meltembreeze
commited on
Commit
•
279de6c
1
Parent(s):
9347866
Upload PPO LunarLander-v2 trained agent
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: 269.52 +/- 13.10
|
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 0x7fb4d9f98820>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb4d9f988b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb4d9f98940>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb4d9f989d0>", "_build": "<function ActorCriticPolicy._build at 0x7fb4d9f98a60>", "forward": "<function ActorCriticPolicy.forward at 0x7fb4d9f98af0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fb4d9f98b80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb4d9f98c10>", "_predict": "<function ActorCriticPolicy._predict at 0x7fb4d9f98ca0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb4d9f98d30>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb4d9f98dc0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb4d9f98e50>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fb4d9f999c0>"}, "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": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1678374536068096316, "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": 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-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "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:c0abdbad6767dff4e42c404fee35eef1a57469d3595940cd0db5be03f8a1a6b4
|
3 |
+
size 147425
|
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 0x7fb4d9f98820>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb4d9f988b0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb4d9f98940>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb4d9f989d0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fb4d9f98a60>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fb4d9f98af0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7fb4d9f98b80>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb4d9f98c10>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fb4d9f98ca0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb4d9f98d30>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb4d9f98dc0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb4d9f98e50>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7fb4d9f999c0>"
|
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": 1015808,
|
47 |
+
"_total_timesteps": 1000000,
|
48 |
+
"_num_timesteps_at_start": 0,
|
49 |
+
"seed": null,
|
50 |
+
"action_noise": null,
|
51 |
+
"start_time": 1678374536068096316,
|
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": 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 sha256:5dd427c7ff710aeaefd2e4b11ba1609eb48e2299b0b62d364185ebc5279d0881
|
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:ffe79fc5e058674d26d0b144747f38675d7dd2c4ff519a80efa9812737129eca
|
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-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
+
- Python: 3.9.16
|
3 |
+
- Stable-Baselines3: 1.7.0
|
4 |
+
- PyTorch: 1.13.1+cu116
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.22.4
|
7 |
+
- Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (189 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 269.52307071826607, "std_reward": 13.095766137782972, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-09T16:00:11.230802"}
|