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

model = PPO.load(
    load_from_hub("zozo-dejante/ppo-LunarLander-v3", "ppo_LunarLander.zip")
)

test_env = gym.make("LunarLander-v3", render_mode="human", max_episode_steps=400)
observation, _info = test_env.reset()
while True:
    action, _states = model.predict(observation)
    observation, reward, terminated, truncated, info = test_env.step(action)

    test_env.render()

    if terminated or truncated:
        observation, _info = test_env.reset()