nayanaaa01/ppo-LunarLander-v3

PPO Agent playing LunarLander-v2

This is a trained model of a PPO agent playing LunarLander-v2 using the Stable-Baselines3 library.

Environment

• Environment: LunarLander-v2
• Algorithm: PPO
• Policy: MlpPolicy
• Library: Stable-Baselines3
• Training timesteps: 1,000,000

Evaluation Results

• Mean reward: 266.12
• Standard deviation: 10.79
• Leaderboard score: 255.33

Model

The trained model is:

ppo-LunarLander-v2.zip

Replay

A replay video of the trained agent is included as replay.mp4.

Usage

from stable_baselines3 import PPO
import gymnasium as gym

model = PPO.load("ppo-LunarLander-v2")

env = gym.make("LunarLander-v2", render_mode="human")

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()