Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization

TL;DR

This paper introduces OMIGA, a novel offline multi-agent reinforcement learning algorithm that leverages implicit global-to-local value regularization to improve policy learning in complex multi-agent environments.

Contribution

OMIGA provides a new framework converting global value regularization into implicit local regularizations, enhancing offline multi-agent RL performance.

Findings

OMIGA outperforms state-of-the-art methods on MuJoCo tasks.

OMIGA demonstrates superior results in StarCraft II micro-management scenarios.

The approach enables effective in-sample learning in offline multi-agent settings.

Abstract

Offline reinforcement learning (RL) has received considerable attention in recent years due to its attractive capability of learning policies from offline datasets without environmental interactions. Despite some success in the single-agent setting, offline multi-agent RL (MARL) remains to be a challenge. The large joint state-action space and the coupled multi-agent behaviors pose extra complexities for offline policy optimization. Most existing offline MARL studies simply apply offline data-related regularizations on individual agents, without fully considering the multi-agent system at the global level. In this work, we present OMIGA, a new offline m ulti-agent RL algorithm with implicit global-to-local v alue regularization. OMIGA provides a principled framework to convert global-level value regularization into equivalent implicit local value regularizations and simultaneously enables in-sample learning, thus elegantly bridging multi-agent value decomposition and policy learning with offline regularizations. Based on comprehensive experiments on the offline multi-agent MuJoCo and StarCraft II micro-management tasks, we show that OMIGA achieves superior performance over the state-of-the-art offline MARL methods in almost all tasks.