maccam912 commited on
Commit
e2db97f
·
verified ·
1 Parent(s): baf5009
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: 257.73 +/- 16.39
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 0x7ab7cfc19990>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ab7cfc19a20>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ab7cfc19ab0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ab7cfc19b40>", "_build": "<function ActorCriticPolicy._build at 0x7ab7cfc19bd0>", "forward": "<function ActorCriticPolicy.forward at 0x7ab7cfc19c60>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ab7cfc19cf0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ab7cfc19d80>", "_predict": "<function ActorCriticPolicy._predict at 0x7ab7cfc19e10>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ab7cfc19ea0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ab7cfc19f30>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ab7cfc19fc0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ab77225cfc0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1732999895098096811, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "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-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:d9b3481e057dc223f779d454b164f6ca67fa950b3a051633fd9923202454006f
3
+ size 147903
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 0x7ab7cfc19990>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ab7cfc19a20>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ab7cfc19ab0>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ab7cfc19b40>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7ab7cfc19bd0>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7ab7cfc19c60>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ab7cfc19cf0>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ab7cfc19d80>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7ab7cfc19e10>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ab7cfc19ea0>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ab7cfc19f30>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ab7cfc19fc0>",
19
+ "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7ab77225cfc0>"
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": 1732999895098096811,
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:": "gAWVdgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=",
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": 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 sha256:1da6dd487e10c0bd56d70ba56f3688b5d16cb6a5713d8a42806446faa9880212
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:e156d2e8e00701c1000eb2beea3fe3884bb52a69badc2195d2eba9c94429b738
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 (173 kB). View file
 
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 257.72995099999997, "std_reward": 16.391096749352958, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-30T21:23:14.297584"}