Reinforcement Learning for Ridesharing: An Extended Survey

TL;DR

This survey comprehensively reviews reinforcement learning applications in ridesharing, covering matching, repositioning, pooling, routing, and pricing, highlighting recent advances and future challenges.

Contribution

It provides an extensive overview of recent RL methods in ridesharing and introduces datasets and simulation tools to support ongoing research.

Findings

RL improves decision-making in ridesharing systems

Recent literature focuses on model complexity and agent coordination

Open datasets and environments facilitate future research

Abstract

In this paper, we present a comprehensive, in-depth survey of the literature on reinforcement learning approaches to decision optimization problems in a typical ridesharing system. Papers on the topics of rideshare matching, vehicle repositioning, ride-pooling, routing, and dynamic pricing are covered. Most of the literature has appeared in the last few years, and several core challenges are to continue to be tackled: model complexity, agent coordination, and joint optimization of multiple levers. Hence, we also introduce popular data sets and open simulation environments to facilitate further research and development. Subsequently, we discuss a number of challenges and opportunities for reinforcement learning research on this important domain.