MohanaSri commited on
Commit
dded324
1 Parent(s): bec4791

Upload PPO Pendulum-v1 trained agent

Browse files
README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - Pendulum-v1
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: Pendulum-v1
16
+ type: Pendulum-v1
17
+ metrics:
18
+ - type: mean_reward
19
+ value: -1348.57 +/- 247.55
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **PPO** Agent playing **Pendulum-v1**
25
+ This is a trained model of a **PPO** agent playing **Pendulum-v1**
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 0x7ee850864e50>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ee850864ee0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ee850864f70>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ee850865000>", "_build": "<function ActorCriticPolicy._build at 0x7ee850865090>", "forward": "<function ActorCriticPolicy.forward at 0x7ee850865120>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ee8508651b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ee850865240>", "_predict": "<function ActorCriticPolicy._predict at 0x7ee8508652d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ee850865360>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ee8508653f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ee850865480>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ee85085cd80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2048, "_total_timesteps": 1000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1693366798510593647, "learning_rate": 0.001, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYMAAAAAAAAALSSTL/y5hk/AO2yPpSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsDhpSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": true, "sde_sample_freq": 4, "_current_progress_remaining": -1.048, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVVAEAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwJNHyZiNKiCMAWyUS8iMAXSUR0A1LfChvitJdX2UKGgGR8CaBOmHxjJ/aAdLyGgIR0A1ksk6cRUWdX2UKGgGR8CSLvWSEDhcaAdLyGgIR0A1+3VCojwAdX2UKGgGR8CQeRNe+mFbaAdLyGgIR0A2VuVHFxXGdX2UKGgGR8CMAoqm0mdBaAdLyGgIR0A2mTjvNNahdX2UKGgGR8CVGbDaXa8IaAdLyGgIR0A22PhAGB4EdX2UKGgGR8CV9pZx7zClaAdLyGgIR0A3F7pV0cOtdX2UKGgGR8CRwZd5Y5ktaAdLyGgIR0A3WkCmuTzNdX2UKGgGR8CRpVAPuognaAdLyGgIR0A3msZYPoV3dX2UKGgGR8CVd/Lh73PBaAdLyGgIR0A32eK8+RozdWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 10, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True]", "bounded_above": "[ True True True]", "_shape": [3], "low": "[-1. -1. -8.]", "high": "[1. 1. 8.]", "low_repr": "[-1. -1. -8.]", "high_repr": "[1. 1. 8.]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True]", "bounded_above": "[ True]", "_shape": [1], "low": "[-2.]", "high": "[2.]", "low_repr": "-2.0", "high_repr": "2.0", "_np_random": null}, "n_envs": 1, "n_steps": 2048, "gamma": 0.98, "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": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
ppo-pendulum-v1.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1611ee4c62105db46dc92747dac5c0407dc78cce41007761fa679449a0e73727
3
+ size 133788
ppo-pendulum-v1/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 2.0.0a5
ppo-pendulum-v1/data ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 0x7ee850864e50>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ee850864ee0>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ee850864f70>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ee850865000>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7ee850865090>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7ee850865120>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ee8508651b0>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ee850865240>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7ee8508652d0>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ee850865360>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ee8508653f0>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ee850865480>",
19
+ "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7ee85085cd80>"
21
+ },
22
+ "verbose": 1,
23
+ "policy_kwargs": {},
24
+ "num_timesteps": 2048,
25
+ "_total_timesteps": 1000,
26
+ "_num_timesteps_at_start": 0,
27
+ "seed": null,
28
+ "action_noise": null,
29
+ "start_time": 1693366798510593647,
30
+ "learning_rate": 0.001,
31
+ "tensorboard_log": null,
32
+ "_last_obs": {
33
+ ":type:": "<class 'numpy.ndarray'>",
34
+ ":serialized:": "gAWVgQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYMAAAAAAAAALSSTL/y5hk/AO2yPpSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsDhpSMAUOUdJRSlC4="
35
+ },
36
+ "_last_episode_starts": {
37
+ ":type:": "<class 'numpy.ndarray'>",
38
+ ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
39
+ },
40
+ "_last_original_obs": null,
41
+ "_episode_num": 0,
42
+ "use_sde": true,
43
+ "sde_sample_freq": 4,
44
+ "_current_progress_remaining": -1.048,
45
+ "_stats_window_size": 100,
46
+ "ep_info_buffer": {
47
+ ":type:": "<class 'collections.deque'>",
48
+ ":serialized:": "gAWVVAEAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwJNHyZiNKiCMAWyUS8iMAXSUR0A1LfChvitJdX2UKGgGR8CaBOmHxjJ/aAdLyGgIR0A1ksk6cRUWdX2UKGgGR8CSLvWSEDhcaAdLyGgIR0A1+3VCojwAdX2UKGgGR8CQeRNe+mFbaAdLyGgIR0A2VuVHFxXGdX2UKGgGR8CMAoqm0mdBaAdLyGgIR0A2mTjvNNahdX2UKGgGR8CVGbDaXa8IaAdLyGgIR0A22PhAGB4EdX2UKGgGR8CV9pZx7zClaAdLyGgIR0A3F7pV0cOtdX2UKGgGR8CRwZd5Y5ktaAdLyGgIR0A3WkCmuTzNdX2UKGgGR8CRpVAPuognaAdLyGgIR0A3msZYPoV3dX2UKGgGR8CVd/Lh73PBaAdLyGgIR0A32eK8+RozdWUu"
49
+ },
50
+ "ep_success_buffer": {
51
+ ":type:": "<class 'collections.deque'>",
52
+ ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
53
+ },
54
+ "_n_updates": 10,
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]",
60
+ "bounded_above": "[ True True True]",
61
+ "_shape": [
62
+ 3
63
+ ],
64
+ "low": "[-1. -1. -8.]",
65
+ "high": "[1. 1. 8.]",
66
+ "low_repr": "[-1. -1. -8.]",
67
+ "high_repr": "[1. 1. 8.]",
68
+ "_np_random": null
69
+ },
70
+ "action_space": {
71
+ ":type:": "<class 'gymnasium.spaces.box.Box'>",
72
+ ":serialized:": "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",
73
+ "dtype": "float32",
74
+ "bounded_below": "[ True]",
75
+ "bounded_above": "[ True]",
76
+ "_shape": [
77
+ 1
78
+ ],
79
+ "low": "[-2.]",
80
+ "high": "[2.]",
81
+ "low_repr": "-2.0",
82
+ "high_repr": "2.0",
83
+ "_np_random": null
84
+ },
85
+ "n_envs": 1,
86
+ "n_steps": 2048,
87
+ "gamma": 0.98,
88
+ "gae_lambda": 0.95,
89
+ "ent_coef": 0.0,
90
+ "vf_coef": 0.5,
91
+ "max_grad_norm": 0.5,
92
+ "batch_size": 64,
93
+ "n_epochs": 10,
94
+ "clip_range": {
95
+ ":type:": "<class 'function'>",
96
+ ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
97
+ },
98
+ "clip_range_vf": null,
99
+ "normalize_advantage": true,
100
+ "target_kl": null,
101
+ "lr_schedule": {
102
+ ":type:": "<class 'function'>",
103
+ ":serialized:": "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"
104
+ }
105
+ }
ppo-pendulum-v1/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e1cde19665e9a5eeb0be62a91688de386abab7553a1f27c87e19297082b008e
3
+ size 82480
ppo-pendulum-v1/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d67efe213e32d6e3aa3d5f081a3675accfad9fabefa4f5dce162e3228e9b9bb
3
+ size 40510
ppo-pendulum-v1/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
3
+ size 431
ppo-pendulum-v1/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: True
6
+ - Numpy: 1.23.5
7
+ - Cloudpickle: 2.2.1
8
+ - Gymnasium: 0.28.1
9
+ - OpenAI Gym: 0.25.2
replay.mp4 ADDED
Binary file (329 kB). View file
 
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": -1348.5673974215983, "std_reward": 247.55307447687898, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-30T03:51:10.465386"}