andylolu24
commited on
Commit
•
9ccfcd8
1
Parent(s):
f044575
Initial 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 +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: 259.56 +/- 21.49
|
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 0x7f70fdddb820>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f70fdddb8b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f70fdddb940>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f70fdddb9d0>", "_build": "<function ActorCriticPolicy._build at 0x7f70fdddba60>", "forward": "<function ActorCriticPolicy.forward at 0x7f70fdddbaf0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f70fdddbb80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f70fdddbc10>", "_predict": "<function ActorCriticPolicy._predict at 0x7f70fdddbca0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f70fdddbd30>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f70fdddbdc0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f70fdddbe50>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f70fe9ca100>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVnwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoCksIhZSMAUOUdJRSlIwEaGlnaJRoEiiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoCksIhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolggAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYIAAAAAAAAAAAAAAAAAAAAlGghSwiFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu", "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": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1679086493704882588, "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, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 268, "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-6.1.11-100.fc36.x86_64-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Feb 9 20:36:30 UTC 2023", "Python": "3.9.15", "Stable-Baselines3": "1.8.0a9", "PyTorch": "1.11.0+cu102", "GPU Enabled": "True", "Numpy": "1.21.2", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0db3ab06a44873fe4fe6f270cecc6ea9d69613bed2827c51a6d18b5946f0d145
|
3 |
+
size 147716
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.8.0a9
|
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 0x7f70fdddb820>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f70fdddb8b0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f70fdddb940>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f70fdddb9d0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f70fdddba60>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f70fdddbaf0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f70fdddbb80>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f70fdddbc10>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f70fdddbca0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f70fdddbd30>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f70fdddbdc0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f70fdddbe50>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f70fe9ca100>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"observation_space": {
|
25 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
26 |
+
":serialized:": "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",
|
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": 507904,
|
47 |
+
"_total_timesteps": 500000,
|
48 |
+
"_num_timesteps_at_start": 0,
|
49 |
+
"seed": null,
|
50 |
+
"action_noise": null,
|
51 |
+
"start_time": 1679086493704882588,
|
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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": 268,
|
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:b8dbcdb248f800fc0bae1b11f08021a7d0a677923e37daf7a462d1bf5812328c
|
3 |
+
size 88057
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0951038c5ee517c1b12531f521b51fe0884f5bd2a8a4c58b61f846b07265f766
|
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 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-6.1.11-100.fc36.x86_64-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Feb 9 20:36:30 UTC 2023
|
2 |
+
- Python: 3.9.15
|
3 |
+
- Stable-Baselines3: 1.8.0a9
|
4 |
+
- PyTorch: 1.11.0+cu102
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.21.2
|
7 |
+
- Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (202 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 259.5573445411909, "std_reward": 21.48915889035112, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-18T22:32:10.769864"}
|