Downloads · 30 days
2
7% of all-time downloads
ppo-LunarLander-v3
poisqy/ppo-LunarLander-v3
ppo-LunarLander-v3 is a reinforcement learning model from poisqy. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. It is set up for stable-baselines3.
Preview <video controls <source src="https://huggingface.co/poisqy/ppo-LunarLander-v3/blob/main/rl-video-step-0-to-step-1000.mp4" type="video/mp4" Ton navigateur ne supporte pas la balise vidéo. </video
All-time downloads
29
Public
Repo size
463 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.mp4181 KB · 37%
At a glance
- Task
- Reinforcement Learning
- Library
- stable-baselines3
- Access
- Public
- Created
- Aug 21, 2026
- Updated
- Aug 21, 2026
- SHA
- 3ab30df7
Model card
From the Hugging Face model README
PPO Agent playing LunarLander-v3
Preview <video controls> <source src="https://huggingface.co/poisqy/ppo-LunarLander-v3/blob/main/rl-video-step-0-to-step-1000.mp4" type="video/mp4"> Ton navigateur ne supporte pas la balise vidéo. </video>
This is a trained model of a PPO agent playing LunarLander-v3 using the stable-baselines3 library.
Usage (with Stable-baselines3)
import gymnasium as gym
from stable_baselines3 import PPO
from stable_baselines3.common.env_util import make_vec_env
env = make_vec_env("LunarLander-v3", n_envs=8)
model = PPO(
policy="MlpPolicy",
env=env,
n_steps=1024,
batch_size=64,
n_epochs=4,
gamma=0.999,
gae_lambda=0.98,
ent_coef=0.01,
verbose=1,
)
model.learn(total_timesteps=1_000_000)
model.save("ppo-lunarlander-v3-full")
print("Entraînement terminé et modèle sauvegardé !")
- Task
- Reinforcement Learning
- Library
- stable-baselines3
- Created
- Aug 21, 2026
- Updated
- Aug 21, 2026