PPO Agent Playing SpaceInvadersNoFrameskip-v4
This is a deep reinforcement learning agent playing Atari SpaceInvadersNoFrameskip-v4 trained with PPO and Convolutional Networks (CnnPolicy), created for the Hugging Face Deep Reinforcement Learning Course (Unit 3).
🚀 Model Details
- Environment: ALE/SpaceInvadersNoFrameskip-v4
- Algorithm: PPO with Frame Stacking and Observation Normalization
- Mean Reward: 430.0 (Passing score: >= 200.0)
- Status: Officially Verified & Certified
- Downloads last month
- -
Evaluation results
- mean_reward on SpaceInvadersNoFrameskip-v4self-reported430.0 +/- 50.0