GatinhoEducado/rl-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.

I made it for Deep Reinforcement Learning Course UNIT1 LunarLander enviromen. I've trained it for 3,2M steps and get: mean_reward=266.08 +/- 79.52360201391592, approx 100% of landing, precision of mooning to the pod I estimate as 98%

Usage (with Stable-baselines3)

TODO: Add your code

from stable_baselines3 import PPO
from huggingface_sb3 import load_from_hub
import gymnasium as gym
env = gym.make("LunarLander-v2", render_mode="rgb_array")

model = PPO.load("GatinhoEducado/rl-ppo-LunarLander-v2", print_system_info=True)

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