PPO agent playing ML-Agents-SoccerTwos

This is a trained model of an PPO agent playing ML-Agents-SoccerTwos for the Hugging Face Deep Reinforcement Learning Course (Unit 7).

Evaluation Results

• Mean Reward: 0.50 +/- 0.10
• Environment: ML-Agents-SoccerTwos
• Algorithm: PPO
• Library: ml-agents

Usage

Trained and evaluated for the Hugging Face Deep RL Course certification.