thomasarmstrong/ppo-LunarLander-v3

PPO Agent playing LunarLander-v3

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 huggingface_sb3 import load_from_hub

checkpoint = load_from_hub("thomasarmstrong/ppo-LunarLander-v3", "ppo-LunarLander-v3.zip")
model = PPO.load(checkpoint)

env = gym.make("LunarLander-v3")
obs, info = env.reset()
while True:
    action, _ = model.predict(obs, deterministic=True)
    obs, reward, terminated, truncated, info = env.step(action)
    if terminated or truncated:
        obs, info = env.reset()