An Introduction to Multi-Agent Reinforcement Learning and Review of its Application to Autonomous Mobility

TL;DR

This paper provides an overview of Multi-Agent Reinforcement Learning (MARL) and reviews its applications in autonomous mobility, highlighting how MARL can improve cooperative behavior among autonomous vehicles.

Contribution

It introduces key concepts and paradigms of MARL and surveys its recent applications in autonomous mobility scenarios, offering a comprehensive overview for researchers.

Findings

MARL enhances cooperative strategies in autonomous vehicles

State-of-the-art MARL methods improve traffic efficiency

MARL applications are diverse in autonomous mobility scenarios

Abstract

Many scenarios in mobility and traffic involve multiple different agents that need to cooperate to find a joint solution. Recent advances in behavioral planning use Reinforcement Learning to find effective and performant behavior strategies. However, as autonomous vehicles and vehicle-to-X communications become more mature, solutions that only utilize single, independent agents leave potential performance gains on the road. Multi-Agent Reinforcement Learning (MARL) is a research field that aims to find optimal solutions for multiple agents that interact with each other. This work aims to give an overview of the field to researchers in autonomous mobility. We first explain MARL and introduce important concepts. Then, we discuss the central paradigms that underlie MARL algorithms, and give an overview of state-of-the-art methods and ideas in each paradigm. With this background, we survey applications of MARL in autonomous mobility scenarios and give an overview of existing scenarios and implementations.