Hugging Face's logo

qgallouedec
/
ppo-CartPole-v1-2542014453

Reinforcement Learning
stable-baselines3
CartPole-v1
deep-reinforcement-learning
Eval Results
Model card Files Community
Quentin Gallouédec commited on
Commit
b1aa77e
•
1 Parent(s): 2c98502

Initial commit

Browse files
Files changed (15) hide show
  1. .gitattributes +1 -0
  2. README.md +77 -0
  3. args.yml +83 -0
  4. config.yml +23 -0
  5. env_kwargs.yml +1 -0
  6. ppo-CartPole-v1.zip +3 -0
  7. ppo-CartPole-v1/_stable_baselines3_version +1 -0
  8. ppo-CartPole-v1/data +95 -0
  9. ppo-CartPole-v1/policy.optimizer.pth +3 -0
  10. ppo-CartPole-v1/policy.pth +3 -0
  11. ppo-CartPole-v1/pytorch_variables.pth +3 -0
  12. ppo-CartPole-v1/system_info.txt +7 -0
  13. replay.mp4 +3 -0
  14. results.json +1 -0
  15. train_eval_metrics.zip +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
+ - CartPole-v1
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - stable-baselines3
8
+ model-index:
9
+ - name: PPO
10
+ results:
11
+ - task:
12
+ type: reinforcement-learning
13
+ name: reinforcement-learning
14
+ dataset:
15
+ name: CartPole-v1
16
+ type: CartPole-v1
17
+ metrics:
18
+ - type: mean_reward
19
+ value: 500.00 +/- 0.00
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **PPO** Agent playing **CartPole-v1**
25
+ This is a trained model of a **PPO** agent playing **CartPole-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 ppo --env CartPole-v1 -orga qgallouedec -f logs/
47
+ python -m rl_zoo3.enjoy --algo ppo --env CartPole-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 ppo --env CartPole-v1 -orga qgallouedec -f logs/
53
+ python -m rl_zoo3.enjoy --algo ppo --env CartPole-v1 -f logs/
54
+ ```
55
+
56
+ ## Training (with the RL Zoo)
57
+ ```
58
+ python -m rl_zoo3.train --algo ppo --env CartPole-v1 -f logs/
59
+ # Upload the model and generate video (when possible)
60
+ python -m rl_zoo3.push_to_hub --algo ppo --env CartPole-v1 -f logs/ -orga qgallouedec
61
+ ```
62
+
63
+ ## Hyperparameters
64
+ ```python
65
+ OrderedDict([('batch_size', 256),
66
+ ('clip_range', 'lin_0.2'),
67
+ ('ent_coef', 0.0),
68
+ ('gae_lambda', 0.8),
69
+ ('gamma', 0.98),
70
+ ('learning_rate', 'lin_0.001'),
71
+ ('n_envs', 8),
72
+ ('n_epochs', 20),
73
+ ('n_steps', 32),
74
+ ('n_timesteps', 100000.0),
75
+ ('policy', 'MlpPolicy'),
76
+ ('normalize', False)])
77
+ ```
args.yml ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - ppo
4
+ - - conf_file
5
+ - null
6
+ - - device
7
+ - auto
8
+ - - env
9
+ - CartPole-v1
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
+ - 2542014453
58
+ - - storage
59
+ - null
60
+ - - study_name
61
+ - null
62
+ - - tensorboard_log
63
+ - runs/CartPole-v1__ppo__2542014453__1675782355
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 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - batch_size
3
+ - 256
4
+ - - clip_range
5
+ - lin_0.2
6
+ - - ent_coef
7
+ - 0.0
8
+ - - gae_lambda
9
+ - 0.8
10
+ - - gamma
11
+ - 0.98
12
+ - - learning_rate
13
+ - lin_0.001
14
+ - - n_envs
15
+ - 8
16
+ - - n_epochs
17
+ - 20
18
+ - - n_steps
19
+ - 32
20
+ - - n_timesteps
21
+ - 100000.0
22
+ - - policy
23
+ - MlpPolicy
env_kwargs.yml ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
ppo-CartPole-v1.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cf9bd2598aa14572ff38a745365b3450251f027dfa114032acf7b0029f60783
3
+ size 143001
ppo-CartPole-v1/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.8.0a6
ppo-CartPole-v1/data ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 0x7f1c806d3ee0>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f1c806d3f70>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f1c806d4040>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f1c806d40d0>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7f1c806d4160>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7f1c806d41f0>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f1c806d4280>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f1c806d4310>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7f1c806d43a0>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f1c806d4430>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f1c806d44c0>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f1c806d4550>",
19
+ "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7f1c806d5400>"
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
+ 4
30
+ ],
31
+ "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]",
32
+ "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]",
33
+ "bounded_below": "[ True True True True]",
34
+ "bounded_above": "[ True True True True]",
35
+ "_np_random": null
36
+ },
37
+ "action_space": {
38
+ ":type:": "<class 'gym.spaces.discrete.Discrete'>",
39
+ ":serialized:": "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",
40
+ "n": 2,
41
+ "_shape": [],
42
+ "dtype": "int64",
43
+ "_np_random": "RandomState(MT19937)"
44
+ },
45
+ "n_envs": 1,
46
+ "num_timesteps": 100096,
47
+ "_total_timesteps": 100000,
48
+ "_num_timesteps_at_start": 0,
49
+ "seed": 0,
50
+ "action_noise": null,
51
+ "start_time": 1675782377194422399,
52
+ "learning_rate": {
53
+ ":type:": "<class 'function'>",
54
+ ":serialized:": "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"
55
+ },
56
+ "tensorboard_log": "runs/CartPole-v1__ppo__2542014453__1675782355/CartPole-v1",
57
+ "lr_schedule": {
58
+ ":type:": "<class 'function'>",
59
+ ":serialized:": "gAWVjgMAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAksTQwh8AIgAFABTAJSMhAogICAgICAgIFByb2dyZXNzIHdpbGwgZGVjcmVhc2UgZnJvbSAxIChiZWdpbm5pbmcpIHRvIDAKICAgICAgICA6cGFyYW0gcHJvZ3Jlc3NfcmVtYWluaW5nOiAoZmxvYXQpCiAgICAgICAgOnJldHVybjogKGZsb2F0KQogICAgICAgIJSFlCmMEnByb2dyZXNzX3JlbWFpbmluZ5SFlIxNL2hvbWUvcWdhbGxvdWVkZWMvZW52X2JlbmNobWFyay9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3JsX3pvbzMvdXRpbHMucHmUjARmdW5jlE0mAUMCCAaUjA5pbml0aWFsX3ZhbHVlX5SFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMB3JsX3pvbzOUjAhfX25hbWVfX5SMDXJsX3pvbzMudXRpbHOUjAhfX2ZpbGVfX5SMTS9ob21lL3FnYWxsb3VlZGVjL2Vudl9iZW5jaG1hcmsvbGliL3B5dGhvbjMuMTAvc2l0ZS1wYWNrYWdlcy9ybF96b28zL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMHWxpbmVhcl9zY2hlZHVsZS48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UKIwScHJvZ3Jlc3NfcmVtYWluaW5nlIwIYnVpbHRpbnOUjAVmbG9hdJSTlIwGcmV0dXJulGgtdYwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBiMB19fZG9jX1+UaAmMC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz9QYk3S8an8hZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
60
+ },
61
+ "_last_obs": null,
62
+ "_last_episode_starts": {
63
+ ":type:": "<class 'numpy.ndarray'>",
64
+ ":serialized:": "gAWVewAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlC4="
65
+ },
66
+ "_last_original_obs": null,
67
+ "_episode_num": 0,
68
+ "use_sde": false,
69
+ "sde_sample_freq": -1,
70
+ "_current_progress_remaining": -0.0009600000000000719,
71
+ "ep_info_buffer": {
72
+ ":type:": "<class 'collections.deque'>",
73
+ ":serialized:": "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"
74
+ },
75
+ "ep_success_buffer": {
76
+ ":type:": "<class 'collections.deque'>",
77
+ ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
78
+ },
79
+ "_n_updates": 7820,
80
+ "n_steps": 32,
81
+ "gamma": 0.98,
82
+ "gae_lambda": 0.8,
83
+ "ent_coef": 0.0,
84
+ "vf_coef": 0.5,
85
+ "max_grad_norm": 0.5,
86
+ "batch_size": 256,
87
+ "n_epochs": 20,
88
+ "clip_range": {
89
+ ":type:": "<class 'function'>",
90
+ ":serialized:": "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"
91
+ },
92
+ "clip_range_vf": null,
93
+ "normalize_advantage": true,
94
+ "target_kl": null
95
+ }
ppo-CartPole-v1/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a43cfb5825c41162f373922da9241f9449e649abc4bd46edce30af96ae83a296
3
+ size 82937
ppo-CartPole-v1/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b5a09d2d154d851a49b55c1dfb9b2dbb3174d381206d419e1a4f8dda6a4f21f
3
+ size 40769
ppo-CartPole-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
ppo-CartPole-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
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e434a2bf06a9382077b8e7737382131b6aeee086ce44551e3d85f3de72f7bf8
3
+ size 59865
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-28T15:39:50.198080"}
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e67305ea0d614901fd4fdef35c6b78aff211f7279ae5389a5b214e65d44f37d
3
+ size 10487