Hugging Face's logo

Kommunarus
/
rl_course_vizdoom_health_gathering_supreme

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results
Model card Files
xet
Metrics Community
Kommunarus commited on
Commit
345acbf
·
verified ·
1 Parent(s): 034bf9b

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. .summary/0/events.out.tfevents.1738343608.neptun-AX370 +3 -0
  3. README.md +56 -0
  4. checkpoint_p0/best_000000978_4005888_reward_27.484.pth +3 -0
  5. checkpoint_p0/checkpoint_000000714_2924544.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 +274 -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.1738343608.neptun-AX370 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16f2ed316281377c309cad1e0dc1733768962681732cd76947ab6189bbda5bdb
3
+ size 305246
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: 11.82 +/- 5.71
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 Kommunarus/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_000000978_4005888_reward_27.484.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:357f6d9e8e8e31853f3600bc18e820c4663bb177f70d29d9049408266cf45d38
3
+ size 34929051
checkpoint_p0/checkpoint_000000714_2924544.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e500e5adc210e20baa9dea94e8da260bde6c0172c7a86272f9e67b219b2fbd5
3
+ size 34929477
checkpoint_p0/checkpoint_000000978_4005888.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa79e50e1a2a321502e752f207dd81d526be33add4083e26fe3dcde09c3505d5
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/neptun/PycharmProjects/RL_course/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 sha256:4ea753e9c46c9d9e62df29a036f346bd5c1e48f7b5007441116f98761b06ad2a
3
+ size 23153136
sf_log.txt ADDED
@@ -0,0 +1,274 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [2025-01-31 20:13:33,790][46432] Worker 3 uses CPU cores [6, 7]
2
+ [2025-01-31 20:13:33,868][46435] Worker 6 uses CPU cores [12, 13]
3
+ [2025-01-31 20:13:33,891][46433] Worker 2 uses CPU cores [4, 5]
4
+ [2025-01-31 20:13:33,909][46434] Worker 4 uses CPU cores [8, 9]
5
+ [2025-01-31 20:13:34,088][46429] Using GPUs [0] for process 0 (actually maps to GPUs [0])
6
+ [2025-01-31 20:13:34,088][46429] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
7
+ [2025-01-31 20:13:34,113][46429] Num visible devices: 1
8
+ [2025-01-31 20:13:34,119][46430] Worker 0 uses CPU cores [0, 1]
9
+ [2025-01-31 20:13:34,141][46431] Worker 1 uses CPU cores [2, 3]
10
+ [2025-01-31 20:13:34,147][46416] Using GPUs [0] for process 0 (actually maps to GPUs [0])
11
+ [2025-01-31 20:13:34,148][46416] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
12
+ [2025-01-31 20:13:34,172][46416] Num visible devices: 1
13
+ [2025-01-31 20:13:34,176][46416] Starting seed is not provided
14
+ [2025-01-31 20:13:34,176][46416] Using GPUs [0] for process 0 (actually maps to GPUs [0])
15
+ [2025-01-31 20:13:34,176][46416] Initializing actor-critic model on device cuda:0
16
+ [2025-01-31 20:13:34,177][46416] RunningMeanStd input shape: (3, 72, 128)
17
+ [2025-01-31 20:13:34,177][46416] RunningMeanStd input shape: (1,)
18
+ [2025-01-31 20:13:34,191][46416] ConvEncoder: input_channels=3
19
+ [2025-01-31 20:13:34,219][46437] Worker 5 uses CPU cores [10, 11]
20
+ [2025-01-31 20:13:34,288][46436] Worker 7 uses CPU cores [14, 15]
21
+ [2025-01-31 20:13:34,315][46416] Conv encoder output size: 512
22
+ [2025-01-31 20:13:34,315][46416] Policy head output size: 512
23
+ [2025-01-31 20:13:34,330][46416] Created Actor Critic model with architecture:
24
+ [2025-01-31 20:13:34,330][46416] ActorCriticSharedWeights(
25
+ (obs_normalizer): ObservationNormalizer(
26
+ (running_mean_std): RunningMeanStdDictInPlace(
27
+ (running_mean_std): ModuleDict(
28
+ (obs): RunningMeanStdInPlace()
29
+ )
30
+ )
31
+ )
32
+ (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
33
+ (encoder): VizdoomEncoder(
34
+ (basic_encoder): ConvEncoder(
35
+ (enc): RecursiveScriptModule(
36
+ original_name=ConvEncoderImpl
37
+ (conv_head): RecursiveScriptModule(
38
+ original_name=Sequential
39
+ (0): RecursiveScriptModule(original_name=Conv2d)
40
+ (1): RecursiveScriptModule(original_name=ELU)
41
+ (2): RecursiveScriptModule(original_name=Conv2d)
42
+ (3): RecursiveScriptModule(original_name=ELU)
43
+ (4): RecursiveScriptModule(original_name=Conv2d)
44
+ (5): RecursiveScriptModule(original_name=ELU)
45
+ )
46
+ (mlp_layers): RecursiveScriptModule(
47
+ original_name=Sequential
48
+ (0): RecursiveScriptModule(original_name=Linear)
49
+ (1): RecursiveScriptModule(original_name=ELU)
50
+ )
51
+ )
52
+ )
53
+ )
54
+ (core): ModelCoreRNN(
55
+ (core): GRU(512, 512)
56
+ )
57
+ (decoder): MlpDecoder(
58
+ (mlp): Identity()
59
+ )
60
+ (critic_linear): Linear(in_features=512, out_features=1, bias=True)
61
+ (action_parameterization): ActionParameterizationDefault(
62
+ (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
63
+ )
64
+ )
65
+ [2025-01-31 20:13:34,494][46416] Using optimizer <class 'torch.optim.adam.Adam'>
66
+ [2025-01-31 20:13:35,209][46416] No checkpoints found
67
+ [2025-01-31 20:13:35,209][46416] Did not load from checkpoint, starting from scratch!
68
+ [2025-01-31 20:13:35,209][46416] Initialized policy 0 weights for model version 0
69
+ [2025-01-31 20:13:35,213][46416] LearnerWorker_p0 finished initialization!
70
+ [2025-01-31 20:13:35,213][46416] Using GPUs [0] for process 0 (actually maps to GPUs [0])
71
+ [2025-01-31 20:13:35,337][46429] RunningMeanStd input shape: (3, 72, 128)
72
+ [2025-01-31 20:13:35,338][46429] RunningMeanStd input shape: (1,)
73
+ [2025-01-31 20:13:35,350][46429] ConvEncoder: input_channels=3
74
+ [2025-01-31 20:13:35,461][46429] Conv encoder output size: 512
75
+ [2025-01-31 20:13:35,461][46429] Policy head output size: 512
76
+ [2025-01-31 20:13:35,547][46437] Doom resolution: 160x120, resize resolution: (128, 72)
77
+ [2025-01-31 20:13:35,550][46430] Doom resolution: 160x120, resize resolution: (128, 72)
78
+ [2025-01-31 20:13:35,556][46433] Doom resolution: 160x120, resize resolution: (128, 72)
79
+ [2025-01-31 20:13:35,557][46435] Doom resolution: 160x120, resize resolution: (128, 72)
80
+ [2025-01-31 20:13:35,561][46434] Doom resolution: 160x120, resize resolution: (128, 72)
81
+ [2025-01-31 20:13:35,568][46431] Doom resolution: 160x120, resize resolution: (128, 72)
82
+ [2025-01-31 20:13:35,579][46436] Doom resolution: 160x120, resize resolution: (128, 72)
83
+ [2025-01-31 20:13:35,579][46432] Doom resolution: 160x120, resize resolution: (128, 72)
84
+ [2025-01-31 20:13:35,925][46433] Decorrelating experience for 0 frames...
85
+ [2025-01-31 20:13:35,945][46436] Decorrelating experience for 0 frames...
86
+ [2025-01-31 20:13:35,953][46430] Decorrelating experience for 0 frames...
87
+ [2025-01-31 20:13:35,953][46437] Decorrelating experience for 0 frames...
88
+ [2025-01-31 20:13:35,963][46434] Decorrelating experience for 0 frames...
89
+ [2025-01-31 20:13:35,971][46431] Decorrelating experience for 0 frames...
90
+ [2025-01-31 20:13:36,308][46433] Decorrelating experience for 32 frames...
91
+ [2025-01-31 20:13:36,323][46437] Decorrelating experience for 32 frames...
92
+ [2025-01-31 20:13:36,326][46434] Decorrelating experience for 32 frames...
93
+ [2025-01-31 20:13:36,332][46435] Decorrelating experience for 0 frames...
94
+ [2025-01-31 20:13:36,338][46431] Decorrelating experience for 32 frames...
95
+ [2025-01-31 20:13:36,356][46432] Decorrelating experience for 0 frames...
96
+ [2025-01-31 20:13:36,373][46436] Decorrelating experience for 32 frames...
97
+ [2025-01-31 20:13:36,392][46430] Decorrelating experience for 32 frames...
98
+ [2025-01-31 20:13:36,721][46432] Decorrelating experience for 32 frames...
99
+ [2025-01-31 20:13:36,746][46431] Decorrelating experience for 64 frames...
100
+ [2025-01-31 20:13:36,747][46433] Decorrelating experience for 64 frames...
101
+ [2025-01-31 20:13:36,755][46435] Decorrelating experience for 32 frames...
102
+ [2025-01-31 20:13:36,823][46436] Decorrelating experience for 64 frames...
103
+ [2025-01-31 20:13:37,106][46430] Decorrelating experience for 64 frames...
104
+ [2025-01-31 20:13:37,128][46433] Decorrelating experience for 96 frames...
105
+ [2025-01-31 20:13:37,164][46434] Decorrelating experience for 64 frames...
106
+ [2025-01-31 20:13:37,196][46436] Decorrelating experience for 96 frames...
107
+ [2025-01-31 20:13:37,200][46435] Decorrelating experience for 64 frames...
108
+ [2025-01-31 20:13:37,440][46437] Decorrelating experience for 64 frames...
109
+ [2025-01-31 20:13:37,533][46430] Decorrelating experience for 96 frames...
110
+ [2025-01-31 20:13:37,547][46431] Decorrelating experience for 96 frames...
111
+ [2025-01-31 20:13:37,586][46434] Decorrelating experience for 96 frames...
112
+ [2025-01-31 20:13:37,591][46435] Decorrelating experience for 96 frames...
113
+ [2025-01-31 20:13:37,864][46432] Decorrelating experience for 64 frames...
114
+ [2025-01-31 20:13:37,877][46437] Decorrelating experience for 96 frames...
115
+ [2025-01-31 20:13:38,289][46432] Decorrelating experience for 96 frames...
116
+ [2025-01-31 20:13:38,658][46416] Signal inference workers to stop experience collection...
117
+ [2025-01-31 20:13:38,665][46429] InferenceWorker_p0-w0: stopping experience collection
118
+ [2025-01-31 20:13:41,309][46416] Signal inference workers to resume experience collection...
119
+ [2025-01-31 20:13:41,310][46429] InferenceWorker_p0-w0: resuming experience collection
120
+ [2025-01-31 20:13:44,232][46429] Updated weights for policy 0, policy_version 10 (0.0219)
121
+ [2025-01-31 20:13:47,366][46429] Updated weights for policy 0, policy_version 20 (0.0014)
122
+ [2025-01-31 20:13:50,648][46429] Updated weights for policy 0, policy_version 30 (0.0013)
123
+ [2025-01-31 20:13:53,577][46416] Saving new best policy, reward=4.509!
124
+ [2025-01-31 20:13:53,890][46429] Updated weights for policy 0, policy_version 40 (0.0014)
125
+ [2025-01-31 20:13:57,165][46429] Updated weights for policy 0, policy_version 50 (0.0014)
126
+ [2025-01-31 20:14:00,354][46429] Updated weights for policy 0, policy_version 60 (0.0012)
127
+ [2025-01-31 20:14:03,499][46429] Updated weights for policy 0, policy_version 70 (0.0013)
128
+ [2025-01-31 20:14:06,678][46429] Updated weights for policy 0, policy_version 80 (0.0013)
129
+ [2025-01-31 20:14:09,805][46429] Updated weights for policy 0, policy_version 90 (0.0014)
130
+ [2025-01-31 20:14:12,954][46429] Updated weights for policy 0, policy_version 100 (0.0013)
131
+ [2025-01-31 20:14:13,634][46416] Saving new best policy, reward=4.791!
132
+ [2025-01-31 20:14:16,207][46429] Updated weights for policy 0, policy_version 110 (0.0015)
133
+ [2025-01-31 20:14:19,474][46429] Updated weights for policy 0, policy_version 120 (0.0013)
134
+ [2025-01-31 20:14:22,495][46429] Updated weights for policy 0, policy_version 130 (0.0013)
135
+ [2025-01-31 20:14:25,795][46429] Updated weights for policy 0, policy_version 140 (0.0013)
136
+ [2025-01-31 20:14:28,975][46429] Updated weights for policy 0, policy_version 150 (0.0014)
137
+ [2025-01-31 20:14:32,173][46429] Updated weights for policy 0, policy_version 160 (0.0013)
138
+ [2025-01-31 20:14:33,578][46416] Saving new best policy, reward=4.804!
139
+ [2025-01-31 20:14:35,393][46429] Updated weights for policy 0, policy_version 170 (0.0013)
140
+ [2025-01-31 20:14:38,482][46429] Updated weights for policy 0, policy_version 180 (0.0013)
141
+ [2025-01-31 20:14:38,583][46416] Saving new best policy, reward=5.109!
142
+ [2025-01-31 20:14:41,545][46429] Updated weights for policy 0, policy_version 190 (0.0012)
143
+ [2025-01-31 20:14:43,578][46416] Saving new best policy, reward=5.574!
144
+ [2025-01-31 20:14:44,782][46429] Updated weights for policy 0, policy_version 200 (0.0014)
145
+ [2025-01-31 20:14:47,936][46429] Updated weights for policy 0, policy_version 210 (0.0013)
146
+ [2025-01-31 20:14:48,613][46416] Saving new best policy, reward=6.122!
147
+ [2025-01-31 20:14:51,163][46429] Updated weights for policy 0, policy_version 220 (0.0013)
148
+ [2025-01-31 20:14:54,369][46429] Updated weights for policy 0, policy_version 230 (0.0012)
149
+ [2025-01-31 20:14:57,579][46429] Updated weights for policy 0, policy_version 240 (0.0015)
150
+ [2025-01-31 20:15:00,685][46429] Updated weights for policy 0, policy_version 250 (0.0012)
151
+ [2025-01-31 20:15:03,578][46416] Saving new best policy, reward=6.260!
152
+ [2025-01-31 20:15:03,812][46429] Updated weights for policy 0, policy_version 260 (0.0012)
153
+ [2025-01-31 20:15:06,989][46429] Updated weights for policy 0, policy_version 270 (0.0013)
154
+ [2025-01-31 20:15:08,586][46416] Saving new best policy, reward=6.538!
155
+ [2025-01-31 20:15:10,133][46429] Updated weights for policy 0, policy_version 280 (0.0013)
156
+ [2025-01-31 20:15:13,201][46429] Updated weights for policy 0, policy_version 290 (0.0013)
157
+ [2025-01-31 20:15:13,578][46416] Saving new best policy, reward=7.909!
158
+ [2025-01-31 20:15:16,388][46429] Updated weights for policy 0, policy_version 300 (0.0014)
159
+ [2025-01-31 20:15:18,606][46416] Saving new best policy, reward=8.551!
160
+ [2025-01-31 20:15:19,573][46429] Updated weights for policy 0, policy_version 310 (0.0013)
161
+ [2025-01-31 20:15:22,678][46429] Updated weights for policy 0, policy_version 320 (0.0012)
162
+ [2025-01-31 20:15:23,578][46416] Saving new best policy, reward=10.038!
163
+ [2025-01-31 20:15:25,952][46429] Updated weights for policy 0, policy_version 330 (0.0014)
164
+ [2025-01-31 20:15:28,587][46416] Saving /home/neptun/PycharmProjects/RL_course/train_dir/default_experiment/checkpoint_p0/checkpoint_000000338_1384448.pth...
165
+ [2025-01-31 20:15:29,205][46429] Updated weights for policy 0, policy_version 340 (0.0014)
166
+ [2025-01-31 20:15:32,504][46429] Updated weights for policy 0, policy_version 350 (0.0014)
167
+ [2025-01-31 20:15:33,578][46416] Saving new best policy, reward=10.544!
168
+ [2025-01-31 20:15:35,771][46429] Updated weights for policy 0, policy_version 360 (0.0013)
169
+ [2025-01-31 20:15:38,583][46416] Saving new best policy, reward=10.780!
170
+ [2025-01-31 20:15:39,001][46429] Updated weights for policy 0, policy_version 370 (0.0014)
171
+ [2025-01-31 20:15:42,201][46429] Updated weights for policy 0, policy_version 380 (0.0014)
172
+ [2025-01-31 20:15:43,578][46416] Saving new best policy, reward=11.704!
173
+ [2025-01-31 20:15:45,508][46429] Updated weights for policy 0, policy_version 390 (0.0013)
174
+ [2025-01-31 20:15:48,582][46416] Saving new best policy, reward=13.792!
175
+ [2025-01-31 20:15:48,734][46429] Updated weights for policy 0, policy_version 400 (0.0014)
176
+ [2025-01-31 20:15:51,771][46429] Updated weights for policy 0, policy_version 410 (0.0013)
177
+ [2025-01-31 20:15:53,578][46416] Saving new best policy, reward=14.734!
178
+ [2025-01-31 20:15:55,029][46429] Updated weights for policy 0, policy_version 420 (0.0013)
179
+ [2025-01-31 20:15:58,172][46429] Updated weights for policy 0, policy_version 430 (0.0014)
180
+ [2025-01-31 20:15:58,582][46416] Saving new best policy, reward=15.724!
181
+ [2025-01-31 20:16:01,354][46429] Updated weights for policy 0, policy_version 440 (0.0013)
182
+ [2025-01-31 20:16:04,536][46429] Updated weights for policy 0, policy_version 450 (0.0012)
183
+ [2025-01-31 20:16:07,723][46429] Updated weights for policy 0, policy_version 460 (0.0014)
184
+ [2025-01-31 20:16:08,640][46416] Saving new best policy, reward=15.740!
185
+ [2025-01-31 20:16:10,822][46429] Updated weights for policy 0, policy_version 470 (0.0013)
186
+ [2025-01-31 20:16:13,579][46416] Saving new best policy, reward=17.087!
187
+ [2025-01-31 20:16:14,126][46429] Updated weights for policy 0, policy_version 480 (0.0013)
188
+ [2025-01-31 20:16:17,260][46429] Updated weights for policy 0, policy_version 490 (0.0012)
189
+ [2025-01-31 20:16:18,585][46416] Saving new best policy, reward=18.021!
190
+ [2025-01-31 20:16:20,422][46429] Updated weights for policy 0, policy_version 500 (0.0014)
191
+ [2025-01-31 20:16:23,465][46429] Updated weights for policy 0, policy_version 510 (0.0013)
192
+ [2025-01-31 20:16:23,579][46416] Saving new best policy, reward=19.312!
193
+ [2025-01-31 20:16:26,748][46429] Updated weights for policy 0, policy_version 520 (0.0013)
194
+ [2025-01-31 20:16:29,934][46429] Updated weights for policy 0, policy_version 530 (0.0014)
195
+ [2025-01-31 20:16:33,082][46429] Updated weights for policy 0, policy_version 540 (0.0013)
196
+ [2025-01-31 20:16:33,578][46416] Saving new best policy, reward=19.714!
197
+ [2025-01-31 20:16:36,231][46429] Updated weights for policy 0, policy_version 550 (0.0013)
198
+ [2025-01-31 20:16:39,448][46429] Updated weights for policy 0, policy_version 560 (0.0015)
199
+ [2025-01-31 20:16:42,603][46429] Updated weights for policy 0, policy_version 570 (0.0012)
200
+ [2025-01-31 20:16:43,578][46416] Saving new best policy, reward=20.811!
201
+ [2025-01-31 20:16:45,765][46429] Updated weights for policy 0, policy_version 580 (0.0014)
202
+ [2025-01-31 20:16:48,582][46416] Saving new best policy, reward=22.924!
203
+ [2025-01-31 20:16:48,888][46429] Updated weights for policy 0, policy_version 590 (0.0013)
204
+ [2025-01-31 20:16:52,060][46429] Updated weights for policy 0, policy_version 600 (0.0013)
205
+ [2025-01-31 20:16:55,236][46429] Updated weights for policy 0, policy_version 610 (0.0013)
206
+ [2025-01-31 20:16:58,599][46416] Saving new best policy, reward=24.094!
207
+ [2025-01-31 20:16:58,602][46429] Updated weights for policy 0, policy_version 620 (0.0014)
208
+ [2025-01-31 20:17:01,769][46429] Updated weights for policy 0, policy_version 630 (0.0013)
209
+ [2025-01-31 20:17:03,578][46416] Saving new best policy, reward=25.401!
210
+ [2025-01-31 20:17:04,949][46429] Updated weights for policy 0, policy_version 640 (0.0014)
211
+ [2025-01-31 20:17:08,060][46429] Updated weights for policy 0, policy_version 650 (0.0014)
212
+ [2025-01-31 20:17:11,268][46429] Updated weights for policy 0, policy_version 660 (0.0013)
213
+ [2025-01-31 20:17:14,343][46429] Updated weights for policy 0, policy_version 670 (0.0014)
214
+ [2025-01-31 20:17:17,552][46429] Updated weights for policy 0, policy_version 680 (0.0013)
215
+ [2025-01-31 20:17:18,591][46416] Saving new best policy, reward=26.343!
216
+ [2025-01-31 20:17:20,770][46429] Updated weights for policy 0, policy_version 690 (0.0013)
217
+ [2025-01-31 20:17:23,579][46416] Saving new best policy, reward=26.357!
218
+ [2025-01-31 20:17:23,870][46429] Updated weights for policy 0, policy_version 700 (0.0013)
219
+ [2025-01-31 20:17:27,039][46429] Updated weights for policy 0, policy_version 710 (0.0012)
220
+ [2025-01-31 20:17:28,583][46416] Saving /home/neptun/PycharmProjects/RL_course/train_dir/default_experiment/checkpoint_p0/checkpoint_000000714_2924544.pth...
221
+ [2025-01-31 20:17:30,340][46429] Updated weights for policy 0, policy_version 720 (0.0013)
222
+ [2025-01-31 20:17:33,487][46429] Updated weights for policy 0, policy_version 730 (0.0013)
223
+ [2025-01-31 20:17:36,627][46429] Updated weights for policy 0, policy_version 740 (0.0014)
224
+ [2025-01-31 20:17:39,812][46429] Updated weights for policy 0, policy_version 750 (0.0013)
225
+ [2025-01-31 20:17:42,885][46429] Updated weights for policy 0, policy_version 760 (0.0013)
226
+ [2025-01-31 20:17:46,008][46429] Updated weights for policy 0, policy_version 770 (0.0014)
227
+ [2025-01-31 20:17:49,232][46429] Updated weights for policy 0, policy_version 780 (0.0013)
228
+ [2025-01-31 20:17:52,321][46429] Updated weights for policy 0, policy_version 790 (0.0013)
229
+ [2025-01-31 20:17:55,575][46429] Updated weights for policy 0, policy_version 800 (0.0014)
230
+ [2025-01-31 20:17:58,730][46429] Updated weights for policy 0, policy_version 810 (0.0014)
231
+ [2025-01-31 20:18:01,923][46429] Updated weights for policy 0, policy_version 820 (0.0013)
232
+ [2025-01-31 20:18:05,043][46429] Updated weights for policy 0, policy_version 830 (0.0014)
233
+ [2025-01-31 20:18:08,157][46429] Updated weights for policy 0, policy_version 840 (0.0013)
234
+ [2025-01-31 20:18:11,258][46429] Updated weights for policy 0, policy_version 850 (0.0013)
235
+ [2025-01-31 20:18:14,438][46429] Updated weights for policy 0, policy_version 860 (0.0014)
236
+ [2025-01-31 20:18:17,488][46429] Updated weights for policy 0, policy_version 870 (0.0013)
237
+ [2025-01-31 20:18:20,750][46429] Updated weights for policy 0, policy_version 880 (0.0013)
238
+ [2025-01-31 20:18:23,921][46429] Updated weights for policy 0, policy_version 890 (0.0013)
239
+ [2025-01-31 20:18:27,184][46429] Updated weights for policy 0, policy_version 900 (0.0014)
240
+ [2025-01-31 20:18:30,373][46429] Updated weights for policy 0, policy_version 910 (0.0015)
241
+ [2025-01-31 20:18:33,523][46429] Updated weights for policy 0, policy_version 920 (0.0012)
242
+ [2025-01-31 20:18:36,624][46429] Updated weights for policy 0, policy_version 930 (0.0013)
243
+ [2025-01-31 20:18:39,829][46429] Updated weights for policy 0, policy_version 940 (0.0013)
244
+ [2025-01-31 20:18:43,000][46429] Updated weights for policy 0, policy_version 950 (0.0014)
245
+ [2025-01-31 20:18:46,093][46429] Updated weights for policy 0, policy_version 960 (0.0013)
246
+ [2025-01-31 20:18:48,585][46416] Saving new best policy, reward=26.837!
247
+ [2025-01-31 20:18:49,276][46429] Updated weights for policy 0, policy_version 970 (0.0013)
248
+ [2025-01-31 20:18:51,780][46416] Saving /home/neptun/PycharmProjects/RL_course/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
249
+ [2025-01-31 20:18:51,780][46416] Stopping Batcher_0...
250
+ [2025-01-31 20:18:51,788][46416] Loop batcher_evt_loop terminating...
251
+ [2025-01-31 20:18:51,808][46429] Weights refcount: 2 0
252
+ [2025-01-31 20:18:51,810][46429] Stopping InferenceWorker_p0-w0...
253
+ [2025-01-31 20:18:51,811][46429] Loop inference_proc0-0_evt_loop terminating...
254
+ [2025-01-31 20:18:51,839][46434] Stopping RolloutWorker_w4...
255
+ [2025-01-31 20:18:51,839][46434] Loop rollout_proc4_evt_loop terminating...
256
+ [2025-01-31 20:18:51,841][46433] Stopping RolloutWorker_w2...
257
+ [2025-01-31 20:18:51,842][46433] Loop rollout_proc2_evt_loop terminating...
258
+ [2025-01-31 20:18:51,847][46437] Stopping RolloutWorker_w5...
259
+ [2025-01-31 20:18:51,848][46437] Loop rollout_proc5_evt_loop terminating...
260
+ [2025-01-31 20:18:51,848][46435] Stopping RolloutWorker_w6...
261
+ [2025-01-31 20:18:51,849][46435] Loop rollout_proc6_evt_loop terminating...
262
+ [2025-01-31 20:18:51,850][46430] Stopping RolloutWorker_w0...
263
+ [2025-01-31 20:18:51,851][46430] Loop rollout_proc0_evt_loop terminating...
264
+ [2025-01-31 20:18:51,855][46431] Stopping RolloutWorker_w1...
265
+ [2025-01-31 20:18:51,856][46436] Stopping RolloutWorker_w7...
266
+ [2025-01-31 20:18:51,856][46431] Loop rollout_proc1_evt_loop terminating...
267
+ [2025-01-31 20:18:51,857][46436] Loop rollout_proc7_evt_loop terminating...
268
+ [2025-01-31 20:18:51,858][46432] Stopping RolloutWorker_w3...
269
+ [2025-01-31 20:18:51,858][46432] Loop rollout_proc3_evt_loop terminating...
270
+ [2025-01-31 20:18:51,891][46416] Removing /home/neptun/PycharmProjects/RL_course/train_dir/default_experiment/checkpoint_p0/checkpoint_000000338_1384448.pth
271
+ [2025-01-31 20:18:51,908][46416] Saving new best policy, reward=27.484!
272
+ [2025-01-31 20:18:52,110][46416] Saving /home/neptun/PycharmProjects/RL_course/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
273
+ [2025-01-31 20:18:52,383][46416] Stopping LearnerWorker_p0...
274
+ [2025-01-31 20:18:52,383][46416] Loop learner_proc0_evt_loop terminating...