Hugging Face's logo

qgallouedec
/
trpo-BipedalWalkerHardcore-v3-4007792454

Reinforcement Learning
stable-baselines3
BipedalWalkerHardcore-v3
deep-reinforcement-learning
Eval Results
Model card Files Community
Quentin Gallouédec commited on
Commit
67e3402
•
1 Parent(s): e781f91

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-BipedalWalkerHardcore-v3.zip +3 -0
  10. trpo-BipedalWalkerHardcore-v3/_stable_baselines3_version +1 -0
  11. trpo-BipedalWalkerHardcore-v3/data +103 -0
  12. trpo-BipedalWalkerHardcore-v3/policy.optimizer.pth +3 -0
  13. trpo-BipedalWalkerHardcore-v3/policy.pth +3 -0
  14. trpo-BipedalWalkerHardcore-v3/pytorch_variables.pth +3 -0
  15. trpo-BipedalWalkerHardcore-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
+ - BipedalWalkerHardcore-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: BipedalWalkerHardcore-v3
16
+ type: BipedalWalkerHardcore-v3
17
+ metrics:
18
+ - type: mean_reward
19
+ value: -99.80 +/- 14.91
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **TRPO** Agent playing **BipedalWalkerHardcore-v3**
25
+ This is a trained model of a **TRPO** agent playing **BipedalWalkerHardcore-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 BipedalWalkerHardcore-v3 -orga qgallouedec -f logs/
47
+ python -m rl_zoo3.enjoy --algo trpo --env BipedalWalkerHardcore-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 BipedalWalkerHardcore-v3 -orga qgallouedec -f logs/
53
+ python -m rl_zoo3.enjoy --algo trpo --env BipedalWalkerHardcore-v3 -f logs/
54
+ ```
55
+
56
+ ## Training (with the RL Zoo)
57
+ ```
58
+ python -m rl_zoo3.train --algo trpo --env BipedalWalkerHardcore-v3 -f logs/
59
+ # Upload the model and generate video (when possible)
60
+ python -m rl_zoo3.push_to_hub --algo trpo --env BipedalWalkerHardcore-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', 10000000.0),
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
+ - BipedalWalkerHardcore-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
+ - 4007792454
58
+ - - storage
59
+ - null
60
+ - - study_name
61
+ - null
62
+ - - tensorboard_log
63
+ - runs/BipedalWalkerHardcore-v3__trpo__4007792454__1675980740
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
+ - 10000000.0
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 sha256:2a4111c0107a0fd14caea3f6d2bb94c6f4cf26420a68de3630c16dc3528c63da
3
+ size 349854
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": -99.80029110000001, "std_reward": 14.907024143680612, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-28T13:51:48.988148"}
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be0a975c9d5c19419de3b0203ef0f827f658b5c4a8752bc95aed0fb17de91e1c
3
+ size 383445
trpo-BipedalWalkerHardcore-v3.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50f5d79df044743f766a3044dec8c4718a92fe6e000b6d0ade49be57c13a980f
3
+ size 124156
trpo-BipedalWalkerHardcore-v3/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.8.0a6
trpo-BipedalWalkerHardcore-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 0x7fdb58452ee0>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fdb58452f70>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fdb58454040>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fdb584540d0>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7fdb58454160>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7fdb584541f0>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fdb58454280>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fdb58454310>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7fdb584543a0>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fdb58454430>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fdb584544c0>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fdb58454550>",
19
+ "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7fdb58451d40>"
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": "float32",
28
+ "_shape": [
29
+ 24
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]",
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]",
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]",
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]",
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
+ 4
43
+ ],
44
+ "low": "[-1. -1. -1. -1.]",
45
+ "high": "[1. 1. 1. 1.]",
46
+ "bounded_below": "[ True True True True]",
47
+ "bounded_above": "[ True True True True]",
48
+ "_np_random": "RandomState(MT19937)"
49
+ },
50
+ "n_envs": 1,
51
+ "num_timesteps": 10000384,
52
+ "_total_timesteps": 10000000,
53
+ "_num_timesteps_at_start": 0,
54
+ "seed": 0,
55
+ "action_noise": null,
56
+ "start_time": 1675980752055973402,
57
+ "learning_rate": {
58
+ ":type:": "<class 'function'>",
59
+ ":serialized:": "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"
60
+ },
61
+ "tensorboard_log": "runs/BipedalWalkerHardcore-v3__trpo__4007792454__1675980740/BipedalWalkerHardcore-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:": "gAWVNQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJbAAAAAAAAAAHQNNDuLNoi3/I+lOjQSg7xPRLw9jXzautY7XD9gqSw7AACAP6FuBD3DeNq6LpVaPw+EmjoAAIA/YLLhPolC5D6bP+w+U6b6Pva6CD/jOho/yIo1P27MYj8AAIA/AACAP+4ONDvtsA63sG8tOlESg7wAfLw9heBkuto3XD9+PAY7AACAP9PeBD293GS6F5FaP1fdIToAAIA/YLLhPolC5D6bP+w+U6b6Pva6CD/jOho/yIo1P27MYj+ce3A/AACAP5SMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAksYhpSMAUOUdJRSlC4="
74
+ },
75
+ "_episode_num": 0,
76
+ "use_sde": false,
77
+ "sde_sample_freq": -1,
78
+ "_current_progress_remaining": -3.8399999999993994e-05,
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": 4883,
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-BipedalWalkerHardcore-v3/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69329b967821a09c058e7e3f1a49cdd75eadca110786dc1e0c949db6d537034
3
+ size 51631
trpo-BipedalWalkerHardcore-v3/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dda6d002c854416bc19d1f468d40760a8100595d6bc1e1ad6b78dc4e921ef8a
3
+ size 51838
trpo-BipedalWalkerHardcore-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-BipedalWalkerHardcore-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 sha256:0ff8660f9bbadbb1b1bd72b4cc8ff1642ecc8a985afe8b7a6f0afa8b91a9f1ed
3
+ size 4815