Hugging Face's logo

qgallouedec
/
a2c-Acrobot-v1-2453577583

Reinforcement Learning
stable-baselines3
Acrobot-v1
deep-reinforcement-learning
Eval Results
Model card Files Community
Quentin Gallouédec commited on
Commit
e442a2d
•
1 Parent(s): 3114a6c

Initial commit

Browse files
Files changed (16) hide show
  1. .gitattributes +1 -0
  2. README.md +71 -0
  3. a2c-Acrobot-v1.zip +3 -0
  4. a2c-Acrobot-v1/_stable_baselines3_version +1 -0
  5. a2c-Acrobot-v1/data +96 -0
  6. a2c-Acrobot-v1/policy.optimizer.pth +3 -0
  7. a2c-Acrobot-v1/policy.pth +3 -0
  8. a2c-Acrobot-v1/pytorch_variables.pth +3 -0
  9. a2c-Acrobot-v1/system_info.txt +7 -0
  10. args.yml +79 -0
  11. config.yml +11 -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 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - Acrobot-v1
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: Acrobot-v1
16
+ type: Acrobot-v1
17
+ metrics:
18
+ - type: mean_reward
19
+ value: -80.20 +/- 7.82
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **A2C** Agent playing **Acrobot-v1**
25
+ This is a trained model of a **A2C** agent playing **Acrobot-v1**
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 Acrobot-v1 -orga qgallouedec -f logs/
47
+ python -m rl_zoo3.enjoy --algo a2c --env Acrobot-v1 -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 Acrobot-v1 -orga qgallouedec -f logs/
53
+ python -m rl_zoo3.enjoy --algo a2c --env Acrobot-v1 -f logs/
54
+ ```
55
+
56
+ ## Training (with the RL Zoo)
57
+ ```
58
+ python -m rl_zoo3.train --algo a2c --env Acrobot-v1 -f logs/
59
+ # Upload the model and generate video (when possible)
60
+ python -m rl_zoo3.push_to_hub --algo a2c --env Acrobot-v1 -f logs/ -orga qgallouedec
61
+ ```
62
+
63
+ ## Hyperparameters
64
+ ```python
65
+ OrderedDict([('ent_coef', 0.0),
66
+ ('n_envs', 16),
67
+ ('n_timesteps', 500000.0),
68
+ ('normalize', True),
69
+ ('policy', 'MlpPolicy'),
70
+ ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
71
+ ```
a2c-Acrobot-v1.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24884eb6bf2a66e3d132166a544f973b7d073f28f88d0b0ebc5cdf67314ca476
3
+ size 100826
a2c-Acrobot-v1/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.8.0a6
a2c-Acrobot-v1/data ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 0x7f112bc50d30>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f112bc50dc0>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f112bc50e50>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f112bc50ee0>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7f112bc50f70>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7f112bc52040>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f112bc520d0>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f112bc52160>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7f112bc521f0>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f112bc52280>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f112bc52310>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f112bc523a0>",
19
+ "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7f112bc4e980>"
21
+ },
22
+ "verbose": 1,
23
+ "policy_kwargs": {
24
+ ":type:": "<class 'dict'>",
25
+ ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=",
26
+ "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>",
27
+ "optimizer_kwargs": {
28
+ "alpha": 0.99,
29
+ "eps": 1e-05,
30
+ "weight_decay": 0
31
+ }
32
+ },
33
+ "observation_space": {
34
+ ":type:": "<class 'gym.spaces.box.Box'>",
35
+ ":serialized:": "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",
36
+ "dtype": "float32",
37
+ "_shape": [
38
+ 6
39
+ ],
40
+ "low": "[ -1. -1. -1. -1. -12.566371 -28.274334]",
41
+ "high": "[ 1. 1. 1. 1. 12.566371 28.274334]",
42
+ "bounded_below": "[ True True True True True True]",
43
+ "bounded_above": "[ True True True True True True]",
44
+ "_np_random": null
45
+ },
46
+ "action_space": {
47
+ ":type:": "<class 'gym.spaces.discrete.Discrete'>",
48
+ ":serialized:": "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",
49
+ "n": 3,
50
+ "_shape": [],
51
+ "dtype": "int64",
52
+ "_np_random": "RandomState(MT19937)"
53
+ },
54
+ "n_envs": 1,
55
+ "num_timesteps": 500000,
56
+ "_total_timesteps": 500000,
57
+ "_num_timesteps_at_start": 0,
58
+ "seed": 0,
59
+ "action_noise": null,
60
+ "start_time": 1670933474141942728,
61
+ "learning_rate": 0.0007,
62
+ "tensorboard_log": "runs/Acrobot-v1__a2c__2453577583__1670933471/Acrobot-v1",
63
+ "lr_schedule": {
64
+ ":type:": "<class 'function'>",
65
+ ":serialized:": "gAWVvQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMRS9ob21lL3FnYWxsb3VlZGVjL3N0YWJsZS1iYXNlbGluZXMzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMRS9ob21lL3FnYWxsb3VlZGVjL3N0YWJsZS1iYXNlbGluZXMzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/RvAGjbi6x4WUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
66
+ },
67
+ "_last_obs": null,
68
+ "_last_episode_starts": {
69
+ ":type:": "<class 'numpy.ndarray'>",
70
+ ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAQAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
71
+ },
72
+ "_last_original_obs": {
73
+ ":type:": "<class 'numpy.ndarray'>",
74
+ ":serialized:": "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"
75
+ },
76
+ "_episode_num": 0,
77
+ "use_sde": false,
78
+ "sde_sample_freq": -1,
79
+ "_current_progress_remaining": 0.0,
80
+ "ep_info_buffer": {
81
+ ":type:": "<class 'collections.deque'>",
82
+ ":serialized:": "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"
83
+ },
84
+ "ep_success_buffer": {
85
+ ":type:": "<class 'collections.deque'>",
86
+ ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
87
+ },
88
+ "_n_updates": 6250,
89
+ "n_steps": 5,
90
+ "gamma": 0.99,
91
+ "gae_lambda": 1.0,
92
+ "ent_coef": 0.0,
93
+ "vf_coef": 0.5,
94
+ "max_grad_norm": 0.5,
95
+ "normalize_advantage": false
96
+ }
a2c-Acrobot-v1/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:329c488e0f9a36a1099a45924be05fe51dd14c4bccd44d56d73723a5d69e40da
3
+ size 41345
a2c-Acrobot-v1/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:999879ba55c298e2bfb8df8b395c631662e66f0fe037efef7408797d0bcaf93b
3
+ size 42049
a2c-Acrobot-v1/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-Acrobot-v1/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
+ - Acrobot-v1
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
+ - 2453577583
56
+ - - storage
57
+ - null
58
+ - - study_name
59
+ - null
60
+ - - tensorboard_log
61
+ - runs/Acrobot-v1__a2c__2453577583__1670933471
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 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - ent_coef
3
+ - 0.0
4
+ - - n_envs
5
+ - 16
6
+ - - n_timesteps
7
+ - 500000.0
8
+ - - normalize
9
+ - true
10
+ - - policy
11
+ - MlpPolicy
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 sha256:53264d26c02815c06dbd8872a2dd89725c686622379c6d1d50741ad5ffd1f574
3
+ size 950748
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": -80.2, "std_reward": 7.8204859184068605, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T14:51:58.490724"}
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e14257f25886aa9f0baf940f66c9f88403315afadc183096af0aac244c3c7633
3
+ size 118323
vec_normalize.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37641476c459e1366ea18427848b1360ad2032cd80399cf399ab6a56355d817c
3
+ size 4500