PPO agent playing ML-Agents-SnowballFight-1vs1

This is a trained model of an PPO agent playing ML-Agents-SnowballFight-1vs1 for the Hugging Face Deep Reinforcement Learning Course.

Downloads last month
-
Video Preview
loading

Evaluation results

  • mean_reward on ML-Agents-SnowballFight-1vs1
    self-reported
    1.20 +/- 0.30