microwave1005 commited on
Commit
7194a9b
·
verified ·
1 Parent(s): 54e4dc9

Initial commit, add PPO LunarLander-v2 trained

Browse files
README.md CHANGED
@@ -1,3 +1,37 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 273.50 +/- 19.37
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 0x7caeba5672e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7caeba567370>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7caeba567400>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7caeba567490>", "_build": "<function ActorCriticPolicy._build at 0x7caeba567520>", "forward": "<function ActorCriticPolicy.forward at 0x7caeba5675b0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7caeba567640>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7caeba5676d0>", "_predict": "<function ActorCriticPolicy._predict at 0x7caeba567760>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7caeba5677f0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7caeba567880>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7caeba567910>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7cae5f100c40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1731947657090789303, "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": 248, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "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-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.5.1+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.0", "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:f84a4fb4e4d927b0b7fdc78cd93ec965c57f8918eefff1880232aaa6b8351d62
3
+ size 148012
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 0x7caeba5672e0>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7caeba567370>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7caeba567400>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7caeba567490>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7caeba567520>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7caeba5675b0>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7caeba567640>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7caeba5676d0>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7caeba567760>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7caeba5677f0>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7caeba567880>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7caeba567910>",
19
+ "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7cae5f100c40>"
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": 1731947657090789303,
30
+ "learning_rate": 0.0003,
31
+ "tensorboard_log": null,
32
+ "_last_obs": {
33
+ ":type:": "<class 'numpy.ndarray'>",
34
+ ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAAY3Rb5xpCU+vuhHPg00rL2zctA89i62vQAAAAAAAAAAzSrXPBwRX7yUqhe8vYOlPOaUzT0tsYW9AACAPwAAgD9mE+Q84eiYurCquTaVa68xUhPKOjpW2LUAAIA/AACAPxp0yj2/xS0/Bj3XvVbZlr5CayA80J4duwAAAAAAAAAAzZ6wPd8MuTyeqLW9HCqLvmICkLyy6sw9AAAAAAAAAABTQWU+B1ofvfntFzieIy83JTeLvn4cpLcAAIA/AACAPzOIn7ynugc/MxtNPWapSb6LzR+87USYvQAAAAAAAAAAGtUHvZE2qD9Y1KW+CqvFvomnJTxgIMC8AAAAAAAAAAAzD4G9Umy5uybOgruMJoQ8YBEJPbD8YL0AAIA/AACAP2b0Qz2uoeq6boYHu583iDw/FbC7Jr1sPQAAgD8AAIA/zYr1PPTRhj3IPzQ+La1VviCxWD3A9ag8AAAAAAAAAABAmqa+gPcNP2bjIT60cYC+dcwGvUXREz4AAAAAAAAAALtmjr5XWWm9nawCugYvPTvPeMg+mEJEPAAAgD8AAIA/bTRWvrKxZz+1Kue94raFvq6rFb4x7wm5AAAAAAAAAABmqNw97Td6P8FKDj53v4a+3W7UPXSIgD0AAAAAAAAAAAA4U7w80rg/G3SCvXmJtr1eGDG9VgEKvgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="
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": 248,
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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
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 sha256:96f7ef8ea4eae065170fb7dadc63de661f041cc5996fb7e7f6aa78aad44decb4
3
+ size 88362
ppo-LunarLander-v2/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:184fdd1f015ef54cc903b9bdd4312eb6377fedeed127576265d3d8b5146cbfb0
3
+ size 43762
ppo-LunarLander-v2/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
3
+ size 864
ppo-LunarLander-v2/system_info.txt ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ - OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
2
+ - Python: 3.10.12
3
+ - Stable-Baselines3: 2.0.0a5
4
+ - PyTorch: 2.5.1+cu121
5
+ - GPU Enabled: True
6
+ - Numpy: 1.26.4
7
+ - Cloudpickle: 3.1.0
8
+ - Gymnasium: 0.28.1
9
+ - OpenAI Gym: 0.25.2
replay.mp4 ADDED
Binary file (162 kB). View file
 
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 273.5044315, "std_reward": 19.366504140439204, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-18T16:55:39.959978"}