wanxiangche
commited on
Commit
·
d346c8c
1
Parent(s):
d4056ff
PPO-Moon-v0
Browse files- PPO-Moon-v0.zip +3 -0
- PPO-Moon-v0/_stable_baselines3_version +1 -0
- PPO-Moon-v0/data +91 -0
- PPO-Moon-v0/policy.optimizer.pth +3 -0
- PPO-Moon-v0/policy.pth +3 -0
- PPO-Moon-v0/pytorch_variables.pth +3 -0
- PPO-Moon-v0/system_info.txt +7 -0
- README.md +37 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
PPO-Moon-v0.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92d30b28284f3c70a67e21d24006f8bd7197bb890110c0fdb88543bc624a69fd
|
3 |
+
size 146410
|
PPO-Moon-v0/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.6.2
|
PPO-Moon-v0/data
ADDED
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x7f1c66228790>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f1c66228820>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f1c662288b0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f1c66228940>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f1c662289d0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f1c66228a60>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f1c66228af0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f1c66228b80>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f1c66228c10>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f1c66228ca0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f1c66228d30>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f1c66229030>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {},
|
23 |
+
"observation_space": {
|
24 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "gAWVnwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoCksIhZSMAUOUdJRSlIwEaGlnaJRoEiiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoCksIhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolggAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYIAAAAAAAAAAAAAAAAAAAAlGghSwiFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu",
|
26 |
+
"dtype": "float32",
|
27 |
+
"_shape": [
|
28 |
+
8
|
29 |
+
],
|
30 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
31 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
32 |
+
"bounded_below": "[False False False False False False False False]",
|
33 |
+
"bounded_above": "[False False False False False False False False]",
|
34 |
+
"_np_random": null
|
35 |
+
},
|
36 |
+
"action_space": {
|
37 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
+
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
39 |
+
"n": 4,
|
40 |
+
"_shape": [],
|
41 |
+
"dtype": "int64",
|
42 |
+
"_np_random": null
|
43 |
+
},
|
44 |
+
"n_envs": 1,
|
45 |
+
"num_timesteps": 1015808,
|
46 |
+
"_total_timesteps": 1000000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1671067893674370656,
|
51 |
+
"learning_rate": 0.0003,
|
52 |
+
"tensorboard_log": null,
|
53 |
+
"lr_schedule": {
|
54 |
+
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "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"
|
56 |
+
},
|
57 |
+
"_last_obs": null,
|
58 |
+
"_last_episode_starts": {
|
59 |
+
":type:": "<class 'numpy.ndarray'>",
|
60 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
61 |
+
},
|
62 |
+
"_last_original_obs": null,
|
63 |
+
"_episode_num": 0,
|
64 |
+
"use_sde": false,
|
65 |
+
"sde_sample_freq": -1,
|
66 |
+
"_current_progress_remaining": -0.015808000000000044,
|
67 |
+
"ep_info_buffer": {
|
68 |
+
":type:": "<class 'collections.deque'>",
|
69 |
+
":serialized:": "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"
|
70 |
+
},
|
71 |
+
"ep_success_buffer": {
|
72 |
+
":type:": "<class 'collections.deque'>",
|
73 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
74 |
+
},
|
75 |
+
"_n_updates": 248,
|
76 |
+
"n_steps": 1024,
|
77 |
+
"gamma": 0.999,
|
78 |
+
"gae_lambda": 0.98,
|
79 |
+
"ent_coef": 0.01,
|
80 |
+
"vf_coef": 0.5,
|
81 |
+
"max_grad_norm": 0.5,
|
82 |
+
"batch_size": 64,
|
83 |
+
"n_epochs": 4,
|
84 |
+
"clip_range": {
|
85 |
+
":type:": "<class 'function'>",
|
86 |
+
":serialized:": "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"
|
87 |
+
},
|
88 |
+
"clip_range_vf": null,
|
89 |
+
"normalize_advantage": true,
|
90 |
+
"target_kl": null
|
91 |
+
}
|
PPO-Moon-v0/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db8e59f1e5c7d4f055f0f922b424d1358a2526aa2511b3c9d2569564698babd6
|
3 |
+
size 88057
|
PPO-Moon-v0/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5d742db42d0e5cb22ad9a7741ce9383dc92b2d53382cba65a7e08688989d9e0
|
3 |
+
size 43201
|
PPO-Moon-v0/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-Moon-v0/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
|
2 |
+
Python: 3.8.16
|
3 |
+
Stable-Baselines3: 1.6.2
|
4 |
+
PyTorch: 1.13.0+cu116
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
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: 249.45 +/- 15.84
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x7f1c66228790>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f1c66228820>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f1c662288b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f1c66228940>", "_build": "<function ActorCriticPolicy._build at 0x7f1c662289d0>", "forward": "<function ActorCriticPolicy.forward at 0x7f1c66228a60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f1c66228af0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f1c66228b80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f1c66228c10>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f1c66228ca0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f1c66228d30>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f1c66229030>"}, "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": 1, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1671067893674370656, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": null, "_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, "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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
replay.mp4
ADDED
Binary file (227 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 249.4526727219615, "std_reward": 15.841568810547177, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-15T03:00:50.837017"}
|