loicspigeleer commited on
Commit
a01f098
1 Parent(s): d6eac12

Upload PPO LunarLander-v2 trained agent

Browse files
FirstRLAgent.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:364caad9b8a00dc50b68e69b89506edaaf96b9c9c9efe57ec3e9e65d57e1f496
3
+ size 146170
FirstRLAgent/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 2.0.0a5
FirstRLAgent/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 0x7d8826e84430>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d8826e844c0>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d8826e84550>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d8826e845e0>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7d8826e84670>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7d8826e84700>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d8826e84790>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d8826e84820>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7d8826e848b0>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d8826e84940>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d8826e849d0>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d8826e84a60>",
19
+ "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7d8827013b80>"
21
+ },
22
+ "verbose": 0,
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": 1692703216721344013,
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:": "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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:": "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": 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
+ }
FirstRLAgent/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc6e2c8dec2134a2daff955740d4eecafcced331c82ac668c4c0e0cf1c318f29
3
+ size 87545
FirstRLAgent/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29eb4732ca609e7f7e4729fe6b0ad3ee5d7e59727dd77e3aeacbb9fcdde15a29
3
+ size 43201
FirstRLAgent/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
3
+ size 431
FirstRLAgent/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: False
6
+ - Numpy: 1.23.5
7
+ - Cloudpickle: 2.2.1
8
+ - Gymnasium: 0.28.1
9
+ - OpenAI Gym: 0.25.2
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: 272.06 +/- 16.19
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 0x7d8826e84430>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d8826e844c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d8826e84550>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d8826e845e0>", "_build": "<function ActorCriticPolicy._build at 0x7d8826e84670>", "forward": "<function ActorCriticPolicy.forward at 0x7d8826e84700>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d8826e84790>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d8826e84820>", "_predict": "<function ActorCriticPolicy._predict at 0x7d8826e848b0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d8826e84940>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d8826e849d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d8826e84a60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d8827013b80>"}, "verbose": 0, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1692703216721344013, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAHMtSD4Sj+A8EPfSOg4Lkzlw1nk+CsQeugAAgD8AAIA/zS5HvewKtbuWhkQ83mejPEtQCr3urok9AACAPwAAgD8FDpG+AVprPz+BEr6FPsq+wUY+vrUfdj0AAAAAAAAAAN29uD7zuWI/HaTxPk1ABr9vtKE+KxzGPQAAAAAAAAAAzbG5PY/yArqQwXo6qeZoNTzcKrtmVpG5AAAAAAAAgD/G7I8+kvODPvwtlr2x5ZS+zWAxPWLmcL0AAAAAAAAAAOZwMz6BiZe84lSDO8C+z7l80Qa+FhuuugAAgD8AAIA/ens6viEm1rybuH8+8yP5vY1hNz4i7HQ+AACAPwAAgD8GZlo+7qq/vMULdbtbcM85kYwuvpsSpToAAIA/AACAP4bUMz42i2i83EmjPPNi/7qOVcm9gy3PuwAAgD8AAIA/Wpy5vV2HNj6SjGw9XX13vkZBKb0ejh+8AAAAAAAAAADmtkS9Yjy8P/K+Kr9RDZk+06ttPMhoNL0AAAAAAAAAAFp+TD5O+6u8CFFqOx5T/7w7yR2+MWMMPQAAAAAAAAAAMzaaPb1iMTwu5UQ9nOlqvhaTGTxeFRI9AAAAAAAAAABDMnK+4afzPto79j0aqLW+p1tVvTixkbsAAAAAAAAAAMb9Gz7GZBI/qptHPZUn4L5wWrY9IkFpvAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="}, "_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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "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-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": "False", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
replay.mp4 ADDED
Binary file (178 kB). View file
 
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 272.0551385, "std_reward": 16.186348451393712, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-22T11:55:54.346344"}