jcps88/ppo-LunarLander-v2

PPO Agent playing LunarLander-v2

This is a trained model of a PPO agent playing LunarLander-v2 using Stable-Baselines3, achieving a mean reward of 213.9.

Usage

from stable_baselines3 import PPO
from huggingface_sb3 import load_from_hub

# Load model
checkpoint = load_from_hub(
    repo_id="jcps88/ppo-LunarLander-v2",
    filename="best_model.zip",
)
model = PPO.load(checkpoint)