AmirMesbah
commited on
Commit
·
1140202
1
Parent(s):
e25a1ec
Upload first model on hugging FACE
Browse files- README.md +37 -0
- config.json +1 -0
- ppo-LunarLander-v2.zip +3 -0
- ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2/data +95 -0
- ppo-LunarLander-v2/policy.optimizer.pth +3 -0
- ppo-LunarLander-v2/policy.pth +3 -0
- ppo-LunarLander-v2/pytorch_variables.pth +3 -0
- ppo-LunarLander-v2/system_info.txt +7 -0
- replay.mp4 +0 -0
- results.json +1 -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: 244.49 +/- 10.91
|
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 0x7fc590b9e790>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc590b9e820>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc590b9e8b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc590b9e940>", "_build": "<function ActorCriticPolicy._build at 0x7fc590b9e9d0>", "forward": "<function ActorCriticPolicy.forward at 0x7fc590b9ea60>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fc590b9eaf0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc590b9eb80>", "_predict": "<function ActorCriticPolicy._predict at 0x7fc590b9ec10>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc590b9eca0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc590b9ed30>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc590b9edc0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fc590b94900>"}, "verbose": 1, "policy_kwargs": {}, "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, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1673423459543041888, "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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAEAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "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-glibc2.27 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ffaba7c038db3b9bcf4386e0805417d7a06b26b41cedb0f3580d0b4b0bd98a5f
|
3 |
+
size 147420
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.7.0
|
ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 0x7fc590b9e790>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc590b9e820>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc590b9e8b0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc590b9e940>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fc590b9e9d0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fc590b9ea60>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7fc590b9eaf0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc590b9eb80>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fc590b9ec10>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc590b9eca0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc590b9ed30>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc590b9edc0>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7fc590b94900>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"observation_space": {
|
25 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
26 |
+
":serialized:": "gAWVnwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoCksIhZSMAUOUdJRSlIwEaGlnaJRoEiiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoCksIhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolggAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYIAAAAAAAAAAAAAAAAAAAAlGghSwiFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu",
|
27 |
+
"dtype": "float32",
|
28 |
+
"_shape": [
|
29 |
+
8
|
30 |
+
],
|
31 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
32 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
33 |
+
"bounded_below": "[False False False False False False False False]",
|
34 |
+
"bounded_above": "[False False False False False False False False]",
|
35 |
+
"_np_random": null
|
36 |
+
},
|
37 |
+
"action_space": {
|
38 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
39 |
+
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
40 |
+
"n": 4,
|
41 |
+
"_shape": [],
|
42 |
+
"dtype": "int64",
|
43 |
+
"_np_random": null
|
44 |
+
},
|
45 |
+
"n_envs": 16,
|
46 |
+
"num_timesteps": 1015808,
|
47 |
+
"_total_timesteps": 1000000,
|
48 |
+
"_num_timesteps_at_start": 0,
|
49 |
+
"seed": null,
|
50 |
+
"action_noise": null,
|
51 |
+
"start_time": 1673423459543041888,
|
52 |
+
"learning_rate": 0.0003,
|
53 |
+
"tensorboard_log": null,
|
54 |
+
"lr_schedule": {
|
55 |
+
":type:": "<class 'function'>",
|
56 |
+
":serialized:": "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"
|
57 |
+
},
|
58 |
+
"_last_obs": {
|
59 |
+
":type:": "<class 'numpy.ndarray'>",
|
60 |
+
":serialized:": "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"
|
61 |
+
},
|
62 |
+
"_last_episode_starts": {
|
63 |
+
":type:": "<class 'numpy.ndarray'>",
|
64 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAEAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
65 |
+
},
|
66 |
+
"_last_original_obs": null,
|
67 |
+
"_episode_num": 0,
|
68 |
+
"use_sde": false,
|
69 |
+
"sde_sample_freq": -1,
|
70 |
+
"_current_progress_remaining": -0.015808000000000044,
|
71 |
+
"ep_info_buffer": {
|
72 |
+
":type:": "<class 'collections.deque'>",
|
73 |
+
":serialized:": "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"
|
74 |
+
},
|
75 |
+
"ep_success_buffer": {
|
76 |
+
":type:": "<class 'collections.deque'>",
|
77 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
78 |
+
},
|
79 |
+
"_n_updates": 248,
|
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 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f66ab20252d3dcff71f1388b5cd6ecbee529aacf29f87cb7c3bb514544694dba
|
3 |
+
size 87929
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e96612ee20e07e61ff73d34a2348159be8a21fdd5bde456c2857aec9a445f0c5
|
3 |
+
size 43393
|
ppo-LunarLander-v2/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-v2/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.10.147+-x86_64-with-glibc2.27 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
+
- Python: 3.8.16
|
3 |
+
- Stable-Baselines3: 1.7.0
|
4 |
+
- PyTorch: 1.13.0+cu116
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.21.6
|
7 |
+
- Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (224 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 244.48589454054485, "std_reward": 10.913847110474183, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-11T08:17:21.078076"}
|