EricMingle69/poca-SoccerTwos

poca Agent playing SoccerTwos

This is a trained model of a poca agent playing SoccerTwos, trained with Unity ML-Agents as part of the Hugging Face Deep Reinforcement Learning Course.

Evaluation

Real inference run with the exported ONNX policy in the Unity environment.

• episodes: 100
• mean_reward: -0.114
• std_reward: 0.557
• score (mean - std): -0.671