Hugging Face's logo

rahatchd
/
rl_course_vizdoom_health_gathering_supreme

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results
Model card Files Metrics Community
rahatchd commited on
Commit
c249454
·
verified ·
1 Parent(s): c7cb1e8

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. .summary/0/events.out.tfevents.1733610845.anne-hackaway +3 -0
  3. README.md +56 -0
  4. checkpoint_p0/best_000000772_3162112_reward_27.345.pth +3 -0
  5. checkpoint_p0/checkpoint_000000597_2445312.pth +3 -0
  6. checkpoint_p0/checkpoint_000000978_4005888.pth +3 -0
  7. config.json +142 -0
  8. replay.mp4 +3 -0
  9. sf_log.txt +684 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ replay.mp4 filter=lfs diff=lfs merge=lfs -text
.summary/0/events.out.tfevents.1733610845.anne-hackaway ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c68d0ef779fba2176f6062c4d377d995b16fad6a762482378daedd0dcef83dd4
3
+ size 178181
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: sample-factory
3
+ tags:
4
+ - deep-reinforcement-learning
5
+ - reinforcement-learning
6
+ - sample-factory
7
+ model-index:
8
+ - name: APPO
9
+ results:
10
+ - task:
11
+ type: reinforcement-learning
12
+ name: reinforcement-learning
13
+ dataset:
14
+ name: doom_health_gathering_supreme
15
+ type: doom_health_gathering_supreme
16
+ metrics:
17
+ - type: mean_reward
18
+ value: 9.26 +/- 3.64
19
+ name: mean_reward
20
+ verified: false
21
+ ---
22
+
23
+ A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
24
+
25
+ This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
26
+ Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
27
+
28
+
29
+ ## Downloading the model
30
+
31
+ After installing Sample-Factory, download the model with:
32
+ ```
33
+ python -m sample_factory.huggingface.load_from_hub -r rahatchd/rl_course_vizdoom_health_gathering_supreme
34
+ ```
35
+
36
+
37
+ ## Using the model
38
+
39
+ To run the model after download, use the `enjoy` script corresponding to this environment:
40
+ ```
41
+ python -m <path.to.enjoy.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
42
+ ```
43
+
44
+
45
+ You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
46
+ See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
47
+
48
+ ## Training with this model
49
+
50
+ To continue training with this model, use the `train` script corresponding to this environment:
51
+ ```
52
+ python -m <path.to.train.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
53
+ ```
54
+
55
+ Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
56
+
checkpoint_p0/best_000000772_3162112_reward_27.345.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d8e625029d33f15f0e7532db24d3216e76835b42f57e98b81bb644445e0170f
3
+ size 34929051
checkpoint_p0/checkpoint_000000597_2445312.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99bd23c65514c90b23ba61f9f656d13b4d5a68e7874f60e591e7d1c2f3daee5e
3
+ size 34929541
checkpoint_p0/checkpoint_000000978_4005888.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3acc9971f7b95b9c1771bb994c387d39bf679edec2fe807449ccf824f4fd7b2d
3
+ size 34929477
config.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "help": false,
3
+ "algo": "APPO",
4
+ "env": "doom_health_gathering_supreme",
5
+ "experiment": "default_experiment",
6
+ "train_dir": "/home/rahatchd/code/deep-rl-hugging-face/unit8/train_dir",
7
+ "restart_behavior": "resume",
8
+ "device": "gpu",
9
+ "seed": null,
10
+ "num_policies": 1,
11
+ "async_rl": true,
12
+ "serial_mode": false,
13
+ "batched_sampling": false,
14
+ "num_batches_to_accumulate": 2,
15
+ "worker_num_splits": 2,
16
+ "policy_workers_per_policy": 1,
17
+ "max_policy_lag": 1000,
18
+ "num_workers": 8,
19
+ "num_envs_per_worker": 4,
20
+ "batch_size": 1024,
21
+ "num_batches_per_epoch": 1,
22
+ "num_epochs": 1,
23
+ "rollout": 32,
24
+ "recurrence": 32,
25
+ "shuffle_minibatches": false,
26
+ "gamma": 0.99,
27
+ "reward_scale": 1.0,
28
+ "reward_clip": 1000.0,
29
+ "value_bootstrap": false,
30
+ "normalize_returns": true,
31
+ "exploration_loss_coeff": 0.001,
32
+ "value_loss_coeff": 0.5,
33
+ "kl_loss_coeff": 0.0,
34
+ "exploration_loss": "symmetric_kl",
35
+ "gae_lambda": 0.95,
36
+ "ppo_clip_ratio": 0.1,
37
+ "ppo_clip_value": 0.2,
38
+ "with_vtrace": false,
39
+ "vtrace_rho": 1.0,
40
+ "vtrace_c": 1.0,
41
+ "optimizer": "adam",
42
+ "adam_eps": 1e-06,
43
+ "adam_beta1": 0.9,
44
+ "adam_beta2": 0.999,
45
+ "max_grad_norm": 4.0,
46
+ "learning_rate": 0.0001,
47
+ "lr_schedule": "constant",
48
+ "lr_schedule_kl_threshold": 0.008,
49
+ "lr_adaptive_min": 1e-06,
50
+ "lr_adaptive_max": 0.01,
51
+ "obs_subtract_mean": 0.0,
52
+ "obs_scale": 255.0,
53
+ "normalize_input": true,
54
+ "normalize_input_keys": null,
55
+ "decorrelate_experience_max_seconds": 0,
56
+ "decorrelate_envs_on_one_worker": true,
57
+ "actor_worker_gpus": [],
58
+ "set_workers_cpu_affinity": true,
59
+ "force_envs_single_thread": false,
60
+ "default_niceness": 0,
61
+ "log_to_file": true,
62
+ "experiment_summaries_interval": 10,
63
+ "flush_summaries_interval": 30,
64
+ "stats_avg": 100,
65
+ "summaries_use_frameskip": true,
66
+ "heartbeat_interval": 20,
67
+ "heartbeat_reporting_interval": 600,
68
+ "train_for_env_steps": 4000000,
69
+ "train_for_seconds": 10000000000,
70
+ "save_every_sec": 120,
71
+ "keep_checkpoints": 2,
72
+ "load_checkpoint_kind": "latest",
73
+ "save_milestones_sec": -1,
74
+ "save_best_every_sec": 5,
75
+ "save_best_metric": "reward",
76
+ "save_best_after": 100000,
77
+ "benchmark": false,
78
+ "encoder_mlp_layers": [
79
+ 512,
80
+ 512
81
+ ],
82
+ "encoder_conv_architecture": "convnet_simple",
83
+ "encoder_conv_mlp_layers": [
84
+ 512
85
+ ],
86
+ "use_rnn": true,
87
+ "rnn_size": 512,
88
+ "rnn_type": "gru",
89
+ "rnn_num_layers": 1,
90
+ "decoder_mlp_layers": [],
91
+ "nonlinearity": "elu",
92
+ "policy_initialization": "orthogonal",
93
+ "policy_init_gain": 1.0,
94
+ "actor_critic_share_weights": true,
95
+ "adaptive_stddev": true,
96
+ "continuous_tanh_scale": 0.0,
97
+ "initial_stddev": 1.0,
98
+ "use_env_info_cache": false,
99
+ "env_gpu_actions": false,
100
+ "env_gpu_observations": true,
101
+ "env_frameskip": 4,
102
+ "env_framestack": 1,
103
+ "pixel_format": "CHW",
104
+ "use_record_episode_statistics": false,
105
+ "with_wandb": false,
106
+ "wandb_user": null,
107
+ "wandb_project": "sample_factory",
108
+ "wandb_group": null,
109
+ "wandb_job_type": "SF",
110
+ "wandb_tags": [],
111
+ "with_pbt": false,
112
+ "pbt_mix_policies_in_one_env": true,
113
+ "pbt_period_env_steps": 5000000,
114
+ "pbt_start_mutation": 20000000,
115
+ "pbt_replace_fraction": 0.3,
116
+ "pbt_mutation_rate": 0.15,
117
+ "pbt_replace_reward_gap": 0.1,
118
+ "pbt_replace_reward_gap_absolute": 1e-06,
119
+ "pbt_optimize_gamma": false,
120
+ "pbt_target_objective": "true_objective",
121
+ "pbt_perturb_min": 1.1,
122
+ "pbt_perturb_max": 1.5,
123
+ "num_agents": -1,
124
+ "num_humans": 0,
125
+ "num_bots": -1,
126
+ "start_bot_difficulty": null,
127
+ "timelimit": null,
128
+ "res_w": 128,
129
+ "res_h": 72,
130
+ "wide_aspect_ratio": false,
131
+ "eval_env_frameskip": 1,
132
+ "fps": 35,
133
+ "command_line": "--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=4000000",
134
+ "cli_args": {
135
+ "env": "doom_health_gathering_supreme",
136
+ "num_workers": 8,
137
+ "num_envs_per_worker": 4,
138
+ "train_for_env_steps": 4000000
139
+ },
140
+ "git_hash": "unknown",
141
+ "git_repo_name": "not a git repository"
142
+ }
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:771a84f36fff5a9f6c0f347eb2570410f7c1f0c413dbb8fe45b841c6ac9e0482
3
+ size 17446371
sf_log.txt ADDED
@@ -0,0 +1,684 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [2024-12-07 14:34:08,376][19013] Saving configuration to /home/rahatchd/code/deep-rl-hugging-face/unit8/train_dir/default_experiment/config.json...
2
+ [2024-12-07 14:34:08,376][19013] Rollout worker 0 uses device cpu
3
+ [2024-12-07 14:34:08,377][19013] Rollout worker 1 uses device cpu
4
+ [2024-12-07 14:34:08,377][19013] Rollout worker 2 uses device cpu
5
+ [2024-12-07 14:34:08,377][19013] Rollout worker 3 uses device cpu
6
+ [2024-12-07 14:34:08,378][19013] Rollout worker 4 uses device cpu
7
+ [2024-12-07 14:34:08,378][19013] Rollout worker 5 uses device cpu
8
+ [2024-12-07 14:34:08,378][19013] Rollout worker 6 uses device cpu
9
+ [2024-12-07 14:34:08,379][19013] Rollout worker 7 uses device cpu
10
+ [2024-12-07 14:34:08,444][19013] Using GPUs [0] for process 0 (actually maps to GPUs [0])
11
+ [2024-12-07 14:34:08,444][19013] InferenceWorker_p0-w0: min num requests: 2
12
+ [2024-12-07 14:34:08,474][19013] Starting all processes...
13
+ [2024-12-07 14:34:08,474][19013] Starting process learner_proc0
14
+ [2024-12-07 14:34:08,524][19013] Starting all processes...
15
+ [2024-12-07 14:34:08,528][19013] Starting process inference_proc0-0
16
+ [2024-12-07 14:34:08,528][19013] Starting process rollout_proc0
17
+ [2024-12-07 14:34:08,528][19013] Starting process rollout_proc1
18
+ [2024-12-07 14:34:08,529][19013] Starting process rollout_proc2
19
+ [2024-12-07 14:34:08,529][19013] Starting process rollout_proc3
20
+ [2024-12-07 14:34:08,529][19013] Starting process rollout_proc4
21
+ [2024-12-07 14:34:08,530][19013] Starting process rollout_proc5
22
+ [2024-12-07 14:34:08,530][19013] Starting process rollout_proc6
23
+ [2024-12-07 14:34:08,530][19013] Starting process rollout_proc7
24
+ [2024-12-07 14:34:09,922][23822] Worker 3 uses CPU cores [9, 10, 11]
25
+ [2024-12-07 14:34:09,956][23826] Worker 7 uses CPU cores [21, 22, 23]
26
+ [2024-12-07 14:34:09,973][23806] Using GPUs [0] for process 0 (actually maps to GPUs [0])
27
+ [2024-12-07 14:34:09,973][23806] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
28
+ [2024-12-07 14:34:09,975][23824] Worker 5 uses CPU cores [15, 16, 17]
29
+ [2024-12-07 14:34:09,976][23827] Worker 6 uses CPU cores [18, 19, 20]
30
+ [2024-12-07 14:34:09,988][23806] Num visible devices: 1
31
+ [2024-12-07 14:34:09,994][23825] Worker 2 uses CPU cores [6, 7, 8]
32
+ [2024-12-07 14:34:09,996][23820] Worker 0 uses CPU cores [0, 1, 2]
33
+ [2024-12-07 14:34:10,005][23806] Starting seed is not provided
34
+ [2024-12-07 14:34:10,005][23806] Using GPUs [0] for process 0 (actually maps to GPUs [0])
35
+ [2024-12-07 14:34:10,006][23806] Initializing actor-critic model on device cuda:0
36
+ [2024-12-07 14:34:10,006][23806] RunningMeanStd input shape: (3, 72, 128)
37
+ [2024-12-07 14:34:10,007][23806] RunningMeanStd input shape: (1,)
38
+ [2024-12-07 14:34:10,015][23806] ConvEncoder: input_channels=3
39
+ [2024-12-07 14:34:10,022][23821] Worker 1 uses CPU cores [3, 4, 5]
40
+ [2024-12-07 14:34:10,045][23823] Worker 4 uses CPU cores [12, 13, 14]
41
+ [2024-12-07 14:34:10,090][23819] Using GPUs [0] for process 0 (actually maps to GPUs [0])
42
+ [2024-12-07 14:34:10,091][23819] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
43
+ [2024-12-07 14:34:10,105][23819] Num visible devices: 1
44
+ [2024-12-07 14:34:10,112][23806] Conv encoder output size: 512
45
+ [2024-12-07 14:34:10,113][23806] Policy head output size: 512
46
+ [2024-12-07 14:34:10,131][23806] Created Actor Critic model with architecture:
47
+ [2024-12-07 14:34:10,131][23806] ActorCriticSharedWeights(
48
+ (obs_normalizer): ObservationNormalizer(
49
+ (running_mean_std): RunningMeanStdDictInPlace(
50
+ (running_mean_std): ModuleDict(
51
+ (obs): RunningMeanStdInPlace()
52
+ )
53
+ )
54
+ )
55
+ (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
56
+ (encoder): VizdoomEncoder(
57
+ (basic_encoder): ConvEncoder(
58
+ (enc): RecursiveScriptModule(
59
+ original_name=ConvEncoderImpl
60
+ (conv_head): RecursiveScriptModule(
61
+ original_name=Sequential
62
+ (0): RecursiveScriptModule(original_name=Conv2d)
63
+ (1): RecursiveScriptModule(original_name=ELU)
64
+ (2): RecursiveScriptModule(original_name=Conv2d)
65
+ (3): RecursiveScriptModule(original_name=ELU)
66
+ (4): RecursiveScriptModule(original_name=Conv2d)
67
+ (5): RecursiveScriptModule(original_name=ELU)
68
+ )
69
+ (mlp_layers): RecursiveScriptModule(
70
+ original_name=Sequential
71
+ (0): RecursiveScriptModule(original_name=Linear)
72
+ (1): RecursiveScriptModule(original_name=ELU)
73
+ )
74
+ )
75
+ )
76
+ )
77
+ (core): ModelCoreRNN(
78
+ (core): GRU(512, 512)
79
+ )
80
+ (decoder): MlpDecoder(
81
+ (mlp): Identity()
82
+ )
83
+ (critic_linear): Linear(in_features=512, out_features=1, bias=True)
84
+ (action_parameterization): ActionParameterizationDefault(
85
+ (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
86
+ )
87
+ )
88
+ [2024-12-07 14:34:10,276][23806] Using optimizer <class 'torch.optim.adam.Adam'>
89
+ [2024-12-07 14:34:11,044][23806] No checkpoints found
90
+ [2024-12-07 14:34:11,044][23806] Did not load from checkpoint, starting from scratch!
91
+ [2024-12-07 14:34:11,044][23806] Initialized policy 0 weights for model version 0
92
+ [2024-12-07 14:34:11,046][23806] LearnerWorker_p0 finished initialization!
93
+ [2024-12-07 14:34:11,046][23806] Using GPUs [0] for process 0 (actually maps to GPUs [0])
94
+ [2024-12-07 14:34:11,160][23819] RunningMeanStd input shape: (3, 72, 128)
95
+ [2024-12-07 14:34:11,160][23819] RunningMeanStd input shape: (1,)
96
+ [2024-12-07 14:34:11,167][23819] ConvEncoder: input_channels=3
97
+ [2024-12-07 14:34:11,230][23819] Conv encoder output size: 512
98
+ [2024-12-07 14:34:11,230][23819] Policy head output size: 512
99
+ [2024-12-07 14:34:11,255][19013] Inference worker 0-0 is ready!
100
+ [2024-12-07 14:34:11,256][19013] All inference workers are ready! Signal rollout workers to start!
101
+ [2024-12-07 14:34:11,298][23820] Doom resolution: 160x120, resize resolution: (128, 72)
102
+ [2024-12-07 14:34:11,298][23823] Doom resolution: 160x120, resize resolution: (128, 72)
103
+ [2024-12-07 14:34:11,300][23821] Doom resolution: 160x120, resize resolution: (128, 72)
104
+ [2024-12-07 14:34:11,300][23824] Doom resolution: 160x120, resize resolution: (128, 72)
105
+ [2024-12-07 14:34:11,301][23822] Doom resolution: 160x120, resize resolution: (128, 72)
106
+ [2024-12-07 14:34:11,301][23826] Doom resolution: 160x120, resize resolution: (128, 72)
107
+ [2024-12-07 14:34:11,304][23825] Doom resolution: 160x120, resize resolution: (128, 72)
108
+ [2024-12-07 14:34:11,306][23827] Doom resolution: 160x120, resize resolution: (128, 72)
109
+ [2024-12-07 14:34:11,542][23824] Decorrelating experience for 0 frames...
110
+ [2024-12-07 14:34:11,542][23826] Decorrelating experience for 0 frames...
111
+ [2024-12-07 14:34:11,542][23820] Decorrelating experience for 0 frames...
112
+ [2024-12-07 14:34:11,543][23827] Decorrelating experience for 0 frames...
113
+ [2024-12-07 14:34:11,749][23827] Decorrelating experience for 32 frames...
114
+ [2024-12-07 14:34:11,749][23824] Decorrelating experience for 32 frames...
115
+ [2024-12-07 14:34:11,750][23826] Decorrelating experience for 32 frames...
116
+ [2024-12-07 14:34:11,788][23825] Decorrelating experience for 0 frames...
117
+ [2024-12-07 14:34:11,791][23823] Decorrelating experience for 0 frames...
118
+ [2024-12-07 14:34:11,993][23825] Decorrelating experience for 32 frames...
119
+ [2024-12-07 14:34:11,999][23823] Decorrelating experience for 32 frames...
120
+ [2024-12-07 14:34:12,004][23827] Decorrelating experience for 64 frames...
121
+ [2024-12-07 14:34:12,010][23826] Decorrelating experience for 64 frames...
122
+ [2024-12-07 14:34:12,234][23827] Decorrelating experience for 96 frames...
123
+ [2024-12-07 14:34:12,248][23825] Decorrelating experience for 64 frames...
124
+ [2024-12-07 14:34:12,252][23823] Decorrelating experience for 64 frames...
125
+ [2024-12-07 14:34:12,473][23825] Decorrelating experience for 96 frames...
126
+ [2024-12-07 14:34:12,507][23824] Decorrelating experience for 64 frames...
127
+ [2024-12-07 14:34:12,676][23823] Decorrelating experience for 96 frames...
128
+ [2024-12-07 14:34:12,733][23824] Decorrelating experience for 96 frames...
129
+ [2024-12-07 14:34:13,342][23806] Signal inference workers to stop experience collection...
130
+ [2024-12-07 14:34:13,344][23819] InferenceWorker_p0-w0: stopping experience collection
131
+ [2024-12-07 14:34:14,621][23806] Signal inference workers to resume experience collection...
132
+ [2024-12-07 14:34:14,621][23819] InferenceWorker_p0-w0: resuming experience collection
133
+ [2024-12-07 14:34:15,572][19013] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 20480. Throughput: 0: nan. Samples: 2290. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
134
+ [2024-12-07 14:34:15,573][19013] Avg episode reward: [(0, '3.977')]
135
+ [2024-12-07 14:34:16,809][23819] Updated weights for policy 0, policy_version 10 (0.0055)
136
+ [2024-12-07 14:34:19,427][23819] Updated weights for policy 0, policy_version 20 (0.0005)
137
+ [2024-12-07 14:34:20,572][19013] Fps is (10 sec: 15564.9, 60 sec: 15564.9, 300 sec: 15564.9). Total num frames: 98304. Throughput: 0: 4348.4. Samples: 24032. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0)
138
+ [2024-12-07 14:34:20,573][19013] Avg episode reward: [(0, '4.353')]
139
+ [2024-12-07 14:34:22,008][23819] Updated weights for policy 0, policy_version 30 (0.0005)
140
+ [2024-12-07 14:34:24,540][23819] Updated weights for policy 0, policy_version 40 (0.0005)
141
+ [2024-12-07 14:34:25,572][19013] Fps is (10 sec: 15564.9, 60 sec: 15564.9, 300 sec: 15564.9). Total num frames: 176128. Throughput: 0: 3386.4. Samples: 36154. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0)
142
+ [2024-12-07 14:34:25,573][19013] Avg episode reward: [(0, '4.445')]
143
+ [2024-12-07 14:34:25,590][23806] Saving new best policy, reward=4.445!
144
+ [2024-12-07 14:34:27,136][23819] Updated weights for policy 0, policy_version 50 (0.0005)
145
+ [2024-12-07 14:34:28,436][19013] Heartbeat connected on Batcher_0
146
+ [2024-12-07 14:34:28,440][19013] Heartbeat connected on LearnerWorker_p0
147
+ [2024-12-07 14:34:28,446][19013] Heartbeat connected on InferenceWorker_p0-w0
148
+ [2024-12-07 14:34:28,458][19013] Heartbeat connected on RolloutWorker_w2
149
+ [2024-12-07 14:34:28,464][19013] Heartbeat connected on RolloutWorker_w4
150
+ [2024-12-07 14:34:28,467][19013] Heartbeat connected on RolloutWorker_w5
151
+ [2024-12-07 14:34:28,474][19013] Heartbeat connected on RolloutWorker_w6
152
+ [2024-12-07 14:34:29,728][23819] Updated weights for policy 0, policy_version 60 (0.0005)
153
+ [2024-12-07 14:34:30,572][19013] Fps is (10 sec: 15974.3, 60 sec: 15837.9, 300 sec: 15837.9). Total num frames: 258048. Throughput: 0: 3843.9. Samples: 59948. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
154
+ [2024-12-07 14:34:30,573][19013] Avg episode reward: [(0, '4.400')]
155
+ [2024-12-07 14:34:31,330][23822] Another process currently holds the lock /tmp/sf2_rahatchd/doom_003.lockfile, attempt: 1
156
+ [2024-12-07 14:34:31,588][23820] Another process currently holds the lock /tmp/sf2_rahatchd/doom_003.lockfile, attempt: 1
157
+ [2024-12-07 14:34:32,034][23826] Another process currently holds the lock /tmp/sf2_rahatchd/doom_003.lockfile, attempt: 1
158
+ [2024-12-07 14:34:32,279][23819] Updated weights for policy 0, policy_version 70 (0.0005)
159
+ [2024-12-07 14:34:34,871][23819] Updated weights for policy 0, policy_version 80 (0.0005)
160
+ [2024-12-07 14:34:35,572][19013] Fps is (10 sec: 15974.4, 60 sec: 15769.6, 300 sec: 15769.6). Total num frames: 335872. Throughput: 0: 4069.7. Samples: 83684. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
161
+ [2024-12-07 14:34:35,573][19013] Avg episode reward: [(0, '4.238')]
162
+ [2024-12-07 14:34:37,529][23819] Updated weights for policy 0, policy_version 90 (0.0005)
163
+ [2024-12-07 14:34:40,153][23819] Updated weights for policy 0, policy_version 100 (0.0005)
164
+ [2024-12-07 14:34:40,258][23826] Decorrelating experience for 96 frames...
165
+ [2024-12-07 14:34:40,299][19013] Heartbeat connected on RolloutWorker_w7
166
+ [2024-12-07 14:34:40,520][23822] Decorrelating experience for 0 frames...
167
+ [2024-12-07 14:34:40,572][19013] Fps is (10 sec: 15564.9, 60 sec: 15728.7, 300 sec: 15728.7). Total num frames: 413696. Throughput: 0: 3723.6. Samples: 95380. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
168
+ [2024-12-07 14:34:40,573][19013] Avg episode reward: [(0, '4.623')]
169
+ [2024-12-07 14:34:40,574][23806] Saving new best policy, reward=4.623!
170
+ [2024-12-07 14:34:40,767][23820] Decorrelating experience for 32 frames...
171
+ [2024-12-07 14:34:40,779][23822] Decorrelating experience for 32 frames...
172
+ [2024-12-07 14:34:41,047][23820] Decorrelating experience for 64 frames...
173
+ [2024-12-07 14:34:41,089][23822] Decorrelating experience for 64 frames...
174
+ [2024-12-07 14:34:41,289][23820] Decorrelating experience for 96 frames...
175
+ [2024-12-07 14:34:41,334][19013] Heartbeat connected on RolloutWorker_w0
176
+ [2024-12-07 14:34:41,366][23822] Decorrelating experience for 96 frames...
177
+ [2024-12-07 14:34:41,413][19013] Heartbeat connected on RolloutWorker_w3
178
+ [2024-12-07 14:34:42,172][23819] Updated weights for policy 0, policy_version 110 (0.0006)
179
+ [2024-12-07 14:34:43,880][23819] Updated weights for policy 0, policy_version 120 (0.0006)
180
+ [2024-12-07 14:34:45,572][19013] Fps is (10 sec: 19251.0, 60 sec: 16930.1, 300 sec: 16930.1). Total num frames: 528384. Throughput: 0: 4111.3. Samples: 125628. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
181
+ [2024-12-07 14:34:45,573][19013] Avg episode reward: [(0, '4.533')]
182
+ [2024-12-07 14:34:45,636][23819] Updated weights for policy 0, policy_version 130 (0.0006)
183
+ [2024-12-07 14:34:47,368][23819] Updated weights for policy 0, policy_version 140 (0.0006)
184
+ [2024-12-07 14:34:49,090][23819] Updated weights for policy 0, policy_version 150 (0.0006)
185
+ [2024-12-07 14:34:50,572][19013] Fps is (10 sec: 23347.2, 60 sec: 17905.4, 300 sec: 17905.4). Total num frames: 647168. Throughput: 0: 4548.9. Samples: 161502. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
186
+ [2024-12-07 14:34:50,572][19013] Avg episode reward: [(0, '4.887')]
187
+ [2024-12-07 14:34:50,599][23806] Saving new best policy, reward=4.887!
188
+ [2024-12-07 14:34:50,759][23819] Updated weights for policy 0, policy_version 160 (0.0006)
189
+ [2024-12-07 14:34:52,474][23819] Updated weights for policy 0, policy_version 170 (0.0006)
190
+ [2024-12-07 14:34:54,205][23819] Updated weights for policy 0, policy_version 180 (0.0006)
191
+ [2024-12-07 14:34:55,572][19013] Fps is (10 sec: 24166.6, 60 sec: 18739.2, 300 sec: 18739.2). Total num frames: 770048. Throughput: 0: 4428.4. Samples: 179426. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
192
+ [2024-12-07 14:34:55,573][19013] Avg episode reward: [(0, '5.630')]
193
+ [2024-12-07 14:34:55,577][23806] Saving new best policy, reward=5.630!
194
+ [2024-12-07 14:34:55,906][23819] Updated weights for policy 0, policy_version 190 (0.0006)
195
+ [2024-12-07 14:34:57,612][23819] Updated weights for policy 0, policy_version 200 (0.0005)
196
+ [2024-12-07 14:34:59,318][23819] Updated weights for policy 0, policy_version 210 (0.0005)
197
+ [2024-12-07 14:35:00,572][19013] Fps is (10 sec: 24166.4, 60 sec: 19296.7, 300 sec: 19296.7). Total num frames: 888832. Throughput: 0: 4731.9. Samples: 215224. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
198
+ [2024-12-07 14:35:00,573][19013] Avg episode reward: [(0, '6.418')]
199
+ [2024-12-07 14:35:00,574][23806] Saving new best policy, reward=6.418!
200
+ [2024-12-07 14:35:01,062][23819] Updated weights for policy 0, policy_version 220 (0.0005)
201
+ [2024-12-07 14:35:02,771][23819] Updated weights for policy 0, policy_version 230 (0.0005)
202
+ [2024-12-07 14:35:04,449][23819] Updated weights for policy 0, policy_version 240 (0.0006)
203
+ [2024-12-07 14:35:05,572][19013] Fps is (10 sec: 23756.6, 60 sec: 19742.7, 300 sec: 19742.7). Total num frames: 1007616. Throughput: 0: 5050.4. Samples: 251302. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
204
+ [2024-12-07 14:35:05,573][19013] Avg episode reward: [(0, '6.368')]
205
+ [2024-12-07 14:35:06,143][23819] Updated weights for policy 0, policy_version 250 (0.0005)
206
+ [2024-12-07 14:35:07,805][23819] Updated weights for policy 0, policy_version 260 (0.0005)
207
+ [2024-12-07 14:35:09,486][23819] Updated weights for policy 0, policy_version 270 (0.0006)
208
+ [2024-12-07 14:35:10,572][19013] Fps is (10 sec: 24166.5, 60 sec: 20182.1, 300 sec: 20182.1). Total num frames: 1130496. Throughput: 0: 5188.9. Samples: 269656. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
209
+ [2024-12-07 14:35:10,572][19013] Avg episode reward: [(0, '6.861')]
210
+ [2024-12-07 14:35:10,574][23806] Saving new best policy, reward=6.861!
211
+ [2024-12-07 14:35:11,214][23819] Updated weights for policy 0, policy_version 280 (0.0006)
212
+ [2024-12-07 14:35:12,978][23819] Updated weights for policy 0, policy_version 290 (0.0006)
213
+ [2024-12-07 14:35:14,732][23819] Updated weights for policy 0, policy_version 300 (0.0005)
214
+ [2024-12-07 14:35:15,572][19013] Fps is (10 sec: 23756.7, 60 sec: 20411.7, 300 sec: 20411.7). Total num frames: 1245184. Throughput: 0: 5446.4. Samples: 305038. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
215
+ [2024-12-07 14:35:15,573][19013] Avg episode reward: [(0, '10.907')]
216
+ [2024-12-07 14:35:15,601][23806] Saving new best policy, reward=10.907!
217
+ [2024-12-07 14:35:16,460][23819] Updated weights for policy 0, policy_version 310 (0.0006)
218
+ [2024-12-07 14:35:18,153][23819] Updated weights for policy 0, policy_version 320 (0.0005)
219
+ [2024-12-07 14:35:19,869][23819] Updated weights for policy 0, policy_version 330 (0.0006)
220
+ [2024-12-07 14:35:20,572][19013] Fps is (10 sec: 23756.7, 60 sec: 21162.7, 300 sec: 20732.1). Total num frames: 1368064. Throughput: 0: 5715.3. Samples: 340872. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
221
+ [2024-12-07 14:35:20,573][19013] Avg episode reward: [(0, '10.922')]
222
+ [2024-12-07 14:35:20,574][23806] Saving new best policy, reward=10.922!
223
+ [2024-12-07 14:35:21,588][23819] Updated weights for policy 0, policy_version 340 (0.0005)
224
+ [2024-12-07 14:35:23,313][23819] Updated weights for policy 0, policy_version 350 (0.0006)
225
+ [2024-12-07 14:35:24,968][23819] Updated weights for policy 0, policy_version 360 (0.0005)
226
+ [2024-12-07 14:35:25,572][19013] Fps is (10 sec: 24166.6, 60 sec: 21845.3, 300 sec: 20948.1). Total num frames: 1486848. Throughput: 0: 5854.0. Samples: 358812. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
227
+ [2024-12-07 14:35:25,573][19013] Avg episode reward: [(0, '14.171')]
228
+ [2024-12-07 14:35:25,576][23806] Saving new best policy, reward=14.171!
229
+ [2024-12-07 14:35:26,667][23819] Updated weights for policy 0, policy_version 370 (0.0006)
230
+ [2024-12-07 14:35:28,436][23819] Updated weights for policy 0, policy_version 380 (0.0006)
231
+ [2024-12-07 14:35:30,136][23819] Updated weights for policy 0, policy_version 390 (0.0006)
232
+ [2024-12-07 14:35:30,572][19013] Fps is (10 sec: 23756.7, 60 sec: 22459.7, 300 sec: 21135.3). Total num frames: 1605632. Throughput: 0: 5982.7. Samples: 394850. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
233
+ [2024-12-07 14:35:30,573][19013] Avg episode reward: [(0, '15.187')]
234
+ [2024-12-07 14:35:30,574][23806] Saving new best policy, reward=15.187!
235
+ [2024-12-07 14:35:31,846][23819] Updated weights for policy 0, policy_version 400 (0.0006)
236
+ [2024-12-07 14:35:33,531][23819] Updated weights for policy 0, policy_version 410 (0.0006)
237
+ [2024-12-07 14:35:35,243][23819] Updated weights for policy 0, policy_version 420 (0.0006)
238
+ [2024-12-07 14:35:35,572][19013] Fps is (10 sec: 23756.8, 60 sec: 23142.4, 300 sec: 21299.2). Total num frames: 1724416. Throughput: 0: 5984.0. Samples: 430784. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
239
+ [2024-12-07 14:35:35,573][19013] Avg episode reward: [(0, '17.358')]
240
+ [2024-12-07 14:35:35,580][23806] Saving new best policy, reward=17.358!
241
+ [2024-12-07 14:35:36,966][23819] Updated weights for policy 0, policy_version 430 (0.0006)
242
+ [2024-12-07 14:35:38,650][23819] Updated weights for policy 0, policy_version 440 (0.0006)
243
+ [2024-12-07 14:35:40,348][23819] Updated weights for policy 0, policy_version 450 (0.0006)
244
+ [2024-12-07 14:35:40,572][19013] Fps is (10 sec: 24166.6, 60 sec: 23893.3, 300 sec: 21492.0). Total num frames: 1847296. Throughput: 0: 5988.3. Samples: 448900. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
245
+ [2024-12-07 14:35:40,573][19013] Avg episode reward: [(0, '14.961')]
246
+ [2024-12-07 14:35:42,052][23819] Updated weights for policy 0, policy_version 460 (0.0006)
247
+ [2024-12-07 14:35:43,761][23819] Updated weights for policy 0, policy_version 470 (0.0006)
248
+ [2024-12-07 14:35:45,477][23819] Updated weights for policy 0, policy_version 480 (0.0005)
249
+ [2024-12-07 14:35:45,572][19013] Fps is (10 sec: 24166.5, 60 sec: 23961.6, 300 sec: 21617.8). Total num frames: 1966080. Throughput: 0: 5992.3. Samples: 484878. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
250
+ [2024-12-07 14:35:45,572][19013] Avg episode reward: [(0, '17.778')]
251
+ [2024-12-07 14:35:45,574][23806] Saving new best policy, reward=17.778!
252
+ [2024-12-07 14:35:47,212][23819] Updated weights for policy 0, policy_version 490 (0.0006)
253
+ [2024-12-07 14:35:48,912][23819] Updated weights for policy 0, policy_version 500 (0.0006)
254
+ [2024-12-07 14:35:50,572][19013] Fps is (10 sec: 23756.7, 60 sec: 23961.6, 300 sec: 21730.4). Total num frames: 2084864. Throughput: 0: 5987.8. Samples: 520754. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
255
+ [2024-12-07 14:35:50,573][19013] Avg episode reward: [(0, '17.858')]
256
+ [2024-12-07 14:35:50,593][23806] Saving new best policy, reward=17.858!
257
+ [2024-12-07 14:35:50,593][23819] Updated weights for policy 0, policy_version 510 (0.0005)
258
+ [2024-12-07 14:35:52,338][23819] Updated weights for policy 0, policy_version 520 (0.0006)
259
+ [2024-12-07 14:35:54,023][23819] Updated weights for policy 0, policy_version 530 (0.0005)
260
+ [2024-12-07 14:35:55,572][19013] Fps is (10 sec: 24166.2, 60 sec: 23961.6, 300 sec: 21872.6). Total num frames: 2207744. Throughput: 0: 5980.4. Samples: 538776. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
261
+ [2024-12-07 14:35:55,573][19013] Avg episode reward: [(0, '18.651')]
262
+ [2024-12-07 14:35:55,577][23806] Saving new best policy, reward=18.651!
263
+ [2024-12-07 14:35:55,691][23819] Updated weights for policy 0, policy_version 540 (0.0005)
264
+ [2024-12-07 14:35:57,355][23819] Updated weights for policy 0, policy_version 550 (0.0005)
265
+ [2024-12-07 14:35:59,071][23819] Updated weights for policy 0, policy_version 560 (0.0006)
266
+ [2024-12-07 14:36:00,572][19013] Fps is (10 sec: 24166.4, 60 sec: 23961.6, 300 sec: 21962.4). Total num frames: 2326528. Throughput: 0: 6000.2. Samples: 575048. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
267
+ [2024-12-07 14:36:00,573][19013] Avg episode reward: [(0, '20.626')]
268
+ [2024-12-07 14:36:00,574][23806] Saving new best policy, reward=20.626!
269
+ [2024-12-07 14:36:00,803][23819] Updated weights for policy 0, policy_version 570 (0.0005)
270
+ [2024-12-07 14:36:02,587][23819] Updated weights for policy 0, policy_version 580 (0.0006)
271
+ [2024-12-07 14:36:04,280][23819] Updated weights for policy 0, policy_version 590 (0.0006)
272
+ [2024-12-07 14:36:05,572][19013] Fps is (10 sec: 23756.9, 60 sec: 23961.6, 300 sec: 22043.9). Total num frames: 2445312. Throughput: 0: 5993.6. Samples: 610586. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
273
+ [2024-12-07 14:36:05,573][19013] Avg episode reward: [(0, '19.659')]
274
+ [2024-12-07 14:36:05,578][23806] Saving /home/rahatchd/code/deep-rl-hugging-face/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000597_2445312.pth...
275
+ [2024-12-07 14:36:06,010][23819] Updated weights for policy 0, policy_version 600 (0.0006)
276
+ [2024-12-07 14:36:07,722][23819] Updated weights for policy 0, policy_version 610 (0.0006)
277
+ [2024-12-07 14:36:09,485][23819] Updated weights for policy 0, policy_version 620 (0.0006)
278
+ [2024-12-07 14:36:10,572][19013] Fps is (10 sec: 23756.8, 60 sec: 23893.3, 300 sec: 22118.4). Total num frames: 2564096. Throughput: 0: 5989.9. Samples: 628358. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
279
+ [2024-12-07 14:36:10,573][19013] Avg episode reward: [(0, '20.821')]
280
+ [2024-12-07 14:36:10,573][23806] Saving new best policy, reward=20.821!
281
+ [2024-12-07 14:36:11,223][23819] Updated weights for policy 0, policy_version 630 (0.0006)
282
+ [2024-12-07 14:36:12,900][23819] Updated weights for policy 0, policy_version 640 (0.0005)
283
+ [2024-12-07 14:36:14,589][23819] Updated weights for policy 0, policy_version 650 (0.0005)
284
+ [2024-12-07 14:36:15,572][19013] Fps is (10 sec: 23756.7, 60 sec: 23961.6, 300 sec: 22186.7). Total num frames: 2682880. Throughput: 0: 5983.3. Samples: 664100. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
285
+ [2024-12-07 14:36:15,573][19013] Avg episode reward: [(0, '25.818')]
286
+ [2024-12-07 14:36:15,599][23806] Saving new best policy, reward=25.818!
287
+ [2024-12-07 14:36:16,313][23819] Updated weights for policy 0, policy_version 660 (0.0006)
288
+ [2024-12-07 14:36:18,010][23819] Updated weights for policy 0, policy_version 670 (0.0006)
289
+ [2024-12-07 14:36:19,721][23819] Updated weights for policy 0, policy_version 680 (0.0006)
290
+ [2024-12-07 14:36:20,572][19013] Fps is (10 sec: 23756.9, 60 sec: 23893.4, 300 sec: 22249.5). Total num frames: 2801664. Throughput: 0: 5985.2. Samples: 700118. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
291
+ [2024-12-07 14:36:20,573][19013] Avg episode reward: [(0, '23.182')]
292
+ [2024-12-07 14:36:21,452][23819] Updated weights for policy 0, policy_version 690 (0.0006)
293
+ [2024-12-07 14:36:23,178][23819] Updated weights for policy 0, policy_version 700 (0.0006)
294
+ [2024-12-07 14:36:24,922][23819] Updated weights for policy 0, policy_version 710 (0.0006)
295
+ [2024-12-07 14:36:25,572][19013] Fps is (10 sec: 24166.6, 60 sec: 23961.6, 300 sec: 22339.0). Total num frames: 2924544. Throughput: 0: 5977.3. Samples: 717878. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
296
+ [2024-12-07 14:36:25,572][19013] Avg episode reward: [(0, '25.883')]
297
+ [2024-12-07 14:36:25,577][23806] Saving new best policy, reward=25.883!
298
+ [2024-12-07 14:36:26,623][23819] Updated weights for policy 0, policy_version 720 (0.0006)
299
+ [2024-12-07 14:36:28,373][23819] Updated weights for policy 0, policy_version 730 (0.0006)
300
+ [2024-12-07 14:36:30,077][23819] Updated weights for policy 0, policy_version 740 (0.0006)
301
+ [2024-12-07 14:36:30,572][19013] Fps is (10 sec: 24166.4, 60 sec: 23961.6, 300 sec: 22391.5). Total num frames: 3043328. Throughput: 0: 5966.4. Samples: 753368. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
302
+ [2024-12-07 14:36:30,573][19013] Avg episode reward: [(0, '24.200')]
303
+ [2024-12-07 14:36:31,784][23819] Updated weights for policy 0, policy_version 750 (0.0006)
304
+ [2024-12-07 14:36:33,524][23819] Updated weights for policy 0, policy_version 760 (0.0006)
305
+ [2024-12-07 14:36:35,223][23819] Updated weights for policy 0, policy_version 770 (0.0006)
306
+ [2024-12-07 14:36:35,572][19013] Fps is (10 sec: 23346.9, 60 sec: 23893.3, 300 sec: 22411.0). Total num frames: 3158016. Throughput: 0: 5966.9. Samples: 789264. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
307
+ [2024-12-07 14:36:35,573][19013] Avg episode reward: [(0, '27.345')]
308
+ [2024-12-07 14:36:35,584][23806] Saving new best policy, reward=27.345!
309
+ [2024-12-07 14:36:36,970][23819] Updated weights for policy 0, policy_version 780 (0.0006)
310
+ [2024-12-07 14:36:38,637][23819] Updated weights for policy 0, policy_version 790 (0.0005)
311
+ [2024-12-07 14:36:40,311][23819] Updated weights for policy 0, policy_version 800 (0.0005)
312
+ [2024-12-07 14:36:40,572][19013] Fps is (10 sec: 23756.6, 60 sec: 23893.3, 300 sec: 22485.6). Total num frames: 3280896. Throughput: 0: 5969.2. Samples: 807390. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
313
+ [2024-12-07 14:36:40,573][19013] Avg episode reward: [(0, '24.428')]
314
+ [2024-12-07 14:36:41,986][23819] Updated weights for policy 0, policy_version 810 (0.0005)
315
+ [2024-12-07 14:36:43,711][23819] Updated weights for policy 0, policy_version 820 (0.0006)
316
+ [2024-12-07 14:36:45,438][23819] Updated weights for policy 0, policy_version 830 (0.0006)
317
+ [2024-12-07 14:36:45,572][19013] Fps is (10 sec: 24166.6, 60 sec: 23893.3, 300 sec: 22528.0). Total num frames: 3399680. Throughput: 0: 5968.0. Samples: 843610. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
318
+ [2024-12-07 14:36:45,573][19013] Avg episode reward: [(0, '26.352')]
319
+ [2024-12-07 14:36:47,139][23819] Updated weights for policy 0, policy_version 840 (0.0006)
320
+ [2024-12-07 14:36:48,865][23819] Updated weights for policy 0, policy_version 850 (0.0006)
321
+ [2024-12-07 14:36:50,541][23819] Updated weights for policy 0, policy_version 860 (0.0006)
322
+ [2024-12-07 14:36:50,572][19013] Fps is (10 sec: 24166.3, 60 sec: 23961.6, 300 sec: 22594.1). Total num frames: 3522560. Throughput: 0: 5975.9. Samples: 879504. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
323
+ [2024-12-07 14:36:50,573][19013] Avg episode reward: [(0, '25.960')]
324
+ [2024-12-07 14:36:52,301][23819] Updated weights for policy 0, policy_version 870 (0.0005)
325
+ [2024-12-07 14:36:54,003][23819] Updated weights for policy 0, policy_version 880 (0.0006)
326
+ [2024-12-07 14:36:55,572][19013] Fps is (10 sec: 24166.6, 60 sec: 23893.4, 300 sec: 22630.4). Total num frames: 3641344. Throughput: 0: 5978.9. Samples: 897410. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
327
+ [2024-12-07 14:36:55,572][19013] Avg episode reward: [(0, '26.897')]
328
+ [2024-12-07 14:36:55,723][23819] Updated weights for policy 0, policy_version 890 (0.0006)
329
+ [2024-12-07 14:36:57,435][23819] Updated weights for policy 0, policy_version 900 (0.0006)
330
+ [2024-12-07 14:36:59,172][23819] Updated weights for policy 0, policy_version 910 (0.0005)
331
+ [2024-12-07 14:37:00,572][19013] Fps is (10 sec: 23756.8, 60 sec: 23893.3, 300 sec: 22664.5). Total num frames: 3760128. Throughput: 0: 5978.4. Samples: 933130. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
332
+ [2024-12-07 14:37:00,573][19013] Avg episode reward: [(0, '25.898')]
333
+ [2024-12-07 14:37:00,844][23819] Updated weights for policy 0, policy_version 920 (0.0005)
334
+ [2024-12-07 14:37:02,559][23819] Updated weights for policy 0, policy_version 930 (0.0006)
335
+ [2024-12-07 14:37:04,287][23819] Updated weights for policy 0, policy_version 940 (0.0006)
336
+ [2024-12-07 14:37:05,572][19013] Fps is (10 sec: 23756.4, 60 sec: 23893.3, 300 sec: 22696.6). Total num frames: 3878912. Throughput: 0: 5973.1. Samples: 968908. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
337
+ [2024-12-07 14:37:05,573][19013] Avg episode reward: [(0, '26.120')]
338
+ [2024-12-07 14:37:06,038][23819] Updated weights for policy 0, policy_version 950 (0.0006)
339
+ [2024-12-07 14:37:07,756][23819] Updated weights for policy 0, policy_version 960 (0.0006)
340
+ [2024-12-07 14:37:09,463][23819] Updated weights for policy 0, policy_version 970 (0.0005)
341
+ [2024-12-07 14:37:10,572][19013] Fps is (10 sec: 23757.1, 60 sec: 23893.4, 300 sec: 22727.0). Total num frames: 3997696. Throughput: 0: 5973.8. Samples: 986698. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
342
+ [2024-12-07 14:37:10,573][19013] Avg episode reward: [(0, '25.009')]
343
+ [2024-12-07 14:37:10,814][23806] Stopping Batcher_0...
344
+ [2024-12-07 14:37:10,814][23806] Saving /home/rahatchd/code/deep-rl-hugging-face/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
345
+ [2024-12-07 14:37:10,814][19013] Component Batcher_0 stopped!
346
+ [2024-12-07 14:37:10,816][19013] Component RolloutWorker_w1 process died already! Don't wait for it.
347
+ [2024-12-07 14:37:10,815][23806] Loop batcher_evt_loop terminating...
348
+ [2024-12-07 14:37:10,832][23819] Weights refcount: 2 0
349
+ [2024-12-07 14:37:10,833][23819] Stopping InferenceWorker_p0-w0...
350
+ [2024-12-07 14:37:10,833][23819] Loop inference_proc0-0_evt_loop terminating...
351
+ [2024-12-07 14:37:10,833][19013] Component InferenceWorker_p0-w0 stopped!
352
+ [2024-12-07 14:37:10,849][23824] Stopping RolloutWorker_w5...
353
+ [2024-12-07 14:37:10,850][23824] Loop rollout_proc5_evt_loop terminating...
354
+ [2024-12-07 14:37:10,849][19013] Component RolloutWorker_w5 stopped!
355
+ [2024-12-07 14:37:10,851][23823] Stopping RolloutWorker_w4...
356
+ [2024-12-07 14:37:10,851][19013] Component RolloutWorker_w4 stopped!
357
+ [2024-12-07 14:37:10,851][23820] Stopping RolloutWorker_w0...
358
+ [2024-12-07 14:37:10,851][23823] Loop rollout_proc4_evt_loop terminating...
359
+ [2024-12-07 14:37:10,851][23820] Loop rollout_proc0_evt_loop terminating...
360
+ [2024-12-07 14:37:10,851][19013] Component RolloutWorker_w0 stopped!
361
+ [2024-12-07 14:37:10,851][23826] Stopping RolloutWorker_w7...
362
+ [2024-12-07 14:37:10,852][23826] Loop rollout_proc7_evt_loop terminating...
363
+ [2024-12-07 14:37:10,852][19013] Component RolloutWorker_w7 stopped!
364
+ [2024-12-07 14:37:10,852][23827] Stopping RolloutWorker_w6...
365
+ [2024-12-07 14:37:10,852][23822] Stopping RolloutWorker_w3...
366
+ [2024-12-07 14:37:10,853][23822] Loop rollout_proc3_evt_loop terminating...
367
+ [2024-12-07 14:37:10,853][23827] Loop rollout_proc6_evt_loop terminating...
368
+ [2024-12-07 14:37:10,852][19013] Component RolloutWorker_w6 stopped!
369
+ [2024-12-07 14:37:10,853][19013] Component RolloutWorker_w3 stopped!
370
+ [2024-12-07 14:37:10,854][23825] Stopping RolloutWorker_w2...
371
+ [2024-12-07 14:37:10,854][23825] Loop rollout_proc2_evt_loop terminating...
372
+ [2024-12-07 14:37:10,854][19013] Component RolloutWorker_w2 stopped!
373
+ [2024-12-07 14:37:10,869][23806] Saving /home/rahatchd/code/deep-rl-hugging-face/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
374
+ [2024-12-07 14:37:10,939][23806] Stopping LearnerWorker_p0...
375
+ [2024-12-07 14:37:10,939][23806] Loop learner_proc0_evt_loop terminating...
376
+ [2024-12-07 14:37:10,939][19013] Component LearnerWorker_p0 stopped!
377
+ [2024-12-07 14:37:10,940][19013] Waiting for process learner_proc0 to stop...
378
+ [2024-12-07 14:37:11,717][19013] Waiting for process inference_proc0-0 to join...
379
+ [2024-12-07 14:37:11,718][19013] Waiting for process rollout_proc0 to join...
380
+ [2024-12-07 14:37:11,718][19013] Waiting for process rollout_proc1 to join...
381
+ [2024-12-07 14:37:11,719][19013] Waiting for process rollout_proc2 to join...
382
+ [2024-12-07 14:37:11,720][19013] Waiting for process rollout_proc3 to join...
383
+ [2024-12-07 14:37:11,721][19013] Waiting for process rollout_proc4 to join...
384
+ [2024-12-07 14:37:11,722][19013] Waiting for process rollout_proc5 to join...
385
+ [2024-12-07 14:37:11,723][19013] Waiting for process rollout_proc6 to join...
386
+ [2024-12-07 14:37:11,724][19013] Waiting for process rollout_proc7 to join...
387
+ [2024-12-07 14:37:11,725][19013] Batcher 0 profile tree view:
388
+ batching: 10.5578, releasing_batches: 0.0212
389
+ [2024-12-07 14:37:11,726][19013] InferenceWorker_p0-w0 profile tree view:
390
+ wait_policy: 0.0000
391
+ wait_policy_total: 4.8273
392
+ update_model: 2.0921
393
+ weight_update: 0.0005
394
+ one_step: 0.0017
395
+ handle_policy_step: 163.6695
396
+ deserialize: 5.4997, stack: 0.7929, obs_to_device_normalize: 41.8845, forward: 72.2956, send_messages: 7.4725
397
+ prepare_outputs: 29.4647
398
+ to_cpu: 21.6545
399
+ [2024-12-07 14:37:11,726][19013] Learner 0 profile tree view:
400
+ misc: 0.0039, prepare_batch: 7.2401
401
+ train: 26.4145
402
+ epoch_init: 0.0037, minibatch_init: 0.0042, losses_postprocess: 0.3988, kl_divergence: 0.3982, after_optimizer: 9.2403
403
+ calculate_losses: 9.3937
404
+ losses_init: 0.0027, forward_head: 0.5595, bptt_initial: 6.1467, tail: 0.4752, advantages_returns: 0.1337, losses: 0.9484
405
+ bptt: 0.9985
406
+ bptt_forward_core: 0.9580
407
+ update: 6.6839
408
+ clip: 0.6204
409
+ [2024-12-07 14:37:11,727][19013] RolloutWorker_w0 profile tree view:
410
+ wait_for_trajectories: 0.1300, enqueue_policy_requests: 8.3049, env_step: 101.9303, overhead: 4.5937, complete_rollouts: 0.1726
411
+ save_policy_outputs: 8.8612
412
+ split_output_tensors: 2.9795
413
+ [2024-12-07 14:37:11,728][19013] RolloutWorker_w7 profile tree view:
414
+ wait_for_trajectories: 0.1243, enqueue_policy_requests: 8.2736, env_step: 100.7709, overhead: 4.5028, complete_rollouts: 0.1745
415
+ save_policy_outputs: 8.7132
416
+ split_output_tensors: 2.9265
417
+ [2024-12-07 14:37:11,729][19013] Loop Runner_EvtLoop terminating...
418
+ [2024-12-07 14:37:11,730][19013] Runner profile tree view:
419
+ main_loop: 183.2567
420
+ [2024-12-07 14:37:11,732][19013] Collected {0: 4005888}, FPS: 21859.4
421
+ [2024-12-07 14:39:41,500][19013] Loading existing experiment configuration from /home/rahatchd/code/deep-rl-hugging-face/unit8/train_dir/default_experiment/config.json
422
+ [2024-12-07 14:39:41,500][19013] Overriding arg 'num_workers' with value 1 passed from command line
423
+ [2024-12-07 14:39:41,501][19013] Adding new argument 'no_render'=True that is not in the saved config file!
424
+ [2024-12-07 14:39:41,501][19013] Adding new argument 'save_video'=True that is not in the saved config file!
425
+ [2024-12-07 14:39:41,502][19013] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
426
+ [2024-12-07 14:39:41,502][19013] Adding new argument 'video_name'=None that is not in the saved config file!
427
+ [2024-12-07 14:39:41,503][19013] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
428
+ [2024-12-07 14:39:41,504][19013] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
429
+ [2024-12-07 14:39:41,504][19013] Adding new argument 'push_to_hub'=False that is not in the saved config file!
430
+ [2024-12-07 14:39:41,504][19013] Adding new argument 'hf_repository'=None that is not in the saved config file!
431
+ [2024-12-07 14:39:41,505][19013] Adding new argument 'policy_index'=0 that is not in the saved config file!
432
+ [2024-12-07 14:39:41,505][19013] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
433
+ [2024-12-07 14:39:41,505][19013] Adding new argument 'train_script'=None that is not in the saved config file!
434
+ [2024-12-07 14:39:41,506][19013] Adding new argument 'enjoy_script'=None that is not in the saved config file!
435
+ [2024-12-07 14:39:41,506][19013] Using frameskip 1 and render_action_repeat=4 for evaluation
436
+ [2024-12-07 14:39:41,526][19013] Doom resolution: 160x120, resize resolution: (128, 72)
437
+ [2024-12-07 14:39:41,528][19013] RunningMeanStd input shape: (3, 72, 128)
438
+ [2024-12-07 14:39:41,529][19013] RunningMeanStd input shape: (1,)
439
+ [2024-12-07 14:39:41,535][19013] ConvEncoder: input_channels=3
440
+ [2024-12-07 14:39:41,599][19013] Conv encoder output size: 512
441
+ [2024-12-07 14:39:41,599][19013] Policy head output size: 512
442
+ [2024-12-07 14:39:41,735][19013] Loading state from checkpoint /home/rahatchd/code/deep-rl-hugging-face/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
443
+ [2024-12-07 14:39:42,277][19013] Num frames 100...
444
+ [2024-12-07 14:39:42,353][19013] Num frames 200...
445
+ [2024-12-07 14:39:42,433][19013] Num frames 300...
446
+ [2024-12-07 14:39:42,515][19013] Num frames 400...
447
+ [2024-12-07 14:39:42,589][19013] Num frames 500...
448
+ [2024-12-07 14:39:42,665][19013] Num frames 600...
449
+ [2024-12-07 14:39:42,741][19013] Num frames 700...
450
+ [2024-12-07 14:39:42,823][19013] Num frames 800...
451
+ [2024-12-07 14:39:42,906][19013] Num frames 900...
452
+ [2024-12-07 14:39:43,035][19013] Avg episode rewards: #0: 19.920, true rewards: #0: 9.920
453
+ [2024-12-07 14:39:43,036][19013] Avg episode reward: 19.920, avg true_objective: 9.920
454
+ [2024-12-07 14:39:43,045][19013] Num frames 1000...
455
+ [2024-12-07 14:39:43,164][19013] Num frames 1100...
456
+ [2024-12-07 14:39:43,256][19013] Num frames 1200...
457
+ [2024-12-07 14:39:43,336][19013] Num frames 1300...
458
+ [2024-12-07 14:39:43,419][19013] Num frames 1400...
459
+ [2024-12-07 14:39:43,499][19013] Num frames 1500...
460
+ [2024-12-07 14:39:43,586][19013] Num frames 1600...
461
+ [2024-12-07 14:39:43,674][19013] Num frames 1700...
462
+ [2024-12-07 14:39:43,760][19013] Num frames 1800...
463
+ [2024-12-07 14:39:43,842][19013] Num frames 1900...
464
+ [2024-12-07 14:39:43,924][19013] Num frames 2000...
465
+ [2024-12-07 14:39:44,007][19013] Num frames 2100...
466
+ [2024-12-07 14:39:44,104][19013] Avg episode rewards: #0: 22.220, true rewards: #0: 10.720
467
+ [2024-12-07 14:39:44,105][19013] Avg episode reward: 22.220, avg true_objective: 10.720
468
+ [2024-12-07 14:39:44,179][19013] Num frames 2200...
469
+ [2024-12-07 14:39:44,285][19013] Num frames 2300...
470
+ [2024-12-07 14:39:44,370][19013] Num frames 2400...
471
+ [2024-12-07 14:39:44,450][19013] Num frames 2500...
472
+ [2024-12-07 14:39:44,532][19013] Num frames 2600...
473
+ [2024-12-07 14:39:44,613][19013] Num frames 2700...
474
+ [2024-12-07 14:39:44,694][19013] Num frames 2800...
475
+ [2024-12-07 14:39:44,778][19013] Num frames 2900...
476
+ [2024-12-07 14:39:44,859][19013] Num frames 3000...
477
+ [2024-12-07 14:39:44,941][19013] Num frames 3100...
478
+ [2024-12-07 14:39:45,018][19013] Num frames 3200...
479
+ [2024-12-07 14:39:45,085][19013] Num frames 3300...
480
+ [2024-12-07 14:39:45,154][19013] Num frames 3400...
481
+ [2024-12-07 14:39:45,222][19013] Num frames 3500...
482
+ [2024-12-07 14:39:45,292][19013] Num frames 3600...
483
+ [2024-12-07 14:39:45,360][19013] Num frames 3700...
484
+ [2024-12-07 14:39:45,430][19013] Num frames 3800...
485
+ [2024-12-07 14:39:45,500][19013] Num frames 3900...
486
+ [2024-12-07 14:39:45,569][19013] Num frames 4000...
487
+ [2024-12-07 14:39:45,640][19013] Num frames 4100...
488
+ [2024-12-07 14:39:45,710][19013] Num frames 4200...
489
+ [2024-12-07 14:39:45,794][19013] Avg episode rewards: #0: 35.480, true rewards: #0: 14.147
490
+ [2024-12-07 14:39:45,794][19013] Avg episode reward: 35.480, avg true_objective: 14.147
491
+ [2024-12-07 14:39:45,861][19013] Num frames 4300...
492
+ [2024-12-07 14:39:45,944][19013] Num frames 4400...
493
+ [2024-12-07 14:39:46,013][19013] Num frames 4500...
494
+ [2024-12-07 14:39:46,083][19013] Num frames 4600...
495
+ [2024-12-07 14:39:46,152][19013] Num frames 4700...
496
+ [2024-12-07 14:39:46,222][19013] Num frames 4800...
497
+ [2024-12-07 14:39:46,291][19013] Num frames 4900...
498
+ [2024-12-07 14:39:46,361][19013] Num frames 5000...
499
+ [2024-12-07 14:39:46,430][19013] Num frames 5100...
500
+ [2024-12-07 14:39:46,519][19013] Avg episode rewards: #0: 32.100, true rewards: #0: 12.850
501
+ [2024-12-07 14:39:46,520][19013] Avg episode reward: 32.100, avg true_objective: 12.850
502
+ [2024-12-07 14:39:46,584][19013] Num frames 5200...
503
+ [2024-12-07 14:39:46,691][19013] Num frames 5300...
504
+ [2024-12-07 14:39:46,770][19013] Num frames 5400...
505
+ [2024-12-07 14:39:46,852][19013] Num frames 5500...
506
+ [2024-12-07 14:39:46,979][19013] Avg episode rewards: #0: 27.376, true rewards: #0: 11.176
507
+ [2024-12-07 14:39:46,980][19013] Avg episode reward: 27.376, avg true_objective: 11.176
508
+ [2024-12-07 14:39:46,996][19013] Num frames 5600...
509
+ [2024-12-07 14:39:47,115][19013] Num frames 5700...
510
+ [2024-12-07 14:39:47,210][19013] Num frames 5800...
511
+ [2024-12-07 14:39:47,292][19013] Num frames 5900...
512
+ [2024-12-07 14:39:47,373][19013] Num frames 6000...
513
+ [2024-12-07 14:39:47,455][19013] Num frames 6100...
514
+ [2024-12-07 14:39:47,535][19013] Num frames 6200...
515
+ [2024-12-07 14:39:47,615][19013] Num frames 6300...
516
+ [2024-12-07 14:39:47,697][19013] Num frames 6400...
517
+ [2024-12-07 14:39:47,793][19013] Avg episode rewards: #0: 25.587, true rewards: #0: 10.753
518
+ [2024-12-07 14:39:47,794][19013] Avg episode reward: 25.587, avg true_objective: 10.753
519
+ [2024-12-07 14:39:47,853][19013] Num frames 6500...
520
+ [2024-12-07 14:39:47,966][19013] Num frames 6600...
521
+ [2024-12-07 14:39:48,057][19013] Num frames 6700...
522
+ [2024-12-07 14:39:48,137][19013] Num frames 6800...
523
+ [2024-12-07 14:39:48,216][19013] Num frames 6900...
524
+ [2024-12-07 14:39:48,292][19013] Num frames 7000...
525
+ [2024-12-07 14:39:48,385][19013] Avg episode rewards: #0: 23.228, true rewards: #0: 10.086
526
+ [2024-12-07 14:39:48,386][19013] Avg episode reward: 23.228, avg true_objective: 10.086
527
+ [2024-12-07 14:39:48,438][19013] Num frames 7100...
528
+ [2024-12-07 14:39:48,539][19013] Num frames 7200...
529
+ [2024-12-07 14:39:48,609][19013] Num frames 7300...
530
+ [2024-12-07 14:39:48,679][19013] Num frames 7400...
531
+ [2024-12-07 14:39:48,749][19013] Num frames 7500...
532
+ [2024-12-07 14:39:48,820][19013] Num frames 7600...
533
+ [2024-12-07 14:39:48,897][19013] Avg episode rewards: #0: 21.545, true rewards: #0: 9.545
534
+ [2024-12-07 14:39:48,898][19013] Avg episode reward: 21.545, avg true_objective: 9.545
535
+ [2024-12-07 14:39:48,972][19013] Num frames 7700...
536
+ [2024-12-07 14:39:49,056][19013] Num frames 7800...
537
+ [2024-12-07 14:39:49,125][19013] Num frames 7900...
538
+ [2024-12-07 14:39:49,194][19013] Num frames 8000...
539
+ [2024-12-07 14:39:49,284][19013] Avg episode rewards: #0: 19.949, true rewards: #0: 8.949
540
+ [2024-12-07 14:39:49,284][19013] Avg episode reward: 19.949, avg true_objective: 8.949
541
+ [2024-12-07 14:39:49,342][19013] Num frames 8100...
542
+ [2024-12-07 14:39:49,431][19013] Num frames 8200...
543
+ [2024-12-07 14:39:49,502][19013] Num frames 8300...
544
+ [2024-12-07 14:39:49,572][19013] Num frames 8400...
545
+ [2024-12-07 14:39:49,641][19013] Num frames 8500...
546
+ [2024-12-07 14:39:49,711][19013] Num frames 8600...
547
+ [2024-12-07 14:39:49,782][19013] Num frames 8700...
548
+ [2024-12-07 14:39:49,864][19013] Avg episode rewards: #0: 19.336, true rewards: #0: 8.736
549
+ [2024-12-07 14:39:49,865][19013] Avg episode reward: 19.336, avg true_objective: 8.736
550
+ [2024-12-07 14:40:01,237][19013] Replay video saved to /home/rahatchd/code/deep-rl-hugging-face/unit8/train_dir/default_experiment/replay.mp4!
551
+ [2024-12-07 14:41:09,726][19013] Loading existing experiment configuration from /home/rahatchd/code/deep-rl-hugging-face/unit8/train_dir/default_experiment/config.json
552
+ [2024-12-07 14:41:09,727][19013] Overriding arg 'num_workers' with value 1 passed from command line
553
+ [2024-12-07 14:41:09,727][19013] Adding new argument 'no_render'=True that is not in the saved config file!
554
+ [2024-12-07 14:41:09,728][19013] Adding new argument 'save_video'=True that is not in the saved config file!
555
+ [2024-12-07 14:41:09,728][19013] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
556
+ [2024-12-07 14:41:09,729][19013] Adding new argument 'video_name'=None that is not in the saved config file!
557
+ [2024-12-07 14:41:09,730][19013] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
558
+ [2024-12-07 14:41:09,730][19013] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
559
+ [2024-12-07 14:41:09,731][19013] Adding new argument 'push_to_hub'=True that is not in the saved config file!
560
+ [2024-12-07 14:41:09,731][19013] Adding new argument 'hf_repository'='rahatchd/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
561
+ [2024-12-07 14:41:09,731][19013] Adding new argument 'policy_index'=0 that is not in the saved config file!
562
+ [2024-12-07 14:41:09,732][19013] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
563
+ [2024-12-07 14:41:09,732][19013] Adding new argument 'train_script'=None that is not in the saved config file!
564
+ [2024-12-07 14:41:09,732][19013] Adding new argument 'enjoy_script'=None that is not in the saved config file!
565
+ [2024-12-07 14:41:09,733][19013] Using frameskip 1 and render_action_repeat=4 for evaluation
566
+ [2024-12-07 14:41:09,758][19013] RunningMeanStd input shape: (3, 72, 128)
567
+ [2024-12-07 14:41:09,759][19013] RunningMeanStd input shape: (1,)
568
+ [2024-12-07 14:41:09,769][19013] ConvEncoder: input_channels=3
569
+ [2024-12-07 14:41:09,803][19013] Conv encoder output size: 512
570
+ [2024-12-07 14:41:09,804][19013] Policy head output size: 512
571
+ [2024-12-07 14:41:09,836][19013] Loading state from checkpoint /home/rahatchd/code/deep-rl-hugging-face/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
572
+ [2024-12-07 14:41:10,172][19013] Num frames 100...
573
+ [2024-12-07 14:41:10,256][19013] Num frames 200...
574
+ [2024-12-07 14:41:10,340][19013] Num frames 300...
575
+ [2024-12-07 14:41:10,423][19013] Num frames 400...
576
+ [2024-12-07 14:41:10,506][19013] Num frames 500...
577
+ [2024-12-07 14:41:10,589][19013] Num frames 600...
578
+ [2024-12-07 14:41:10,676][19013] Num frames 700...
579
+ [2024-12-07 14:41:10,758][19013] Num frames 800...
580
+ [2024-12-07 14:41:10,843][19013] Num frames 900...
581
+ [2024-12-07 14:41:10,926][19013] Num frames 1000...
582
+ [2024-12-07 14:41:11,000][19013] Avg episode rewards: #0: 24.240, true rewards: #0: 10.240
583
+ [2024-12-07 14:41:11,000][19013] Avg episode reward: 24.240, avg true_objective: 10.240
584
+ [2024-12-07 14:41:11,065][19013] Num frames 1100...
585
+ [2024-12-07 14:41:11,148][19013] Num frames 1200...
586
+ [2024-12-07 14:41:11,230][19013] Num frames 1300...
587
+ [2024-12-07 14:41:11,317][19013] Num frames 1400...
588
+ [2024-12-07 14:41:11,404][19013] Num frames 1500...
589
+ [2024-12-07 14:41:11,486][19013] Num frames 1600...
590
+ [2024-12-07 14:41:11,568][19013] Avg episode rewards: #0: 18.160, true rewards: #0: 8.160
591
+ [2024-12-07 14:41:11,568][19013] Avg episode reward: 18.160, avg true_objective: 8.160
592
+ [2024-12-07 14:41:11,664][19013] Num frames 1700...
593
+ [2024-12-07 14:41:11,758][19013] Num frames 1800...
594
+ [2024-12-07 14:41:11,839][19013] Num frames 1900...
595
+ [2024-12-07 14:41:11,919][19013] Num frames 2000...
596
+ [2024-12-07 14:41:11,999][19013] Num frames 2100...
597
+ [2024-12-07 14:41:12,114][19013] Avg episode rewards: #0: 15.587, true rewards: #0: 7.253
598
+ [2024-12-07 14:41:12,115][19013] Avg episode reward: 15.587, avg true_objective: 7.253
599
+ [2024-12-07 14:41:12,145][19013] Num frames 2200...
600
+ [2024-12-07 14:41:12,265][19013] Num frames 2300...
601
+ [2024-12-07 14:41:12,352][19013] Num frames 2400...
602
+ [2024-12-07 14:41:12,432][19013] Num frames 2500...
603
+ [2024-12-07 14:41:12,515][19013] Num frames 2600...
604
+ [2024-12-07 14:41:12,596][19013] Num frames 2700...
605
+ [2024-12-07 14:41:12,679][19013] Num frames 2800...
606
+ [2024-12-07 14:41:12,762][19013] Num frames 2900...
607
+ [2024-12-07 14:41:12,842][19013] Num frames 3000...
608
+ [2024-12-07 14:41:12,922][19013] Num frames 3100...
609
+ [2024-12-07 14:41:13,032][19013] Avg episode rewards: #0: 16.420, true rewards: #0: 7.920
610
+ [2024-12-07 14:41:13,033][19013] Avg episode reward: 16.420, avg true_objective: 7.920
611
+ [2024-12-07 14:41:13,072][19013] Num frames 3200...
612
+ [2024-12-07 14:41:13,186][19013] Num frames 3300...
613
+ [2024-12-07 14:41:13,297][19013] Num frames 3400...
614
+ [2024-12-07 14:41:13,369][19013] Num frames 3500...
615
+ [2024-12-07 14:41:13,439][19013] Num frames 3600...
616
+ [2024-12-07 14:41:13,513][19013] Num frames 3700...
617
+ [2024-12-07 14:41:13,585][19013] Num frames 3800...
618
+ [2024-12-07 14:41:13,662][19013] Num frames 3900...
619
+ [2024-12-07 14:41:13,745][19013] Num frames 4000...
620
+ [2024-12-07 14:41:13,828][19013] Num frames 4100...
621
+ [2024-12-07 14:41:13,912][19013] Num frames 4200...
622
+ [2024-12-07 14:41:13,994][19013] Num frames 4300...
623
+ [2024-12-07 14:41:14,077][19013] Num frames 4400...
624
+ [2024-12-07 14:41:14,162][19013] Num frames 4500...
625
+ [2024-12-07 14:41:14,246][19013] Num frames 4600...
626
+ [2024-12-07 14:41:14,328][19013] Num frames 4700...
627
+ [2024-12-07 14:41:14,409][19013] Num frames 4800...
628
+ [2024-12-07 14:41:14,492][19013] Num frames 4900...
629
+ [2024-12-07 14:41:14,621][19013] Avg episode rewards: #0: 21.584, true rewards: #0: 9.984
630
+ [2024-12-07 14:41:14,621][19013] Avg episode reward: 21.584, avg true_objective: 9.984
631
+ [2024-12-07 14:41:14,632][19013] Num frames 5000...
632
+ [2024-12-07 14:41:14,751][19013] Num frames 5100...
633
+ [2024-12-07 14:41:14,832][19013] Num frames 5200...
634
+ [2024-12-07 14:41:14,902][19013] Num frames 5300...
635
+ [2024-12-07 14:41:14,972][19013] Num frames 5400...
636
+ [2024-12-07 14:41:15,052][19013] Num frames 5500...
637
+ [2024-12-07 14:41:15,129][19013] Num frames 5600...
638
+ [2024-12-07 14:41:15,199][19013] Num frames 5700...
639
+ [2024-12-07 14:41:15,322][19013] Avg episode rewards: #0: 20.487, true rewards: #0: 9.653
640
+ [2024-12-07 14:41:15,323][19013] Avg episode reward: 20.487, avg true_objective: 9.653
641
+ [2024-12-07 14:41:15,331][19013] Num frames 5800...
642
+ [2024-12-07 14:41:15,446][19013] Num frames 5900...
643
+ [2024-12-07 14:41:15,525][19013] Num frames 6000...
644
+ [2024-12-07 14:41:15,605][19013] Num frames 6100...
645
+ [2024-12-07 14:41:15,684][19013] Num frames 6200...
646
+ [2024-12-07 14:41:15,764][19013] Num frames 6300...
647
+ [2024-12-07 14:41:15,842][19013] Num frames 6400...
648
+ [2024-12-07 14:41:15,921][19013] Num frames 6500...
649
+ [2024-12-07 14:41:16,002][19013] Num frames 6600...
650
+ [2024-12-07 14:41:16,074][19013] Num frames 6700...
651
+ [2024-12-07 14:41:16,143][19013] Num frames 6800...
652
+ [2024-12-07 14:41:16,213][19013] Num frames 6900...
653
+ [2024-12-07 14:41:16,281][19013] Num frames 7000...
654
+ [2024-12-07 14:41:16,339][19013] Avg episode rewards: #0: 22.154, true rewards: #0: 10.011
655
+ [2024-12-07 14:41:16,340][19013] Avg episode reward: 22.154, avg true_objective: 10.011
656
+ [2024-12-07 14:41:16,439][19013] Num frames 7100...
657
+ [2024-12-07 14:41:16,539][19013] Num frames 7200...
658
+ [2024-12-07 14:41:16,607][19013] Num frames 7300...
659
+ [2024-12-07 14:41:16,677][19013] Num frames 7400...
660
+ [2024-12-07 14:41:16,749][19013] Num frames 7500...
661
+ [2024-12-07 14:41:16,828][19013] Num frames 7600...
662
+ [2024-12-07 14:41:16,906][19013] Num frames 7700...
663
+ [2024-12-07 14:41:16,989][19013] Num frames 7800...
664
+ [2024-12-07 14:41:17,085][19013] Avg episode rewards: #0: 21.191, true rewards: #0: 9.816
665
+ [2024-12-07 14:41:17,086][19013] Avg episode reward: 21.191, avg true_objective: 9.816
666
+ [2024-12-07 14:41:17,144][19013] Num frames 7900...
667
+ [2024-12-07 14:41:17,259][19013] Num frames 8000...
668
+ [2024-12-07 14:41:17,352][19013] Num frames 8100...
669
+ [2024-12-07 14:41:17,432][19013] Num frames 8200...
670
+ [2024-12-07 14:41:17,513][19013] Num frames 8300...
671
+ [2024-12-07 14:41:17,595][19013] Num frames 8400...
672
+ [2024-12-07 14:41:17,676][19013] Num frames 8500...
673
+ [2024-12-07 14:41:17,758][19013] Num frames 8600...
674
+ [2024-12-07 14:41:17,838][19013] Num frames 8700...
675
+ [2024-12-07 14:41:17,906][19013] Avg episode rewards: #0: 20.908, true rewards: #0: 9.686
676
+ [2024-12-07 14:41:17,907][19013] Avg episode reward: 20.908, avg true_objective: 9.686
677
+ [2024-12-07 14:41:18,010][19013] Num frames 8800...
678
+ [2024-12-07 14:41:18,113][19013] Num frames 8900...
679
+ [2024-12-07 14:41:18,183][19013] Num frames 9000...
680
+ [2024-12-07 14:41:18,255][19013] Num frames 9100...
681
+ [2024-12-07 14:41:18,325][19013] Num frames 9200...
682
+ [2024-12-07 14:41:18,420][19013] Avg episode rewards: #0: 19.561, true rewards: #0: 9.261
683
+ [2024-12-07 14:41:18,421][19013] Avg episode reward: 19.561, avg true_objective: 9.261
684
+ [2024-12-07 14:41:34,293][19013] Replay video saved to /home/rahatchd/code/deep-rl-hugging-face/unit8/train_dir/default_experiment/replay.mp4!