Hugging Face's logo

qgallouedec
/
ars-HalfCheetahBulletEnv-v0-1258369920

Reinforcement Learning
stable-baselines3
HalfCheetahBulletEnv-v0
deep-reinforcement-learning
Eval Results
Model card Files Community
Quentin Gallouédec commited on
Commit
45d457f
•
1 Parent(s): febcb09

Initial commit

Browse files
Files changed (15) hide show
  1. .gitattributes +1 -0
  2. README.md +77 -0
  3. args.yml +79 -0
  4. ars-HalfCheetahBulletEnv-v0.zip +3 -0
  5. ars-HalfCheetahBulletEnv-v0/_stable_baselines3_version +1 -0
  6. ars-HalfCheetahBulletEnv-v0/data +164 -0
  7. ars-HalfCheetahBulletEnv-v0/policy.pth +3 -0
  8. ars-HalfCheetahBulletEnv-v0/pytorch_variables.pth +3 -0
  9. ars-HalfCheetahBulletEnv-v0/system_info.txt +7 -0
  10. config.yml +23 -0
  11. env_kwargs.yml +1 -0
  12. replay.mp4 +3 -0
  13. results.json +1 -0
  14. train_eval_metrics.zip +3 -0
  15. 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 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - HalfCheetahBulletEnv-v0
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - stable-baselines3
8
+ model-index:
9
+ - name: ARS
10
+ results:
11
+ - task:
12
+ type: reinforcement-learning
13
+ name: reinforcement-learning
14
+ dataset:
15
+ name: HalfCheetahBulletEnv-v0
16
+ type: HalfCheetahBulletEnv-v0
17
+ metrics:
18
+ - type: mean_reward
19
+ value: 1091.01 +/- 18.13
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **ARS** Agent playing **HalfCheetahBulletEnv-v0**
25
+ This is a trained model of a **ARS** agent playing **HalfCheetahBulletEnv-v0**
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 ars --env HalfCheetahBulletEnv-v0 -orga qgallouedec -f logs/
47
+ python -m rl_zoo3.enjoy --algo ars --env HalfCheetahBulletEnv-v0 -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 ars --env HalfCheetahBulletEnv-v0 -orga qgallouedec -f logs/
53
+ python -m rl_zoo3.enjoy --algo ars --env HalfCheetahBulletEnv-v0 -f logs/
54
+ ```
55
+
56
+ ## Training (with the RL Zoo)
57
+ ```
58
+ python -m rl_zoo3.train --algo ars --env HalfCheetahBulletEnv-v0 -f logs/
59
+ # Upload the model and generate video (when possible)
60
+ python -m rl_zoo3.push_to_hub --algo ars --env HalfCheetahBulletEnv-v0 -f logs/ -orga qgallouedec
61
+ ```
62
+
63
+ ## Hyperparameters
64
+ ```python
65
+ OrderedDict([('alive_bonus_offset', 0),
66
+ ('delta_std', 0.03),
67
+ ('learning_rate', 0.02),
68
+ ('n_delta', 8),
69
+ ('n_envs', 1),
70
+ ('n_timesteps', 75000000.0),
71
+ ('n_top', 8),
72
+ ('normalize', 'dict(norm_obs=True, norm_reward=False)'),
73
+ ('policy', 'MlpPolicy'),
74
+ ('policy_kwargs', 'dict(net_arch=[64, 64])'),
75
+ ('zero_policy', False),
76
+ ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
77
+ ```
args.yml ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - ars
4
+ - - device
5
+ - auto
6
+ - - env
7
+ - HalfCheetahBulletEnv-v0
8
+ - - env_kwargs
9
+ - null
10
+ - - eval_episodes
11
+ - 5
12
+ - - eval_freq
13
+ - 25000
14
+ - - gym_packages
15
+ - []
16
+ - - hyperparams
17
+ - null
18
+ - - log_folder
19
+ - logs
20
+ - - log_interval
21
+ - -1
22
+ - - max_total_trials
23
+ - null
24
+ - - n_eval_envs
25
+ - 1
26
+ - - n_evaluations
27
+ - null
28
+ - - n_jobs
29
+ - 1
30
+ - - n_startup_trials
31
+ - 10
32
+ - - n_timesteps
33
+ - -1
34
+ - - n_trials
35
+ - 500
36
+ - - no_optim_plots
37
+ - false
38
+ - - num_threads
39
+ - -1
40
+ - - optimization_log_path
41
+ - null
42
+ - - optimize_hyperparameters
43
+ - false
44
+ - - progress
45
+ - false
46
+ - - pruner
47
+ - median
48
+ - - sampler
49
+ - tpe
50
+ - - save_freq
51
+ - -1
52
+ - - save_replay_buffer
53
+ - false
54
+ - - seed
55
+ - 1258369920
56
+ - - storage
57
+ - null
58
+ - - study_name
59
+ - null
60
+ - - tensorboard_log
61
+ - runs/HalfCheetahBulletEnv-v0__ars__1258369920__1671558289
62
+ - - track
63
+ - true
64
+ - - trained_agent
65
+ - ''
66
+ - - truncate_last_trajectory
67
+ - true
68
+ - - uuid
69
+ - false
70
+ - - vec_env
71
+ - dummy
72
+ - - verbose
73
+ - 1
74
+ - - wandb_entity
75
+ - openrlbenchmark
76
+ - - wandb_project_name
77
+ - sb3
78
+ - - yaml_file
79
+ - null
ars-HalfCheetahBulletEnv-v0.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a70c134e7adf2510133660fee6739661d77f8d62251fbc3dc03784b5570aa782
3
+ size 76450
ars-HalfCheetahBulletEnv-v0/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.8.0a6
ars-HalfCheetahBulletEnv-v0/data ADDED
@@ -0,0 +1,164 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "policy_class": {
3
+ ":type:": "<class 'abc.ABCMeta'>",
4
+ ":serialized:": "gAWVKgAAAAAAAACMGHNiM19jb250cmliLmFycy5wb2xpY2llc5SMCUFSU1BvbGljeZSTlC4=",
5
+ "__module__": "sb3_contrib.ars.policies",
6
+ "__doc__": "\n Policy network for ARS.\n\n :param observation_space: The observation space of the environment\n :param action_space: The action space of the environment\n :param net_arch: Network architecture, defaults to a 2 layers MLP with 64 hidden nodes.\n :param activation_fn: Activation function\n :param with_bias: If set to False, the layers will not learn an additive bias\n :param squash_output: For continuous actions, whether the output is squashed\n or not using a ``tanh()`` function. If not squashed with tanh the output will instead be clipped.\n ",
7
+ "__init__": "<function ARSPolicy.__init__ at 0x7f7ef035a280>",
8
+ "_get_constructor_parameters": "<function ARSPolicy._get_constructor_parameters at 0x7f7ef035a310>",
9
+ "forward": "<function ARSPolicy.forward at 0x7f7ef035a3a0>",
10
+ "_predict": "<function ARSPolicy._predict at 0x7f7ef035a430>",
11
+ "__abstractmethods__": "frozenset()",
12
+ "_abc_impl": "<_abc._abc_data object at 0x7f7ef035e280>"
13
+ },
14
+ "verbose": 1,
15
+ "policy_kwargs": {
16
+ "net_arch": [
17
+ 64,
18
+ 64
19
+ ]
20
+ },
21
+ "observation_space": {
22
+ ":type:": "<class 'gym.spaces.box.Box'>",
23
+ ":serialized:": "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",
24
+ "dtype": "float32",
25
+ "_shape": [
26
+ 26
27
+ ],
28
+ "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]",
29
+ "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]",
30
+ "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]",
31
+ "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]",
32
+ "_np_random": null
33
+ },
34
+ "action_space": {
35
+ ":type:": "<class 'gym.spaces.box.Box'>",
36
+ ":serialized:": "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",
37
+ "dtype": "float32",
38
+ "_shape": [
39
+ 6
40
+ ],
41
+ "low": "[-1. -1. -1. -1. -1. -1.]",
42
+ "high": "[1. 1. 1. 1. 1. 1.]",
43
+ "bounded_below": "[ True True True True True True]",
44
+ "bounded_above": "[ True True True True True True]",
45
+ "_np_random": "RandomState(MT19937)"
46
+ },
47
+ "n_envs": 1,
48
+ "num_timesteps": 75008000,
49
+ "_total_timesteps": 75000000,
50
+ "_num_timesteps_at_start": 0,
51
+ "seed": 0,
52
+ "action_noise": null,
53
+ "start_time": 1671558291389277503,
54
+ "learning_rate": {
55
+ ":type:": "<class 'function'>",
56
+ ":serialized:": "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"
57
+ },
58
+ "tensorboard_log": "runs/HalfCheetahBulletEnv-v0__ars__1258369920__1671558289/HalfCheetahBulletEnv-v0",
59
+ "lr_schedule": {
60
+ ":type:": "<class 'function'>",
61
+ ":serialized:": "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"
62
+ },
63
+ "_last_obs": null,
64
+ "_last_episode_starts": {
65
+ ":type:": "<class 'numpy.ndarray'>",
66
+ ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
67
+ },
68
+ "_last_original_obs": {
69
+ ":type:": "<class 'numpy.ndarray'>",
70
+ ":serialized:": "gAWV3QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZoAAAAAAAAAAAAAAAAAAAAAACAPwAAAAAAAAAAAAAAAAAAAAAAAACARqLJvgAAAACVNkE9AAAAAO/SSr4AAAAAu5xvPgAAAADhIgg9AAAAALKWmj8AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSxqGlIwBQ5R0lFKULg=="
71
+ },
72
+ "_episode_num": 0,
73
+ "use_sde": false,
74
+ "sde_sample_freq": -1,
75
+ "_current_progress_remaining": 0.00010666666666669933,
76
+ "ep_info_buffer": [
77
+ {
78
+ "r": 1066.851531,
79
+ "l": 1000
80
+ },
81
+ {
82
+ "r": 1102.159395,
83
+ "l": 1000
84
+ },
85
+ {
86
+ "r": 1097.22042,
87
+ "l": 1000
88
+ },
89
+ {
90
+ "r": 1080.063169,
91
+ "l": 1000
92
+ },
93
+ {
94
+ "r": 1093.574283,
95
+ "l": 1000
96
+ },
97
+ {
98
+ "r": 1023.788472,
99
+ "l": 1000
100
+ },
101
+ {
102
+ "r": 1103.732663,
103
+ "l": 1000
104
+ },
105
+ {
106
+ "r": 1079.24171,
107
+ "l": 1000
108
+ },
109
+ {
110
+ "r": 1085.415005,
111
+ "l": 1000
112
+ },
113
+ {
114
+ "r": 1026.439862,
115
+ "l": 1000
116
+ },
117
+ {
118
+ "r": 1060.826476,
119
+ "l": 1000
120
+ },
121
+ {
122
+ "r": 1085.501782,
123
+ "l": 1000
124
+ },
125
+ {
126
+ "r": 1058.041115,
127
+ "l": 1000
128
+ },
129
+ {
130
+ "r": 1064.989285,
131
+ "l": 1000
132
+ },
133
+ {
134
+ "r": 1093.202669,
135
+ "l": 1000
136
+ },
137
+ {
138
+ "r": 1050.530637,
139
+ "l": 1000
140
+ }
141
+ ],
142
+ "ep_success_buffer": {
143
+ ":type:": "<class 'collections.deque'>",
144
+ ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
145
+ },
146
+ "_n_updates": 4688,
147
+ "n_delta": 8,
148
+ "pop_size": 16,
149
+ "delta_std_schedule": {
150
+ ":type:": "<class 'function'>",
151
+ ":serialized:": "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"
152
+ },
153
+ "n_eval_episodes": 1,
154
+ "n_top": 8,
155
+ "alive_bonus_offset": 0,
156
+ "zero_policy": false,
157
+ "weights": {
158
+ ":type:": "<class 'torch.Tensor'>",
159
+ ":serialized:": "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"
160
+ },
161
+ "processes": null,
162
+ "old_count": 0,
163
+ "n_params": 6278
164
+ }
ars-HalfCheetahBulletEnv-v0/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce5d37ad6f3b1e69af3b0cd2569861e5c762132b6f8353a5781fdc881843727d
3
+ size 27223
ars-HalfCheetahBulletEnv-v0/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
3
+ size 431
ars-HalfCheetahBulletEnv-v0/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
config.yml ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - alive_bonus_offset
3
+ - 0
4
+ - - delta_std
5
+ - 0.03
6
+ - - learning_rate
7
+ - 0.02
8
+ - - n_delta
9
+ - 8
10
+ - - n_envs
11
+ - 1
12
+ - - n_timesteps
13
+ - 75000000.0
14
+ - - n_top
15
+ - 8
16
+ - - normalize
17
+ - dict(norm_obs=True, norm_reward=False)
18
+ - - policy
19
+ - MlpPolicy
20
+ - - policy_kwargs
21
+ - dict(net_arch=[64, 64])
22
+ - - zero_policy
23
+ - false
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 sha256:5d0782a5b36f7f63ff473c4f7ca0a04f1911c3740b6249c67bb185c449d87f9d
3
+ size 1187935
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 1091.0104115, "std_reward": 18.132339769104025, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T15:08:26.077777"}
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74ae7f1997f07c44d88842099b29bb2bbb318c996adacbbca50a53b49cede8ef
3
+ size 2530331
vec_normalize.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9361a6e654404b80b4ed8a409b43dda3bc37b57fa70c35b23e7006f8a97c8234
3
+ size 4801