davmel/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.

Usage (with Stable-baselines3)

from stable_baselines3.common.evaluation import evaluate_policy
from stable_baselines3.common.monitor import Monitor
import gymnasium as gym

from stable_baselines3 import PPO

from huggingface_sb3 import load_from_hub

if __name__ == '__main__':
    # loading
    repo_id = 'davmel/ppo-LunarLander-v2'
    filename = "ppo-LunarLander-v2.zip"  # The model filename.zip

    checkpoint = load_from_hub(repo_id, filename)
    custom_objects = {
        "learning_rate": 0.0,
        "lr_schedule": lambda _: 0.0,
        "clip_range": lambda _: 0.0,
    }

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

    # evaluation
    eval_env = Monitor(gym.make("LunarLander-v2"))
    mean_reward, std_reward = evaluate_policy(model, eval_env, n_eval_episodes=10, deterministic=True)
    print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")