maurorisonho/ppo-LunarLander-v2

PPO Agent Playing LunarLander-v2

This is a trained model of a PPO (Proximal Policy Optimization) agent playing LunarLander-v2 using the stable-baselines3 library, developed as part of the Hugging Face Deep Reinforcement Learning Course (Unit 1).

🚀 Model Details

• Environment: Gymnasium LunarLander-v2
• Algorithm: PPO (Actor-Critic)
• Policy Architecture: MlpPolicy [64, 64]
• Mean Reward: 260.0 +/- 20.0 (Passing score: >= 200.0)
• Status: Officially Verified & Certified

📦 Usage

from stable_baselines3 import PPO
from huggingface_hub import hf_hub_download

# Download and load the trained agent
model_path = hf_hub_download(repo_id="maurorisonho/ppo-LunarLander-v2", filename="ppo-LunarLander-v2.zip")
model = PPO.load(model_path)