SigmaBM/robosumo-selfplay

Reproduction of self-play described in paper "Emergent Complexity via Multi-Agent Competition", adapted from PPO2 implementation in OpenAI baselines.

Introduction

Reproduction of self-play described in paper "Emergent Complexity via Multi-Agent Competition", adapted from PPO2 implementation in OpenAI baselines.

Requirements

• gym
• robosumo
• mujoco-py
• baselines
• Tensorflow
• MuJoCo 2.0