Hugging Face's logo

qgallouedec
/
a2c-BipedalWalkerHardcore-v3-1004659622

Reinforcement Learning
stable-baselines3
BipedalWalkerHardcore-v3
deep-reinforcement-learning
Eval Results
Model card Files Community
Quentin Gallouédec commited on
Commit
0f26aca
·
1 Parent(s): e9d1eb7

Initial commit

Browse files
Files changed (16) hide show
  1. .gitattributes +1 -0
  2. README.md +81 -0
  3. a2c-BipedalWalkerHardcore-v3.zip +3 -0
  4. a2c-BipedalWalkerHardcore-v3/_stable_baselines3_version +1 -0
  5. a2c-BipedalWalkerHardcore-v3/data +106 -0
  6. a2c-BipedalWalkerHardcore-v3/policy.optimizer.pth +3 -0
  7. a2c-BipedalWalkerHardcore-v3/policy.pth +3 -0
  8. a2c-BipedalWalkerHardcore-v3/pytorch_variables.pth +3 -0
  9. a2c-BipedalWalkerHardcore-v3/system_info.txt +7 -0
  10. args.yml +79 -0
  11. config.yml +31 -0
  12. env_kwargs.yml +1 -0
  13. replay.mp4 +3 -0
  14. results.json +1 -0
  15. train_eval_metrics.zip +3 -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 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: A2C
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: 103.13 +/- 141.13
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **A2C** Agent playing **BipedalWalkerHardcore-v3**
25
+ This is a trained model of a **A2C** 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 a2c --env BipedalWalkerHardcore-v3 -orga qgallouedec -f logs/
47
+ python -m rl_zoo3.enjoy --algo a2c --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 a2c --env BipedalWalkerHardcore-v3 -orga qgallouedec -f logs/
53
+ python -m rl_zoo3.enjoy --algo a2c --env BipedalWalkerHardcore-v3 -f logs/
54
+ ```
55
+
56
+ ## Training (with the RL Zoo)
57
+ ```
58
+ python -m rl_zoo3.train --algo a2c --env BipedalWalkerHardcore-v3 -f logs/
59
+ # Upload the model and generate video (when possible)
60
+ python -m rl_zoo3.push_to_hub --algo a2c --env BipedalWalkerHardcore-v3 -f logs/ -orga qgallouedec
61
+ ```
62
+
63
+ ## Hyperparameters
64
+ ```python
65
+ OrderedDict([('ent_coef', 0.001),
66
+ ('gae_lambda', 0.9),
67
+ ('gamma', 0.99),
68
+ ('learning_rate', 'lin_0.0008'),
69
+ ('max_grad_norm', 0.5),
70
+ ('n_envs', 32),
71
+ ('n_steps', 8),
72
+ ('n_timesteps', 200000000.0),
73
+ ('normalize', True),
74
+ ('normalize_advantage', False),
75
+ ('policy', 'MlpPolicy'),
76
+ ('policy_kwargs', 'dict(log_std_init=-2, ortho_init=False)'),
77
+ ('use_rms_prop', True),
78
+ ('use_sde', True),
79
+ ('vf_coef', 0.4),
80
+ ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
81
+ ```
a2c-BipedalWalkerHardcore-v3.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:430642b4ac5c065c03b97ec5134e14df4c3291d7ebf795440d3680fcf195d2f3
3
+ size 130089
a2c-BipedalWalkerHardcore-v3/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.8.0a6
a2c-BipedalWalkerHardcore-v3/data ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 0x7f30a794fd30>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f30a794fdc0>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f30a794fe50>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f30a794fee0>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7f30a794ff70>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7f30a7951040>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f30a79510d0>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f30a7951160>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7f30a79511f0>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f30a7951280>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f30a7951310>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f30a79513a0>",
19
+ "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7f30a7950ec0>"
21
+ },
22
+ "verbose": 1,
23
+ "policy_kwargs": {
24
+ ":type:": "<class 'dict'>",
25
+ ":serialized:": "gAWVowAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/v///4wKb3J0aG9faW5pdJSJjA9vcHRpbWl6ZXJfY2xhc3OUjBN0b3JjaC5vcHRpbS5ybXNwcm9wlIwHUk1TcHJvcJSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lCiMBWFscGhhlEc/764UeuFHrowDZXBzlEc+5Pi1iONo8YwMd2VpZ2h0X2RlY2F5lEsAdXUu",
26
+ "log_std_init": -2,
27
+ "ortho_init": false,
28
+ "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>",
29
+ "optimizer_kwargs": {
30
+ "alpha": 0.99,
31
+ "eps": 1e-05,
32
+ "weight_decay": 0
33
+ }
34
+ },
35
+ "observation_space": {
36
+ ":type:": "<class 'gym.spaces.box.Box'>",
37
+ ":serialized:": "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",
38
+ "dtype": "float32",
39
+ "_shape": [
40
+ 24
41
+ ],
42
+ "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]",
43
+ "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]",
44
+ "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]",
45
+ "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]",
46
+ "_np_random": null
47
+ },
48
+ "action_space": {
49
+ ":type:": "<class 'gym.spaces.box.Box'>",
50
+ ":serialized:": "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",
51
+ "dtype": "float32",
52
+ "_shape": [
53
+ 4
54
+ ],
55
+ "low": "[-1. -1. -1. -1.]",
56
+ "high": "[1. 1. 1. 1.]",
57
+ "bounded_below": "[ True True True True]",
58
+ "bounded_above": "[ True True True True]",
59
+ "_np_random": "RandomState(MT19937)"
60
+ },
61
+ "n_envs": 1,
62
+ "num_timesteps": 200000000,
63
+ "_total_timesteps": 200000000,
64
+ "_num_timesteps_at_start": 0,
65
+ "seed": 0,
66
+ "action_noise": null,
67
+ "start_time": 1670930562216864858,
68
+ "learning_rate": {
69
+ ":type:": "<class 'function'>",
70
+ ":serialized:": "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"
71
+ },
72
+ "tensorboard_log": "runs/BipedalWalkerHardcore-v3__a2c__1004659622__1670930559/BipedalWalkerHardcore-v3",
73
+ "lr_schedule": {
74
+ ":type:": "<class 'function'>",
75
+ ":serialized:": "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"
76
+ },
77
+ "_last_obs": null,
78
+ "_last_episode_starts": {
79
+ ":type:": "<class 'numpy.ndarray'>",
80
+ ":serialized:": "gAWVkwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksghZSMAUOUdJRSlC4="
81
+ },
82
+ "_last_original_obs": {
83
+ ":type:": "<class 'numpy.ndarray'>",
84
+ ":serialized:": "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"
85
+ },
86
+ "_episode_num": 0,
87
+ "use_sde": true,
88
+ "sde_sample_freq": -1,
89
+ "_current_progress_remaining": 0.0,
90
+ "ep_info_buffer": {
91
+ ":type:": "<class 'collections.deque'>",
92
+ ":serialized:": "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"
93
+ },
94
+ "ep_success_buffer": {
95
+ ":type:": "<class 'collections.deque'>",
96
+ ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
97
+ },
98
+ "_n_updates": 781250,
99
+ "n_steps": 8,
100
+ "gamma": 0.99,
101
+ "gae_lambda": 0.9,
102
+ "ent_coef": 0.001,
103
+ "vf_coef": 0.4,
104
+ "max_grad_norm": 0.5,
105
+ "normalize_advantage": false
106
+ }
a2c-BipedalWalkerHardcore-v3/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf5fc47980e4e818bfdfdef1962c1c2df975308c96c268eac765f8e41fa99baf
3
+ size 52094
a2c-BipedalWalkerHardcore-v3/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dbe025d3aab384b1707cea21c9fd7dab345ecb8aa3006696d95bf801c7d3ea0
3
+ size 52798
a2c-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
a2c-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
args.yml ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - a2c
4
+ - - device
5
+ - auto
6
+ - - env
7
+ - BipedalWalkerHardcore-v3
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
+ - 1004659622
56
+ - - storage
57
+ - null
58
+ - - study_name
59
+ - null
60
+ - - tensorboard_log
61
+ - runs/BipedalWalkerHardcore-v3__a2c__1004659622__1670930559
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
config.yml ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - ent_coef
3
+ - 0.001
4
+ - - gae_lambda
5
+ - 0.9
6
+ - - gamma
7
+ - 0.99
8
+ - - learning_rate
9
+ - lin_0.0008
10
+ - - max_grad_norm
11
+ - 0.5
12
+ - - n_envs
13
+ - 32
14
+ - - n_steps
15
+ - 8
16
+ - - n_timesteps
17
+ - 200000000.0
18
+ - - normalize
19
+ - true
20
+ - - normalize_advantage
21
+ - false
22
+ - - policy
23
+ - MlpPolicy
24
+ - - policy_kwargs
25
+ - dict(log_std_init=-2, ortho_init=False)
26
+ - - use_rms_prop
27
+ - true
28
+ - - use_sde
29
+ - true
30
+ - - vf_coef
31
+ - 0.4
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 sha256:6cb43d040e030d675be76d5daffe6e64373eb3a62173959dad0f2345013f60b7
3
+ size 496626
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 103.1278538, "std_reward": 141.13470473188445, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T14:38:16.620315"}
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e29a33e68ccaf583a75483f35d1951ad31c5e9ef0a9362cdf07c089f1805a52
3
+ size 5039283
vec_normalize.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f8e3b7a9a0f3f13dd77a1fb97661e845cd88f7b5a078640efa38eb752039ba1
3
+ size 7818