magjico commited on
Commit
3bc22db
1 Parent(s): 56936ef

Upload PPO LunarLander-v2 trained agent

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: 273.09 +/- 18.13
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 0x7d3756f741f0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d3756f74280>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d3756f74310>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d3756f743a0>", "_build": "<function ActorCriticPolicy._build at 0x7d3756f74430>", "forward": "<function ActorCriticPolicy.forward at 0x7d3756f744c0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d3756f74550>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d3756f745e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7d3756f74670>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d3756f74700>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d3756f74790>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d3756f74820>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d3756f70ac0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1711466961485821664, "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-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.1+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "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:a88a23c3d9242e8ba31450fe3db1e5216d5b35eff11f946aab8db55ce54e2b29
3
+ size 148020
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 0x7d3756f741f0>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d3756f74280>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d3756f74310>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d3756f743a0>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7d3756f74430>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7d3756f744c0>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d3756f74550>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d3756f745e0>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7d3756f74670>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d3756f74700>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d3756f74790>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d3756f74820>",
19
+ "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7d3756f70ac0>"
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": 1711466961485821664,
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": 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 sha256:82e306e17e3ddb5f97058e6d4b3f514b61e46cc840cb4777c97ec83c36ae0d42
3
+ size 88362
ppo-LunarLander-v2/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07357d4dc92be38d4e1c43fce42ecab5dba9d4034325586faf4c65c5988ae975
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-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
2
+ - Python: 3.10.12
3
+ - Stable-Baselines3: 2.0.0a5
4
+ - PyTorch: 2.2.1+cu121
5
+ - GPU Enabled: True
6
+ - Numpy: 1.25.2
7
+ - Cloudpickle: 2.2.1
8
+ - Gymnasium: 0.28.1
9
+ - OpenAI Gym: 0.25.2
replay.mp4 ADDED
Binary file (184 kB). View file
 
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 273.0883688, "std_reward": 18.13142972800575, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-26T15:47:37.738692"}