Saujana commited on
Commit
faedf49
1 Parent(s): 0ff9b08

Upload PPO LunarLander-v2 Agent

Browse files
PPO-LunarLander-v2.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a8ca27acd0637f464e5d99dd81f36729939993ad86fa40ec142ba791f40936b
3
+ size 146654
PPO-LunarLander-v2/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 2.0.0a5
PPO-LunarLander-v2/data ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 0x7f9e8e7cdb40>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9e8e7cdbd0>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9e8e7cdc60>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9e8e7cdcf0>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7f9e8e7cdd80>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7f9e8e7cde10>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f9e8e7cdea0>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9e8e7cdf30>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7f9e8e7cdfc0>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9e8e7ce050>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9e8e7ce0e0>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9e8e7ce170>",
19
+ "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7f9e9655b000>"
21
+ },
22
+ "verbose": 1,
23
+ "policy_kwargs": {},
24
+ "num_timesteps": 1015808,
25
+ "_total_timesteps": 1000000,
26
+ "_num_timesteps_at_start": 0,
27
+ "seed": null,
28
+ "action_noise": null,
29
+ "start_time": 1697463860468437530,
30
+ "learning_rate": 0.0003,
31
+ "tensorboard_log": null,
32
+ "_last_obs": {
33
+ ":type:": "<class 'numpy.ndarray'>",
34
+ ":serialized:": "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"
35
+ },
36
+ "_last_episode_starts": {
37
+ ":type:": "<class 'numpy.ndarray'>",
38
+ ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
39
+ },
40
+ "_last_original_obs": null,
41
+ "_episode_num": 0,
42
+ "use_sde": false,
43
+ "sde_sample_freq": -1,
44
+ "_current_progress_remaining": -0.015808000000000044,
45
+ "_stats_window_size": 100,
46
+ "ep_info_buffer": {
47
+ ":type:": "<class 'collections.deque'>",
48
+ ":serialized:": "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"
49
+ },
50
+ "ep_success_buffer": {
51
+ ":type:": "<class 'collections.deque'>",
52
+ ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
53
+ },
54
+ "_n_updates": 310,
55
+ "observation_space": {
56
+ ":type:": "<class 'gymnasium.spaces.box.Box'>",
57
+ ":serialized:": "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",
58
+ "dtype": "float32",
59
+ "bounded_below": "[ True True True True True True True True]",
60
+ "bounded_above": "[ True True True True True True True True]",
61
+ "_shape": [
62
+ 8
63
+ ],
64
+ "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
65
+ "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
66
+ "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
67
+ "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
68
+ "_np_random": null
69
+ },
70
+ "action_space": {
71
+ ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
72
+ ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
73
+ "n": "4",
74
+ "start": "0",
75
+ "_shape": [],
76
+ "dtype": "int64",
77
+ "_np_random": null
78
+ },
79
+ "n_envs": 16,
80
+ "n_steps": 2048,
81
+ "gamma": 0.99,
82
+ "gae_lambda": 0.95,
83
+ "ent_coef": 0.0,
84
+ "vf_coef": 0.5,
85
+ "max_grad_norm": 0.5,
86
+ "batch_size": 64,
87
+ "n_epochs": 10,
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
+ "lr_schedule": {
96
+ ":type:": "<class 'function'>",
97
+ ":serialized:": "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"
98
+ }
99
+ }
PPO-LunarLander-v2/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:793c17ab528b4ad53927e626e2844812e434e576935ec062615e4b0554fab598
3
+ size 87929
PPO-LunarLander-v2/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:550e4e1da188bb36b50c54b5cc612e314b7428b0dc10207d763882f28e7cc497
3
+ size 43329
PPO-LunarLander-v2/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-LunarLander-v2/system_info.txt ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ - OS: Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023
2
+ - Python: 3.10.12
3
+ - Stable-Baselines3: 2.0.0a5
4
+ - PyTorch: 2.0.1+cu118
5
+ - GPU Enabled: True
6
+ - Numpy: 1.23.5
7
+ - Cloudpickle: 2.2.1
8
+ - Gymnasium: 0.28.1
9
+ - OpenAI Gym: 0.25.2
README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - LunarLander-v2
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: LunarLander-v2
16
+ type: LunarLander-v2
17
+ metrics:
18
+ - type: mean_reward
19
+ value: 259.32 +/- 20.34
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **PPO** Agent playing **LunarLander-v2**
25
+ This is a trained model of a **PPO** agent playing **LunarLander-v2**
26
+ using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
27
+
28
+ ## Usage (with Stable-baselines3)
29
+ TODO: Add your code
30
+
31
+
32
+ ```python
33
+ from stable_baselines3 import ...
34
+ from huggingface_sb3 import load_from_hub
35
+
36
+ ...
37
+ ```
config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__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 ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f9e8e7cdb40>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9e8e7cdbd0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9e8e7cdc60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9e8e7cdcf0>", "_build": "<function ActorCriticPolicy._build at 0x7f9e8e7cdd80>", "forward": "<function ActorCriticPolicy.forward at 0x7f9e8e7cde10>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f9e8e7cdea0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9e8e7cdf30>", "_predict": "<function ActorCriticPolicy._predict at 0x7f9e8e7cdfc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9e8e7ce050>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9e8e7ce0e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9e8e7ce170>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f9e9655b000>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1697463860468437530, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 310, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
replay.mp4 ADDED
Binary file (177 kB). View file
 
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 259.3176274, "std_reward": 20.3359852175439, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-16T14:14:41.726835"}