rchan26 commited on
Commit
c98a63f
1 Parent(s): 30b5eb4

upload model from HF-RL course unit 1

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: 257.83 +/- 14.38
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 0x7eadae9a5a20>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7eadae9a5ab0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7eadae9a5b40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7eadae9a5bd0>", "_build": "<function ActorCriticPolicy._build at 0x7eadae9a5c60>", "forward": "<function ActorCriticPolicy.forward at 0x7eadae9a5cf0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7eadae9a5d80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7eadae9a5e10>", "_predict": "<function ActorCriticPolicy._predict at 0x7eadae9a5ea0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7eadae9a5f30>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7eadae9a5fc0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7eadae9a6050>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ead5178d1c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1731945131133932058, "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 sha256:49f6eb6ff8a8a647d5de9d83306c6927686ffd9f107359d68cc160e2c8a826ef
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 0x7eadae9a5a20>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7eadae9a5ab0>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7eadae9a5b40>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7eadae9a5bd0>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7eadae9a5c60>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7eadae9a5cf0>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7eadae9a5d80>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7eadae9a5e10>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7eadae9a5ea0>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7eadae9a5f30>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7eadae9a5fc0>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7eadae9a6050>",
19
+ "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7ead5178d1c0>"
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": 1731945131133932058,
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:e0250742a0fc77cc9a17fbc7ae122ede28db7ef096719b742498a6ad228fe039
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:fd5bc0284017c9a571ced744e074a4ead33e460076347b4c0c8e0101c9f4b676
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 (169 kB). View file
 
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 257.8304031, "std_reward": 14.378318928150195, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-18T16:13:40.279751"}