 0: 627.2. Samples: 28222. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2024-07-27 17:40:40,409][00473] Avg episode reward: [(0, '17.626')]
+[2024-07-27 17:40:40,827][18876] Updated weights for policy 0, policy_version 1010 (0.0024)
+[2024-07-27 17:40:45,403][00473] Fps is (10 sec: 3688.1, 60 sec: 2532.1, 300 sec: 2532.1). Total num frames: 4153344. Throughput: 0: 751.2. Samples: 34222. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2024-07-27 17:40:45,408][00473] Avg episode reward: [(0, '18.829')]
+[2024-07-27 17:40:45,412][18863] Saving new best policy, reward=18.829!
+[2024-07-27 17:40:50,404][00473] Fps is (10 sec: 3686.3, 60 sec: 2594.1, 300 sec: 2594.1). Total num frames: 4169728. Throughput: 0: 824.3. Samples: 39496. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0)
+[2024-07-27 17:40:50,408][00473] Avg episode reward: [(0, '18.931')]
+[2024-07-27 17:40:50,426][18863] Saving new best policy, reward=18.931!
+[2024-07-27 17:40:53,148][18876] Updated weights for policy 0, policy_version 1020 (0.0033)
+[2024-07-27 17:40:55,403][00473] Fps is (10 sec: 2867.2, 60 sec: 2799.1, 300 sec: 2583.6). Total num frames: 4182016. Throughput: 0: 840.8. Samples: 41266. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-07-27 17:40:55,405][00473] Avg episode reward: [(0, '18.576')]
+[2024-07-27 17:41:00,403][00473] Fps is (10 sec: 3277.0, 60 sec: 3140.3, 300 sec: 2691.7). Total num frames: 4202496. Throughput: 0: 822.0. Samples: 46170. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-07-27 17:41:00,405][00473] Avg episode reward: [(0, '17.721')]
+[2024-07-27 17:41:04,256][18876] Updated weights for policy 0, policy_version 1030 (0.0017)
+[2024-07-27 17:41:05,403][00473] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 2785.3). Total num frames: 4222976. Throughput: 0: 876.9. Samples: 52462. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-07-27 17:41:05,406][00473] Avg episode reward: [(0, '17.163')]
+[2024-07-27 17:41:10,409][00473] Fps is (10 sec: 3274.9, 60 sec: 3344.8, 300 sec: 2764.6). Total num frames: 4235264. Throughput: 0: 861.1. Samples: 54606. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-07-27 17:41:10,416][00473] Avg episode reward: [(0, '17.196')]
+[2024-07-27 17:41:15,403][00473] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 2794.9). Total num frames: 4251648. Throughput: 0: 821.3. Samples: 58728. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-07-27 17:41:15,405][00473] Avg episode reward: [(0, '17.044')]
+[2024-07-27 17:41:17,167][18876] Updated weights for policy 0, policy_version 1040 (0.0015)
+[2024-07-27 17:41:20,403][00473] Fps is (10 sec: 3688.4, 60 sec: 3481.6, 300 sec: 2867.2). Total num frames: 4272128. Throughput: 0: 857.2. Samples: 64820. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-07-27 17:41:20,405][00473] Avg episode reward: [(0, '17.607')]
+[2024-07-27 17:41:25,403][00473] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 2888.8). Total num frames: 4288512. Throughput: 0: 883.3. Samples: 67970. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-07-27 17:41:25,407][00473] Avg episode reward: [(0, '18.281')]
+[2024-07-27 17:41:29,513][18876] Updated weights for policy 0, policy_version 1050 (0.0016)
+[2024-07-27 17:41:30,403][00473] Fps is (10 sec: 2867.3, 60 sec: 3276.8, 300 sec: 2867.2). Total num frames: 4300800. Throughput: 0: 834.9. Samples: 71794. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-07-27 17:41:30,410][00473] Avg episode reward: [(0, '18.080')]
+[2024-07-27 17:41:30,425][18863] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001050_4300800.pth...
+[2024-07-27 17:41:30,599][18863] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth
+[2024-07-27 17:41:35,403][00473] Fps is (10 sec: 3276.8, 60 sec: 3413.6, 300 sec: 2925.7). Total num frames: 4321280. Throughput: 0: 840.5. Samples: 77316. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-07-27 17:41:35,411][00473] Avg episode reward: [(0, '20.107')]
+[2024-07-27 17:41:35,413][18863] Saving new best policy, reward=20.107!
+[2024-07-27 17:41:40,160][18876] Updated weights for policy 0, policy_version 1060 (0.0026)
+[2024-07-27 17:41:40,403][00473] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 2978.9). Total num frames: 4341760. Throughput: 0: 867.3. Samples: 80296. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-07-27 17:41:40,409][00473] Avg episode reward: [(0, '19.189')]
+[2024-07-27 17:41:45,404][00473] Fps is (10 sec: 3276.6, 60 sec: 3345.0, 300 sec: 2956.2). Total num frames: 4354048. Throughput: 0: 865.1. Samples: 85102. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-07-27 17:41:45,406][00473] Avg episode reward: [(0, '18.620')]
+[2024-07-27 17:41:50,403][00473] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 2969.6). Total num frames: 4370432. Throughput: 0: 822.8. Samples: 89488. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-07-27 17:41:50,411][00473] Avg episode reward: [(0, '18.749')]
+[2024-07-27 17:41:53,106][18876] Updated weights for policy 0, policy_version 1070 (0.0021)
+[2024-07-27 17:41:55,403][00473] Fps is (10 sec: 3686.5, 60 sec: 3481.6, 300 sec: 3014.6). Total num frames: 4390912. Throughput: 0: 844.9. Samples: 92620. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-07-27 17:41:55,413][00473] Avg episode reward: [(0, '17.540')]
+[2024-07-27 17:42:00,404][00473] Fps is (10 sec: 3686.0, 60 sec: 3413.3, 300 sec: 3024.7). Total num frames: 4407296. Throughput: 0: 887.8. Samples: 98678. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-07-27 17:42:00,408][00473] Avg episode reward: [(0, '16.795')]
+[2024-07-27 17:42:05,403][00473] Fps is (10 sec: 2867.3, 60 sec: 3276.8, 300 sec: 3003.7). Total num frames: 4419584. Throughput: 0: 836.8. Samples: 102474. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-07-27 17:42:05,405][00473] Avg episode reward: [(0, '17.038')]
+[2024-07-27 17:42:05,599][18876] Updated weights for policy 0, policy_version 1080 (0.0013)
+[2024-07-27 17:42:10,403][00473] Fps is (10 sec: 3277.1, 60 sec: 3413.6, 300 sec: 3042.7). Total num frames: 4440064. Throughput: 0: 826.2. Samples: 105150. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-07-27 17:42:10,406][00473] Avg episode reward: [(0, '19.360')]
+[2024-07-27 17:42:15,403][00473] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3079.1). Total num frames: 4460544. Throughput: 0: 868.5. Samples: 110876. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-07-27 17:42:15,410][00473] Avg episode reward: [(0, '19.294')]
+[2024-07-27 17:42:16,213][18876] Updated weights for policy 0, policy_version 1090 (0.0024)
+[2024-07-27 17:42:20,403][00473] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3058.3). Total num frames: 4472832. Throughput: 0: 848.5. Samples: 115500. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-07-27 17:42:20,411][00473] Avg episode reward: [(0, '18.425')]
+[2024-07-27 17:42:25,404][00473] Fps is (10 sec: 2457.3, 60 sec: 3276.7, 300 sec: 3038.9). Total num frames: 4485120. Throughput: 0: 823.6. Samples: 117358. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-07-27 17:42:25,406][00473] Avg episode reward: [(0, '18.760')]
+[2024-07-27 17:42:29,257][18876] Updated weights for policy 0, policy_version 1100 (0.0030)
+[2024-07-27 17:42:30,403][00473] Fps is (10 sec: 3276.6, 60 sec: 3413.3, 300 sec: 3072.0). Total num frames: 4505600. Throughput: 0: 845.9. Samples: 123168. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-07-27 17:42:30,407][00473] Avg episode reward: [(0, '18.340')]
+[2024-07-27 17:42:30,534][18863] Stopping Batcher_0...
+[2024-07-27 17:42:30,535][18863] Loop batcher_evt_loop terminating...
+[2024-07-27 17:42:30,534][00473] Component Batcher_0 stopped!
+[2024-07-27 17:42:30,539][18863] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001101_4509696.pth...
+[2024-07-27 17:42:30,601][00473] Component RolloutWorker_w3 stopped!
+[2024-07-27 17:42:30,603][18880] Stopping RolloutWorker_w3...
+[2024-07-27 17:42:30,612][18881] Stopping RolloutWorker_w4...
+[2024-07-27 17:42:30,612][00473] Component RolloutWorker_w4 stopped!
+[2024-07-27 17:42:30,609][18880] Loop rollout_proc3_evt_loop terminating...
+[2024-07-27 17:42:30,620][18881] Loop rollout_proc4_evt_loop terminating...
+[2024-07-27 17:42:30,624][00473] Component RolloutWorker_w1 stopped!
+[2024-07-27 17:42:30,627][18877] Stopping RolloutWorker_w1...
+[2024-07-27 17:42:30,656][18877] Loop rollout_proc1_evt_loop terminating...
+[2024-07-27 17:42:30,659][18884] Stopping RolloutWorker_w6...
+[2024-07-27 17:42:30,660][18884] Loop rollout_proc6_evt_loop terminating...
+[2024-07-27 17:42:30,662][00473] Component RolloutWorker_w6 stopped!
+[2024-07-27 17:42:30,641][18876] Weights refcount: 2 0
+[2024-07-27 17:42:30,681][00473] Component InferenceWorker_p0-w0 stopped!
+[2024-07-27 17:42:30,686][18876] Stopping InferenceWorker_p0-w0...
+[2024-07-27 17:42:30,689][18876] Loop inference_proc0-0_evt_loop terminating...
+[2024-07-27 17:42:30,692][00473] Component RolloutWorker_w7 stopped!
+[2024-07-27 17:42:30,695][18883] Stopping RolloutWorker_w7...
+[2024-07-27 17:42:30,696][18883] Loop rollout_proc7_evt_loop terminating...
+[2024-07-27 17:42:30,706][00473] Component RolloutWorker_w5 stopped!
+[2024-07-27 17:42:30,711][18882] Stopping RolloutWorker_w5...
+[2024-07-27 17:42:30,718][18878] Stopping RolloutWorker_w0...
+[2024-07-27 17:42:30,719][18878] Loop rollout_proc0_evt_loop terminating...
+[2024-07-27 17:42:30,722][18879] Stopping RolloutWorker_w2...
+[2024-07-27 17:42:30,718][00473] Component RolloutWorker_w0 stopped!
+[2024-07-27 17:42:30,725][18879] Loop rollout_proc2_evt_loop terminating...
+[2024-07-27 17:42:30,725][00473] Component RolloutWorker_w2 stopped!
+[2024-07-27 17:42:30,712][18882] Loop rollout_proc5_evt_loop terminating...
+[2024-07-27 17:42:30,754][18863] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000980_4014080.pth
+[2024-07-27 17:42:30,768][18863] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001101_4509696.pth...
+[2024-07-27 17:42:31,000][00473] Component LearnerWorker_p0 stopped!
+[2024-07-27 17:42:31,001][00473] Waiting for process learner_proc0 to stop...
+[2024-07-27 17:42:30,999][18863] Stopping LearnerWorker_p0...
+[2024-07-27 17:42:31,018][18863] Loop learner_proc0_evt_loop terminating...
+[2024-07-27 17:42:32,425][00473] Waiting for process inference_proc0-0 to join...
+[2024-07-27 17:42:32,428][00473] Waiting for process rollout_proc0 to join...
+[2024-07-27 17:42:34,518][00473] Waiting for process rollout_proc1 to join...
+[2024-07-27 17:42:34,558][00473] Waiting for process rollout_proc2 to join...
+[2024-07-27 17:42:34,561][00473] Waiting for process rollout_proc3 to join...
+[2024-07-27 17:42:34,564][00473] Waiting for process rollout_proc4 to join...
+[2024-07-27 17:42:34,572][00473] Waiting for process rollout_proc5 to join...
+[2024-07-27 17:42:34,575][00473] Waiting for process rollout_proc6 to join...
+[2024-07-27 17:42:34,583][00473] Waiting for process rollout_proc7 to join...
+[2024-07-27 17:42:34,589][00473] Batcher 0 profile tree view:
+batching: 3.2638, releasing_batches: 0.0064
+[2024-07-27 17:42:34,593][00473] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0001
+  wait_policy_total: 67.6765
+update_model: 1.3268
+  weight_update: 0.0039
+one_step: 0.0049
+  handle_policy_step: 84.2539
+    deserialize: 2.1267, stack: 0.4427, obs_to_device_normalize: 17.0462, forward: 45.6140, send_messages: 3.9128
+    prepare_outputs: 11.0594
+      to_cpu: 6.4650
+[2024-07-27 17:42:34,595][00473] Learner 0 profile tree view:
+misc: 0.0007, prepare_batch: 4.2685
+train: 12.2778
+  epoch_init: 0.0007, minibatch_init: 0.0009, losses_postprocess: 0.0813, kl_divergence: 0.1217, after_optimizer: 0.5455
+  calculate_losses: 5.0106
+    losses_init: 0.0005, forward_head: 0.5302, bptt_initial: 3.3199, tail: 0.3049, advantages_returns: 0.0295, losses: 0.5035
+    bptt: 0.2665
+      bptt_forward_core: 0.2500
+  update: 6.4516
+    clip: 0.1431
+[2024-07-27 17:42:34,597][00473] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.0341, enqueue_policy_requests: 17.7626, env_step: 117.1943, overhead: 2.2659, complete_rollouts: 1.0716
+save_policy_outputs: 2.8331
+  split_output_tensors: 1.1090
+[2024-07-27 17:42:34,599][00473] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.0488, enqueue_policy_requests: 17.4188, env_step: 116.0178, overhead: 2.1658, complete_rollouts: 0.9147
+save_policy_outputs: 3.1246
+  split_output_tensors: 1.1803
+[2024-07-27 17:42:34,601][00473] Loop Runner_EvtLoop terminating...
+[2024-07-27 17:42:34,603][00473] Runner profile tree view:
+main_loop: 181.9323
+[2024-07-27 17:42:34,609][00473] Collected {0: 4509696}, FPS: 2724.2
+[2024-07-27 17:42:34,644][00473] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-07-27 17:42:34,647][00473] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-07-27 17:42:34,649][00473] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-07-27 17:42:34,650][00473] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-07-27 17:42:34,651][00473] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-07-27 17:42:34,652][00473] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-07-27 17:42:34,653][00473] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2024-07-27 17:42:34,654][00473] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-07-27 17:42:34,655][00473] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2024-07-27 17:42:34,656][00473] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2024-07-27 17:42:34,658][00473] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-07-27 17:42:34,659][00473] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-07-27 17:42:34,660][00473] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-07-27 17:42:34,661][00473] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-07-27 17:42:34,662][00473] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-07-27 17:42:34,712][00473] RunningMeanStd input shape: (3, 72, 128)
+[2024-07-27 17:42:34,715][00473] RunningMeanStd input shape: (1,)
+[2024-07-27 17:42:34,738][00473] ConvEncoder: input_channels=3
+[2024-07-27 17:42:34,806][00473] Conv encoder output size: 512
+[2024-07-27 17:42:34,808][00473] Policy head output size: 512
+[2024-07-27 17:42:34,838][00473] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001101_4509696.pth...
+[2024-07-27 17:42:35,509][00473] Num frames 100...
+[2024-07-27 17:42:35,712][00473] Num frames 200...
+[2024-07-27 17:42:35,902][00473] Num frames 300...
+[2024-07-27 17:42:36,103][00473] Num frames 400...
+[2024-07-27 17:42:36,292][00473] Num frames 500...
+[2024-07-27 17:42:36,481][00473] Num frames 600...
+[2024-07-27 17:42:36,678][00473] Num frames 700...
+[2024-07-27 17:42:36,821][00473] Num frames 800...
+[2024-07-27 17:42:36,957][00473] Num frames 900...
+[2024-07-27 17:42:37,095][00473] Num frames 1000...
+[2024-07-27 17:42:37,222][00473] Num frames 1100...
+[2024-07-27 17:42:37,349][00473] Num frames 1200...
+[2024-07-27 17:42:37,474][00473] Num frames 1300...
+[2024-07-27 17:42:37,606][00473] Num frames 1400...
+[2024-07-27 17:42:37,740][00473] Num frames 1500...
+[2024-07-27 17:42:37,870][00473] Num frames 1600...
+[2024-07-27 17:42:37,999][00473] Num frames 1700...
+[2024-07-27 17:42:38,141][00473] Num frames 1800...
+[2024-07-27 17:42:38,274][00473] Avg episode rewards: #0: 51.599, true rewards: #0: 18.600
+[2024-07-27 17:42:38,276][00473] Avg episode reward: 51.599, avg true_objective: 18.600
+[2024-07-27 17:42:38,330][00473] Num frames 1900...
+[2024-07-27 17:42:38,463][00473] Num frames 2000...
+[2024-07-27 17:42:38,590][00473] Num frames 2100...
+[2024-07-27 17:42:38,732][00473] Num frames 2200...
+[2024-07-27 17:42:38,863][00473] Num frames 2300...
+[2024-07-27 17:42:38,992][00473] Num frames 2400...
+[2024-07-27 17:42:39,133][00473] Num frames 2500...
+[2024-07-27 17:42:39,260][00473] Num frames 2600...
+[2024-07-27 17:42:39,387][00473] Num frames 2700...
+[2024-07-27 17:42:39,520][00473] Num frames 2800...
+[2024-07-27 17:42:39,657][00473] Num frames 2900...
+[2024-07-27 17:42:39,798][00473] Num frames 3000...
+[2024-07-27 17:42:39,933][00473] Num frames 3100...
+[2024-07-27 17:42:40,001][00473] Avg episode rewards: #0: 38.540, true rewards: #0: 15.540
+[2024-07-27 17:42:40,002][00473] Avg episode reward: 38.540, avg true_objective: 15.540
+[2024-07-27 17:42:40,136][00473] Num frames 3200...
+[2024-07-27 17:42:40,269][00473] Num frames 3300...
+[2024-07-27 17:42:40,402][00473] Num frames 3400...
+[2024-07-27 17:42:40,538][00473] Num frames 3500...
+[2024-07-27 17:42:40,669][00473] Num frames 3600...
+[2024-07-27 17:42:40,811][00473] Num frames 3700...
+[2024-07-27 17:42:40,938][00473] Num frames 3800...
+[2024-07-27 17:42:41,071][00473] Num frames 3900...
+[2024-07-27 17:42:41,215][00473] Num frames 4000...
+[2024-07-27 17:42:41,344][00473] Num frames 4100...
+[2024-07-27 17:42:41,475][00473] Num frames 4200...
+[2024-07-27 17:42:41,651][00473] Avg episode rewards: #0: 33.306, true rewards: #0: 14.307
+[2024-07-27 17:42:41,652][00473] Avg episode reward: 33.306, avg true_objective: 14.307
+[2024-07-27 17:42:41,666][00473] Num frames 4300...
+[2024-07-27 17:42:41,799][00473] Num frames 4400...
+[2024-07-27 17:42:41,931][00473] Num frames 4500...
+[2024-07-27 17:42:42,059][00473] Num frames 4600...
+[2024-07-27 17:42:42,196][00473] Num frames 4700...
+[2024-07-27 17:42:42,322][00473] Num frames 4800...
+[2024-07-27 17:42:42,448][00473] Num frames 4900...
+[2024-07-27 17:42:42,578][00473] Num frames 5000...
+[2024-07-27 17:42:42,712][00473] Num frames 5100...
+[2024-07-27 17:42:42,885][00473] Avg episode rewards: #0: 30.717, true rewards: #0: 12.967
+[2024-07-27 17:42:42,887][00473] Avg episode reward: 30.717, avg true_objective: 12.967
+[2024-07-27 17:42:42,906][00473] Num frames 5200...
+[2024-07-27 17:42:43,035][00473] Num frames 5300...
+[2024-07-27 17:42:43,172][00473] Num frames 5400...
+[2024-07-27 17:42:43,299][00473] Num frames 5500...
+[2024-07-27 17:42:43,426][00473] Num frames 5600...
+[2024-07-27 17:42:43,525][00473] Avg episode rewards: #0: 25.670, true rewards: #0: 11.270
+[2024-07-27 17:42:43,528][00473] Avg episode reward: 25.670, avg true_objective: 11.270
+[2024-07-27 17:42:43,613][00473] Num frames 5700...
+[2024-07-27 17:42:43,749][00473] Num frames 5800...
+[2024-07-27 17:42:43,879][00473] Num frames 5900...
+[2024-07-27 17:42:44,007][00473] Num frames 6000...
+[2024-07-27 17:42:44,134][00473] Num frames 6100...
+[2024-07-27 17:42:44,277][00473] Num frames 6200...
+[2024-07-27 17:42:44,406][00473] Num frames 6300...
+[2024-07-27 17:42:44,536][00473] Num frames 6400...
+[2024-07-27 17:42:44,678][00473] Num frames 6500...
+[2024-07-27 17:42:44,772][00473] Avg episode rewards: #0: 24.043, true rewards: #0: 10.877
+[2024-07-27 17:42:44,774][00473] Avg episode reward: 24.043, avg true_objective: 10.877
+[2024-07-27 17:42:44,868][00473] Num frames 6600...
+[2024-07-27 17:42:44,998][00473] Num frames 6700...
+[2024-07-27 17:42:45,132][00473] Num frames 6800...
+[2024-07-27 17:42:45,271][00473] Num frames 6900...
+[2024-07-27 17:42:45,403][00473] Num frames 7000...
+[2024-07-27 17:42:45,534][00473] Num frames 7100...
+[2024-07-27 17:42:45,664][00473] Num frames 7200...
+[2024-07-27 17:42:45,802][00473] Num frames 7300...
+[2024-07-27 17:42:45,929][00473] Num frames 7400...
+[2024-07-27 17:42:46,060][00473] Num frames 7500...
+[2024-07-27 17:42:46,198][00473] Num frames 7600...
+[2024-07-27 17:42:46,339][00473] Num frames 7700...
+[2024-07-27 17:42:46,470][00473] Num frames 7800...
+[2024-07-27 17:42:46,606][00473] Num frames 7900...
+[2024-07-27 17:42:46,763][00473] Num frames 8000...
+[2024-07-27 17:42:46,956][00473] Num frames 8100...
+[2024-07-27 17:42:47,147][00473] Num frames 8200...
+[2024-07-27 17:42:47,338][00473] Num frames 8300...
+[2024-07-27 17:42:47,525][00473] Num frames 8400...
+[2024-07-27 17:42:47,706][00473] Num frames 8500...
+[2024-07-27 17:42:47,893][00473] Num frames 8600...
+[2024-07-27 17:42:48,004][00473] Avg episode rewards: #0: 28.180, true rewards: #0: 12.323
+[2024-07-27 17:42:48,007][00473] Avg episode reward: 28.180, avg true_objective: 12.323
+[2024-07-27 17:42:48,143][00473] Num frames 8700...
+[2024-07-27 17:42:48,340][00473] Num frames 8800...
+[2024-07-27 17:42:48,529][00473] Num frames 8900...
+[2024-07-27 17:42:48,729][00473] Num frames 9000...
+[2024-07-27 17:42:48,916][00473] Num frames 9100...
+[2024-07-27 17:42:49,108][00473] Num frames 9200...
+[2024-07-27 17:42:49,293][00473] Num frames 9300...
+[2024-07-27 17:42:49,429][00473] Num frames 9400...
+[2024-07-27 17:42:49,560][00473] Num frames 9500...
+[2024-07-27 17:42:49,645][00473] Avg episode rewards: #0: 27.027, true rewards: #0: 11.902
+[2024-07-27 17:42:49,647][00473] Avg episode reward: 27.027, avg true_objective: 11.902
+[2024-07-27 17:42:49,752][00473] Num frames 9600...
+[2024-07-27 17:42:49,883][00473] Num frames 9700...
+[2024-07-27 17:42:50,013][00473] Num frames 9800...
+[2024-07-27 17:42:50,141][00473] Num frames 9900...
+[2024-07-27 17:42:50,269][00473] Num frames 10000...
+[2024-07-27 17:42:50,404][00473] Num frames 10100...
+[2024-07-27 17:42:50,581][00473] Avg episode rewards: #0: 25.215, true rewards: #0: 11.327
+[2024-07-27 17:42:50,583][00473] Avg episode reward: 25.215, avg true_objective: 11.327
+[2024-07-27 17:42:50,594][00473] Num frames 10200...
+[2024-07-27 17:42:50,729][00473] Num frames 10300...
+[2024-07-27 17:42:50,863][00473] Num frames 10400...
+[2024-07-27 17:42:50,998][00473] Num frames 10500...
+[2024-07-27 17:42:51,128][00473] Num frames 10600...
+[2024-07-27 17:42:51,259][00473] Num frames 10700...
+[2024-07-27 17:42:51,399][00473] Num frames 10800...
+[2024-07-27 17:42:51,535][00473] Num frames 10900...
+[2024-07-27 17:42:51,672][00473] Num frames 11000...
+[2024-07-27 17:42:51,815][00473] Num frames 11100...
+[2024-07-27 17:42:51,949][00473] Num frames 11200...
+[2024-07-27 17:42:52,118][00473] Avg episode rewards: #0: 25.187, true rewards: #0: 11.287
+[2024-07-27 17:42:52,120][00473] Avg episode reward: 25.187, avg true_objective: 11.287
+[2024-07-27 17:44:02,468][00473] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2024-07-27 17:45:25,025][00473] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-07-27 17:45:25,027][00473] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-07-27 17:45:25,029][00473] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-07-27 17:45:25,031][00473] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-07-27 17:45:25,033][00473] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-07-27 17:45:25,034][00473] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-07-27 17:45:25,035][00473] Adding new argument 'max_num_frames'=1000000 that is not in the saved config file!
+[2024-07-27 17:45:25,037][00473] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-07-27 17:45:25,039][00473] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2024-07-27 17:45:25,041][00473] Adding new argument 'hf_repository'='rishisim/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2024-07-27 17:45:25,042][00473] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-07-27 17:45:25,044][00473] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-07-27 17:45:25,045][00473] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-07-27 17:45:25,046][00473] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-07-27 17:45:25,049][00473] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-07-27 17:45:25,077][00473] RunningMeanStd input shape: (3, 72, 128)
+[2024-07-27 17:45:25,079][00473] RunningMeanStd input shape: (1,)
+[2024-07-27 17:45:25,093][00473] ConvEncoder: input_channels=3
+[2024-07-27 17:45:25,131][00473] Conv encoder output size: 512
+[2024-07-27 17:45:25,132][00473] Policy head output size: 512
+[2024-07-27 17:45:25,151][00473] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001101_4509696.pth...
+[2024-07-27 17:45:25,589][00473] Num frames 100...
+[2024-07-27 17:45:25,727][00473] Num frames 200...
+[2024-07-27 17:45:25,876][00473] Num frames 300...
+[2024-07-27 17:45:26,006][00473] Num frames 400...
+[2024-07-27 17:45:26,135][00473] Num frames 500...
+[2024-07-27 17:45:26,272][00473] Num frames 600...
+[2024-07-27 17:45:26,429][00473] Avg episode rewards: #0: 13.730, true rewards: #0: 6.730
+[2024-07-27 17:45:26,431][00473] Avg episode reward: 13.730, avg true_objective: 6.730
+[2024-07-27 17:45:26,468][00473] Num frames 700...
+[2024-07-27 17:45:26,626][00473] Num frames 800...
+[2024-07-27 17:45:26,818][00473] Num frames 900...
+[2024-07-27 17:45:27,007][00473] Num frames 1000...
+[2024-07-27 17:45:27,193][00473] Num frames 1100...
+[2024-07-27 17:45:27,377][00473] Num frames 1200...
+[2024-07-27 17:45:27,567][00473] Num frames 1300...
+[2024-07-27 17:45:27,763][00473] Num frames 1400...
+[2024-07-27 17:45:27,976][00473] Num frames 1500...
+[2024-07-27 17:45:28,169][00473] Num frames 1600...
+[2024-07-27 17:45:28,231][00473] Avg episode rewards: #0: 15.505, true rewards: #0: 8.005
+[2024-07-27 17:45:28,234][00473] Avg episode reward: 15.505, avg true_objective: 8.005
+[2024-07-27 17:45:28,443][00473] Num frames 1700...
+[2024-07-27 17:45:28,632][00473] Num frames 1800...
+[2024-07-27 17:45:28,817][00473] Num frames 1900...
+[2024-07-27 17:45:29,018][00473] Num frames 2000...
+[2024-07-27 17:45:29,198][00473] Num frames 2100...
+[2024-07-27 17:45:29,330][00473] Num frames 2200...
+[2024-07-27 17:45:29,459][00473] Num frames 2300...
+[2024-07-27 17:45:29,603][00473] Num frames 2400...
+[2024-07-27 17:45:29,744][00473] Num frames 2500...
+[2024-07-27 17:45:29,876][00473] Num frames 2600...
+[2024-07-27 17:45:30,013][00473] Num frames 2700...
+[2024-07-27 17:45:30,073][00473] Avg episode rewards: #0: 18.003, true rewards: #0: 9.003
+[2024-07-27 17:45:30,075][00473] Avg episode reward: 18.003, avg true_objective: 9.003
+[2024-07-27 17:45:30,217][00473] Num frames 2800...
+[2024-07-27 17:45:30,350][00473] Num frames 2900...
+[2024-07-27 17:45:30,479][00473] Num frames 3000...
+[2024-07-27 17:45:30,618][00473] Num frames 3100...
+[2024-07-27 17:45:30,758][00473] Num frames 3200...
+[2024-07-27 17:45:30,900][00473] Num frames 3300...
+[2024-07-27 17:45:31,030][00473] Num frames 3400...
+[2024-07-27 17:45:31,157][00473] Num frames 3500...
+[2024-07-27 17:45:31,288][00473] Num frames 3600...
+[2024-07-27 17:45:31,420][00473] Num frames 3700...
+[2024-07-27 17:45:31,556][00473] Num frames 3800...
+[2024-07-27 17:45:31,689][00473] Num frames 3900...
+[2024-07-27 17:45:31,827][00473] Num frames 4000...
+[2024-07-27 17:45:31,958][00473] Num frames 4100...
+[2024-07-27 17:45:32,088][00473] Num frames 4200...
+[2024-07-27 17:45:32,257][00473] Num frames 4300...
+[2024-07-27 17:45:32,357][00473] Avg episode rewards: #0: 23.080, true rewards: #0: 10.830
+[2024-07-27 17:45:32,358][00473] Avg episode reward: 23.080, avg true_objective: 10.830
+[2024-07-27 17:45:32,448][00473] Num frames 4400...
+[2024-07-27 17:45:32,586][00473] Num frames 4500...
+[2024-07-27 17:45:32,719][00473] Num frames 4600...
+[2024-07-27 17:45:32,850][00473] Num frames 4700...
+[2024-07-27 17:45:32,981][00473] Num frames 4800...
+[2024-07-27 17:45:33,108][00473] Num frames 4900...
+[2024-07-27 17:45:33,237][00473] Num frames 5000...
+[2024-07-27 17:45:33,376][00473] Num frames 5100...
+[2024-07-27 17:45:33,507][00473] Num frames 5200...
+[2024-07-27 17:45:33,646][00473] Num frames 5300...
+[2024-07-27 17:45:33,785][00473] Num frames 5400...
+[2024-07-27 17:45:33,914][00473] Num frames 5500...
+[2024-07-27 17:45:34,044][00473] Num frames 5600...
+[2024-07-27 17:45:34,172][00473] Num frames 5700...
+[2024-07-27 17:45:34,307][00473] Num frames 5800...
+[2024-07-27 17:45:34,442][00473] Num frames 5900...
+[2024-07-27 17:45:34,577][00473] Num frames 6000...
+[2024-07-27 17:45:34,727][00473] Num frames 6100...
+[2024-07-27 17:45:34,858][00473] Num frames 6200...
+[2024-07-27 17:45:34,989][00473] Num frames 6300...
+[2024-07-27 17:45:35,118][00473] Num frames 6400...
+[2024-07-27 17:45:35,215][00473] Avg episode rewards: #0: 29.664, true rewards: #0: 12.864
+[2024-07-27 17:45:35,217][00473] Avg episode reward: 29.664, avg true_objective: 12.864
+[2024-07-27 17:45:35,312][00473] Num frames 6500...
+[2024-07-27 17:45:35,440][00473] Num frames 6600...
+[2024-07-27 17:45:35,570][00473] Num frames 6700...
+[2024-07-27 17:45:35,714][00473] Num frames 6800...
+[2024-07-27 17:45:35,886][00473] Avg episode rewards: #0: 25.633, true rewards: #0: 11.467
+[2024-07-27 17:45:35,888][00473] Avg episode reward: 25.633, avg true_objective: 11.467
+[2024-07-27 17:45:35,918][00473] Num frames 6900...
+[2024-07-27 17:45:36,046][00473] Num frames 7000...
+[2024-07-27 17:45:36,176][00473] Num frames 7100...
+[2024-07-27 17:45:36,307][00473] Num frames 7200...
+[2024-07-27 17:45:36,436][00473] Num frames 7300...
+[2024-07-27 17:45:36,566][00473] Num frames 7400...
+[2024-07-27 17:45:36,703][00473] Num frames 7500...
+[2024-07-27 17:45:36,790][00473] Avg episode rewards: #0: 24.028, true rewards: #0: 10.743
+[2024-07-27 17:45:36,791][00473] Avg episode reward: 24.028, avg true_objective: 10.743
+[2024-07-27 17:45:36,898][00473] Num frames 7600...
+[2024-07-27 17:45:37,026][00473] Num frames 7700...
+[2024-07-27 17:45:37,151][00473] Num frames 7800...
+[2024-07-27 17:45:37,286][00473] Num frames 7900...
+[2024-07-27 17:45:37,415][00473] Num frames 8000...
+[2024-07-27 17:45:37,543][00473] Num frames 8100...
+[2024-07-27 17:45:37,673][00473] Num frames 8200...
+[2024-07-27 17:45:37,820][00473] Num frames 8300...
+[2024-07-27 17:45:37,988][00473] Avg episode rewards: #0: 23.360, true rewards: #0: 10.485
+[2024-07-27 17:45:37,990][00473] Avg episode reward: 23.360, avg true_objective: 10.485
+[2024-07-27 17:45:38,012][00473] Num frames 8400...
+[2024-07-27 17:45:38,147][00473] Num frames 8500...
+[2024-07-27 17:45:38,278][00473] Num frames 8600...
+[2024-07-27 17:45:38,409][00473] Num frames 8700...
+[2024-07-27 17:45:38,541][00473] Num frames 8800...
+[2024-07-27 17:45:38,675][00473] Num frames 8900...
+[2024-07-27 17:45:38,819][00473] Num frames 9000...
+[2024-07-27 17:45:38,948][00473] Num frames 9100...
+[2024-07-27 17:45:39,079][00473] Num frames 9200...
+[2024-07-27 17:45:39,237][00473] Num frames 9300...
+[2024-07-27 17:45:39,429][00473] Num frames 9400...
+[2024-07-27 17:45:39,567][00473] Avg episode rewards: #0: 23.160, true rewards: #0: 10.493
+[2024-07-27 17:45:39,569][00473] Avg episode reward: 23.160, avg true_objective: 10.493
+[2024-07-27 17:45:39,673][00473] Num frames 9500...
+[2024-07-27 17:45:39,885][00473] Num frames 9600...
+[2024-07-27 17:45:40,068][00473] Num frames 9700...
+[2024-07-27 17:45:40,251][00473] Num frames 9800...
+[2024-07-27 17:45:40,438][00473] Num frames 9900...
+[2024-07-27 17:45:40,627][00473] Num frames 10000...
+[2024-07-27 17:45:40,837][00473] Num frames 10100...
+[2024-07-27 17:45:41,032][00473] Num frames 10200...
+[2024-07-27 17:45:41,228][00473] Num frames 10300...
+[2024-07-27 17:45:41,425][00473] Num frames 10400...
+[2024-07-27 17:45:41,622][00473] Num frames 10500...
+[2024-07-27 17:45:41,784][00473] Num frames 10600...
+[2024-07-27 17:45:41,937][00473] Num frames 10700...
+[2024-07-27 17:45:42,070][00473] Num frames 10800...
+[2024-07-27 17:45:42,198][00473] Num frames 10900...
+[2024-07-27 17:45:42,333][00473] Num frames 11000...
+[2024-07-27 17:45:42,463][00473] Num frames 11100...
+[2024-07-27 17:45:42,596][00473] Num frames 11200...
+[2024-07-27 17:45:42,732][00473] Num frames 11300...
+[2024-07-27 17:45:42,863][00473] Num frames 11400...
+[2024-07-27 17:45:43,003][00473] Num frames 11500...
+[2024-07-27 17:45:43,116][00473] Avg episode rewards: #0: 26.544, true rewards: #0: 11.544
+[2024-07-27 17:45:43,118][00473] Avg episode reward: 26.544, avg true_objective: 11.544
+[2024-07-27 17:46:54,499][00473] Replay video saved to /content/train_dir/default_experiment/replay.mp4!