Game-Theoretic Multiagent Reinforcement Learning

TL;DR

This paper provides a comprehensive, up-to-date overview of multiagent reinforcement learning (MARL) from a game-theoretic perspective, covering fundamentals and recent advances since 2010.

Contribution

It offers a self-contained, modern survey of MARL with a focus on game-theoretic foundations and recent developments, filling gaps left by outdated previous surveys.

Findings

Summarizes recent advances in MARL since 2010

Highlights game-theoretic approaches in MARL

Serves as a resource for new and experienced researchers

Abstract

Tremendous advances have been made in multiagent reinforcement learning (MARL). MARL corresponds to the learning problem in a multiagent system in which multiple agents learn simultaneously. It is an interdisciplinary field of study with a long history that includes game theory, machine learning, stochastic control, psychology, and optimization. Despite great successes in MARL, there is a lack of a self-contained overview of the literature that covers game-theoretic foundations of modern MARL methods and summarizes the recent advances. The majority of existing surveys are outdated and do not fully cover the recent developments since 2010. In this work, we provide a monograph on MARL that covers both the fundamentals and the latest developments on the research frontier. The goal of this monograph is to provide a self-contained assessment of the current state-of-the-art MARL techniques from a game-theoretic perspective. We expect this work to serve as a stepping stone for both new researchers who are about to enter this fast-growing field and experts in the field who want to obtain a panoramic view and identify new directions based on recent advances.