Coordinated Proximal Policy Optimization

Part of Advances in Neural Information Processing Systems 34 (NeurIPS 2021)

Bibtex Paper Reviews And Public Comment » Supplemental

Authors

Zifan Wu, Chao Yu, Deheng Ye, Junge Zhang, haiyin piao, Hankz Hankui Zhuo

Abstract

We present Coordinated Proximal Policy Optimization (CoPPO), an algorithm that extends the original Proximal Policy Optimization (PPO) to the multi-agent setting. The key idea lies in the coordinated adaptation of step size during the policy update process among multiple agents. We prove the monotonicity of policy improvement when optimizing a theoretically-grounded joint objective, and derive a simplified optimization objective based on a set of approximations. We then interpret that such an objective in CoPPO can achieve dynamic credit assignment among agents, thereby alleviating the high variance issue during the concurrent update of agent policies. Finally, we demonstrate that CoPPO outperforms several strong baselines and is competitive with the latest multi-agent PPO method (i.e. MAPPO) under typical multi-agent settings, including cooperative matrix games and the StarCraft II micromanagement tasks.