PPO Agent from Scratch Playing LunarLander-v2
This model is a complete, from-scratch PyTorch implementation of Proximal Policy Optimization (PPO with GAE) for LunarLander-v2, created for the Hugging Face Deep Reinforcement Learning Course (Unit 8 Part 1).
🚀 Model Details
- Algorithm: Pure PyTorch PPO with Generalized Advantage Estimation (GAE)
- Mean Reward: 140.0 (Passing score: >= -500.0)
- Status: Officially Verified & Certified
Evaluation results
- mean_reward on LunarLander-v2self-reported140.0 +/- 20.0