Upload folder using huggingface_hub
Browse files- .ipynb_checkpoints/result-checkpoint.json +1 -0
- README.md +37 -0
- config.json +1 -0
- ppo-LunarLander-v2 (1).zip +3 -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/stable_baselines3_version +1 -0
- ppo-LunarLander-v2/system_info.txt +9 -0
- result.json +1 -0
.ipynb_checkpoints/result-checkpoint.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": -548.6125257000001, "std_reward": 130.60415665801284}
|
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: 267.66 +/- 20.67
|
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": "MlpPolicy", "learning_rate": 0.0003, "n_steps": 1024, "batch_size": 64, "n_epochs": 4, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01}
|
ppo-LunarLander-v2 (1).zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff6ec58a0a00c1117bae0201773288f14305c342c3d7cf5dd44319a856f8d0bf
|
3 |
+
size 150357
|
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 0x7c70fb7796c0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c70fb779750>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c70fb7797e0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c70fb779870>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7c70fb779900>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7c70fb779990>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7c70fb779a20>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c70fb779ab0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7c70fb779b40>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c70fb779bd0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c70fb779c60>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7c70fb779cf0>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7c70fb71db40>"
|
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": 1722811820327280177,
|
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": 248,
|
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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
|
73 |
+
"n": "4",
|
74 |
+
"start": "0",
|
75 |
+
"_shape": [],
|
76 |
+
"dtype": "int64",
|
77 |
+
"_np_random": null
|
78 |
+
},
|
79 |
+
"n_envs": 16,
|
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 |
+
"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 sha256:3a3635884aeba68f425daedd895f6c27ec4fea1f5fbe0dd4b12042b95c1a07e8
|
3 |
+
size 88362
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee6b9d09ba7e8e230cbd0c0db3a18d6eb5e493306e89a299fc77fc8e1e81f22d
|
3 |
+
size 43762
|
ppo-LunarLander-v2/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
|
3 |
+
size 864
|
ppo-LunarLander-v2/stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.0.0a5
|
ppo-LunarLander-v2/system_info.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
|
2 |
+
- Python: 3.10.12
|
3 |
+
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.3.1+cu121
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.26.4
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.25.2
|
result.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": -548.6125257000001, "std_reward": 130.60415665801284}
|