Hugging Face's logo

ToonAga
/
rl_course_vizdoom_health_gathering_supreme

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results
Model card Files Metrics Community
ToonAga commited on
Commit
2e728c9
•
1 Parent(s): 0b5042b

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. .gitattributes +1 -0
  2. .summary/0/events.out.tfevents.1723716687.aa +3 -0
  3. README.md +56 -0
  4. checkpoint_p0/best_000000903_3698688_reward_25.759.pth +3 -0
  5. checkpoint_p0/checkpoint_000000978_4005888.pth +3 -0
  6. config.json +142 -0
  7. replay.mp4 +3 -0
  8. sf_log.txt +642 -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.1723716687.aa ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4980604d304d5ae9e5ae1fa952695406e8df40540c74f6fe9e544d01d308288b
3
+ size 88202
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: 9.43 +/- 4.74
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 ToonAga/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_000000903_3698688_reward_25.759.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90d99fbe5fd130c6e81874dd6c87372311aebc9bb068114a7192f214f4275fe6
3
+ size 34928614
checkpoint_p0/checkpoint_000000978_4005888.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf09f03b1aa88189c0dd4283c06501c3ef9c9bea4a0036aac15e8310e9bdf29f
3
+ size 34929028
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/aa/Documents/GitHub/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 sha256:548e82a06ec9f4d69319a0cfce434889781687134a2f2dba962bb361609e1fe9
3
+ size 18531599
sf_log.txt ADDED
@@ -0,0 +1,642 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [2024-08-15 13:11:28,399][3168197] Saving configuration to /home/aa/Documents/GitHub/RL-hugging_face/unit8/train_dir/default_experiment/config.json...
2
+ [2024-08-15 13:11:28,399][3168197] Rollout worker 0 uses device cpu
3
+ [2024-08-15 13:11:28,400][3168197] Rollout worker 1 uses device cpu
4
+ [2024-08-15 13:11:28,400][3168197] Rollout worker 2 uses device cpu
5
+ [2024-08-15 13:11:28,400][3168197] Rollout worker 3 uses device cpu
6
+ [2024-08-15 13:11:28,400][3168197] Rollout worker 4 uses device cpu
7
+ [2024-08-15 13:11:28,401][3168197] Rollout worker 5 uses device cpu
8
+ [2024-08-15 13:11:28,401][3168197] Rollout worker 6 uses device cpu
9
+ [2024-08-15 13:11:28,401][3168197] Rollout worker 7 uses device cpu
10
+ [2024-08-15 13:11:28,429][3168197] Using GPUs [0] for process 0 (actually maps to GPUs [0])
11
+ [2024-08-15 13:11:28,430][3168197] InferenceWorker_p0-w0: min num requests: 2
12
+ [2024-08-15 13:11:28,446][3168197] Starting all processes...
13
+ [2024-08-15 13:11:28,446][3168197] Starting process learner_proc0
14
+ [2024-08-15 13:11:28,496][3168197] Starting all processes...
15
+ [2024-08-15 13:11:28,501][3168197] Starting process inference_proc0-0
16
+ [2024-08-15 13:11:28,501][3168197] Starting process rollout_proc0
17
+ [2024-08-15 13:11:28,501][3168197] Starting process rollout_proc1
18
+ [2024-08-15 13:11:28,501][3168197] Starting process rollout_proc2
19
+ [2024-08-15 13:11:28,501][3168197] Starting process rollout_proc3
20
+ [2024-08-15 13:11:28,502][3168197] Starting process rollout_proc4
21
+ [2024-08-15 13:11:28,502][3168197] Starting process rollout_proc5
22
+ [2024-08-15 13:11:28,502][3168197] Starting process rollout_proc6
23
+ [2024-08-15 13:11:28,504][3168197] Starting process rollout_proc7
24
+ [2024-08-15 13:11:29,293][3172197] Using GPUs [0] for process 0 (actually maps to GPUs [0])
25
+ [2024-08-15 13:11:29,293][3172197] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
26
+ [2024-08-15 13:11:29,303][3172197] Num visible devices: 1
27
+ [2024-08-15 13:11:29,331][3172197] Starting seed is not provided
28
+ [2024-08-15 13:11:29,331][3172197] Using GPUs [0] for process 0 (actually maps to GPUs [0])
29
+ [2024-08-15 13:11:29,331][3172197] Initializing actor-critic model on device cuda:0
30
+ [2024-08-15 13:11:29,331][3172197] RunningMeanStd input shape: (3, 72, 128)
31
+ [2024-08-15 13:11:29,331][3172197] RunningMeanStd input shape: (1,)
32
+ [2024-08-15 13:11:29,338][3172197] ConvEncoder: input_channels=3
33
+ [2024-08-15 13:11:29,345][3172212] Worker 0 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19]
34
+ [2024-08-15 13:11:29,374][3172218] Worker 7 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19]
35
+ [2024-08-15 13:11:29,377][3172210] Worker 1 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19]
36
+ [2024-08-15 13:11:29,391][3172211] Using GPUs [0] for process 0 (actually maps to GPUs [0])
37
+ [2024-08-15 13:11:29,392][3172211] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
38
+ [2024-08-15 13:11:29,402][3172211] Num visible devices: 1
39
+ [2024-08-15 13:11:29,403][3172197] Conv encoder output size: 512
40
+ [2024-08-15 13:11:29,403][3172197] Policy head output size: 512
41
+ [2024-08-15 13:11:29,407][3172217] Worker 6 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19]
42
+ [2024-08-15 13:11:29,408][3172216] Worker 5 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19]
43
+ [2024-08-15 13:11:29,412][3172197] Created Actor Critic model with architecture:
44
+ [2024-08-15 13:11:29,412][3172197] ActorCriticSharedWeights(
45
+ (obs_normalizer): ObservationNormalizer(
46
+ (running_mean_std): RunningMeanStdDictInPlace(
47
+ (running_mean_std): ModuleDict(
48
+ (obs): RunningMeanStdInPlace()
49
+ )
50
+ )
51
+ )
52
+ (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
53
+ (encoder): VizdoomEncoder(
54
+ (basic_encoder): ConvEncoder(
55
+ (enc): RecursiveScriptModule(
56
+ original_name=ConvEncoderImpl
57
+ (conv_head): RecursiveScriptModule(
58
+ original_name=Sequential
59
+ (0): RecursiveScriptModule(original_name=Conv2d)
60
+ (1): RecursiveScriptModule(original_name=ELU)
61
+ (2): RecursiveScriptModule(original_name=Conv2d)
62
+ (3): RecursiveScriptModule(original_name=ELU)
63
+ (4): RecursiveScriptModule(original_name=Conv2d)
64
+ (5): RecursiveScriptModule(original_name=ELU)
65
+ )
66
+ (mlp_layers): RecursiveScriptModule(
67
+ original_name=Sequential
68
+ (0): RecursiveScriptModule(original_name=Linear)
69
+ (1): RecursiveScriptModule(original_name=ELU)
70
+ )
71
+ )
72
+ )
73
+ )
74
+ (core): ModelCoreRNN(
75
+ (core): GRU(512, 512)
76
+ )
77
+ (decoder): MlpDecoder(
78
+ (mlp): Identity()
79
+ )
80
+ (critic_linear): Linear(in_features=512, out_features=1, bias=True)
81
+ (action_parameterization): ActionParameterizationDefault(
82
+ (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
83
+ )
84
+ )
85
+ [2024-08-15 13:11:29,413][3172213] Worker 2 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19]
86
+ [2024-08-15 13:11:29,426][3172214] Worker 4 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19]
87
+ [2024-08-15 13:11:29,540][3172215] Worker 3 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19]
88
+ [2024-08-15 13:11:30,026][3172197] Using optimizer <class 'torch.optim.adam.Adam'>
89
+ [2024-08-15 13:11:30,026][3172197] No checkpoints found
90
+ [2024-08-15 13:11:30,026][3172197] Did not load from checkpoint, starting from scratch!
91
+ [2024-08-15 13:11:30,027][3172197] Initialized policy 0 weights for model version 0
92
+ [2024-08-15 13:11:30,028][3172197] LearnerWorker_p0 finished initialization!
93
+ [2024-08-15 13:11:30,028][3172197] Using GPUs [0] for process 0 (actually maps to GPUs [0])
94
+ [2024-08-15 13:11:30,065][3172211] RunningMeanStd input shape: (3, 72, 128)
95
+ [2024-08-15 13:11:30,066][3172211] RunningMeanStd input shape: (1,)
96
+ [2024-08-15 13:11:30,072][3172211] ConvEncoder: input_channels=3
97
+ [2024-08-15 13:11:30,113][3172211] Conv encoder output size: 512
98
+ [2024-08-15 13:11:30,113][3172211] Policy head output size: 512
99
+ [2024-08-15 13:11:30,625][3168197] Inference worker 0-0 is ready!
100
+ [2024-08-15 13:11:30,626][3168197] All inference workers are ready! Signal rollout workers to start!
101
+ [2024-08-15 13:11:30,640][3172210] Doom resolution: 160x120, resize resolution: (128, 72)
102
+ [2024-08-15 13:11:30,640][3172216] Doom resolution: 160x120, resize resolution: (128, 72)
103
+ [2024-08-15 13:11:30,641][3172214] Doom resolution: 160x120, resize resolution: (128, 72)
104
+ [2024-08-15 13:11:30,641][3172213] Doom resolution: 160x120, resize resolution: (128, 72)
105
+ [2024-08-15 13:11:30,641][3172217] Doom resolution: 160x120, resize resolution: (128, 72)
106
+ [2024-08-15 13:11:30,641][3172215] Doom resolution: 160x120, resize resolution: (128, 72)
107
+ [2024-08-15 13:11:30,641][3172212] Doom resolution: 160x120, resize resolution: (128, 72)
108
+ [2024-08-15 13:11:30,643][3172218] Doom resolution: 160x120, resize resolution: (128, 72)
109
+ [2024-08-15 13:11:31,104][3172215] Decorrelating experience for 0 frames...
110
+ [2024-08-15 13:11:31,107][3172210] Decorrelating experience for 0 frames...
111
+ [2024-08-15 13:11:31,108][3172217] Decorrelating experience for 0 frames...
112
+ [2024-08-15 13:11:31,108][3172218] Decorrelating experience for 0 frames...
113
+ [2024-08-15 13:11:31,109][3172212] Decorrelating experience for 0 frames...
114
+ [2024-08-15 13:11:31,109][3172216] Decorrelating experience for 0 frames...
115
+ [2024-08-15 13:11:31,111][3172213] Decorrelating experience for 0 frames...
116
+ [2024-08-15 13:11:31,306][3172213] Decorrelating experience for 32 frames...
117
+ [2024-08-15 13:11:31,311][3172215] Decorrelating experience for 32 frames...
118
+ [2024-08-15 13:11:31,312][3172216] Decorrelating experience for 32 frames...
119
+ [2024-08-15 13:11:31,314][3172210] Decorrelating experience for 32 frames...
120
+ [2024-08-15 13:11:31,346][3172214] Decorrelating experience for 0 frames...
121
+ [2024-08-15 13:11:31,404][3172217] Decorrelating experience for 32 frames...
122
+ [2024-08-15 13:11:31,511][3172213] Decorrelating experience for 64 frames...
123
+ [2024-08-15 13:11:31,513][3172212] Decorrelating experience for 32 frames...
124
+ [2024-08-15 13:11:31,535][3172214] Decorrelating experience for 32 frames...
125
+ [2024-08-15 13:11:31,544][3172215] Decorrelating experience for 64 frames...
126
+ [2024-08-15 13:11:31,588][3172218] Decorrelating experience for 32 frames...
127
+ [2024-08-15 13:11:31,636][3172217] Decorrelating experience for 64 frames...
128
+ [2024-08-15 13:11:31,736][3172216] Decorrelating experience for 64 frames...
129
+ [2024-08-15 13:11:31,742][3172214] Decorrelating experience for 64 frames...
130
+ [2024-08-15 13:11:31,761][3172213] Decorrelating experience for 96 frames...
131
+ [2024-08-15 13:11:31,766][3172212] Decorrelating experience for 64 frames...
132
+ [2024-08-15 13:11:31,771][3172215] Decorrelating experience for 96 frames...
133
+ [2024-08-15 13:11:31,799][3172218] Decorrelating experience for 64 frames...
134
+ [2024-08-15 13:11:31,859][3172217] Decorrelating experience for 96 frames...
135
+ [2024-08-15 13:11:31,945][3172210] Decorrelating experience for 64 frames...
136
+ [2024-08-15 13:11:31,976][3172212] Decorrelating experience for 96 frames...
137
+ [2024-08-15 13:11:31,987][3172218] Decorrelating experience for 96 frames...
138
+ [2024-08-15 13:11:31,990][3172216] Decorrelating experience for 96 frames...
139
+ [2024-08-15 13:11:32,058][3172214] Decorrelating experience for 96 frames...
140
+ [2024-08-15 13:11:32,076][3168197] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
141
+ [2024-08-15 13:11:32,299][3172210] Decorrelating experience for 96 frames...
142
+ [2024-08-15 13:11:32,370][3172197] Signal inference workers to stop experience collection...
143
+ [2024-08-15 13:11:32,372][3172211] InferenceWorker_p0-w0: stopping experience collection
144
+ [2024-08-15 13:11:33,006][3172197] Signal inference workers to resume experience collection...
145
+ [2024-08-15 13:11:33,006][3172211] InferenceWorker_p0-w0: resuming experience collection
146
+ [2024-08-15 13:11:34,056][3172211] Updated weights for policy 0, policy_version 10 (0.0154)
147
+ [2024-08-15 13:11:34,925][3172211] Updated weights for policy 0, policy_version 20 (0.0004)
148
+ [2024-08-15 13:11:35,796][3172211] Updated weights for policy 0, policy_version 30 (0.0004)
149
+ [2024-08-15 13:11:36,649][3172211] Updated weights for policy 0, policy_version 40 (0.0004)
150
+ [2024-08-15 13:11:37,076][3168197] Fps is (10 sec: 36045.0, 60 sec: 36045.0, 300 sec: 36045.0). Total num frames: 180224. Throughput: 0: 8297.2. Samples: 41486. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
151
+ [2024-08-15 13:11:37,077][3168197] Avg episode reward: [(0, '4.445')]
152
+ [2024-08-15 13:11:37,088][3172197] Saving new best policy, reward=4.445!
153
+ [2024-08-15 13:11:37,537][3172211] Updated weights for policy 0, policy_version 50 (0.0004)
154
+ [2024-08-15 13:11:38,389][3172211] Updated weights for policy 0, policy_version 60 (0.0004)
155
+ [2024-08-15 13:11:39,274][3172211] Updated weights for policy 0, policy_version 70 (0.0004)
156
+ [2024-08-15 13:11:40,124][3172211] Updated weights for policy 0, policy_version 80 (0.0004)
157
+ [2024-08-15 13:11:40,985][3172211] Updated weights for policy 0, policy_version 90 (0.0004)
158
+ [2024-08-15 13:11:41,854][3172211] Updated weights for policy 0, policy_version 100 (0.0004)
159
+ [2024-08-15 13:11:42,076][3168197] Fps is (10 sec: 41778.8, 60 sec: 41778.8, 300 sec: 41778.8). Total num frames: 417792. Throughput: 0: 7677.9. Samples: 76780. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
160
+ [2024-08-15 13:11:42,077][3168197] Avg episode reward: [(0, '4.514')]
161
+ [2024-08-15 13:11:42,078][3172197] Saving new best policy, reward=4.514!
162
+ [2024-08-15 13:11:42,747][3172211] Updated weights for policy 0, policy_version 110 (0.0004)
163
+ [2024-08-15 13:11:43,616][3172211] Updated weights for policy 0, policy_version 120 (0.0004)
164
+ [2024-08-15 13:11:44,492][3172211] Updated weights for policy 0, policy_version 130 (0.0004)
165
+ [2024-08-15 13:11:45,375][3172211] Updated weights for policy 0, policy_version 140 (0.0003)
166
+ [2024-08-15 13:11:46,255][3172211] Updated weights for policy 0, policy_version 150 (0.0004)
167
+ [2024-08-15 13:11:47,076][3168197] Fps is (10 sec: 47103.8, 60 sec: 43417.6, 300 sec: 43417.6). Total num frames: 651264. Throughput: 0: 9817.6. Samples: 147264. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
168
+ [2024-08-15 13:11:47,077][3168197] Avg episode reward: [(0, '4.628')]
169
+ [2024-08-15 13:11:47,079][3172197] Saving new best policy, reward=4.628!
170
+ [2024-08-15 13:11:47,140][3172211] Updated weights for policy 0, policy_version 160 (0.0004)
171
+ [2024-08-15 13:11:48,013][3172211] Updated weights for policy 0, policy_version 170 (0.0004)
172
+ [2024-08-15 13:11:48,423][3168197] Heartbeat connected on Batcher_0
173
+ [2024-08-15 13:11:48,426][3168197] Heartbeat connected on LearnerWorker_p0
174
+ [2024-08-15 13:11:48,431][3168197] Heartbeat connected on InferenceWorker_p0-w0
175
+ [2024-08-15 13:11:48,433][3168197] Heartbeat connected on RolloutWorker_w0
176
+ [2024-08-15 13:11:48,436][3168197] Heartbeat connected on RolloutWorker_w1
177
+ [2024-08-15 13:11:48,437][3168197] Heartbeat connected on RolloutWorker_w2
178
+ [2024-08-15 13:11:48,440][3168197] Heartbeat connected on RolloutWorker_w4
179
+ [2024-08-15 13:11:48,441][3168197] Heartbeat connected on RolloutWorker_w3
180
+ [2024-08-15 13:11:48,442][3168197] Heartbeat connected on RolloutWorker_w5
181
+ [2024-08-15 13:11:48,443][3168197] Heartbeat connected on RolloutWorker_w6
182
+ [2024-08-15 13:11:48,446][3168197] Heartbeat connected on RolloutWorker_w7
183
+ [2024-08-15 13:11:48,895][3172211] Updated weights for policy 0, policy_version 180 (0.0004)
184
+ [2024-08-15 13:11:49,765][3172211] Updated weights for policy 0, policy_version 190 (0.0004)
185
+ [2024-08-15 13:11:50,636][3172211] Updated weights for policy 0, policy_version 200 (0.0003)
186
+ [2024-08-15 13:11:51,502][3172211] Updated weights for policy 0, policy_version 210 (0.0003)
187
+ [2024-08-15 13:11:52,076][3168197] Fps is (10 sec: 46695.0, 60 sec: 44236.8, 300 sec: 44236.8). Total num frames: 884736. Throughput: 0: 10870.5. Samples: 217410. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
188
+ [2024-08-15 13:11:52,077][3168197] Avg episode reward: [(0, '4.880')]
189
+ [2024-08-15 13:11:52,078][3172197] Saving new best policy, reward=4.880!
190
+ [2024-08-15 13:11:52,396][3172211] Updated weights for policy 0, policy_version 220 (0.0004)
191
+ [2024-08-15 13:11:53,249][3172211] Updated weights for policy 0, policy_version 230 (0.0003)
192
+ [2024-08-15 13:11:54,116][3172211] Updated weights for policy 0, policy_version 240 (0.0003)
193
+ [2024-08-15 13:11:54,974][3172211] Updated weights for policy 0, policy_version 250 (0.0004)
194
+ [2024-08-15 13:11:55,824][3172211] Updated weights for policy 0, policy_version 260 (0.0003)
195
+ [2024-08-15 13:11:56,706][3172211] Updated weights for policy 0, policy_version 270 (0.0004)
196
+ [2024-08-15 13:11:57,076][3168197] Fps is (10 sec: 47103.8, 60 sec: 44892.1, 300 sec: 44892.1). Total num frames: 1122304. Throughput: 0: 10109.1. Samples: 252728. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
197
+ [2024-08-15 13:11:57,077][3168197] Avg episode reward: [(0, '5.626')]
198
+ [2024-08-15 13:11:57,079][3172197] Saving new best policy, reward=5.626!
199
+ [2024-08-15 13:11:57,573][3172211] Updated weights for policy 0, policy_version 280 (0.0003)
200
+ [2024-08-15 13:11:58,444][3172211] Updated weights for policy 0, policy_version 290 (0.0004)
201
+ [2024-08-15 13:11:59,315][3172211] Updated weights for policy 0, policy_version 300 (0.0004)
202
+ [2024-08-15 13:12:00,181][3172211] Updated weights for policy 0, policy_version 310 (0.0004)
203
+ [2024-08-15 13:12:01,066][3172211] Updated weights for policy 0, policy_version 320 (0.0003)
204
+ [2024-08-15 13:12:01,926][3172211] Updated weights for policy 0, policy_version 330 (0.0003)
205
+ [2024-08-15 13:12:02,076][3168197] Fps is (10 sec: 47103.8, 60 sec: 45192.5, 300 sec: 45192.5). Total num frames: 1355776. Throughput: 0: 10783.3. Samples: 323498. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
206
+ [2024-08-15 13:12:02,077][3168197] Avg episode reward: [(0, '6.828')]
207
+ [2024-08-15 13:12:02,078][3172197] Saving new best policy, reward=6.828!
208
+ [2024-08-15 13:12:02,830][3172211] Updated weights for policy 0, policy_version 340 (0.0004)
209
+ [2024-08-15 13:12:03,696][3172211] Updated weights for policy 0, policy_version 350 (0.0003)
210
+ [2024-08-15 13:12:04,564][3172211] Updated weights for policy 0, policy_version 360 (0.0004)
211
+ [2024-08-15 13:12:05,482][3172211] Updated weights for policy 0, policy_version 370 (0.0004)
212
+ [2024-08-15 13:12:06,361][3172211] Updated weights for policy 0, policy_version 380 (0.0004)
213
+ [2024-08-15 13:12:07,076][3168197] Fps is (10 sec: 46694.8, 60 sec: 45407.1, 300 sec: 45407.1). Total num frames: 1589248. Throughput: 0: 11232.9. Samples: 393152. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
214
+ [2024-08-15 13:12:07,077][3168197] Avg episode reward: [(0, '10.695')]
215
+ [2024-08-15 13:12:07,079][3172197] Saving new best policy, reward=10.695!
216
+ [2024-08-15 13:12:07,245][3172211] Updated weights for policy 0, policy_version 390 (0.0004)
217
+ [2024-08-15 13:12:08,131][3172211] Updated weights for policy 0, policy_version 400 (0.0004)
218
+ [2024-08-15 13:12:08,993][3172211] Updated weights for policy 0, policy_version 410 (0.0003)
219
+ [2024-08-15 13:12:09,852][3172211] Updated weights for policy 0, policy_version 420 (0.0003)
220
+ [2024-08-15 13:12:10,727][3172211] Updated weights for policy 0, policy_version 430 (0.0004)
221
+ [2024-08-15 13:12:11,589][3172211] Updated weights for policy 0, policy_version 440 (0.0004)
222
+ [2024-08-15 13:12:12,076][3168197] Fps is (10 sec: 46694.6, 60 sec: 45568.0, 300 sec: 45568.0). Total num frames: 1822720. Throughput: 0: 10705.9. Samples: 428234. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
223
+ [2024-08-15 13:12:12,077][3168197] Avg episode reward: [(0, '12.163')]
224
+ [2024-08-15 13:12:12,078][3172197] Saving new best policy, reward=12.163!
225
+ [2024-08-15 13:12:12,460][3172211] Updated weights for policy 0, policy_version 450 (0.0003)
226
+ [2024-08-15 13:12:13,334][3172211] Updated weights for policy 0, policy_version 460 (0.0003)
227
+ [2024-08-15 13:12:14,198][3172211] Updated weights for policy 0, policy_version 470 (0.0003)
228
+ [2024-08-15 13:12:15,069][3172211] Updated weights for policy 0, policy_version 480 (0.0004)
229
+ [2024-08-15 13:12:15,946][3172211] Updated weights for policy 0, policy_version 490 (0.0004)
230
+ [2024-08-15 13:12:16,823][3172211] Updated weights for policy 0, policy_version 500 (0.0004)
231
+ [2024-08-15 13:12:17,076][3168197] Fps is (10 sec: 46694.3, 60 sec: 45693.1, 300 sec: 45693.1). Total num frames: 2056192. Throughput: 0: 11089.5. Samples: 499028. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
232
+ [2024-08-15 13:12:17,077][3168197] Avg episode reward: [(0, '15.741')]
233
+ [2024-08-15 13:12:17,084][3172197] Saving new best policy, reward=15.741!
234
+ [2024-08-15 13:12:17,704][3172211] Updated weights for policy 0, policy_version 510 (0.0004)
235
+ [2024-08-15 13:12:18,575][3172211] Updated weights for policy 0, policy_version 520 (0.0004)
236
+ [2024-08-15 13:12:19,455][3172211] Updated weights for policy 0, policy_version 530 (0.0003)
237
+ [2024-08-15 13:12:20,333][3172211] Updated weights for policy 0, policy_version 540 (0.0004)
238
+ [2024-08-15 13:12:21,193][3172211] Updated weights for policy 0, policy_version 550 (0.0004)
239
+ [2024-08-15 13:12:22,059][3172211] Updated weights for policy 0, policy_version 560 (0.0004)
240
+ [2024-08-15 13:12:22,076][3168197] Fps is (10 sec: 47103.9, 60 sec: 45875.2, 300 sec: 45875.2). Total num frames: 2293760. Throughput: 0: 11723.2. Samples: 569028. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
241
+ [2024-08-15 13:12:22,077][3168197] Avg episode reward: [(0, '17.828')]
242
+ [2024-08-15 13:12:22,078][3172197] Saving new best policy, reward=17.828!
243
+ [2024-08-15 13:12:22,951][3172211] Updated weights for policy 0, policy_version 570 (0.0004)
244
+ [2024-08-15 13:12:23,809][3172211] Updated weights for policy 0, policy_version 580 (0.0004)
245
+ [2024-08-15 13:12:24,688][3172211] Updated weights for policy 0, policy_version 590 (0.0004)
246
+ [2024-08-15 13:12:25,572][3172211] Updated weights for policy 0, policy_version 600 (0.0004)
247
+ [2024-08-15 13:12:26,449][3172211] Updated weights for policy 0, policy_version 610 (0.0004)
248
+ [2024-08-15 13:12:27,076][3168197] Fps is (10 sec: 47103.5, 60 sec: 45949.6, 300 sec: 45949.6). Total num frames: 2527232. Throughput: 0: 11717.0. Samples: 604044. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
249
+ [2024-08-15 13:12:27,077][3168197] Avg episode reward: [(0, '18.732')]
250
+ [2024-08-15 13:12:27,079][3172197] Saving new best policy, reward=18.732!
251
+ [2024-08-15 13:12:27,346][3172211] Updated weights for policy 0, policy_version 620 (0.0004)
252
+ [2024-08-15 13:12:28,185][3172211] Updated weights for policy 0, policy_version 630 (0.0003)
253
+ [2024-08-15 13:12:29,080][3172211] Updated weights for policy 0, policy_version 640 (0.0004)
254
+ [2024-08-15 13:12:29,961][3172211] Updated weights for policy 0, policy_version 650 (0.0003)
255
+ [2024-08-15 13:12:30,833][3172211] Updated weights for policy 0, policy_version 660 (0.0004)
256
+ [2024-08-15 13:12:31,705][3172211] Updated weights for policy 0, policy_version 670 (0.0004)
257
+ [2024-08-15 13:12:32,076][3168197] Fps is (10 sec: 46693.9, 60 sec: 46011.7, 300 sec: 46011.7). Total num frames: 2760704. Throughput: 0: 11712.9. Samples: 674344. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
258
+ [2024-08-15 13:12:32,077][3168197] Avg episode reward: [(0, '18.633')]
259
+ [2024-08-15 13:12:32,592][3172211] Updated weights for policy 0, policy_version 680 (0.0004)
260
+ [2024-08-15 13:12:33,478][3172211] Updated weights for policy 0, policy_version 690 (0.0004)
261
+ [2024-08-15 13:12:34,345][3172211] Updated weights for policy 0, policy_version 700 (0.0003)
262
+ [2024-08-15 13:12:35,215][3172211] Updated weights for policy 0, policy_version 710 (0.0003)
263
+ [2024-08-15 13:12:36,082][3172211] Updated weights for policy 0, policy_version 720 (0.0004)
264
+ [2024-08-15 13:12:36,960][3172211] Updated weights for policy 0, policy_version 730 (0.0003)
265
+ [2024-08-15 13:12:37,076][3168197] Fps is (10 sec: 46694.7, 60 sec: 46899.1, 300 sec: 46064.2). Total num frames: 2994176. Throughput: 0: 11715.3. Samples: 744598. Policy #0 lag: (min: 0.0, avg: 0.9, max: 1.0)
266
+ [2024-08-15 13:12:37,077][3168197] Avg episode reward: [(0, '20.341')]
267
+ [2024-08-15 13:12:37,079][3172197] Saving new best policy, reward=20.341!
268
+ [2024-08-15 13:12:37,841][3172211] Updated weights for policy 0, policy_version 740 (0.0004)
269
+ [2024-08-15 13:12:38,688][3172211] Updated weights for policy 0, policy_version 750 (0.0004)
270
+ [2024-08-15 13:12:39,546][3172211] Updated weights for policy 0, policy_version 760 (0.0004)
271
+ [2024-08-15 13:12:40,411][3172211] Updated weights for policy 0, policy_version 770 (0.0004)
272
+ [2024-08-15 13:12:41,294][3172211] Updated weights for policy 0, policy_version 780 (0.0004)
273
+ [2024-08-15 13:12:42,076][3168197] Fps is (10 sec: 46694.6, 60 sec: 46831.0, 300 sec: 46109.2). Total num frames: 3227648. Throughput: 0: 11714.5. Samples: 779880. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
274
+ [2024-08-15 13:12:42,077][3168197] Avg episode reward: [(0, '22.969')]
275
+ [2024-08-15 13:12:42,086][3172197] Saving new best policy, reward=22.969!
276
+ [2024-08-15 13:12:42,178][3172211] Updated weights for policy 0, policy_version 790 (0.0004)
277
+ [2024-08-15 13:12:43,053][3172211] Updated weights for policy 0, policy_version 800 (0.0004)
278
+ [2024-08-15 13:12:43,939][3172211] Updated weights for policy 0, policy_version 810 (0.0004)
279
+ [2024-08-15 13:12:44,819][3172211] Updated weights for policy 0, policy_version 820 (0.0003)
280
+ [2024-08-15 13:12:45,699][3172211] Updated weights for policy 0, policy_version 830 (0.0004)
281
+ [2024-08-15 13:12:46,556][3172211] Updated weights for policy 0, policy_version 840 (0.0004)
282
+ [2024-08-15 13:12:47,076][3168197] Fps is (10 sec: 46694.4, 60 sec: 46830.9, 300 sec: 46148.2). Total num frames: 3461120. Throughput: 0: 11700.8. Samples: 850036. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
283
+ [2024-08-15 13:12:47,077][3168197] Avg episode reward: [(0, '22.828')]
284
+ [2024-08-15 13:12:47,432][3172211] Updated weights for policy 0, policy_version 850 (0.0003)
285
+ [2024-08-15 13:12:48,292][3172211] Updated weights for policy 0, policy_version 860 (0.0004)
286
+ [2024-08-15 13:12:49,167][3172211] Updated weights for policy 0, policy_version 870 (0.0003)
287
+ [2024-08-15 13:12:50,038][3172211] Updated weights for policy 0, policy_version 880 (0.0003)
288
+ [2024-08-15 13:12:50,900][3172211] Updated weights for policy 0, policy_version 890 (0.0004)
289
+ [2024-08-15 13:12:51,758][3172211] Updated weights for policy 0, policy_version 900 (0.0004)
290
+ [2024-08-15 13:12:52,076][3168197] Fps is (10 sec: 47103.7, 60 sec: 46899.1, 300 sec: 46233.5). Total num frames: 3698688. Throughput: 0: 11723.1. Samples: 920692. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
291
+ [2024-08-15 13:12:52,077][3168197] Avg episode reward: [(0, '25.759')]
292
+ [2024-08-15 13:12:52,078][3172197] Saving new best policy, reward=25.759!
293
+ [2024-08-15 13:12:52,639][3172211] Updated weights for policy 0, policy_version 910 (0.0004)
294
+ [2024-08-15 13:12:53,552][3172211] Updated weights for policy 0, policy_version 920 (0.0004)
295
+ [2024-08-15 13:12:54,413][3172211] Updated weights for policy 0, policy_version 930 (0.0003)
296
+ [2024-08-15 13:12:55,282][3172211] Updated weights for policy 0, policy_version 940 (0.0003)
297
+ [2024-08-15 13:12:56,165][3172211] Updated weights for policy 0, policy_version 950 (0.0004)
298
+ [2024-08-15 13:12:57,048][3172211] Updated weights for policy 0, policy_version 960 (0.0004)
299
+ [2024-08-15 13:12:57,076][3168197] Fps is (10 sec: 47104.1, 60 sec: 46831.0, 300 sec: 46260.7). Total num frames: 3932160. Throughput: 0: 11717.8. Samples: 955536. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
300
+ [2024-08-15 13:12:57,077][3168197] Avg episode reward: [(0, '25.022')]
301
+ [2024-08-15 13:12:57,924][3172211] Updated weights for policy 0, policy_version 970 (0.0004)
302
+ [2024-08-15 13:12:58,621][3172197] Stopping Batcher_0...
303
+ [2024-08-15 13:12:58,621][3172197] Saving /home/aa/Documents/GitHub/RL-hugging_face/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
304
+ [2024-08-15 13:12:58,621][3168197] Component Batcher_0 stopped!
305
+ [2024-08-15 13:12:58,622][3172197] Loop batcher_evt_loop terminating...
306
+ [2024-08-15 13:12:58,628][3172211] Weights refcount: 2 0
307
+ [2024-08-15 13:12:58,628][3172211] Stopping InferenceWorker_p0-w0...
308
+ [2024-08-15 13:12:58,629][3172211] Loop inference_proc0-0_evt_loop terminating...
309
+ [2024-08-15 13:12:58,629][3168197] Component InferenceWorker_p0-w0 stopped!
310
+ [2024-08-15 13:12:58,650][3172197] Saving /home/aa/Documents/GitHub/RL-hugging_face/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
311
+ [2024-08-15 13:12:58,693][3172197] Stopping LearnerWorker_p0...
312
+ [2024-08-15 13:12:58,693][3172197] Loop learner_proc0_evt_loop terminating...
313
+ [2024-08-15 13:12:58,693][3168197] Component LearnerWorker_p0 stopped!
314
+ [2024-08-15 13:12:58,754][3172213] Stopping RolloutWorker_w2...
315
+ [2024-08-15 13:12:58,754][3172216] Stopping RolloutWorker_w5...
316
+ [2024-08-15 13:12:58,755][3172213] Loop rollout_proc2_evt_loop terminating...
317
+ [2024-08-15 13:12:58,755][3172216] Loop rollout_proc5_evt_loop terminating...
318
+ [2024-08-15 13:12:58,754][3168197] Component RolloutWorker_w2 stopped!
319
+ [2024-08-15 13:12:58,755][3168197] Component RolloutWorker_w5 stopped!
320
+ [2024-08-15 13:12:58,758][3172215] Stopping RolloutWorker_w3...
321
+ [2024-08-15 13:12:58,758][3172214] Stopping RolloutWorker_w4...
322
+ [2024-08-15 13:12:58,759][3172214] Loop rollout_proc4_evt_loop terminating...
323
+ [2024-08-15 13:12:58,759][3172215] Loop rollout_proc3_evt_loop terminating...
324
+ [2024-08-15 13:12:58,758][3168197] Component RolloutWorker_w3 stopped!
325
+ [2024-08-15 13:12:58,759][3168197] Component RolloutWorker_w4 stopped!
326
+ [2024-08-15 13:12:58,762][3172217] Stopping RolloutWorker_w6...
327
+ [2024-08-15 13:12:58,763][3172217] Loop rollout_proc6_evt_loop terminating...
328
+ [2024-08-15 13:12:58,762][3168197] Component RolloutWorker_w6 stopped!
329
+ [2024-08-15 13:12:58,766][3172210] Stopping RolloutWorker_w1...
330
+ [2024-08-15 13:12:58,767][3172210] Loop rollout_proc1_evt_loop terminating...
331
+ [2024-08-15 13:12:58,767][3168197] Component RolloutWorker_w1 stopped!
332
+ [2024-08-15 13:12:58,775][3172212] Stopping RolloutWorker_w0...
333
+ [2024-08-15 13:12:58,775][3172218] Stopping RolloutWorker_w7...
334
+ [2024-08-15 13:12:58,775][3172218] Loop rollout_proc7_evt_loop terminating...
335
+ [2024-08-15 13:12:58,775][3172212] Loop rollout_proc0_evt_loop terminating...
336
+ [2024-08-15 13:12:58,775][3168197] Component RolloutWorker_w0 stopped!
337
+ [2024-08-15 13:12:58,776][3168197] Component RolloutWorker_w7 stopped!
338
+ [2024-08-15 13:12:58,777][3168197] Waiting for process learner_proc0 to stop...
339
+ [2024-08-15 13:12:59,139][3168197] Waiting for process inference_proc0-0 to join...
340
+ [2024-08-15 13:12:59,140][3168197] Waiting for process rollout_proc0 to join...
341
+ [2024-08-15 13:12:59,140][3168197] Waiting for process rollout_proc1 to join...
342
+ [2024-08-15 13:12:59,141][3168197] Waiting for process rollout_proc2 to join...
343
+ [2024-08-15 13:12:59,141][3168197] Waiting for process rollout_proc3 to join...
344
+ [2024-08-15 13:12:59,142][3168197] Waiting for process rollout_proc4 to join...
345
+ [2024-08-15 13:12:59,142][3168197] Waiting for process rollout_proc5 to join...
346
+ [2024-08-15 13:12:59,142][3168197] Waiting for process rollout_proc6 to join...
347
+ [2024-08-15 13:12:59,143][3168197] Waiting for process rollout_proc7 to join...
348
+ [2024-08-15 13:12:59,143][3168197] Batcher 0 profile tree view:
349
+ batching: 10.6741, releasing_batches: 0.0124
350
+ [2024-08-15 13:12:59,143][3168197] InferenceWorker_p0-w0 profile tree view:
351
+ wait_policy: 0.0000
352
+ wait_policy_total: 2.1037
353
+ update_model: 1.3475
354
+ weight_update: 0.0004
355
+ one_step: 0.0011
356
+ handle_policy_step: 79.5799
357
+ deserialize: 3.9274, stack: 0.4281, obs_to_device_normalize: 20.3408, forward: 33.8913, send_messages: 4.7144
358
+ prepare_outputs: 13.3851
359
+ to_cpu: 9.1897
360
+ [2024-08-15 13:12:59,144][3168197] Learner 0 profile tree view:
361
+ misc: 0.0035, prepare_batch: 4.7486
362
+ train: 11.9903
363
+ epoch_init: 0.0025, minibatch_init: 0.0029, losses_postprocess: 0.1409, kl_divergence: 0.1522, after_optimizer: 2.5395
364
+ calculate_losses: 5.2697
365
+ losses_init: 0.0013, forward_head: 0.5091, bptt_initial: 3.4423, tail: 0.2683, advantages_returns: 0.0777, losses: 0.4859
366
+ bptt: 0.4023
367
+ bptt_forward_core: 0.3841
368
+ update: 3.7039
369
+ clip: 0.4612
370
+ [2024-08-15 13:12:59,144][3168197] RolloutWorker_w0 profile tree view:
371
+ wait_for_trajectories: 0.0762, enqueue_policy_requests: 4.2272, env_step: 45.6476, overhead: 3.0472, complete_rollouts: 0.1297
372
+ save_policy_outputs: 4.6212
373
+ split_output_tensors: 1.6420
374
+ [2024-08-15 13:12:59,144][3168197] RolloutWorker_w7 profile tree view:
375
+ wait_for_trajectories: 0.0735, enqueue_policy_requests: 4.1537, env_step: 45.6444, overhead: 3.0266, complete_rollouts: 0.1277
376
+ save_policy_outputs: 4.6463
377
+ split_output_tensors: 1.6661
378
+ [2024-08-15 13:12:59,144][3168197] Loop Runner_EvtLoop terminating...
379
+ [2024-08-15 13:12:59,145][3168197] Runner profile tree view:
380
+ main_loop: 90.6988
381
+ [2024-08-15 13:12:59,145][3168197] Collected {0: 4005888}, FPS: 44167.0
382
+ [2024-08-15 13:13:38,128][3168197] Loading existing experiment configuration from /home/aa/Documents/GitHub/RL-hugging_face/unit8/train_dir/default_experiment/config.json
383
+ [2024-08-15 13:13:38,129][3168197] Overriding arg 'num_workers' with value 1 passed from command line
384
+ [2024-08-15 13:13:38,130][3168197] Adding new argument 'no_render'=True that is not in the saved config file!
385
+ [2024-08-15 13:13:38,130][3168197] Adding new argument 'save_video'=True that is not in the saved config file!
386
+ [2024-08-15 13:13:38,130][3168197] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
387
+ [2024-08-15 13:13:38,131][3168197] Adding new argument 'video_name'=None that is not in the saved config file!
388
+ [2024-08-15 13:13:38,131][3168197] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
389
+ [2024-08-15 13:13:38,131][3168197] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
390
+ [2024-08-15 13:13:38,132][3168197] Adding new argument 'push_to_hub'=False that is not in the saved config file!
391
+ [2024-08-15 13:13:38,132][3168197] Adding new argument 'hf_repository'=None that is not in the saved config file!
392
+ [2024-08-15 13:13:38,132][3168197] Adding new argument 'policy_index'=0 that is not in the saved config file!
393
+ [2024-08-15 13:13:38,132][3168197] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
394
+ [2024-08-15 13:13:38,132][3168197] Adding new argument 'train_script'=None that is not in the saved config file!
395
+ [2024-08-15 13:13:38,132][3168197] Adding new argument 'enjoy_script'=None that is not in the saved config file!
396
+ [2024-08-15 13:13:38,132][3168197] Using frameskip 1 and render_action_repeat=4 for evaluation
397
+ [2024-08-15 13:13:38,138][3168197] Doom resolution: 160x120, resize resolution: (128, 72)
398
+ [2024-08-15 13:13:38,138][3168197] RunningMeanStd input shape: (3, 72, 128)
399
+ [2024-08-15 13:13:38,139][3168197] RunningMeanStd input shape: (1,)
400
+ [2024-08-15 13:13:38,144][3168197] ConvEncoder: input_channels=3
401
+ [2024-08-15 13:13:38,203][3168197] Conv encoder output size: 512
402
+ [2024-08-15 13:13:38,204][3168197] Policy head output size: 512
403
+ [2024-08-15 13:13:38,771][3168197] Loading state from checkpoint /home/aa/Documents/GitHub/RL-hugging_face/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
404
+ [2024-08-15 13:13:39,495][3168197] Num frames 100...
405
+ [2024-08-15 13:13:39,536][3168197] Num frames 200...
406
+ [2024-08-15 13:13:39,576][3168197] Num frames 300...
407
+ [2024-08-15 13:13:39,617][3168197] Num frames 400...
408
+ [2024-08-15 13:13:39,657][3168197] Num frames 500...
409
+ [2024-08-15 13:13:39,697][3168197] Num frames 600...
410
+ [2024-08-15 13:13:39,738][3168197] Num frames 700...
411
+ [2024-08-15 13:13:39,780][3168197] Num frames 800...
412
+ [2024-08-15 13:13:39,821][3168197] Num frames 900...
413
+ [2024-08-15 13:13:39,862][3168197] Num frames 1000...
414
+ [2024-08-15 13:13:39,902][3168197] Num frames 1100...
415
+ [2024-08-15 13:13:39,944][3168197] Num frames 1200...
416
+ [2024-08-15 13:13:39,985][3168197] Num frames 1300...
417
+ [2024-08-15 13:13:40,026][3168197] Num frames 1400...
418
+ [2024-08-15 13:13:40,067][3168197] Num frames 1500...
419
+ [2024-08-15 13:13:40,108][3168197] Num frames 1600...
420
+ [2024-08-15 13:13:40,149][3168197] Num frames 1700...
421
+ [2024-08-15 13:13:40,190][3168197] Num frames 1800...
422
+ [2024-08-15 13:13:40,232][3168197] Num frames 1900...
423
+ [2024-08-15 13:13:40,273][3168197] Num frames 2000...
424
+ [2024-08-15 13:13:40,325][3168197] Num frames 2100...
425
+ [2024-08-15 13:13:40,376][3168197] Avg episode rewards: #0: 55.999, true rewards: #0: 21.000
426
+ [2024-08-15 13:13:40,377][3168197] Avg episode reward: 55.999, avg true_objective: 21.000
427
+ [2024-08-15 13:13:40,419][3168197] Num frames 2200...
428
+ [2024-08-15 13:13:40,460][3168197] Num frames 2300...
429
+ [2024-08-15 13:13:40,501][3168197] Num frames 2400...
430
+ [2024-08-15 13:13:40,542][3168197] Num frames 2500...
431
+ [2024-08-15 13:13:40,583][3168197] Num frames 2600...
432
+ [2024-08-15 13:13:40,667][3168197] Avg episode rewards: #0: 32.379, true rewards: #0: 13.380
433
+ [2024-08-15 13:13:40,667][3168197] Avg episode reward: 32.379, avg true_objective: 13.380
434
+ [2024-08-15 13:13:40,678][3168197] Num frames 2700...
435
+ [2024-08-15 13:13:40,719][3168197] Num frames 2800...
436
+ [2024-08-15 13:13:40,760][3168197] Num frames 2900...
437
+ [2024-08-15 13:13:40,800][3168197] Num frames 3000...
438
+ [2024-08-15 13:13:40,840][3168197] Num frames 3100...
439
+ [2024-08-15 13:13:40,880][3168197] Num frames 3200...
440
+ [2024-08-15 13:13:40,921][3168197] Num frames 3300...
441
+ [2024-08-15 13:13:40,961][3168197] Num frames 3400...
442
+ [2024-08-15 13:13:41,001][3168197] Num frames 3500...
443
+ [2024-08-15 13:13:41,042][3168197] Num frames 3600...
444
+ [2024-08-15 13:13:41,083][3168197] Num frames 3700...
445
+ [2024-08-15 13:13:41,123][3168197] Num frames 3800...
446
+ [2024-08-15 13:13:41,163][3168197] Num frames 3900...
447
+ [2024-08-15 13:13:41,247][3168197] Avg episode rewards: #0: 32.593, true rewards: #0: 13.260
448
+ [2024-08-15 13:13:41,248][3168197] Avg episode reward: 32.593, avg true_objective: 13.260
449
+ [2024-08-15 13:13:41,259][3168197] Num frames 4000...
450
+ [2024-08-15 13:13:41,299][3168197] Num frames 4100...
451
+ [2024-08-15 13:13:41,339][3168197] Num frames 4200...
452
+ [2024-08-15 13:13:41,379][3168197] Num frames 4300...
453
+ [2024-08-15 13:13:41,420][3168197] Num frames 4400...
454
+ [2024-08-15 13:13:41,460][3168197] Num frames 4500...
455
+ [2024-08-15 13:13:41,500][3168197] Num frames 4600...
456
+ [2024-08-15 13:13:41,540][3168197] Num frames 4700...
457
+ [2024-08-15 13:13:41,579][3168197] Num frames 4800...
458
+ [2024-08-15 13:13:41,640][3168197] Avg episode rewards: #0: 29.050, true rewards: #0: 12.050
459
+ [2024-08-15 13:13:41,640][3168197] Avg episode reward: 29.050, avg true_objective: 12.050
460
+ [2024-08-15 13:13:41,674][3168197] Num frames 4900...
461
+ [2024-08-15 13:13:41,714][3168197] Num frames 5000...
462
+ [2024-08-15 13:13:41,754][3168197] Num frames 5100...
463
+ [2024-08-15 13:13:41,794][3168197] Num frames 5200...
464
+ [2024-08-15 13:13:41,835][3168197] Num frames 5300...
465
+ [2024-08-15 13:13:41,875][3168197] Num frames 5400...
466
+ [2024-08-15 13:13:41,915][3168197] Num frames 5500...
467
+ [2024-08-15 13:13:41,956][3168197] Num frames 5600...
468
+ [2024-08-15 13:13:41,996][3168197] Num frames 5700...
469
+ [2024-08-15 13:13:42,039][3168197] Num frames 5800...
470
+ [2024-08-15 13:13:42,111][3168197] Avg episode rewards: #0: 27.694, true rewards: #0: 11.694
471
+ [2024-08-15 13:13:42,112][3168197] Avg episode reward: 27.694, avg true_objective: 11.694
472
+ [2024-08-15 13:13:42,135][3168197] Num frames 5900...
473
+ [2024-08-15 13:13:42,178][3168197] Num frames 6000...
474
+ [2024-08-15 13:13:42,220][3168197] Num frames 6100...
475
+ [2024-08-15 13:13:42,296][3168197] Avg episode rewards: #0: 23.923, true rewards: #0: 10.257
476
+ [2024-08-15 13:13:42,297][3168197] Avg episode reward: 23.923, avg true_objective: 10.257
477
+ [2024-08-15 13:13:42,317][3168197] Num frames 6200...
478
+ [2024-08-15 13:13:42,359][3168197] Num frames 6300...
479
+ [2024-08-15 13:13:42,402][3168197] Num frames 6400...
480
+ [2024-08-15 13:13:42,444][3168197] Num frames 6500...
481
+ [2024-08-15 13:13:42,487][3168197] Num frames 6600...
482
+ [2024-08-15 13:13:42,530][3168197] Num frames 6700...
483
+ [2024-08-15 13:13:42,595][3168197] Avg episode rewards: #0: 21.900, true rewards: #0: 9.614
484
+ [2024-08-15 13:13:42,595][3168197] Avg episode reward: 21.900, avg true_objective: 9.614
485
+ [2024-08-15 13:13:42,625][3168197] Num frames 6800...
486
+ [2024-08-15 13:13:42,667][3168197] Num frames 6900...
487
+ [2024-08-15 13:13:42,710][3168197] Num frames 7000...
488
+ [2024-08-15 13:13:42,789][3168197] Avg episode rewards: #0: 19.827, true rewards: #0: 8.827
489
+ [2024-08-15 13:13:42,790][3168197] Avg episode reward: 19.827, avg true_objective: 8.827
490
+ [2024-08-15 13:13:42,807][3168197] Num frames 7100...
491
+ [2024-08-15 13:13:42,850][3168197] Num frames 7200...
492
+ [2024-08-15 13:13:42,892][3168197] Num frames 7300...
493
+ [2024-08-15 13:13:42,935][3168197] Num frames 7400...
494
+ [2024-08-15 13:13:42,993][3168197] Avg episode rewards: #0: 18.127, true rewards: #0: 8.238
495
+ [2024-08-15 13:13:42,994][3168197] Avg episode reward: 18.127, avg true_objective: 8.238
496
+ [2024-08-15 13:13:43,031][3168197] Num frames 7500...
497
+ [2024-08-15 13:13:43,074][3168197] Num frames 7600...
498
+ [2024-08-15 13:13:43,116][3168197] Num frames 7700...
499
+ [2024-08-15 13:13:43,159][3168197] Num frames 7800...
500
+ [2024-08-15 13:13:43,201][3168197] Num frames 7900...
501
+ [2024-08-15 13:13:43,245][3168197] Num frames 8000...
502
+ [2024-08-15 13:13:43,288][3168197] Num frames 8100...
503
+ [2024-08-15 13:13:43,331][3168197] Num frames 8200...
504
+ [2024-08-15 13:13:43,403][3168197] Avg episode rewards: #0: 17.846, true rewards: #0: 8.246
505
+ [2024-08-15 13:13:43,403][3168197] Avg episode reward: 17.846, avg true_objective: 8.246
506
+ [2024-08-15 13:13:51,561][3168197] Replay video saved to /home/aa/Documents/GitHub/RL-hugging_face/unit8/train_dir/default_experiment/replay.mp4!
507
+ [2024-08-15 13:16:21,918][3168197] Loading existing experiment configuration from /home/aa/Documents/GitHub/RL-hugging_face/unit8/train_dir/default_experiment/config.json
508
+ [2024-08-15 13:16:21,919][3168197] Overriding arg 'num_workers' with value 1 passed from command line
509
+ [2024-08-15 13:16:21,919][3168197] Adding new argument 'no_render'=True that is not in the saved config file!
510
+ [2024-08-15 13:16:21,919][3168197] Adding new argument 'save_video'=True that is not in the saved config file!
511
+ [2024-08-15 13:16:21,919][3168197] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
512
+ [2024-08-15 13:16:21,919][3168197] Adding new argument 'video_name'=None that is not in the saved config file!
513
+ [2024-08-15 13:16:21,920][3168197] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
514
+ [2024-08-15 13:16:21,920][3168197] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
515
+ [2024-08-15 13:16:21,920][3168197] Adding new argument 'push_to_hub'=True that is not in the saved config file!
516
+ [2024-08-15 13:16:21,920][3168197] Adding new argument 'hf_repository'='ToonAga/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
517
+ [2024-08-15 13:16:21,921][3168197] Adding new argument 'policy_index'=0 that is not in the saved config file!
518
+ [2024-08-15 13:16:21,921][3168197] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
519
+ [2024-08-15 13:16:21,921][3168197] Adding new argument 'train_script'=None that is not in the saved config file!
520
+ [2024-08-15 13:16:21,921][3168197] Adding new argument 'enjoy_script'=None that is not in the saved config file!
521
+ [2024-08-15 13:16:21,921][3168197] Using frameskip 1 and render_action_repeat=4 for evaluation
522
+ [2024-08-15 13:16:21,927][3168197] RunningMeanStd input shape: (3, 72, 128)
523
+ [2024-08-15 13:16:21,927][3168197] RunningMeanStd input shape: (1,)
524
+ [2024-08-15 13:16:21,932][3168197] ConvEncoder: input_channels=3
525
+ [2024-08-15 13:16:21,946][3168197] Conv encoder output size: 512
526
+ [2024-08-15 13:16:21,946][3168197] Policy head output size: 512
527
+ [2024-08-15 13:16:21,972][3168197] Loading state from checkpoint /home/aa/Documents/GitHub/RL-hugging_face/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
528
+ [2024-08-15 13:16:22,484][3168197] Num frames 100...
529
+ [2024-08-15 13:16:22,524][3168197] Num frames 200...
530
+ [2024-08-15 13:16:22,563][3168197] Num frames 300...
531
+ [2024-08-15 13:16:22,604][3168197] Num frames 400...
532
+ [2024-08-15 13:16:22,643][3168197] Num frames 500...
533
+ [2024-08-15 13:16:22,699][3168197] Avg episode rewards: #0: 11.100, true rewards: #0: 5.100
534
+ [2024-08-15 13:16:22,700][3168197] Avg episode reward: 11.100, avg true_objective: 5.100
535
+ [2024-08-15 13:16:22,737][3168197] Num frames 600...
536
+ [2024-08-15 13:16:22,776][3168197] Num frames 700...
537
+ [2024-08-15 13:16:22,815][3168197] Num frames 800...
538
+ [2024-08-15 13:16:22,854][3168197] Num frames 900...
539
+ [2024-08-15 13:16:22,893][3168197] Num frames 1000...
540
+ [2024-08-15 13:16:22,932][3168197] Num frames 1100...
541
+ [2024-08-15 13:16:22,972][3168197] Num frames 1200...
542
+ [2024-08-15 13:16:23,030][3168197] Avg episode rewards: #0: 13.070, true rewards: #0: 6.070
543
+ [2024-08-15 13:16:23,030][3168197] Avg episode reward: 13.070, avg true_objective: 6.070
544
+ [2024-08-15 13:16:23,066][3168197] Num frames 1300...
545
+ [2024-08-15 13:16:23,105][3168197] Num frames 1400...
546
+ [2024-08-15 13:16:23,145][3168197] Num frames 1500...
547
+ [2024-08-15 13:16:23,186][3168197] Num frames 1600...
548
+ [2024-08-15 13:16:23,227][3168197] Num frames 1700...
549
+ [2024-08-15 13:16:23,268][3168197] Num frames 1800...
550
+ [2024-08-15 13:16:23,307][3168197] Num frames 1900...
551
+ [2024-08-15 13:16:23,347][3168197] Num frames 2000...
552
+ [2024-08-15 13:16:23,387][3168197] Num frames 2100...
553
+ [2024-08-15 13:16:23,426][3168197] Num frames 2200...
554
+ [2024-08-15 13:16:23,465][3168197] Num frames 2300...
555
+ [2024-08-15 13:16:23,539][3168197] Avg episode rewards: #0: 17.513, true rewards: #0: 7.847
556
+ [2024-08-15 13:16:23,540][3168197] Avg episode reward: 17.513, avg true_objective: 7.847
557
+ [2024-08-15 13:16:23,559][3168197] Num frames 2400...
558
+ [2024-08-15 13:16:23,598][3168197] Num frames 2500...
559
+ [2024-08-15 13:16:23,638][3168197] Num frames 2600...
560
+ [2024-08-15 13:16:23,677][3168197] Num frames 2700...
561
+ [2024-08-15 13:16:23,716][3168197] Num frames 2800...
562
+ [2024-08-15 13:16:23,756][3168197] Num frames 2900...
563
+ [2024-08-15 13:16:23,795][3168197] Num frames 3000...
564
+ [2024-08-15 13:16:23,835][3168197] Num frames 3100...
565
+ [2024-08-15 13:16:23,911][3168197] Avg episode rewards: #0: 18.403, true rewards: #0: 7.902
566
+ [2024-08-15 13:16:23,912][3168197] Avg episode reward: 18.403, avg true_objective: 7.902
567
+ [2024-08-15 13:16:23,928][3168197] Num frames 3200...
568
+ [2024-08-15 13:16:23,967][3168197] Num frames 3300...
569
+ [2024-08-15 13:16:24,006][3168197] Num frames 3400...
570
+ [2024-08-15 13:16:24,046][3168197] Num frames 3500...
571
+ [2024-08-15 13:16:24,085][3168197] Num frames 3600...
572
+ [2024-08-15 13:16:24,125][3168197] Num frames 3700...
573
+ [2024-08-15 13:16:24,165][3168197] Num frames 3800...
574
+ [2024-08-15 13:16:24,206][3168197] Num frames 3900...
575
+ [2024-08-15 13:16:24,246][3168197] Num frames 4000...
576
+ [2024-08-15 13:16:24,287][3168197] Num frames 4100...
577
+ [2024-08-15 13:16:24,329][3168197] Num frames 4200...
578
+ [2024-08-15 13:16:24,370][3168197] Num frames 4300...
579
+ [2024-08-15 13:16:24,409][3168197] Num frames 4400...
580
+ [2024-08-15 13:16:24,449][3168197] Num frames 4500...
581
+ [2024-08-15 13:16:24,489][3168197] Num frames 4600...
582
+ [2024-08-15 13:16:24,528][3168197] Num frames 4700...
583
+ [2024-08-15 13:16:24,569][3168197] Num frames 4800...
584
+ [2024-08-15 13:16:24,623][3168197] Num frames 4900...
585
+ [2024-08-15 13:16:24,664][3168197] Num frames 5000...
586
+ [2024-08-15 13:16:24,704][3168197] Num frames 5100...
587
+ [2024-08-15 13:16:24,743][3168197] Num frames 5200...
588
+ [2024-08-15 13:16:24,820][3168197] Avg episode rewards: #0: 25.322, true rewards: #0: 10.522
589
+ [2024-08-15 13:16:24,821][3168197] Avg episode reward: 25.322, avg true_objective: 10.522
590
+ [2024-08-15 13:16:24,837][3168197] Num frames 5300...
591
+ [2024-08-15 13:16:24,877][3168197] Num frames 5400...
592
+ [2024-08-15 13:16:24,916][3168197] Num frames 5500...
593
+ [2024-08-15 13:16:24,955][3168197] Num frames 5600...
594
+ [2024-08-15 13:16:24,995][3168197] Num frames 5700...
595
+ [2024-08-15 13:16:25,037][3168197] Num frames 5800...
596
+ [2024-08-15 13:16:25,077][3168197] Num frames 5900...
597
+ [2024-08-15 13:16:25,117][3168197] Num frames 6000...
598
+ [2024-08-15 13:16:25,157][3168197] Num frames 6100...
599
+ [2024-08-15 13:16:25,196][3168197] Num frames 6200...
600
+ [2024-08-15 13:16:25,235][3168197] Num frames 6300...
601
+ [2024-08-15 13:16:25,311][3168197] Avg episode rewards: #0: 25.598, true rewards: #0: 10.598
602
+ [2024-08-15 13:16:25,311][3168197] Avg episode reward: 25.598, avg true_objective: 10.598
603
+ [2024-08-15 13:16:25,330][3168197] Num frames 6400...
604
+ [2024-08-15 13:16:25,372][3168197] Num frames 6500...
605
+ [2024-08-15 13:16:25,411][3168197] Num frames 6600...
606
+ [2024-08-15 13:16:25,450][3168197] Num frames 6700...
607
+ [2024-08-15 13:16:25,490][3168197] Num frames 6800...
608
+ [2024-08-15 13:16:25,529][3168197] Num frames 6900...
609
+ [2024-08-15 13:16:25,569][3168197] Num frames 7000...
610
+ [2024-08-15 13:16:25,633][3168197] Avg episode rewards: #0: 23.759, true rewards: #0: 10.044
611
+ [2024-08-15 13:16:25,634][3168197] Avg episode reward: 23.759, avg true_objective: 10.044
612
+ [2024-08-15 13:16:25,663][3168197] Num frames 7100...
613
+ [2024-08-15 13:16:25,703][3168197] Num frames 7200...
614
+ [2024-08-15 13:16:25,791][3168197] Avg episode rewards: #0: 21.109, true rewards: #0: 9.109
615
+ [2024-08-15 13:16:25,792][3168197] Avg episode reward: 21.109, avg true_objective: 9.109
616
+ [2024-08-15 13:16:25,799][3168197] Num frames 7300...
617
+ [2024-08-15 13:16:25,839][3168197] Num frames 7400...
618
+ [2024-08-15 13:16:25,880][3168197] Num frames 7500...
619
+ [2024-08-15 13:16:25,920][3168197] Num frames 7600...
620
+ [2024-08-15 13:16:25,960][3168197] Num frames 7700...
621
+ [2024-08-15 13:16:26,002][3168197] Num frames 7800...
622
+ [2024-08-15 13:16:26,043][3168197] Num frames 7900...
623
+ [2024-08-15 13:16:26,083][3168197] Num frames 8000...
624
+ [2024-08-15 13:16:26,125][3168197] Num frames 8100...
625
+ [2024-08-15 13:16:26,166][3168197] Num frames 8200...
626
+ [2024-08-15 13:16:26,209][3168197] Num frames 8300...
627
+ [2024-08-15 13:16:26,279][3168197] Avg episode rewards: #0: 21.382, true rewards: #0: 9.271
628
+ [2024-08-15 13:16:26,279][3168197] Avg episode reward: 21.382, avg true_objective: 9.271
629
+ [2024-08-15 13:16:26,305][3168197] Num frames 8400...
630
+ [2024-08-15 13:16:26,347][3168197] Num frames 8500...
631
+ [2024-08-15 13:16:26,391][3168197] Num frames 8600...
632
+ [2024-08-15 13:16:26,435][3168197] Num frames 8700...
633
+ [2024-08-15 13:16:26,478][3168197] Num frames 8800...
634
+ [2024-08-15 13:16:26,522][3168197] Num frames 8900...
635
+ [2024-08-15 13:16:26,563][3168197] Num frames 9000...
636
+ [2024-08-15 13:16:26,605][3168197] Num frames 9100...
637
+ [2024-08-15 13:16:26,646][3168197] Num frames 9200...
638
+ [2024-08-15 13:16:26,690][3168197] Num frames 9300...
639
+ [2024-08-15 13:16:26,731][3168197] Num frames 9400...
640
+ [2024-08-15 13:16:26,796][3168197] Avg episode rewards: #0: 21.732, true rewards: #0: 9.432
641
+ [2024-08-15 13:16:26,797][3168197] Avg episode reward: 21.732, avg true_objective: 9.432
642
+ [2024-08-15 13:16:35,950][3168197] Replay video saved to /home/aa/Documents/GitHub/RL-hugging_face/unit8/train_dir/default_experiment/replay.mp4!