Upload . with huggingface_hub

.summary/0/events.out.tfevents.1677248091.1b4f54364242

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40eed92ff0c3aea026cc794369a29d0d3b5337b2a4e2bc36b93cbd90a89b374f
+size 4801

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 8.90 +/- 5.34
+      value: 9.90 +/- 5.25
       name: mean_reward
       verified: false
 ---

checkpoint_p0/checkpoint_000000984_4030464.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0e8008e4bc275114f6c934935d1ee437f4fb0ca8db58f2795d18f5884c32b0b
+size 34929220

config.json

@@ -65,7 +65,7 @@
   "summaries_use_frameskip": true,
   "heartbeat_interval": 20,
   "heartbeat_reporting_interval": 600,
-  "train_for_env_steps": 2000000,
+  "train_for_env_steps": 1000000,
   "train_for_seconds": 10000000000,
   "save_every_sec": 120,
   "keep_checkpoints": 2,

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b55282d8cd2cab67d7d5d558bbfad544466278619d50dd5c36367a4071609c6
-size 16692227
+oid sha256:b1adecf1c1f0ddcff46a2bfe99613d3e75b615aed67d7e7e5150ed0c16c6f88c
+size 19357564

sf_log.txt

@@ -2468,3 +2468,730 @@ main_loop: 38.5571
 [2023-02-24 14:11:36,650][00980] Avg episode rewards: #0: 20.196, true rewards: #0: 8.896
 [2023-02-24 14:11:36,652][00980] Avg episode reward: 20.196, avg true_objective: 8.896
 [2023-02-24 14:12:30,762][00980] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2023-02-24 14:12:33,506][00980] The model has been pushed to https://huggingface.co/mnavas/rl_course_vizdoom_health_gathering_supreme
+[2023-02-24 14:14:51,332][00980] Environment doom_basic already registered, overwriting...
+[2023-02-24 14:14:51,335][00980] Environment doom_two_colors_easy already registered, overwriting...
+[2023-02-24 14:14:51,337][00980] Environment doom_two_colors_hard already registered, overwriting...
+[2023-02-24 14:14:51,338][00980] Environment doom_dm already registered, overwriting...
+[2023-02-24 14:14:51,339][00980] Environment doom_dwango5 already registered, overwriting...
+[2023-02-24 14:14:51,341][00980] Environment doom_my_way_home_flat_actions already registered, overwriting...
+[2023-02-24 14:14:51,342][00980] Environment doom_defend_the_center_flat_actions already registered, overwriting...
+[2023-02-24 14:14:51,343][00980] Environment doom_my_way_home already registered, overwriting...
+[2023-02-24 14:14:51,344][00980] Environment doom_deadly_corridor already registered, overwriting...
+[2023-02-24 14:14:51,345][00980] Environment doom_defend_the_center already registered, overwriting...
+[2023-02-24 14:14:51,347][00980] Environment doom_defend_the_line already registered, overwriting...
+[2023-02-24 14:14:51,348][00980] Environment doom_health_gathering already registered, overwriting...
+[2023-02-24 14:14:51,349][00980] Environment doom_health_gathering_supreme already registered, overwriting...
+[2023-02-24 14:14:51,350][00980] Environment doom_battle already registered, overwriting...
+[2023-02-24 14:14:51,351][00980] Environment doom_battle2 already registered, overwriting...
+[2023-02-24 14:14:51,353][00980] Environment doom_duel_bots already registered, overwriting...
+[2023-02-24 14:14:51,354][00980] Environment doom_deathmatch_bots already registered, overwriting...
+[2023-02-24 14:14:51,356][00980] Environment doom_duel already registered, overwriting...
+[2023-02-24 14:14:51,357][00980] Environment doom_deathmatch_full already registered, overwriting...
+[2023-02-24 14:14:51,358][00980] Environment doom_benchmark already registered, overwriting...
+[2023-02-24 14:14:51,359][00980] register_encoder_factory: <function make_vizdoom_encoder at 0x7ff7e26f99d0>
+[2023-02-24 14:14:51,386][00980] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2023-02-24 14:14:51,387][00980] Overriding arg 'train_for_env_steps' with value 1000000 passed from command line
+[2023-02-24 14:14:51,393][00980] Experiment dir /content/train_dir/default_experiment already exists!
+[2023-02-24 14:14:51,398][00980] Resuming existing experiment from /content/train_dir/default_experiment...
+[2023-02-24 14:14:51,399][00980] Weights and Biases integration disabled
+[2023-02-24 14:14:51,406][00980] Environment var CUDA_VISIBLE_DEVICES is 0
+
+[2023-02-24 14:14:53,401][00980] Starting experiment with the following configuration:
+help=False
+algo=APPO
+env=doom_health_gathering_supreme
+experiment=default_experiment
+train_dir=/content/train_dir
+restart_behavior=resume
+device=gpu
+seed=None
+num_policies=1
+async_rl=True
+serial_mode=False
+batched_sampling=False
+num_batches_to_accumulate=2
+worker_num_splits=2
+policy_workers_per_policy=1
+max_policy_lag=1000
+num_workers=8
+num_envs_per_worker=4
+batch_size=1024
+num_batches_per_epoch=1
+num_epochs=1
+rollout=32
+recurrence=32
+shuffle_minibatches=False
+gamma=0.99
+reward_scale=1.0
+reward_clip=1000.0
+value_bootstrap=False
+normalize_returns=True
+exploration_loss_coeff=0.001
+value_loss_coeff=0.5
+kl_loss_coeff=0.0
+exploration_loss=symmetric_kl
+gae_lambda=0.95
+ppo_clip_ratio=0.1
+ppo_clip_value=0.2
+with_vtrace=False
+vtrace_rho=1.0
+vtrace_c=1.0
+optimizer=adam
+adam_eps=1e-06
+adam_beta1=0.9
+adam_beta2=0.999
+max_grad_norm=4.0
+learning_rate=0.0001
+lr_schedule=constant
+lr_schedule_kl_threshold=0.008
+lr_adaptive_min=1e-06
+lr_adaptive_max=0.01
+obs_subtract_mean=0.0
+obs_scale=255.0
+normalize_input=True
+normalize_input_keys=None
+decorrelate_experience_max_seconds=0
+decorrelate_envs_on_one_worker=True
+actor_worker_gpus=[]
+set_workers_cpu_affinity=True
+force_envs_single_thread=False
+default_niceness=0
+log_to_file=True
+experiment_summaries_interval=10
+flush_summaries_interval=30
+stats_avg=100
+summaries_use_frameskip=True
+heartbeat_interval=20
+heartbeat_reporting_interval=600
+train_for_env_steps=1000000
+train_for_seconds=10000000000
+save_every_sec=120
+keep_checkpoints=2
+load_checkpoint_kind=latest
+save_milestones_sec=-1
+save_best_every_sec=5
+save_best_metric=reward
+save_best_after=100000
+benchmark=False
+encoder_mlp_layers=[512, 512]
+encoder_conv_architecture=convnet_simple
+encoder_conv_mlp_layers=[512]
+use_rnn=True
+rnn_size=512
+rnn_type=gru
+rnn_num_layers=1
+decoder_mlp_layers=[]
+nonlinearity=elu
+policy_initialization=orthogonal
+policy_init_gain=1.0
+actor_critic_share_weights=True
+adaptive_stddev=True
+continuous_tanh_scale=0.0
+initial_stddev=1.0
+use_env_info_cache=False
+env_gpu_actions=False
+env_gpu_observations=True
+env_frameskip=4
+env_framestack=1
+pixel_format=CHW
+use_record_episode_statistics=False
+with_wandb=False
+wandb_user=None
+wandb_project=sample_factory
+wandb_group=None
+wandb_job_type=SF
+wandb_tags=[]
+with_pbt=False
+pbt_mix_policies_in_one_env=True
+pbt_period_env_steps=5000000
+pbt_start_mutation=20000000
+pbt_replace_fraction=0.3
+pbt_mutation_rate=0.15
+pbt_replace_reward_gap=0.1
+pbt_replace_reward_gap_absolute=1e-06
+pbt_optimize_gamma=False
+pbt_target_objective=true_objective
+pbt_perturb_min=1.1
+pbt_perturb_max=1.5
+num_agents=-1
+num_humans=0
+num_bots=-1
+start_bot_difficulty=None
+timelimit=None
+res_w=128
+res_h=72
+wide_aspect_ratio=False
+eval_env_frameskip=1
+fps=35
+command_line=--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=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
+[2023-02-24 14:14:53,404][00980] Saving configuration to /content/train_dir/default_experiment/config.json...
+[2023-02-24 14:14:53,407][00980] Rollout worker 0 uses device cpu
+[2023-02-24 14:14:53,408][00980] Rollout worker 1 uses device cpu
+[2023-02-24 14:14:53,409][00980] Rollout worker 2 uses device cpu
+[2023-02-24 14:14:53,414][00980] Rollout worker 3 uses device cpu
+[2023-02-24 14:14:53,415][00980] Rollout worker 4 uses device cpu
+[2023-02-24 14:14:53,416][00980] Rollout worker 5 uses device cpu
+[2023-02-24 14:14:53,417][00980] Rollout worker 6 uses device cpu
+[2023-02-24 14:14:53,418][00980] Rollout worker 7 uses device cpu
+[2023-02-24 14:14:53,580][00980] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-02-24 14:14:53,582][00980] InferenceWorker_p0-w0: min num requests: 2
+[2023-02-24 14:14:53,630][00980] Starting all processes...
+[2023-02-24 14:14:53,634][00980] Starting process learner_proc0
+[2023-02-24 14:14:53,825][00980] Starting all processes...
+[2023-02-24 14:14:53,836][00980] Starting process inference_proc0-0
+[2023-02-24 14:14:53,837][00980] Starting process rollout_proc0
+[2023-02-24 14:14:53,837][00980] Starting process rollout_proc1
+[2023-02-24 14:14:53,837][00980] Starting process rollout_proc2
+[2023-02-24 14:14:53,837][00980] Starting process rollout_proc3
+[2023-02-24 14:14:53,968][00980] Starting process rollout_proc4
+[2023-02-24 14:14:53,982][00980] Starting process rollout_proc5
+[2023-02-24 14:14:53,987][00980] Starting process rollout_proc6
+[2023-02-24 14:14:53,993][00980] Starting process rollout_proc7
+[2023-02-24 14:15:03,371][26253] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-02-24 14:15:03,375][26253] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2023-02-24 14:15:03,434][26253] Num visible devices: 1
+[2023-02-24 14:15:03,466][26253] Starting seed is not provided
+[2023-02-24 14:15:03,467][26253] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-02-24 14:15:03,468][26253] Initializing actor-critic model on device cuda:0
+[2023-02-24 14:15:03,469][26253] RunningMeanStd input shape: (3, 72, 128)
+[2023-02-24 14:15:03,470][26253] RunningMeanStd input shape: (1,)
+[2023-02-24 14:15:03,546][26253] ConvEncoder: input_channels=3
+[2023-02-24 14:15:04,380][26267] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-02-24 14:15:04,381][26267] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2023-02-24 14:15:04,438][26267] Num visible devices: 1
+[2023-02-24 14:15:04,447][26253] Conv encoder output size: 512
+[2023-02-24 14:15:04,451][26253] Policy head output size: 512
+[2023-02-24 14:15:04,535][26253] Created Actor Critic model with architecture:
+[2023-02-24 14:15:04,537][26253] 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)
+  )
+)
+[2023-02-24 14:15:04,916][26268] Worker 1 uses CPU cores [1]
+[2023-02-24 14:15:05,071][26270] Worker 0 uses CPU cores [0]
+[2023-02-24 14:15:05,141][26272] Worker 3 uses CPU cores [1]
+[2023-02-24 14:15:05,438][26278] Worker 2 uses CPU cores [0]
+[2023-02-24 14:15:05,710][26282] Worker 6 uses CPU cores [0]
+[2023-02-24 14:15:05,772][26280] Worker 4 uses CPU cores [0]
+[2023-02-24 14:15:05,851][26288] Worker 7 uses CPU cores [1]
+[2023-02-24 14:15:05,918][26290] Worker 5 uses CPU cores [1]
+[2023-02-24 14:15:08,019][26253] Using optimizer <class 'torch.optim.adam.Adam'>
+[2023-02-24 14:15:08,021][26253] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000982_4022272.pth...
+[2023-02-24 14:15:08,064][26253] Loading model from checkpoint
+[2023-02-24 14:15:08,071][26253] Loaded experiment state at self.train_step=982, self.env_steps=4022272
+[2023-02-24 14:15:08,072][26253] Initialized policy 0 weights for model version 982
+[2023-02-24 14:15:08,083][26253] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-02-24 14:15:08,090][26253] LearnerWorker_p0 finished initialization!
+[2023-02-24 14:15:08,365][26267] RunningMeanStd input shape: (3, 72, 128)
+[2023-02-24 14:15:08,367][26267] RunningMeanStd input shape: (1,)
+[2023-02-24 14:15:08,389][26267] ConvEncoder: input_channels=3
+[2023-02-24 14:15:08,548][26267] Conv encoder output size: 512
+[2023-02-24 14:15:08,549][26267] Policy head output size: 512
+[2023-02-24 14:15:11,407][00980] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 4022272. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2023-02-24 14:15:11,633][00980] Inference worker 0-0 is ready!
+[2023-02-24 14:15:11,635][00980] All inference workers are ready! Signal rollout workers to start!
+[2023-02-24 14:15:11,741][26272] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 14:15:11,744][26288] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 14:15:11,740][26290] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 14:15:11,738][26268] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 14:15:11,837][26270] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 14:15:11,846][26278] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 14:15:11,840][26282] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 14:15:11,854][26280] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 14:15:12,819][26280] Decorrelating experience for 0 frames...
+[2023-02-24 14:15:12,826][26270] Decorrelating experience for 0 frames...
+[2023-02-24 14:15:13,068][26288] Decorrelating experience for 0 frames...
+[2023-02-24 14:15:13,073][26290] Decorrelating experience for 0 frames...
+[2023-02-24 14:15:13,078][26272] Decorrelating experience for 0 frames...
+[2023-02-24 14:15:13,323][26280] Decorrelating experience for 32 frames...
+[2023-02-24 14:15:13,570][00980] Heartbeat connected on Batcher_0
+[2023-02-24 14:15:13,575][00980] Heartbeat connected on LearnerWorker_p0
+[2023-02-24 14:15:13,606][00980] Heartbeat connected on InferenceWorker_p0-w0
+[2023-02-24 14:15:13,949][26270] Decorrelating experience for 32 frames...
+[2023-02-24 14:15:13,964][26278] Decorrelating experience for 0 frames...
+[2023-02-24 14:15:14,383][26278] Decorrelating experience for 32 frames...
+[2023-02-24 14:15:14,500][26290] Decorrelating experience for 32 frames...
+[2023-02-24 14:15:14,514][26288] Decorrelating experience for 32 frames...
+[2023-02-24 14:15:14,521][26268] Decorrelating experience for 0 frames...
+[2023-02-24 14:15:14,519][26272] Decorrelating experience for 32 frames...
+[2023-02-24 14:15:15,359][26278] Decorrelating experience for 64 frames...
+[2023-02-24 14:15:15,390][26268] Decorrelating experience for 32 frames...
+[2023-02-24 14:15:15,574][26290] Decorrelating experience for 64 frames...
+[2023-02-24 14:15:15,614][26280] Decorrelating experience for 64 frames...
+[2023-02-24 14:15:15,688][26270] Decorrelating experience for 64 frames...
+[2023-02-24 14:15:16,407][00980] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4022272. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2023-02-24 14:15:16,520][26272] Decorrelating experience for 64 frames...
+[2023-02-24 14:15:16,649][26278] Decorrelating experience for 96 frames...
+[2023-02-24 14:15:16,700][26268] Decorrelating experience for 64 frames...
+[2023-02-24 14:15:16,752][26288] Decorrelating experience for 64 frames...
+[2023-02-24 14:15:16,844][00980] Heartbeat connected on RolloutWorker_w2
+[2023-02-24 14:15:16,853][26282] Decorrelating experience for 0 frames...
+[2023-02-24 14:15:16,994][26280] Decorrelating experience for 96 frames...
+[2023-02-24 14:15:17,218][00980] Heartbeat connected on RolloutWorker_w4
+[2023-02-24 14:15:17,608][26270] Decorrelating experience for 96 frames...
+[2023-02-24 14:15:17,961][00980] Heartbeat connected on RolloutWorker_w0
+[2023-02-24 14:15:18,366][26272] Decorrelating experience for 96 frames...
+[2023-02-24 14:15:18,585][26282] Decorrelating experience for 32 frames...
+[2023-02-24 14:15:18,665][00980] Heartbeat connected on RolloutWorker_w3
+[2023-02-24 14:15:18,671][26290] Decorrelating experience for 96 frames...
+[2023-02-24 14:15:18,677][26268] Decorrelating experience for 96 frames...
+[2023-02-24 14:15:18,724][26288] Decorrelating experience for 96 frames...
+[2023-02-24 14:15:19,012][00980] Heartbeat connected on RolloutWorker_w5
+[2023-02-24 14:15:19,020][00980] Heartbeat connected on RolloutWorker_w1
+[2023-02-24 14:15:19,070][00980] Heartbeat connected on RolloutWorker_w7
+[2023-02-24 14:15:21,407][00980] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4022272. Throughput: 0: 175.6. Samples: 1756. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2023-02-24 14:15:21,413][00980] Avg episode reward: [(0, '2.045')]
+[2023-02-24 14:15:21,489][26253] Signal inference workers to stop experience collection...
+[2023-02-24 14:15:21,510][26267] InferenceWorker_p0-w0: stopping experience collection
+[2023-02-24 14:15:21,564][26282] Decorrelating experience for 64 frames...
+[2023-02-24 14:15:22,135][26282] Decorrelating experience for 96 frames...
+[2023-02-24 14:15:22,232][00980] Heartbeat connected on RolloutWorker_w6
+[2023-02-24 14:15:24,615][26253] Signal inference workers to resume experience collection...
+[2023-02-24 14:15:24,647][26253] Stopping Batcher_0...
+[2023-02-24 14:15:24,648][26253] Loop batcher_evt_loop terminating...
+[2023-02-24 14:15:24,644][26267] Weights refcount: 2 0
+[2023-02-24 14:15:24,648][00980] Component Batcher_0 stopped!
+[2023-02-24 14:15:24,658][26267] Stopping InferenceWorker_p0-w0...
+[2023-02-24 14:15:24,659][26267] Loop inference_proc0-0_evt_loop terminating...
+[2023-02-24 14:15:24,658][00980] Component InferenceWorker_p0-w0 stopped!
+[2023-02-24 14:15:24,856][00980] Component RolloutWorker_w7 stopped!
+[2023-02-24 14:15:24,860][26272] Stopping RolloutWorker_w3...
+[2023-02-24 14:15:24,861][00980] Component RolloutWorker_w3 stopped!
+[2023-02-24 14:15:24,861][26288] Stopping RolloutWorker_w7...
+[2023-02-24 14:15:24,868][26288] Loop rollout_proc7_evt_loop terminating...
+[2023-02-24 14:15:24,871][26272] Loop rollout_proc3_evt_loop terminating...
+[2023-02-24 14:15:24,877][00980] Component RolloutWorker_w0 stopped!
+[2023-02-24 14:15:24,877][26268] Stopping RolloutWorker_w1...
+[2023-02-24 14:15:24,878][26290] Stopping RolloutWorker_w5...
+[2023-02-24 14:15:24,881][00980] Component RolloutWorker_w1 stopped!
+[2023-02-24 14:15:24,886][00980] Component RolloutWorker_w5 stopped!
+[2023-02-24 14:15:24,881][26268] Loop rollout_proc1_evt_loop terminating...
+[2023-02-24 14:15:24,881][26290] Loop rollout_proc5_evt_loop terminating...
+[2023-02-24 14:15:24,899][00980] Component RolloutWorker_w4 stopped!
+[2023-02-24 14:15:24,905][26280] Stopping RolloutWorker_w4...
+[2023-02-24 14:15:24,906][26280] Loop rollout_proc4_evt_loop terminating...
+[2023-02-24 14:15:24,911][26282] Stopping RolloutWorker_w6...
+[2023-02-24 14:15:24,911][26282] Loop rollout_proc6_evt_loop terminating...
+[2023-02-24 14:15:24,880][26270] Stopping RolloutWorker_w0...
+[2023-02-24 14:15:24,914][26270] Loop rollout_proc0_evt_loop terminating...
+[2023-02-24 14:15:24,910][00980] Component RolloutWorker_w6 stopped!
+[2023-02-24 14:15:24,931][26278] Stopping RolloutWorker_w2...
+[2023-02-24 14:15:24,932][26278] Loop rollout_proc2_evt_loop terminating...
+[2023-02-24 14:15:24,931][00980] Component RolloutWorker_w2 stopped!
+[2023-02-24 14:15:28,114][26253] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000984_4030464.pth...
+[2023-02-24 14:15:28,273][26253] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000980_4014080.pth
+[2023-02-24 14:15:28,279][26253] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000984_4030464.pth...
+[2023-02-24 14:15:28,479][00980] Component LearnerWorker_p0 stopped!
+[2023-02-24 14:15:28,483][00980] Waiting for process learner_proc0 to stop...
+[2023-02-24 14:15:28,485][26253] Stopping LearnerWorker_p0...
+[2023-02-24 14:15:28,486][26253] Loop learner_proc0_evt_loop terminating...
+[2023-02-24 14:15:29,668][00980] Waiting for process inference_proc0-0 to join...
+[2023-02-24 14:15:29,670][00980] Waiting for process rollout_proc0 to join...
+[2023-02-24 14:15:29,672][00980] Waiting for process rollout_proc1 to join...
+[2023-02-24 14:15:29,674][00980] Waiting for process rollout_proc2 to join...
+[2023-02-24 14:15:29,678][00980] Waiting for process rollout_proc3 to join...
+[2023-02-24 14:15:29,680][00980] Waiting for process rollout_proc4 to join...
+[2023-02-24 14:15:29,682][00980] Waiting for process rollout_proc5 to join...
+[2023-02-24 14:15:29,685][00980] Waiting for process rollout_proc6 to join...
+[2023-02-24 14:15:29,687][00980] Waiting for process rollout_proc7 to join...
+[2023-02-24 14:15:29,689][00980] Batcher 0 profile tree view:
+batching: 0.0539, releasing_batches: 0.0311
+[2023-02-24 14:15:29,691][00980] InferenceWorker_p0-w0 profile tree view:
+update_model: 0.0124
+wait_policy: 0.0012
+  wait_policy_total: 6.5012
+one_step: 0.0023
+  handle_policy_step: 3.1320
+    deserialize: 0.0360, stack: 0.0068, obs_to_device_normalize: 0.2785, forward: 2.5249, send_messages: 0.0576
+    prepare_outputs: 0.1663
+      to_cpu: 0.0961
+[2023-02-24 14:15:29,693][00980] Learner 0 profile tree view:
+misc: 0.0000, prepare_batch: 6.1913
+train: 1.6359
+  epoch_init: 0.0000, minibatch_init: 0.0000, losses_postprocess: 0.0004, kl_divergence: 0.0013, after_optimizer: 0.0296
+  calculate_losses: 0.2418
+    losses_init: 0.0000, forward_head: 0.1123, bptt_initial: 0.1049, tail: 0.0029, advantages_returns: 0.0009, losses: 0.0165
+    bptt: 0.0040
+      bptt_forward_core: 0.0039
+  update: 1.3507
+    clip: 0.0144
+[2023-02-24 14:15:29,696][00980] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.0009, enqueue_policy_requests: 0.4267, env_step: 2.1053, overhead: 0.0685, complete_rollouts: 0.0505
+save_policy_outputs: 0.0325
+  split_output_tensors: 0.0155
+[2023-02-24 14:15:29,698][00980] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.0007, enqueue_policy_requests: 0.4189, env_step: 1.8447, overhead: 0.0353, complete_rollouts: 0.0094
+save_policy_outputs: 0.0314
+  split_output_tensors: 0.0157
+[2023-02-24 14:15:29,702][00980] Loop Runner_EvtLoop terminating...
+[2023-02-24 14:15:29,706][00980] Runner profile tree view:
+main_loop: 36.0757
+[2023-02-24 14:15:29,709][00980] Collected {0: 4030464}, FPS: 227.1
+[2023-02-24 14:15:29,766][00980] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2023-02-24 14:15:29,767][00980] Overriding arg 'num_workers' with value 1 passed from command line
+[2023-02-24 14:15:29,770][00980] Adding new argument 'no_render'=True that is not in the saved config file!
+[2023-02-24 14:15:29,772][00980] Adding new argument 'save_video'=True that is not in the saved config file!
+[2023-02-24 14:15:29,773][00980] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2023-02-24 14:15:29,777][00980] Adding new argument 'video_name'=None that is not in the saved config file!
+[2023-02-24 14:15:29,779][00980] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2023-02-24 14:15:29,785][00980] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2023-02-24 14:15:29,787][00980] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2023-02-24 14:15:29,790][00980] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2023-02-24 14:15:29,792][00980] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2023-02-24 14:15:29,794][00980] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2023-02-24 14:15:29,796][00980] Adding new argument 'train_script'=None that is not in the saved config file!
+[2023-02-24 14:15:29,798][00980] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2023-02-24 14:15:29,799][00980] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2023-02-24 14:15:29,822][00980] RunningMeanStd input shape: (3, 72, 128)
+[2023-02-24 14:15:29,824][00980] RunningMeanStd input shape: (1,)
+[2023-02-24 14:15:29,839][00980] ConvEncoder: input_channels=3
+[2023-02-24 14:15:29,891][00980] Conv encoder output size: 512
+[2023-02-24 14:15:29,893][00980] Policy head output size: 512
+[2023-02-24 14:15:29,920][00980] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000984_4030464.pth...
+[2023-02-24 14:15:30,396][00980] Num frames 100...
+[2023-02-24 14:15:30,515][00980] Num frames 200...
+[2023-02-24 14:15:30,642][00980] Num frames 300...
+[2023-02-24 14:15:30,770][00980] Num frames 400...
+[2023-02-24 14:15:30,891][00980] Num frames 500...
+[2023-02-24 14:15:31,011][00980] Num frames 600...
+[2023-02-24 14:15:31,130][00980] Num frames 700...
+[2023-02-24 14:15:31,247][00980] Num frames 800...
+[2023-02-24 14:15:31,380][00980] Num frames 900...
+[2023-02-24 14:15:31,500][00980] Num frames 1000...
+[2023-02-24 14:15:31,622][00980] Num frames 1100...
+[2023-02-24 14:15:31,753][00980] Num frames 1200...
+[2023-02-24 14:15:31,868][00980] Num frames 1300...
+[2023-02-24 14:15:31,937][00980] Avg episode rewards: #0: 32.120, true rewards: #0: 13.120
+[2023-02-24 14:15:31,941][00980] Avg episode reward: 32.120, avg true_objective: 13.120
+[2023-02-24 14:15:32,038][00980] Num frames 1400...
+[2023-02-24 14:15:32,150][00980] Num frames 1500...
+[2023-02-24 14:15:32,267][00980] Num frames 1600...
+[2023-02-24 14:15:32,426][00980] Num frames 1700...
+[2023-02-24 14:15:32,547][00980] Num frames 1800...
+[2023-02-24 14:15:32,662][00980] Num frames 1900...
+[2023-02-24 14:15:32,779][00980] Num frames 2000...
+[2023-02-24 14:15:32,896][00980] Num frames 2100...
+[2023-02-24 14:15:33,028][00980] Num frames 2200...
+[2023-02-24 14:15:33,171][00980] Avg episode rewards: #0: 26.360, true rewards: #0: 11.360
+[2023-02-24 14:15:33,172][00980] Avg episode reward: 26.360, avg true_objective: 11.360
+[2023-02-24 14:15:33,210][00980] Num frames 2300...
+[2023-02-24 14:15:33,326][00980] Num frames 2400...
+[2023-02-24 14:15:33,457][00980] Num frames 2500...
+[2023-02-24 14:15:33,571][00980] Num frames 2600...
+[2023-02-24 14:15:33,687][00980] Num frames 2700...
+[2023-02-24 14:15:33,804][00980] Num frames 2800...
+[2023-02-24 14:15:33,921][00980] Num frames 2900...
+[2023-02-24 14:15:34,041][00980] Num frames 3000...
+[2023-02-24 14:15:34,159][00980] Num frames 3100...
+[2023-02-24 14:15:34,273][00980] Num frames 3200...
+[2023-02-24 14:15:34,400][00980] Num frames 3300...
+[2023-02-24 14:15:34,516][00980] Num frames 3400...
+[2023-02-24 14:15:34,640][00980] Num frames 3500...
+[2023-02-24 14:15:34,761][00980] Num frames 3600...
+[2023-02-24 14:15:34,880][00980] Num frames 3700...
+[2023-02-24 14:15:35,005][00980] Num frames 3800...
+[2023-02-24 14:15:35,126][00980] Num frames 3900...
+[2023-02-24 14:15:35,241][00980] Num frames 4000...
+[2023-02-24 14:15:35,361][00980] Num frames 4100...
+[2023-02-24 14:15:35,490][00980] Num frames 4200...
+[2023-02-24 14:15:35,608][00980] Num frames 4300...
+[2023-02-24 14:15:35,744][00980] Avg episode rewards: #0: 36.906, true rewards: #0: 14.573
+[2023-02-24 14:15:35,747][00980] Avg episode reward: 36.906, avg true_objective: 14.573
+[2023-02-24 14:15:35,781][00980] Num frames 4400...
+[2023-02-24 14:15:35,898][00980] Num frames 4500...
+[2023-02-24 14:15:36,012][00980] Num frames 4600...
+[2023-02-24 14:15:36,127][00980] Num frames 4700...
+[2023-02-24 14:15:36,241][00980] Num frames 4800...
+[2023-02-24 14:15:36,362][00980] Num frames 4900...
+[2023-02-24 14:15:36,488][00980] Num frames 5000...
+[2023-02-24 14:15:36,611][00980] Num frames 5100...
+[2023-02-24 14:15:36,733][00980] Num frames 5200...
+[2023-02-24 14:15:36,851][00980] Num frames 5300...
+[2023-02-24 14:15:36,973][00980] Num frames 5400...
+[2023-02-24 14:15:37,089][00980] Num frames 5500...
+[2023-02-24 14:15:37,211][00980] Num frames 5600...
+[2023-02-24 14:15:37,290][00980] Avg episode rewards: #0: 34.550, true rewards: #0: 14.050
+[2023-02-24 14:15:37,292][00980] Avg episode reward: 34.550, avg true_objective: 14.050
+[2023-02-24 14:15:37,387][00980] Num frames 5700...
+[2023-02-24 14:15:37,516][00980] Num frames 5800...
+[2023-02-24 14:15:37,633][00980] Num frames 5900...
+[2023-02-24 14:15:37,749][00980] Num frames 6000...
+[2023-02-24 14:15:37,864][00980] Num frames 6100...
+[2023-02-24 14:15:37,987][00980] Num frames 6200...
+[2023-02-24 14:15:38,103][00980] Num frames 6300...
+[2023-02-24 14:15:38,225][00980] Num frames 6400...
+[2023-02-24 14:15:38,353][00980] Num frames 6500...
+[2023-02-24 14:15:38,486][00980] Num frames 6600...
+[2023-02-24 14:15:38,604][00980] Num frames 6700...
+[2023-02-24 14:15:38,729][00980] Num frames 6800...
+[2023-02-24 14:15:38,852][00980] Num frames 6900...
+[2023-02-24 14:15:38,971][00980] Num frames 7000...
+[2023-02-24 14:15:39,085][00980] Num frames 7100...
+[2023-02-24 14:15:39,209][00980] Num frames 7200...
+[2023-02-24 14:15:39,329][00980] Num frames 7300...
+[2023-02-24 14:15:39,455][00980] Num frames 7400...
+[2023-02-24 14:15:39,636][00980] Num frames 7500...
+[2023-02-24 14:15:39,812][00980] Num frames 7600...
+[2023-02-24 14:15:39,987][00980] Num frames 7700...
+[2023-02-24 14:15:40,080][00980] Avg episode rewards: #0: 38.440, true rewards: #0: 15.440
+[2023-02-24 14:15:40,085][00980] Avg episode reward: 38.440, avg true_objective: 15.440
+[2023-02-24 14:15:40,231][00980] Num frames 7800...
+[2023-02-24 14:15:40,392][00980] Num frames 7900...
+[2023-02-24 14:15:40,558][00980] Num frames 8000...
+[2023-02-24 14:15:40,738][00980] Num frames 8100...
+[2023-02-24 14:15:40,913][00980] Num frames 8200...
+[2023-02-24 14:15:41,077][00980] Num frames 8300...
+[2023-02-24 14:15:41,241][00980] Num frames 8400...
+[2023-02-24 14:15:41,422][00980] Num frames 8500...
+[2023-02-24 14:15:41,602][00980] Num frames 8600...
+[2023-02-24 14:15:41,767][00980] Num frames 8700...
+[2023-02-24 14:15:41,940][00980] Num frames 8800...
+[2023-02-24 14:15:42,110][00980] Num frames 8900...
+[2023-02-24 14:15:42,289][00980] Num frames 9000...
+[2023-02-24 14:15:42,463][00980] Num frames 9100...
+[2023-02-24 14:15:42,635][00980] Num frames 9200...
+[2023-02-24 14:15:42,803][00980] Num frames 9300...
+[2023-02-24 14:15:42,946][00980] Avg episode rewards: #0: 39.086, true rewards: #0: 15.587
+[2023-02-24 14:15:42,949][00980] Avg episode reward: 39.086, avg true_objective: 15.587
+[2023-02-24 14:15:43,029][00980] Num frames 9400...
+[2023-02-24 14:15:43,183][00980] Num frames 9500...
+[2023-02-24 14:15:43,304][00980] Num frames 9600...
+[2023-02-24 14:15:43,420][00980] Num frames 9700...
+[2023-02-24 14:15:43,533][00980] Num frames 9800...
+[2023-02-24 14:15:43,655][00980] Num frames 9900...
+[2023-02-24 14:15:43,779][00980] Num frames 10000...
+[2023-02-24 14:15:43,897][00980] Num frames 10100...
+[2023-02-24 14:15:44,021][00980] Avg episode rewards: #0: 35.645, true rewards: #0: 14.503
+[2023-02-24 14:15:44,023][00980] Avg episode reward: 35.645, avg true_objective: 14.503
+[2023-02-24 14:15:44,080][00980] Num frames 10200...
+[2023-02-24 14:15:44,204][00980] Num frames 10300...
+[2023-02-24 14:15:44,320][00980] Num frames 10400...
+[2023-02-24 14:15:44,439][00980] Num frames 10500...
+[2023-02-24 14:15:44,561][00980] Num frames 10600...
+[2023-02-24 14:15:44,685][00980] Num frames 10700...
+[2023-02-24 14:15:44,805][00980] Num frames 10800...
+[2023-02-24 14:15:44,890][00980] Avg episode rewards: #0: 33.030, true rewards: #0: 13.530
+[2023-02-24 14:15:44,892][00980] Avg episode reward: 33.030, avg true_objective: 13.530
+[2023-02-24 14:15:44,983][00980] Num frames 10900...
+[2023-02-24 14:15:45,100][00980] Num frames 11000...
+[2023-02-24 14:15:45,217][00980] Num frames 11100...
+[2023-02-24 14:15:45,335][00980] Num frames 11200...
+[2023-02-24 14:15:45,451][00980] Num frames 11300...
+[2023-02-24 14:15:45,575][00980] Num frames 11400...
+[2023-02-24 14:15:45,700][00980] Num frames 11500...
+[2023-02-24 14:15:45,823][00980] Num frames 11600...
+[2023-02-24 14:15:45,942][00980] Num frames 11700...
+[2023-02-24 14:15:46,060][00980] Num frames 11800...
+[2023-02-24 14:15:46,186][00980] Num frames 11900...
+[2023-02-24 14:15:46,306][00980] Num frames 12000...
+[2023-02-24 14:15:46,428][00980] Num frames 12100...
+[2023-02-24 14:15:46,545][00980] Num frames 12200...
+[2023-02-24 14:15:46,675][00980] Num frames 12300...
+[2023-02-24 14:15:46,792][00980] Num frames 12400...
+[2023-02-24 14:15:46,916][00980] Num frames 12500...
+[2023-02-24 14:15:47,032][00980] Num frames 12600...
+[2023-02-24 14:15:47,152][00980] Num frames 12700...
+[2023-02-24 14:15:47,277][00980] Num frames 12800...
+[2023-02-24 14:15:47,398][00980] Num frames 12900...
+[2023-02-24 14:15:47,490][00980] Avg episode rewards: #0: 36.026, true rewards: #0: 14.360
+[2023-02-24 14:15:47,491][00980] Avg episode reward: 36.026, avg true_objective: 14.360
+[2023-02-24 14:15:47,582][00980] Num frames 13000...
+[2023-02-24 14:15:47,716][00980] Num frames 13100...
+[2023-02-24 14:15:47,833][00980] Num frames 13200...
+[2023-02-24 14:15:47,956][00980] Num frames 13300...
+[2023-02-24 14:15:48,076][00980] Num frames 13400...
+[2023-02-24 14:15:48,190][00980] Num frames 13500...
+[2023-02-24 14:15:48,313][00980] Num frames 13600...
+[2023-02-24 14:15:48,435][00980] Num frames 13700...
+[2023-02-24 14:15:48,560][00980] Num frames 13800...
+[2023-02-24 14:15:48,680][00980] Num frames 13900...
+[2023-02-24 14:15:48,804][00980] Num frames 14000...
+[2023-02-24 14:15:48,921][00980] Num frames 14100...
+[2023-02-24 14:15:49,040][00980] Num frames 14200...
+[2023-02-24 14:15:49,157][00980] Num frames 14300...
+[2023-02-24 14:15:49,279][00980] Num frames 14400...
+[2023-02-24 14:15:49,411][00980] Num frames 14500...
+[2023-02-24 14:15:49,532][00980] Avg episode rewards: #0: 36.556, true rewards: #0: 14.556
+[2023-02-24 14:15:49,535][00980] Avg episode reward: 36.556, avg true_objective: 14.556
+[2023-02-24 14:17:18,905][00980] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2023-02-24 14:17:18,985][00980] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2023-02-24 14:17:18,989][00980] Overriding arg 'num_workers' with value 1 passed from command line
+[2023-02-24 14:17:18,992][00980] Adding new argument 'no_render'=True that is not in the saved config file!
+[2023-02-24 14:17:18,996][00980] Adding new argument 'save_video'=True that is not in the saved config file!
+[2023-02-24 14:17:18,999][00980] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2023-02-24 14:17:19,001][00980] Adding new argument 'video_name'=None that is not in the saved config file!
+[2023-02-24 14:17:19,003][00980] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2023-02-24 14:17:19,006][00980] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2023-02-24 14:17:19,007][00980] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2023-02-24 14:17:19,012][00980] Adding new argument 'hf_repository'='mnavas/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2023-02-24 14:17:19,013][00980] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2023-02-24 14:17:19,014][00980] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2023-02-24 14:17:19,015][00980] Adding new argument 'train_script'=None that is not in the saved config file!
+[2023-02-24 14:17:19,016][00980] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2023-02-24 14:17:19,018][00980] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2023-02-24 14:17:19,052][00980] RunningMeanStd input shape: (3, 72, 128)
+[2023-02-24 14:17:19,055][00980] RunningMeanStd input shape: (1,)
+[2023-02-24 14:17:19,074][00980] ConvEncoder: input_channels=3
+[2023-02-24 14:17:19,143][00980] Conv encoder output size: 512
+[2023-02-24 14:17:19,145][00980] Policy head output size: 512
+[2023-02-24 14:17:19,181][00980] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000984_4030464.pth...
+[2023-02-24 14:17:19,838][00980] Num frames 100...
+[2023-02-24 14:17:20,012][00980] Num frames 200...
+[2023-02-24 14:17:20,171][00980] Num frames 300...
+[2023-02-24 14:17:20,352][00980] Num frames 400...
+[2023-02-24 14:17:20,438][00980] Avg episode rewards: #0: 6.160, true rewards: #0: 4.160
+[2023-02-24 14:17:20,439][00980] Avg episode reward: 6.160, avg true_objective: 4.160
+[2023-02-24 14:17:20,580][00980] Num frames 500...
+[2023-02-24 14:17:20,745][00980] Num frames 600...
+[2023-02-24 14:17:20,914][00980] Num frames 700...
+[2023-02-24 14:17:21,087][00980] Num frames 800...
+[2023-02-24 14:17:21,258][00980] Num frames 900...
+[2023-02-24 14:17:21,441][00980] Num frames 1000...
+[2023-02-24 14:17:21,622][00980] Num frames 1100...
+[2023-02-24 14:17:21,792][00980] Num frames 1200...
+[2023-02-24 14:17:21,958][00980] Num frames 1300...
+[2023-02-24 14:17:22,089][00980] Num frames 1400...
+[2023-02-24 14:17:22,210][00980] Num frames 1500...
+[2023-02-24 14:17:22,333][00980] Num frames 1600...
+[2023-02-24 14:17:22,450][00980] Num frames 1700...
+[2023-02-24 14:17:22,567][00980] Num frames 1800...
+[2023-02-24 14:17:22,680][00980] Num frames 1900...
+[2023-02-24 14:17:22,797][00980] Num frames 2000...
+[2023-02-24 14:17:22,912][00980] Num frames 2100...
+[2023-02-24 14:17:23,025][00980] Num frames 2200...
+[2023-02-24 14:17:23,148][00980] Num frames 2300...
+[2023-02-24 14:17:23,270][00980] Num frames 2400...
+[2023-02-24 14:17:23,398][00980] Num frames 2500...
+[2023-02-24 14:17:23,475][00980] Avg episode rewards: #0: 29.079, true rewards: #0: 12.580
+[2023-02-24 14:17:23,478][00980] Avg episode reward: 29.079, avg true_objective: 12.580
+[2023-02-24 14:17:23,575][00980] Num frames 2600...
+[2023-02-24 14:17:23,691][00980] Num frames 2700...
+[2023-02-24 14:17:23,831][00980] Avg episode rewards: #0: 20.906, true rewards: #0: 9.240
+[2023-02-24 14:17:23,833][00980] Avg episode reward: 20.906, avg true_objective: 9.240
+[2023-02-24 14:17:23,868][00980] Num frames 2800...
+[2023-02-24 14:17:23,988][00980] Num frames 2900...
+[2023-02-24 14:17:24,105][00980] Num frames 3000...
+[2023-02-24 14:17:24,223][00980] Num frames 3100...
+[2023-02-24 14:17:24,347][00980] Num frames 3200...
+[2023-02-24 14:17:24,463][00980] Num frames 3300...
+[2023-02-24 14:17:24,578][00980] Num frames 3400...
+[2023-02-24 14:17:24,692][00980] Num frames 3500...
+[2023-02-24 14:17:24,812][00980] Num frames 3600...
+[2023-02-24 14:17:24,929][00980] Num frames 3700...
+[2023-02-24 14:17:25,002][00980] Avg episode rewards: #0: 21.285, true rewards: #0: 9.285
+[2023-02-24 14:17:25,003][00980] Avg episode reward: 21.285, avg true_objective: 9.285
+[2023-02-24 14:17:25,104][00980] Num frames 3800...
+[2023-02-24 14:17:25,229][00980] Num frames 3900...
+[2023-02-24 14:17:25,358][00980] Num frames 4000...
+[2023-02-24 14:17:25,475][00980] Num frames 4100...
+[2023-02-24 14:17:25,593][00980] Num frames 4200...
+[2023-02-24 14:17:25,712][00980] Num frames 4300...
+[2023-02-24 14:17:25,829][00980] Num frames 4400...
+[2023-02-24 14:17:25,953][00980] Num frames 4500...
+[2023-02-24 14:17:26,071][00980] Num frames 4600...
+[2023-02-24 14:17:26,194][00980] Num frames 4700...
+[2023-02-24 14:17:26,308][00980] Num frames 4800...
+[2023-02-24 14:17:26,431][00980] Num frames 4900...
+[2023-02-24 14:17:26,549][00980] Num frames 5000...
+[2023-02-24 14:17:26,623][00980] Avg episode rewards: #0: 24.032, true rewards: #0: 10.032
+[2023-02-24 14:17:26,627][00980] Avg episode reward: 24.032, avg true_objective: 10.032
+[2023-02-24 14:17:26,723][00980] Num frames 5100...
+[2023-02-24 14:17:26,837][00980] Num frames 5200...
+[2023-02-24 14:17:26,959][00980] Num frames 5300...
+[2023-02-24 14:17:27,078][00980] Num frames 5400...
+[2023-02-24 14:17:27,197][00980] Num frames 5500...
+[2023-02-24 14:17:27,320][00980] Num frames 5600...
+[2023-02-24 14:17:27,438][00980] Num frames 5700...
+[2023-02-24 14:17:27,560][00980] Num frames 5800...
+[2023-02-24 14:17:27,707][00980] Avg episode rewards: #0: 23.467, true rewards: #0: 9.800
+[2023-02-24 14:17:27,709][00980] Avg episode reward: 23.467, avg true_objective: 9.800
+[2023-02-24 14:17:27,735][00980] Num frames 5900...
+[2023-02-24 14:17:27,855][00980] Num frames 6000...
+[2023-02-24 14:17:27,971][00980] Num frames 6100...
+[2023-02-24 14:17:28,088][00980] Num frames 6200...
+[2023-02-24 14:17:28,208][00980] Num frames 6300...
+[2023-02-24 14:17:28,326][00980] Num frames 6400...
+[2023-02-24 14:17:28,447][00980] Num frames 6500...
+[2023-02-24 14:17:28,572][00980] Num frames 6600...
+[2023-02-24 14:17:28,748][00980] Avg episode rewards: #0: 22.854, true rewards: #0: 9.569
+[2023-02-24 14:17:28,751][00980] Avg episode reward: 22.854, avg true_objective: 9.569
+[2023-02-24 14:17:28,755][00980] Num frames 6700...
+[2023-02-24 14:17:28,880][00980] Num frames 6800...
+[2023-02-24 14:17:28,994][00980] Num frames 6900...
+[2023-02-24 14:17:29,113][00980] Num frames 7000...
+[2023-02-24 14:17:29,237][00980] Num frames 7100...
+[2023-02-24 14:17:29,355][00980] Num frames 7200...
+[2023-02-24 14:17:29,470][00980] Avg episode rewards: #0: 21.427, true rewards: #0: 9.052
+[2023-02-24 14:17:29,473][00980] Avg episode reward: 21.427, avg true_objective: 9.052
+[2023-02-24 14:17:29,547][00980] Num frames 7300...
+[2023-02-24 14:17:29,672][00980] Num frames 7400...
+[2023-02-24 14:17:29,787][00980] Num frames 7500...
+[2023-02-24 14:17:29,913][00980] Num frames 7600...
+[2023-02-24 14:17:30,036][00980] Num frames 7700...
+[2023-02-24 14:17:30,152][00980] Num frames 7800...
+[2023-02-24 14:17:30,268][00980] Num frames 7900...
+[2023-02-24 14:17:30,391][00980] Num frames 8000...
+[2023-02-24 14:17:30,516][00980] Num frames 8100...
+[2023-02-24 14:17:30,644][00980] Num frames 8200...
+[2023-02-24 14:17:30,764][00980] Num frames 8300...
+[2023-02-24 14:17:30,883][00980] Num frames 8400...
+[2023-02-24 14:17:31,008][00980] Num frames 8500...
+[2023-02-24 14:17:31,128][00980] Num frames 8600...
+[2023-02-24 14:17:31,250][00980] Num frames 8700...
+[2023-02-24 14:17:31,399][00980] Avg episode rewards: #0: 23.308, true rewards: #0: 9.752
+[2023-02-24 14:17:31,400][00980] Avg episode reward: 23.308, avg true_objective: 9.752
+[2023-02-24 14:17:31,435][00980] Num frames 8800...
+[2023-02-24 14:17:31,553][00980] Num frames 8900...
+[2023-02-24 14:17:31,671][00980] Num frames 9000...
+[2023-02-24 14:17:31,794][00980] Num frames 9100...
+[2023-02-24 14:17:31,913][00980] Num frames 9200...
+[2023-02-24 14:17:32,045][00980] Num frames 9300...
+[2023-02-24 14:17:32,220][00980] Num frames 9400...
+[2023-02-24 14:17:32,391][00980] Num frames 9500...
+[2023-02-24 14:17:32,585][00980] Num frames 9600...
+[2023-02-24 14:17:32,749][00980] Num frames 9700...
+[2023-02-24 14:17:32,909][00980] Num frames 9800...
+[2023-02-24 14:17:33,124][00980] Avg episode rewards: #0: 23.597, true rewards: #0: 9.897
+[2023-02-24 14:17:33,127][00980] Avg episode reward: 23.597, avg true_objective: 9.897
+[2023-02-24 14:17:33,136][00980] Num frames 9900...
+[2023-02-24 14:18:34,473][00980] Replay video saved to /content/train_dir/default_experiment/replay.mp4!