Initial upload PPO model for Lunar Lander
Browse files- PPO_LunarLander.zip +3 -0
- PPO_LunarLander/_stable_baselines3_version +1 -0
- PPO_LunarLander/data +96 -0
- PPO_LunarLander/policy.optimizer.pth +3 -0
- PPO_LunarLander/policy.pth +3 -0
- PPO_LunarLander/pytorch_variables.pth +3 -0
- PPO_LunarLander/system_info.txt +7 -0
- README.md +37 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
PPO_LunarLander.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6e0046092b314c6acdaed36d85107c75a86ce51519b2c93bbaef2ca0d4a227d
|
3 |
+
size 147395
|
PPO_LunarLander/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.8.0
|
PPO_LunarLander/data
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 0x7f8bae0ba790>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f8bae0ba820>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8bae0ba8b0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8bae0ba940>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f8bae0ba9d0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f8bae0baa60>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f8bae0baaf0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8bae0bab80>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f8bae0bac10>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8bae0baca0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8bae0bad30>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8bae0badc0>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f8bae0c15c0>"
|
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": 1680982046731578787,
|
30 |
+
"learning_rate": 0.0003,
|
31 |
+
"tensorboard_log": null,
|
32 |
+
"lr_schedule": {
|
33 |
+
":type:": "<class 'function'>",
|
34 |
+
":serialized:": "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"
|
35 |
+
},
|
36 |
+
"_last_obs": {
|
37 |
+
":type:": "<class 'numpy.ndarray'>",
|
38 |
+
":serialized:": "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"
|
39 |
+
},
|
40 |
+
"_last_episode_starts": {
|
41 |
+
":type:": "<class 'numpy.ndarray'>",
|
42 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
43 |
+
},
|
44 |
+
"_last_original_obs": null,
|
45 |
+
"_episode_num": 0,
|
46 |
+
"use_sde": false,
|
47 |
+
"sde_sample_freq": -1,
|
48 |
+
"_current_progress_remaining": -0.015808000000000044,
|
49 |
+
"_stats_window_size": 100,
|
50 |
+
"ep_info_buffer": {
|
51 |
+
":type:": "<class 'collections.deque'>",
|
52 |
+
":serialized:": "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"
|
53 |
+
},
|
54 |
+
"ep_success_buffer": {
|
55 |
+
":type:": "<class 'collections.deque'>",
|
56 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
57 |
+
},
|
58 |
+
"_n_updates": 248,
|
59 |
+
"observation_space": {
|
60 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
61 |
+
":serialized:": "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",
|
62 |
+
"dtype": "float32",
|
63 |
+
"_shape": [
|
64 |
+
8
|
65 |
+
],
|
66 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
67 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
68 |
+
"bounded_below": "[False False False False False False False False]",
|
69 |
+
"bounded_above": "[False False False False False False False False]",
|
70 |
+
"_np_random": null
|
71 |
+
},
|
72 |
+
"action_space": {
|
73 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
74 |
+
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
75 |
+
"n": 4,
|
76 |
+
"_shape": [],
|
77 |
+
"dtype": "int64",
|
78 |
+
"_np_random": null
|
79 |
+
},
|
80 |
+
"n_envs": 16,
|
81 |
+
"n_steps": 1024,
|
82 |
+
"gamma": 0.999,
|
83 |
+
"gae_lambda": 0.98,
|
84 |
+
"ent_coef": 0.01,
|
85 |
+
"vf_coef": 0.5,
|
86 |
+
"max_grad_norm": 0.5,
|
87 |
+
"batch_size": 64,
|
88 |
+
"n_epochs": 4,
|
89 |
+
"clip_range": {
|
90 |
+
":type:": "<class 'function'>",
|
91 |
+
":serialized:": "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"
|
92 |
+
},
|
93 |
+
"clip_range_vf": null,
|
94 |
+
"normalize_advantage": true,
|
95 |
+
"target_kl": null
|
96 |
+
}
|
PPO_LunarLander/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b179690f9ecc14254098055e34eae6fa21f29a2fd6e39d0530088c5edf476335
|
3 |
+
size 87929
|
PPO_LunarLander/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0a66297f4848e6376ca6938cf2c2092477a688d64bb3f8cbeefa49142bce7fb
|
3 |
+
size 43329
|
PPO_LunarLander/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_LunarLander/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
+
- Python: 3.9.16
|
3 |
+
- Stable-Baselines3: 1.8.0
|
4 |
+
- PyTorch: 2.0.0+cu118
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.22.4
|
7 |
+
- Gym: 0.21.0
|
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: 249.31 +/- 23.40
|
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 0x7f8bae0ba790>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f8bae0ba820>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8bae0ba8b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8bae0ba940>", "_build": "<function ActorCriticPolicy._build at 0x7f8bae0ba9d0>", "forward": "<function ActorCriticPolicy.forward at 0x7f8bae0baa60>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f8bae0baaf0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8bae0bab80>", "_predict": "<function ActorCriticPolicy._predict at 0x7f8bae0bac10>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8bae0baca0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8bae0bad30>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8bae0badc0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f8bae0c15c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1680982046731578787, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_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 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_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, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "Stable-Baselines3": "1.8.0", "PyTorch": "2.0.0+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}
|
replay.mp4
ADDED
Binary file (200 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 249.3147879233302, "std_reward": 23.398218424321495, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-08T20:42:55.511495"}
|