Sun0901/ppo-LunarLander-v2

PPO Agent playing LunarLander-v2

This is a trained model of a PPO agent playing LunarLander-v2 using the stable-baselines3 library.

It was part of a reinforcement learning study exercise using stable-baselines3.

• Environment: LunarLander-v2 from gymnasium
• Algorithm: PPO
• Timesteps: 1,000,000
• Platform: Local Jupyter (Windows, Python 3.10)

This is a study log, not intended for deployment.

Usage (with Stable-baselines3)

You can use the following code to load the trained agent from the Hugging Face Hub:

from stable_baselines3 import PPO
from huggingface_sb3 import load_from_hub

# Load model from Hub
repo_id = "Sun0901/ppo-LunarLander-v2"
filename = "ppo-LunarLander-v2.zip"

checkpoint = load_from_hub(repo_id, filename)

model = PPO.load(checkpoint)

# Now you can use `model.predict()` to evaluate or deploy the agent.