lcdbezerra
commited on
Commit
•
817a9a5
1
Parent(s):
774490a
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 +94 -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: 257.26 +/- 16.54
|
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 0x7f87b7632ca0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f87b7632d30>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f87b7632dc0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f87b7632e50>", "_build": "<function ActorCriticPolicy._build at 0x7f87b7632ee0>", "forward": "<function ActorCriticPolicy.forward at 0x7f87b7632f70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f87b7637040>", "_predict": "<function ActorCriticPolicy._predict at 0x7f87b76370d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f87b7637160>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f87b76371f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f87b7637280>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f87b762f450>"}, "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": 16, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1671642751151795439, "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-5.10.133+-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"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b9a1b747354246347d1daa0c3e531e728ac819f8a974f950def292068c3178b
|
3 |
+
size 147210
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.6.2
|
ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 0x7f87b7632ca0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f87b7632d30>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f87b7632dc0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f87b7632e50>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f87b7632ee0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f87b7632f70>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f87b7637040>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f87b76370d0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f87b7637160>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f87b76371f0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f87b7637280>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f87b762f450>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {},
|
23 |
+
"observation_space": {
|
24 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "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",
|
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": 16,
|
45 |
+
"num_timesteps": 1015808,
|
46 |
+
"_total_timesteps": 1000000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1671642751151795439,
|
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": {
|
58 |
+
":type:": "<class 'numpy.ndarray'>",
|
59 |
+
":serialized:": "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"
|
60 |
+
},
|
61 |
+
"_last_episode_starts": {
|
62 |
+
":type:": "<class 'numpy.ndarray'>",
|
63 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
64 |
+
},
|
65 |
+
"_last_original_obs": null,
|
66 |
+
"_episode_num": 0,
|
67 |
+
"use_sde": false,
|
68 |
+
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.015808000000000044,
|
70 |
+
"ep_info_buffer": {
|
71 |
+
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "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"
|
73 |
+
},
|
74 |
+
"ep_success_buffer": {
|
75 |
+
":type:": "<class 'collections.deque'>",
|
76 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
+
},
|
78 |
+
"_n_updates": 248,
|
79 |
+
"n_steps": 1024,
|
80 |
+
"gamma": 0.999,
|
81 |
+
"gae_lambda": 0.98,
|
82 |
+
"ent_coef": 0.01,
|
83 |
+
"vf_coef": 0.5,
|
84 |
+
"max_grad_norm": 0.5,
|
85 |
+
"batch_size": 64,
|
86 |
+
"n_epochs": 4,
|
87 |
+
"clip_range": {
|
88 |
+
":type:": "<class 'function'>",
|
89 |
+
":serialized:": "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"
|
90 |
+
},
|
91 |
+
"clip_range_vf": null,
|
92 |
+
"normalize_advantage": true,
|
93 |
+
"target_kl": null
|
94 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6302f7b71319ed0085b4f02d7e46017a07bb9dc370b8e46035f89e9fce98f434
|
3 |
+
size 87929
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c211239cedc64c4848ef67b794f97f06395e662360cd0e9df6a14380cf977c1
|
3 |
+
size 43201
|
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-5.10.133+-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
|
replay.mp4
ADDED
Binary file (229 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 257.2565836687618, "std_reward": 16.53853094729921, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-21T17:36:54.286197"}
|