Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1730984134.ali

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63b94cdef6e415ddbb0526608b0aeec84bab1ed76f502a53dc2253bb836dc4ad
+size 3066

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 4.00 +/- 0.58
+      value: 4.09 +/- 0.28
       name: mean_reward
       verified: false
 ---

checkpoint_p0/checkpoint_000001957_8015872.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:297499a87cb551ed79e0a23e15ebfe6c9cce1d619daba0f8cf9ee95af2bd0a36
+size 34929669

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e97dd79cc84566043bc7f37148d9b9076a10c3e97a1ca07a0c143811c8fd34b0
-size 5723967
+oid sha256:4dadc597826f82f8cc03bfea38fe89b15e84fe47b1a75b3a86e6c815b8edfa9f
+size 6270807

sf_log.txt

@@ -5888,3 +5888,569 @@ main_loop: 558.4363
 [2024-11-07 14:52:32,278][04584] Avg episode reward: 4.498, avg true_objective: 3.998
 [2024-11-07 14:52:32,283][04584] Num frames 4000...
 [2024-11-07 14:52:40,832][04584] Replay video saved to /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/replay.mp4!
+[2024-11-07 14:52:50,207][04584] The model has been pushed to https://huggingface.co/alidenewade/rl_course_vizdoom_health_gathering_supreme
+[2024-11-07 14:55:34,046][04584] Environment doom_basic already registered, overwriting...
+[2024-11-07 14:55:34,050][04584] Environment doom_two_colors_easy already registered, overwriting...
+[2024-11-07 14:55:34,053][04584] Environment doom_two_colors_hard already registered, overwriting...
+[2024-11-07 14:55:34,054][04584] Environment doom_dm already registered, overwriting...
+[2024-11-07 14:55:34,055][04584] Environment doom_dwango5 already registered, overwriting...
+[2024-11-07 14:55:34,057][04584] Environment doom_my_way_home_flat_actions already registered, overwriting...
+[2024-11-07 14:55:34,058][04584] Environment doom_defend_the_center_flat_actions already registered, overwriting...
+[2024-11-07 14:55:34,059][04584] Environment doom_my_way_home already registered, overwriting...
+[2024-11-07 14:55:34,060][04584] Environment doom_deadly_corridor already registered, overwriting...
+[2024-11-07 14:55:34,063][04584] Environment doom_defend_the_center already registered, overwriting...
+[2024-11-07 14:55:34,065][04584] Environment doom_defend_the_line already registered, overwriting...
+[2024-11-07 14:55:34,067][04584] Environment doom_health_gathering already registered, overwriting...
+[2024-11-07 14:55:34,069][04584] Environment doom_health_gathering_supreme already registered, overwriting...
+[2024-11-07 14:55:34,070][04584] Environment doom_battle already registered, overwriting...
+[2024-11-07 14:55:34,072][04584] Environment doom_battle2 already registered, overwriting...
+[2024-11-07 14:55:34,073][04584] Environment doom_duel_bots already registered, overwriting...
+[2024-11-07 14:55:34,075][04584] Environment doom_deathmatch_bots already registered, overwriting...
+[2024-11-07 14:55:34,075][04584] Environment doom_duel already registered, overwriting...
+[2024-11-07 14:55:34,078][04584] Environment doom_deathmatch_full already registered, overwriting...
+[2024-11-07 14:55:34,079][04584] Environment doom_benchmark already registered, overwriting...
+[2024-11-07 14:55:34,081][04584] register_encoder_factory: <function make_vizdoom_encoder at 0x7f3d19f46950>
+[2024-11-07 14:55:34,099][04584] Loading existing experiment configuration from /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/config.json
+[2024-11-07 14:55:34,107][04584] Experiment dir /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment already exists!
+[2024-11-07 14:55:34,109][04584] Resuming existing experiment from /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment...
+[2024-11-07 14:55:34,110][04584] Weights and Biases integration disabled
+[2024-11-07 14:55:34,116][04584] Environment var CUDA_VISIBLE_DEVICES is 0
+
+[2024-11-07 14:55:36,623][04584] Starting experiment with the following configuration:
+help=False
+algo=APPO
+env=doom_health_gathering_supreme
+experiment=default_experiment
+train_dir=/root/hfRL/ml/LunarLander-v2/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=8000000
+train_for_seconds=10000000000
+save_every_sec=120
+keep_checkpoints=2
+load_checkpoint_kind=latest
+save_milestones_sec=-1
+save_best_every_sec=5
+save_best_metric=reward
+save_best_after=100000
+benchmark=False
+encoder_mlp_layers=[512, 512]
+encoder_conv_architecture=convnet_simple
+encoder_conv_mlp_layers=[512]
+use_rnn=True
+rnn_size=512
+rnn_type=gru
+rnn_num_layers=1
+decoder_mlp_layers=[]
+nonlinearity=elu
+policy_initialization=orthogonal
+policy_init_gain=1.0
+actor_critic_share_weights=True
+adaptive_stddev=True
+continuous_tanh_scale=0.0
+initial_stddev=1.0
+use_env_info_cache=False
+env_gpu_actions=False
+env_gpu_observations=True
+env_frameskip=4
+env_framestack=1
+pixel_format=CHW
+use_record_episode_statistics=False
+with_wandb=False
+wandb_user=None
+wandb_project=sample_factory
+wandb_group=None
+wandb_job_type=SF
+wandb_tags=[]
+with_pbt=False
+pbt_mix_policies_in_one_env=True
+pbt_period_env_steps=5000000
+pbt_start_mutation=20000000
+pbt_replace_fraction=0.3
+pbt_mutation_rate=0.15
+pbt_replace_reward_gap=0.1
+pbt_replace_reward_gap_absolute=1e-06
+pbt_optimize_gamma=False
+pbt_target_objective=true_objective
+pbt_perturb_min=1.1
+pbt_perturb_max=1.5
+num_agents=-1
+num_humans=0
+num_bots=-1
+start_bot_difficulty=None
+timelimit=None
+res_w=128
+res_h=72
+wide_aspect_ratio=False
+eval_env_frameskip=1
+fps=35
+command_line=--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=4000000
+cli_args={'env': 'doom_health_gathering_supreme', 'num_workers': 8, 'num_envs_per_worker': 4, 'train_for_env_steps': 4000000}
+git_hash=unknown
+git_repo_name=not a git repository
+[2024-11-07 14:55:36,625][04584] Saving configuration to /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/config.json...
+[2024-11-07 14:55:36,628][04584] Rollout worker 0 uses device cpu
+[2024-11-07 14:55:36,629][04584] Rollout worker 1 uses device cpu
+[2024-11-07 14:55:36,631][04584] Rollout worker 2 uses device cpu
+[2024-11-07 14:55:36,633][04584] Rollout worker 3 uses device cpu
+[2024-11-07 14:55:36,635][04584] Rollout worker 4 uses device cpu
+[2024-11-07 14:55:36,637][04584] Rollout worker 5 uses device cpu
+[2024-11-07 14:55:36,639][04584] Rollout worker 6 uses device cpu
+[2024-11-07 14:55:36,641][04584] Rollout worker 7 uses device cpu
+[2024-11-07 14:55:36,708][04584] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-11-07 14:55:36,710][04584] InferenceWorker_p0-w0: min num requests: 2
+[2024-11-07 14:55:36,746][04584] Starting all processes...
+[2024-11-07 14:55:36,748][04584] Starting process learner_proc0
+[2024-11-07 14:55:36,796][04584] Starting all processes...
+[2024-11-07 14:55:36,802][04584] Starting process inference_proc0-0
+[2024-11-07 14:55:36,803][04584] Starting process rollout_proc0
+[2024-11-07 14:55:36,803][04584] Starting process rollout_proc1
+[2024-11-07 14:55:36,803][04584] Starting process rollout_proc2
+[2024-11-07 14:55:36,804][04584] Starting process rollout_proc3
+[2024-11-07 14:55:36,805][04584] Starting process rollout_proc4
+[2024-11-07 14:55:36,806][04584] Starting process rollout_proc5
+[2024-11-07 14:55:36,807][04584] Starting process rollout_proc6
+[2024-11-07 14:55:36,808][04584] Starting process rollout_proc7
+[2024-11-07 14:55:43,371][07866] Worker 0 uses CPU cores [0]
+[2024-11-07 14:55:44,070][07873] Worker 1 uses CPU cores [1]
+[2024-11-07 14:55:44,330][07871] Worker 3 uses CPU cores [3]
+[2024-11-07 14:55:44,346][07852] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-11-07 14:55:44,347][07852] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2024-11-07 14:55:44,350][07865] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-11-07 14:55:44,351][07865] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2024-11-07 14:55:44,383][07852] Num visible devices: 1
+[2024-11-07 14:55:44,418][07865] Num visible devices: 1
+[2024-11-07 14:55:44,418][07852] Starting seed is not provided
+[2024-11-07 14:55:44,418][07852] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-11-07 14:55:44,418][07852] Initializing actor-critic model on device cuda:0
+[2024-11-07 14:55:44,419][07852] RunningMeanStd input shape: (3, 72, 128)
+[2024-11-07 14:55:44,422][07852] RunningMeanStd input shape: (1,)
+[2024-11-07 14:55:44,488][07852] ConvEncoder: input_channels=3
+[2024-11-07 14:55:44,600][07874] Worker 5 uses CPU cores [5]
+[2024-11-07 14:55:44,619][07885] Worker 7 uses CPU cores [0, 1, 2, 3, 4, 5, 6]
+[2024-11-07 14:55:44,664][07884] Worker 6 uses CPU cores [6]
+[2024-11-07 14:55:44,740][07870] Worker 2 uses CPU cores [2]
+[2024-11-07 14:55:44,747][07852] Conv encoder output size: 512
+[2024-11-07 14:55:44,747][07852] Policy head output size: 512
+[2024-11-07 14:55:44,767][07852] Created Actor Critic model with architecture:
+[2024-11-07 14:55:44,768][07852] ActorCriticSharedWeights(
+  (obs_normalizer): ObservationNormalizer(
+    (running_mean_std): RunningMeanStdDictInPlace(
+      (running_mean_std): ModuleDict(
+        (obs): RunningMeanStdInPlace()
+      )
+    )
+  )
+  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
+  (encoder): VizdoomEncoder(
+    (basic_encoder): ConvEncoder(
+      (enc): RecursiveScriptModule(
+        original_name=ConvEncoderImpl
+        (conv_head): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Conv2d)
+          (1): RecursiveScriptModule(original_name=ELU)
+          (2): RecursiveScriptModule(original_name=Conv2d)
+          (3): RecursiveScriptModule(original_name=ELU)
+          (4): RecursiveScriptModule(original_name=Conv2d)
+          (5): RecursiveScriptModule(original_name=ELU)
+        )
+        (mlp_layers): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Linear)
+          (1): RecursiveScriptModule(original_name=ELU)
+        )
+      )
+    )
+  )
+  (core): ModelCoreRNN(
+    (core): GRU(512, 512)
+  )
+  (decoder): MlpDecoder(
+    (mlp): Identity()
+  )
+  (critic_linear): Linear(in_features=512, out_features=1, bias=True)
+  (action_parameterization): ActionParameterizationDefault(
+    (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
+  )
+)
+[2024-11-07 14:55:45,005][07852] Using optimizer <class 'torch.optim.adam.Adam'>
+[2024-11-07 14:55:45,120][07872] Worker 4 uses CPU cores [4]
+[2024-11-07 14:55:46,269][07852] Loading state from checkpoint /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/checkpoint_p0/checkpoint_000001955_8007680.pth...
+[2024-11-07 14:55:46,317][07852] Loading model from checkpoint
+[2024-11-07 14:55:46,320][07852] Loaded experiment state at self.train_step=1955, self.env_steps=8007680
+[2024-11-07 14:55:46,320][07852] Initialized policy 0 weights for model version 1955
+[2024-11-07 14:55:46,327][07852] LearnerWorker_p0 finished initialization!
+[2024-11-07 14:55:46,327][07852] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-11-07 14:55:46,561][07865] RunningMeanStd input shape: (3, 72, 128)
+[2024-11-07 14:55:46,563][07865] RunningMeanStd input shape: (1,)
+[2024-11-07 14:55:46,580][07865] ConvEncoder: input_channels=3
+[2024-11-07 14:55:46,746][07865] Conv encoder output size: 512
+[2024-11-07 14:55:46,747][07865] Policy head output size: 512
+[2024-11-07 14:55:46,824][04584] Inference worker 0-0 is ready!
+[2024-11-07 14:55:46,826][04584] All inference workers are ready! Signal rollout workers to start!
+[2024-11-07 14:55:47,036][07866] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-07 14:55:47,038][07872] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-07 14:55:47,069][07874] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-07 14:55:47,090][07871] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-07 14:55:47,104][07873] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-07 14:55:47,104][07870] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-07 14:55:47,247][07885] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-07 14:55:47,261][07884] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-07 14:55:48,282][07871] Decorrelating experience for 0 frames...
+[2024-11-07 14:55:48,298][07872] Decorrelating experience for 0 frames...
+[2024-11-07 14:55:48,386][07885] Decorrelating experience for 0 frames...
+[2024-11-07 14:55:48,436][07866] Decorrelating experience for 0 frames...
+[2024-11-07 14:55:48,449][07884] Decorrelating experience for 0 frames...
+[2024-11-07 14:55:48,975][07871] Decorrelating experience for 32 frames...
+[2024-11-07 14:55:48,987][07870] Decorrelating experience for 0 frames...
+[2024-11-07 14:55:49,060][07872] Decorrelating experience for 32 frames...
+[2024-11-07 14:55:49,080][07885] Decorrelating experience for 32 frames...
+[2024-11-07 14:55:49,117][04584] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 8007680. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-11-07 14:55:49,212][07884] Decorrelating experience for 32 frames...
+[2024-11-07 14:55:49,240][07866] Decorrelating experience for 32 frames...
+[2024-11-07 14:55:49,253][07874] Decorrelating experience for 0 frames...
+[2024-11-07 14:55:49,700][07870] Decorrelating experience for 32 frames...
+[2024-11-07 14:55:49,826][07872] Decorrelating experience for 64 frames...
+[2024-11-07 14:55:49,939][07871] Decorrelating experience for 64 frames...
+[2024-11-07 14:55:50,064][07885] Decorrelating experience for 64 frames...
+[2024-11-07 14:55:50,088][07874] Decorrelating experience for 32 frames...
+[2024-11-07 14:55:50,292][07870] Decorrelating experience for 64 frames...
+[2024-11-07 14:55:50,415][07873] Decorrelating experience for 0 frames...
+[2024-11-07 14:55:50,424][07866] Decorrelating experience for 64 frames...
+[2024-11-07 14:55:50,533][07872] Decorrelating experience for 96 frames...
+[2024-11-07 14:55:50,673][07884] Decorrelating experience for 64 frames...
+[2024-11-07 14:55:50,733][07871] Decorrelating experience for 96 frames...
+[2024-11-07 14:55:50,841][07885] Decorrelating experience for 96 frames...
+[2024-11-07 14:55:50,955][07870] Decorrelating experience for 96 frames...
+[2024-11-07 14:55:50,987][07873] Decorrelating experience for 32 frames...
+[2024-11-07 14:55:51,133][07866] Decorrelating experience for 96 frames...
+[2024-11-07 14:55:51,244][07874] Decorrelating experience for 64 frames...
+[2024-11-07 14:55:51,659][07873] Decorrelating experience for 64 frames...
+[2024-11-07 14:55:51,785][07874] Decorrelating experience for 96 frames...
+[2024-11-07 14:55:51,817][07884] Decorrelating experience for 96 frames...
+[2024-11-07 14:55:52,517][07873] Decorrelating experience for 96 frames...
+[2024-11-07 14:55:54,118][04584] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 8007680. Throughput: 0: 231.1. Samples: 1156. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-11-07 14:55:54,125][07852] Signal inference workers to stop experience collection...
+[2024-11-07 14:55:54,125][04584] Avg episode reward: [(0, '2.241')]
+[2024-11-07 14:55:54,133][07865] InferenceWorker_p0-w0: stopping experience collection
+[2024-11-07 14:55:56,697][04584] Heartbeat connected on Batcher_0
+[2024-11-07 14:55:56,708][04584] Heartbeat connected on InferenceWorker_p0-w0
+[2024-11-07 14:55:56,717][04584] Heartbeat connected on RolloutWorker_w0
+[2024-11-07 14:55:56,721][04584] Heartbeat connected on RolloutWorker_w1
+[2024-11-07 14:55:56,726][04584] Heartbeat connected on RolloutWorker_w2
+[2024-11-07 14:55:56,738][04584] Heartbeat connected on RolloutWorker_w5
+[2024-11-07 14:55:56,742][04584] Heartbeat connected on RolloutWorker_w3
+[2024-11-07 14:55:56,744][04584] Heartbeat connected on RolloutWorker_w6
+[2024-11-07 14:55:56,746][04584] Heartbeat connected on RolloutWorker_w4
+[2024-11-07 14:55:56,749][04584] Heartbeat connected on RolloutWorker_w7
+[2024-11-07 14:55:59,116][04584] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 8007680. Throughput: 0: 272.4. Samples: 2724. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-11-07 14:55:59,117][04584] Avg episode reward: [(0, '2.386')]
+[2024-11-07 14:56:04,116][04584] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 8007680. Throughput: 0: 181.6. Samples: 2724. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-11-07 14:56:04,121][04584] Avg episode reward: [(0, '2.386')]
+[2024-11-07 14:56:06,231][07852] Signal inference workers to resume experience collection...
+[2024-11-07 14:56:06,233][07865] InferenceWorker_p0-w0: resuming experience collection
+[2024-11-07 14:56:06,236][07852] Stopping Batcher_0...
+[2024-11-07 14:56:06,237][07852] Loop batcher_evt_loop terminating...
+[2024-11-07 14:56:06,247][04584] Component Batcher_0 stopped!
+[2024-11-07 14:56:06,361][04584] Component RolloutWorker_w0 stopped!
+[2024-11-07 14:56:06,362][07866] Stopping RolloutWorker_w0...
+[2024-11-07 14:56:06,365][07866] Loop rollout_proc0_evt_loop terminating...
+[2024-11-07 14:56:06,366][07874] Stopping RolloutWorker_w5...
+[2024-11-07 14:56:06,367][07874] Loop rollout_proc5_evt_loop terminating...
+[2024-11-07 14:56:06,366][04584] Component RolloutWorker_w5 stopped!
+[2024-11-07 14:56:06,377][07865] Weights refcount: 2 0
+[2024-11-07 14:56:06,422][07865] Stopping InferenceWorker_p0-w0...
+[2024-11-07 14:56:06,423][07865] Loop inference_proc0-0_evt_loop terminating...
+[2024-11-07 14:56:06,422][04584] Component InferenceWorker_p0-w0 stopped!
+[2024-11-07 14:56:06,461][07884] Stopping RolloutWorker_w6...
+[2024-11-07 14:56:06,462][07884] Loop rollout_proc6_evt_loop terminating...
+[2024-11-07 14:56:06,461][04584] Component RolloutWorker_w6 stopped!
+[2024-11-07 14:56:06,467][07871] Stopping RolloutWorker_w3...
+[2024-11-07 14:56:06,468][07871] Loop rollout_proc3_evt_loop terminating...
+[2024-11-07 14:56:06,468][04584] Component RolloutWorker_w3 stopped!
+[2024-11-07 14:56:06,479][07872] Stopping RolloutWorker_w4...
+[2024-11-07 14:56:06,479][07872] Loop rollout_proc4_evt_loop terminating...
+[2024-11-07 14:56:06,479][04584] Component RolloutWorker_w4 stopped!
+[2024-11-07 14:56:06,516][07885] Stopping RolloutWorker_w7...
+[2024-11-07 14:56:06,515][04584] Component RolloutWorker_w7 stopped!
+[2024-11-07 14:56:06,517][07885] Loop rollout_proc7_evt_loop terminating...
+[2024-11-07 14:56:06,608][07870] Stopping RolloutWorker_w2...
+[2024-11-07 14:56:06,609][07870] Loop rollout_proc2_evt_loop terminating...
+[2024-11-07 14:56:06,610][04584] Component RolloutWorker_w2 stopped!
+[2024-11-07 14:56:06,634][07873] Stopping RolloutWorker_w1...
+[2024-11-07 14:56:06,635][04584] Component RolloutWorker_w1 stopped!
+[2024-11-07 14:56:06,640][07873] Loop rollout_proc1_evt_loop terminating...
+[2024-11-07 14:56:07,253][07852] Saving /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/checkpoint_p0/checkpoint_000001957_8015872.pth...
+[2024-11-07 14:56:07,252][04584] Heartbeat connected on LearnerWorker_p0
+[2024-11-07 14:56:07,807][07852] Removing /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/checkpoint_p0/checkpoint_000001806_7397376.pth
+[2024-11-07 14:56:07,821][07852] Saving /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/checkpoint_p0/checkpoint_000001957_8015872.pth...
+[2024-11-07 14:56:08,058][07852] Stopping LearnerWorker_p0...
+[2024-11-07 14:56:08,058][07852] Loop learner_proc0_evt_loop terminating...
+[2024-11-07 14:56:08,073][04584] Component LearnerWorker_p0 stopped!
+[2024-11-07 14:56:08,075][04584] Waiting for process learner_proc0 to stop...
+[2024-11-07 14:56:09,968][04584] Waiting for process inference_proc0-0 to join...
+[2024-11-07 14:56:09,970][04584] Waiting for process rollout_proc0 to join...
+[2024-11-07 14:56:09,971][04584] Waiting for process rollout_proc1 to join...
+[2024-11-07 14:56:09,973][04584] Waiting for process rollout_proc2 to join...
+[2024-11-07 14:56:09,975][04584] Waiting for process rollout_proc3 to join...
+[2024-11-07 14:56:09,978][04584] Waiting for process rollout_proc4 to join...
+[2024-11-07 14:56:09,980][04584] Waiting for process rollout_proc5 to join...
+[2024-11-07 14:56:09,982][04584] Waiting for process rollout_proc6 to join...
+[2024-11-07 14:56:09,985][04584] Waiting for process rollout_proc7 to join...
+[2024-11-07 14:56:09,988][04584] Batcher 0 profile tree view:
+batching: 0.0548, releasing_batches: 0.0018
+[2024-11-07 14:56:09,990][04584] InferenceWorker_p0-w0 profile tree view:
+update_model: 0.0160
+wait_policy: 0.0005
+  wait_policy_total: 3.7567
+one_step: 0.0108
+  handle_policy_step: 3.3550
+    deserialize: 0.0684, stack: 0.0110, obs_to_device_normalize: 0.7746, forward: 2.0215, send_messages: 0.1367
+    prepare_outputs: 0.2665
+      to_cpu: 0.1882
+[2024-11-07 14:56:09,992][04584] Learner 0 profile tree view:
+misc: 0.0001, prepare_batch: 2.3351
+train: 11.7240
+  epoch_init: 0.0001, minibatch_init: 0.0000, losses_postprocess: 0.0015, kl_divergence: 0.4367, after_optimizer: 0.9795
+  calculate_losses: 2.5855
+    losses_init: 0.0000, forward_head: 0.4665, bptt_initial: 1.1746, tail: 0.3188, advantages_returns: 0.0022, losses: 0.4083
+    bptt: 0.2146
+      bptt_forward_core: 0.2144
+  update: 7.7171
+    clip: 0.6435
+[2024-11-07 14:56:09,993][04584] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.0039, enqueue_policy_requests: 0.0693, env_step: 0.7017, overhead: 0.0387, complete_rollouts: 0.0014
+save_policy_outputs: 0.0719
+  split_output_tensors: 0.0275
+[2024-11-07 14:56:09,996][04584] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.0008, enqueue_policy_requests: 0.0552, env_step: 1.1240, overhead: 0.0403, complete_rollouts: 0.0010
+save_policy_outputs: 0.0683
+  split_output_tensors: 0.0209
+[2024-11-07 14:56:10,000][04584] Loop Runner_EvtLoop terminating...
+[2024-11-07 14:56:10,003][04584] Runner profile tree view:
+main_loop: 33.2571
+[2024-11-07 14:56:10,006][04584] Collected {0: 8015872}, FPS: 246.3
+[2024-11-07 14:56:10,173][04584] Loading existing experiment configuration from /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/config.json
+[2024-11-07 14:56:10,175][04584] Overriding arg 'num_workers' with value 4 passed from command line
+[2024-11-07 14:56:10,177][04584] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-11-07 14:56:10,179][04584] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-11-07 14:56:10,182][04584] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-11-07 14:56:10,184][04584] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-11-07 14:56:10,185][04584] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2024-11-07 14:56:10,187][04584] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-11-07 14:56:10,189][04584] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2024-11-07 14:56:10,191][04584] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2024-11-07 14:56:10,193][04584] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-11-07 14:56:10,194][04584] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-11-07 14:56:10,195][04584] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-11-07 14:56:10,197][04584] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-11-07 14:56:10,202][04584] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-11-07 14:56:10,254][04584] RunningMeanStd input shape: (3, 72, 128)
+[2024-11-07 14:56:10,256][04584] RunningMeanStd input shape: (1,)
+[2024-11-07 14:56:10,293][04584] ConvEncoder: input_channels=3
+[2024-11-07 14:56:10,355][04584] Conv encoder output size: 512
+[2024-11-07 14:56:10,357][04584] Policy head output size: 512
+[2024-11-07 14:56:10,406][04584] Loading state from checkpoint /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/checkpoint_p0/checkpoint_000001957_8015872.pth...
+[2024-11-07 14:56:13,878][04584] Num frames 100...
+[2024-11-07 14:56:14,106][04584] Num frames 200...
+[2024-11-07 14:56:14,341][04584] Num frames 300...
+[2024-11-07 14:56:14,572][04584] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
+[2024-11-07 14:56:14,574][04584] Avg episode reward: 3.840, avg true_objective: 3.840
+[2024-11-07 14:56:14,609][04584] Num frames 400...
+[2024-11-07 14:56:14,867][04584] Num frames 500...
+[2024-11-07 14:56:15,349][04584] Num frames 600...
+[2024-11-07 14:56:16,008][04584] Num frames 700...
+[2024-11-07 14:56:16,669][04584] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
+[2024-11-07 14:56:16,683][04584] Avg episode reward: 3.840, avg true_objective: 3.840
+[2024-11-07 14:56:16,990][04584] Num frames 800...
+[2024-11-07 14:56:17,996][04584] Num frames 900...
+[2024-11-07 14:56:18,675][04584] Num frames 1000...
+[2024-11-07 14:56:19,397][04584] Num frames 1100...
+[2024-11-07 14:56:19,814][04584] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
+[2024-11-07 14:56:19,818][04584] Avg episode reward: 3.840, avg true_objective: 3.840
+[2024-11-07 14:56:20,211][04584] Num frames 1200...
+[2024-11-07 14:56:20,758][04584] Num frames 1300...
+[2024-11-07 14:56:21,379][04584] Num frames 1400...
+[2024-11-07 14:56:21,844][04584] Num frames 1500...
+[2024-11-07 14:56:22,003][04584] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
+[2024-11-07 14:56:22,005][04584] Avg episode reward: 3.840, avg true_objective: 3.840
+[2024-11-07 14:56:22,207][04584] Num frames 1600...
+[2024-11-07 14:56:22,423][04584] Num frames 1700...
+[2024-11-07 14:56:22,654][04584] Num frames 1800...
+[2024-11-07 14:56:22,864][04584] Num frames 1900...
+[2024-11-07 14:56:22,961][04584] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
+[2024-11-07 14:56:22,962][04584] Avg episode reward: 3.840, avg true_objective: 3.840
+[2024-11-07 14:56:23,201][04584] Num frames 2000...
+[2024-11-07 14:56:23,415][04584] Num frames 2100...
+[2024-11-07 14:56:23,717][04584] Num frames 2200...
+[2024-11-07 14:56:23,940][04584] Num frames 2300...
+[2024-11-07 14:56:24,003][04584] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
+[2024-11-07 14:56:24,005][04584] Avg episode reward: 3.840, avg true_objective: 3.840
+[2024-11-07 14:56:24,222][04584] Num frames 2400...
+[2024-11-07 14:56:24,428][04584] Num frames 2500...
+[2024-11-07 14:56:24,677][04584] Num frames 2600...
+[2024-11-07 14:56:24,929][04584] Num frames 2700...
+[2024-11-07 14:56:25,159][04584] Num frames 2800...
+[2024-11-07 14:56:25,249][04584] Avg episode rewards: #0: 4.309, true rewards: #0: 4.023
+[2024-11-07 14:56:25,250][04584] Avg episode reward: 4.309, avg true_objective: 4.023
+[2024-11-07 14:56:25,442][04584] Num frames 2900...
+[2024-11-07 14:56:25,633][04584] Num frames 3000...
+[2024-11-07 14:56:25,835][04584] Num frames 3100...
+[2024-11-07 14:56:26,055][04584] Num frames 3200...
+[2024-11-07 14:56:26,248][04584] Avg episode rewards: #0: 4.455, true rewards: #0: 4.080
+[2024-11-07 14:56:26,251][04584] Avg episode reward: 4.455, avg true_objective: 4.080
+[2024-11-07 14:56:26,359][04584] Num frames 3300...
+[2024-11-07 14:56:26,561][04584] Num frames 3400...
+[2024-11-07 14:56:26,732][04584] Num frames 3500...
+[2024-11-07 14:56:26,889][04584] Num frames 3600...
+[2024-11-07 14:56:27,027][04584] Avg episode rewards: #0: 4.387, true rewards: #0: 4.053
+[2024-11-07 14:56:27,030][04584] Avg episode reward: 4.387, avg true_objective: 4.053
+[2024-11-07 14:56:27,125][04584] Num frames 3700...
+[2024-11-07 14:56:27,303][04584] Num frames 3800...
+[2024-11-07 14:56:27,472][04584] Num frames 3900...
+[2024-11-07 14:56:27,634][04584] Num frames 4000...
+[2024-11-07 14:56:27,752][04584] Avg episode rewards: #0: 4.332, true rewards: #0: 4.032
+[2024-11-07 14:56:27,754][04584] Avg episode reward: 4.332, avg true_objective: 4.032
+[2024-11-07 14:56:40,409][04584] Replay video saved to /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/replay.mp4!
+[2024-11-07 14:56:40,960][04584] Loading existing experiment configuration from /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/config.json
+[2024-11-07 14:56:40,962][04584] Overriding arg 'num_workers' with value 4 passed from command line
+[2024-11-07 14:56:40,964][04584] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-11-07 14:56:40,966][04584] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-11-07 14:56:40,973][04584] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-11-07 14:56:40,976][04584] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-11-07 14:56:40,979][04584] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2024-11-07 14:56:40,988][04584] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-11-07 14:56:40,990][04584] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2024-11-07 14:56:40,993][04584] Adding new argument 'hf_repository'='alidenewade/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2024-11-07 14:56:40,995][04584] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-11-07 14:56:40,996][04584] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-11-07 14:56:41,005][04584] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-11-07 14:56:41,007][04584] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-11-07 14:56:41,009][04584] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-11-07 14:56:41,091][04584] RunningMeanStd input shape: (3, 72, 128)
+[2024-11-07 14:56:41,095][04584] RunningMeanStd input shape: (1,)
+[2024-11-07 14:56:41,124][04584] ConvEncoder: input_channels=3
+[2024-11-07 14:56:41,187][04584] Conv encoder output size: 512
+[2024-11-07 14:56:41,188][04584] Policy head output size: 512
+[2024-11-07 14:56:41,211][04584] Loading state from checkpoint /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/checkpoint_p0/checkpoint_000001957_8015872.pth...
+[2024-11-07 14:56:41,745][04584] Num frames 100...
+[2024-11-07 14:56:41,957][04584] Num frames 200...
+[2024-11-07 14:56:42,160][04584] Num frames 300...
+[2024-11-07 14:56:42,410][04584] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
+[2024-11-07 14:56:42,414][04584] Avg episode reward: 3.840, avg true_objective: 3.840
+[2024-11-07 14:56:42,475][04584] Num frames 400...
+[2024-11-07 14:56:42,737][04584] Num frames 500...
+[2024-11-07 14:56:43,040][04584] Num frames 600...
+[2024-11-07 14:56:43,312][04584] Num frames 700...
+[2024-11-07 14:56:43,592][04584] Num frames 800...
+[2024-11-07 14:56:43,713][04584] Avg episode rewards: #0: 4.660, true rewards: #0: 4.160
+[2024-11-07 14:56:43,714][04584] Avg episode reward: 4.660, avg true_objective: 4.160
+[2024-11-07 14:56:43,872][04584] Num frames 900...
+[2024-11-07 14:56:44,191][04584] Num frames 1000...
+[2024-11-07 14:56:44,433][04584] Num frames 1100...
+[2024-11-07 14:56:44,628][04584] Num frames 1200...
+[2024-11-07 14:56:44,766][04584] Avg episode rewards: #0: 4.827, true rewards: #0: 4.160
+[2024-11-07 14:56:44,772][04584] Avg episode reward: 4.827, avg true_objective: 4.160
+[2024-11-07 14:56:44,879][04584] Num frames 1300...
+[2024-11-07 14:56:45,064][04584] Num frames 1400...
+[2024-11-07 14:56:45,236][04584] Num frames 1500...
+[2024-11-07 14:56:45,421][04584] Num frames 1600...
+[2024-11-07 14:56:47,592][04584] Avg episode rewards: #0: 4.580, true rewards: #0: 4.080
+[2024-11-07 14:56:47,594][04584] Avg episode reward: 4.580, avg true_objective: 4.080
+[2024-11-07 14:56:47,724][04584] Num frames 1700...
+[2024-11-07 14:56:47,905][04584] Num frames 1800...
+[2024-11-07 14:56:48,109][04584] Num frames 1900...
+[2024-11-07 14:56:48,295][04584] Num frames 2000...
+[2024-11-07 14:56:48,425][04584] Avg episode rewards: #0: 4.680, true rewards: #0: 4.080
+[2024-11-07 14:56:48,428][04584] Avg episode reward: 4.680, avg true_objective: 4.080
+[2024-11-07 14:56:48,562][04584] Num frames 2100...
+[2024-11-07 14:56:48,738][04584] Num frames 2200...
+[2024-11-07 14:56:48,913][04584] Num frames 2300...
+[2024-11-07 14:56:49,095][04584] Num frames 2400...
+[2024-11-07 14:56:49,191][04584] Avg episode rewards: #0: 4.540, true rewards: #0: 4.040
+[2024-11-07 14:56:49,193][04584] Avg episode reward: 4.540, avg true_objective: 4.040
+[2024-11-07 14:56:49,333][04584] Num frames 2500...
+[2024-11-07 14:56:49,501][04584] Num frames 2600...
+[2024-11-07 14:56:49,658][04584] Num frames 2700...
+[2024-11-07 14:56:49,848][04584] Num frames 2800...
+[2024-11-07 14:56:49,918][04584] Avg episode rewards: #0: 4.440, true rewards: #0: 4.011
+[2024-11-07 14:56:49,921][04584] Avg episode reward: 4.440, avg true_objective: 4.011
+[2024-11-07 14:56:50,094][04584] Num frames 2900...
+[2024-11-07 14:56:50,431][04584] Num frames 3000...
+[2024-11-07 14:56:50,666][04584] Num frames 3100...
+[2024-11-07 14:56:50,917][04584] Avg episode rewards: #0: 4.365, true rewards: #0: 3.990
+[2024-11-07 14:56:50,920][04584] Avg episode reward: 4.365, avg true_objective: 3.990
+[2024-11-07 14:56:50,945][04584] Num frames 3200...
+[2024-11-07 14:56:51,105][04584] Num frames 3300...
+[2024-11-07 14:56:51,283][04584] Num frames 3400...
+[2024-11-07 14:56:51,493][04584] Num frames 3500...
+[2024-11-07 14:56:51,666][04584] Num frames 3600...
+[2024-11-07 14:56:51,793][04584] Avg episode rewards: #0: 4.489, true rewards: #0: 4.044
+[2024-11-07 14:56:51,795][04584] Avg episode reward: 4.489, avg true_objective: 4.044
+[2024-11-07 14:56:51,923][04584] Num frames 3700...
+[2024-11-07 14:56:52,126][04584] Num frames 3800...
+[2024-11-07 14:56:52,324][04584] Num frames 3900...
+[2024-11-07 14:56:52,514][04584] Num frames 4000...
+[2024-11-07 14:56:52,732][04584] Avg episode rewards: #0: 4.588, true rewards: #0: 4.088
+[2024-11-07 14:56:52,736][04584] Avg episode reward: 4.588, avg true_objective: 4.088
+[2024-11-07 14:57:02,444][04584] Replay video saved to /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/replay.mp4!