Hugging Face's logo

qgallouedec
/
trpo-Humanoid-v3-4106392303

Reinforcement Learning
stable-baselines3
Humanoid-v3
deep-reinforcement-learning
Humanoid-v4
Eval Results
Model card Files Community
Quentin Gallouédec commited on
Commit
a44dfee
•
1 Parent(s): bfd962b

Initial commit

Browse files
Files changed (16) hide show
  1. .gitattributes +1 -0
  2. README.md +79 -0
  3. args.yml +83 -0
  4. config.yml +27 -0
  5. env_kwargs.yml +1 -0
  6. replay.mp4 +3 -0
  7. results.json +1 -0
  8. train_eval_metrics.zip +3 -0
  9. trpo-Humanoid-v3.zip +3 -0
  10. trpo-Humanoid-v3/_stable_baselines3_version +1 -0
  11. trpo-Humanoid-v3/data +103 -0
  12. trpo-Humanoid-v3/policy.optimizer.pth +3 -0
  13. trpo-Humanoid-v3/policy.pth +3 -0
  14. trpo-Humanoid-v3/pytorch_variables.pth +3 -0
  15. trpo-Humanoid-v3/system_info.txt +7 -0
  16. vec_normalize.pkl +3 -0
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ *.mp4 filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - Humanoid-v3
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - stable-baselines3
8
+ model-index:
9
+ - name: TRPO
10
+ results:
11
+ - task:
12
+ type: reinforcement-learning
13
+ name: reinforcement-learning
14
+ dataset:
15
+ name: Humanoid-v3
16
+ type: Humanoid-v3
17
+ metrics:
18
+ - type: mean_reward
19
+ value: 3706.29 +/- 1857.04
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **TRPO** Agent playing **Humanoid-v3**
25
+ This is a trained model of a **TRPO** agent playing **Humanoid-v3**
26
+ using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
27
+ and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
28
+
29
+ The RL Zoo is a training framework for Stable Baselines3
30
+ reinforcement learning agents,
31
+ with hyperparameter optimization and pre-trained agents included.
32
+
33
+ ## Usage (with SB3 RL Zoo)
34
+
35
+ RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
36
+ SB3: https://github.com/DLR-RM/stable-baselines3<br/>
37
+ SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
38
+
39
+ Install the RL Zoo (with SB3 and SB3-Contrib):
40
+ ```bash
41
+ pip install rl_zoo3
42
+ ```
43
+
44
+ ```
45
+ # Download model and save it into the logs/ folder
46
+ python -m rl_zoo3.load_from_hub --algo trpo --env Humanoid-v3 -orga qgallouedec -f logs/
47
+ python -m rl_zoo3.enjoy --algo trpo --env Humanoid-v3 -f logs/
48
+ ```
49
+
50
+ If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
51
+ ```
52
+ python -m rl_zoo3.load_from_hub --algo trpo --env Humanoid-v3 -orga qgallouedec -f logs/
53
+ python -m rl_zoo3.enjoy --algo trpo --env Humanoid-v3 -f logs/
54
+ ```
55
+
56
+ ## Training (with the RL Zoo)
57
+ ```
58
+ python -m rl_zoo3.train --algo trpo --env Humanoid-v3 -f logs/
59
+ # Upload the model and generate video (when possible)
60
+ python -m rl_zoo3.push_to_hub --algo trpo --env Humanoid-v3 -f logs/ -orga qgallouedec
61
+ ```
62
+
63
+ ## Hyperparameters
64
+ ```python
65
+ OrderedDict([('batch_size', 128),
66
+ ('cg_damping', 0.1),
67
+ ('cg_max_steps', 25),
68
+ ('gae_lambda', 0.95),
69
+ ('gamma', 0.99),
70
+ ('learning_rate', 0.001),
71
+ ('n_critic_updates', 20),
72
+ ('n_envs', 2),
73
+ ('n_steps', 1024),
74
+ ('n_timesteps', 2000000.0),
75
+ ('normalize', True),
76
+ ('policy', 'MlpPolicy'),
77
+ ('sub_sampling_factor', 1),
78
+ ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
79
+ ```
args.yml ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - trpo
4
+ - - conf_file
5
+ - null
6
+ - - device
7
+ - auto
8
+ - - env
9
+ - Humanoid-v3
10
+ - - env_kwargs
11
+ - null
12
+ - - eval_episodes
13
+ - 20
14
+ - - eval_freq
15
+ - 25000
16
+ - - gym_packages
17
+ - []
18
+ - - hyperparams
19
+ - null
20
+ - - log_folder
21
+ - logs
22
+ - - log_interval
23
+ - -1
24
+ - - max_total_trials
25
+ - null
26
+ - - n_eval_envs
27
+ - 5
28
+ - - n_evaluations
29
+ - null
30
+ - - n_jobs
31
+ - 1
32
+ - - n_startup_trials
33
+ - 10
34
+ - - n_timesteps
35
+ - -1
36
+ - - n_trials
37
+ - 500
38
+ - - no_optim_plots
39
+ - false
40
+ - - num_threads
41
+ - -1
42
+ - - optimization_log_path
43
+ - null
44
+ - - optimize_hyperparameters
45
+ - false
46
+ - - progress
47
+ - false
48
+ - - pruner
49
+ - median
50
+ - - sampler
51
+ - tpe
52
+ - - save_freq
53
+ - -1
54
+ - - save_replay_buffer
55
+ - false
56
+ - - seed
57
+ - 4106392303
58
+ - - storage
59
+ - null
60
+ - - study_name
61
+ - null
62
+ - - tensorboard_log
63
+ - runs/Humanoid-v3__trpo__4106392303__1675898901
64
+ - - track
65
+ - true
66
+ - - trained_agent
67
+ - ''
68
+ - - truncate_last_trajectory
69
+ - true
70
+ - - uuid
71
+ - false
72
+ - - vec_env
73
+ - dummy
74
+ - - verbose
75
+ - 1
76
+ - - wandb_entity
77
+ - openrlbenchmark
78
+ - - wandb_project_name
79
+ - sb3
80
+ - - wandb_tags
81
+ - []
82
+ - - yaml_file
83
+ - null
config.yml ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - batch_size
3
+ - 128
4
+ - - cg_damping
5
+ - 0.1
6
+ - - cg_max_steps
7
+ - 25
8
+ - - gae_lambda
9
+ - 0.95
10
+ - - gamma
11
+ - 0.99
12
+ - - learning_rate
13
+ - 0.001
14
+ - - n_critic_updates
15
+ - 20
16
+ - - n_envs
17
+ - 2
18
+ - - n_steps
19
+ - 1024
20
+ - - n_timesteps
21
+ - 2000000.0
22
+ - - normalize
23
+ - true
24
+ - - policy
25
+ - MlpPolicy
26
+ - - sub_sampling_factor
27
+ - 1
env_kwargs.yml ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef786fa833dc3944989b4d90343dfde1d1888107c6637008237e9df1576c068c
3
+ size 1550689
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 3706.2932895, "std_reward": 1857.035305513661, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-28T16:12:42.433531"}
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74767adce086bf17c7bdda2b67086b22c46d1efaaaf72dc69fa676f425ee48df
3
+ size 343877
trpo-Humanoid-v3.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36729959a379e73698e4a2ab7c28148289ae21b8a33df62bbb3cf5cb086929aa
3
+ size 512576
trpo-Humanoid-v3/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.8.0a6
trpo-Humanoid-v3/data ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "policy_class": {
3
+ ":type:": "<class 'abc.ABCMeta'>",
4
+ ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
5
+ "__module__": "stable_baselines3.common.policies",
6
+ "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
7
+ "__init__": "<function ActorCriticPolicy.__init__ at 0x7f2457b53ee0>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2457b53f70>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2457b55040>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2457b550d0>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7f2457b55160>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7f2457b551f0>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f2457b55280>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2457b55310>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7f2457b553a0>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2457b55430>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2457b554c0>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2457b55550>",
19
+ "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7f2457b52c80>"
21
+ },
22
+ "verbose": 1,
23
+ "policy_kwargs": {},
24
+ "observation_space": {
25
+ ":type:": "<class 'gym.spaces.box.Box'>",
26
+ ":serialized:": "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",
27
+ "dtype": "float64",
28
+ "_shape": [
29
+ 376
30
+ ],
31
+ "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]",
32
+ "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf]",
33
+ "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]",
34
+ "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]",
35
+ "_np_random": null
36
+ },
37
+ "action_space": {
38
+ ":type:": "<class 'gym.spaces.box.Box'>",
39
+ ":serialized:": "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",
40
+ "dtype": "float32",
41
+ "_shape": [
42
+ 17
43
+ ],
44
+ "low": "[-0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4\n -0.4 -0.4 -0.4]",
45
+ "high": "[0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4]",
46
+ "bounded_below": "[ True True True True True True True True True True True True\n True True True True True]",
47
+ "bounded_above": "[ True True True True True True True True True True True True\n True True True True True]",
48
+ "_np_random": "RandomState(MT19937)"
49
+ },
50
+ "n_envs": 1,
51
+ "num_timesteps": 2000896,
52
+ "_total_timesteps": 2000000,
53
+ "_num_timesteps_at_start": 0,
54
+ "seed": 0,
55
+ "action_noise": null,
56
+ "start_time": 1675898906314064304,
57
+ "learning_rate": {
58
+ ":type:": "<class 'function'>",
59
+ ":serialized:": "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"
60
+ },
61
+ "tensorboard_log": "runs/Humanoid-v3__trpo__4106392303__1675898901/Humanoid-v3",
62
+ "lr_schedule": {
63
+ ":type:": "<class 'function'>",
64
+ ":serialized:": "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"
65
+ },
66
+ "_last_obs": null,
67
+ "_last_episode_starts": {
68
+ ":type:": "<class 'numpy.ndarray'>",
69
+ ":serialized:": "gAWVdQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYCAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksChZSMAUOUdJRSlC4="
70
+ },
71
+ "_last_original_obs": {
72
+ ":type:": "<class 'numpy.ndarray'>",
73
+ ":serialized:": "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"
74
+ },
75
+ "_episode_num": 0,
76
+ "use_sde": false,
77
+ "sde_sample_freq": -1,
78
+ "_current_progress_remaining": -0.00044800000000000395,
79
+ "ep_info_buffer": {
80
+ ":type:": "<class 'collections.deque'>",
81
+ ":serialized:": "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"
82
+ },
83
+ "ep_success_buffer": {
84
+ ":type:": "<class 'collections.deque'>",
85
+ ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
86
+ },
87
+ "_n_updates": 977,
88
+ "n_steps": 1024,
89
+ "gamma": 0.99,
90
+ "gae_lambda": 0.95,
91
+ "ent_coef": 0.0,
92
+ "vf_coef": 0.0,
93
+ "max_grad_norm": 0.0,
94
+ "normalize_advantage": true,
95
+ "batch_size": 128,
96
+ "cg_max_steps": 25,
97
+ "cg_damping": 0.1,
98
+ "line_search_shrinking_factor": 0.8,
99
+ "line_search_max_iter": 10,
100
+ "target_kl": 0.01,
101
+ "n_critic_updates": 20,
102
+ "sub_sampling_factor": 1
103
+ }
trpo-Humanoid-v3/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7c3648720abc35974fd32f54731c08972bfd0ef1f0abc25ed98824992a4d93f
3
+ size 231855
trpo-Humanoid-v3/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da29db15041cee2ae2d88ee2b85275a4dcf8f5fa9664b357aa475f1a027962b0
3
+ size 235518
trpo-Humanoid-v3/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
3
+ size 431
trpo-Humanoid-v3/system_info.txt ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ - OS: Linux-5.19.0-32-generic-x86_64-with-glibc2.35 # 33~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Jan 30 17:03:34 UTC 2
2
+ - Python: 3.9.12
3
+ - Stable-Baselines3: 1.8.0a6
4
+ - PyTorch: 1.13.1+cu117
5
+ - GPU Enabled: True
6
+ - Numpy: 1.24.1
7
+ - Gym: 0.21.0
vec_normalize.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:114289e5d980b1d19f993808f43e686491f6b84d2ba9374ddfe7868531e3cf71
3
+ size 22958