Reinforcement Learning for Ridesharing: An Extended Survey
It serves as a resource for researchers and practitioners in the ridesharing domain, but is incremental as it synthesizes existing literature without introducing new methods.
This paper provides a comprehensive survey of reinforcement learning applications in ridesharing systems, covering topics like matching, repositioning, and pricing, and identifies ongoing challenges such as model complexity and agent coordination.
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.