ppo-LunarLander-v3

PPO Agent playing LunarLander-v3

PPO model trained on LunarLander-v3.

Usage:

import gymnasium as gym
from stable_baselines3 import PPO
from stable_baseline3.common.evaluation import evaluate_policy
from huggingface_sb3 import load_from_hub

# 1. Load model from Hugging Face
repo_id = "pexa8335/ppo-LunarLander-v3"
filename = "ppo-LunarLander-v3.zip"

checkpoint = load_from_hub(repo_id, filename)
model = PPO.load(checkpoint)

# 2. Run
env = gym.make("LunarLander-v3", render_mode="human")
obs, _ = env.reset()

for _ in range(1000):
    action, _ = model.predict(obs, deterministic=True)
    obs, reward, done, truncated, info = env.step(action)
    if done or truncated:
        obs, _ = env.reset()
env.close()

mean_reward, std_reward = evaluate_policy(model, env, n_eval_episodes=10)
print(f'Score: {mean_reward} +/- {std_reward}')