rmpmalheiro commited on
Commit
2f193c7
·
1 Parent(s): 381469d

My first huggingface commit - LunarLander-v2

Browse files
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: 275.46 +/- 19.09
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 0x7bf6143d2ef0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7bf6143d2f80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7bf6143d3010>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7bf6143d30a0>", "_build": "<function ActorCriticPolicy._build at 0x7bf6143d3130>", "forward": "<function ActorCriticPolicy.forward at 0x7bf6143d31c0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7bf6143d3250>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7bf6143d32e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7bf6143d3370>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7bf6143d3400>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7bf6143d3490>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7bf6143d3520>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7bf6143dcc40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1693947321993388445, "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": 744, "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": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "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-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 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"}}
ppo-LunarLander-v2.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccc7186abf35d70aae59a51e441cd88cde44b88a3e36e88a73d999353d4bf97c
3
+ size 146642
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 0x7bf6143d2ef0>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7bf6143d2f80>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7bf6143d3010>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7bf6143d30a0>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7bf6143d3130>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7bf6143d31c0>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7bf6143d3250>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7bf6143d32e0>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7bf6143d3370>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7bf6143d3400>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7bf6143d3490>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7bf6143d3520>",
19
+ "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7bf6143dcc40>"
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": 1693947321993388445,
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": 744,
55
+ "observation_space": {
56
+ ":type:": "<class 'gymnasium.spaces.box.Box'>",
57
+ ":serialized:": "gAWVcAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=",
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": 1024,
81
+ "gamma": 0.999,
82
+ "gae_lambda": 0.98,
83
+ "ent_coef": 0.01,
84
+ "vf_coef": 0.5,
85
+ "max_grad_norm": 0.5,
86
+ "batch_size": 64,
87
+ "n_epochs": 4,
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 sha256:8e257ac44d4168bb379596076ee95e60a79c2bc04966b90103c68d3dbdeda7b5
3
+ size 87929
ppo-LunarLander-v2/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38bf52851ca78f474389017936ff7fb877398f56e1b6ee68dc8c0eb0458d8570
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-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 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
replay.mp4 ADDED
Binary file (158 kB). View file
 
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 275.4637141, "std_reward": 19.08717078652077, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-05T21:26:52.079889"}