ppo-SoccerTwos

This is a trained model of a PPO agent playing ML-Agents-SoccerTwos.

• Unit: Unit 7 of the Hugging Face Deep RL Course.
• Library: ml-agents
• Algorithm: PPO
• Environment: ML-Agents-SoccerTwos
• Mean Reward: 22.00 +/- 2.00

Description

Trained Unity ML-Agents PPO self-play agent on SoccerTwos for Hugging Face Deep RL Course Unit 7.

Usage

This agent was uploaded as part of the Hugging Face Deep Reinforcement Learning Course assignments by Surya198382.