shenyichong
commited on
Commit
·
f02525c
1
Parent(s):
421f5cf
first commit
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 +99 -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 +9 -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: 263.84 +/- 7.90
|
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 0x7f625346d5a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f625346d630>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f625346d6c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f625346d750>", "_build": "<function ActorCriticPolicy._build at 0x7f625346d7e0>", "forward": "<function ActorCriticPolicy.forward at 0x7f625346d870>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f625346d900>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f625346d990>", "_predict": "<function ActorCriticPolicy._predict at 0x7f625346da20>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f625346dab0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f625346db40>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f625346dbd0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f6253e77840>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1689030334149309536, "learning_rate": 0.0003, "tensorboard_log": null, "_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": 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": 0.999, "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-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f1597a0343d5832ff818cdcef1e33958350170896770dd9bc7e69f72ec21706
|
3 |
+
size 146655
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.0.0a5
|
ppo-LunarLander-v2/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 0x7f625346d5a0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f625346d630>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f625346d6c0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f625346d750>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f625346d7e0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f625346d870>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f625346d900>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f625346d990>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f625346da20>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f625346dab0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f625346db40>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f625346dbd0>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f6253e77840>"
|
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": 1689030334149309536,
|
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": 0.999,
|
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 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7255eb8c52a5afa78bb7d8c3e2b777a3d9533be160ec9ecf111211b7ef2f8c06
|
3 |
+
size 87929
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76d08515653a4f92496de45d66a488fb3737e927bcdba21254b50993b3168dde
|
3 |
+
size 43329
|
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 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 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: 1.22.4
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.25.2
|
replay.mp4
ADDED
Binary file (120 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 263.844807, "std_reward": 7.90495857316147, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-10T23:36:53.620631"}
|