Mobility on Demand (MoD) refers to mobility systems that operate on the basis of immediate travel demand. Typically, such a system consists of a fleet of vehicles that can be booked by customers when needed. The operation of these services consists of two main tasks: deciding how vehicles are assigned to requests (vehicle assignment); and deciding where vehicles move (including charging stations) when they are not serving a request (rebalancing). A field of research is emerging around the design of operation strategies for MoD services, and an increasingly popular trend is the use of learning based (most often Reinforcement Learning) approaches. We review, in this work, the literature on algorithms for operation strategies of MoD systems that use approaches based on Reinforcement Learning with a focus on the types of algorithms being used. The novelty of our review stands in three aspects: First, the algorithmic details are discussed and the approaches classified in a unified framework for sequential decision-making. Second, the use cases on which approaches are tested and their features are taken into account. Finally, validation methods that can be found across the literature are discussed. The review aims at advancing the state of the art by identifying similarities and differences between approaches and highlighting current research directions.

Autonomous mobility on demand systems, though still in their infancy, have very promising prospects in providing urban population with sustainable and safe personal mobility in the near future. While much research has been conducted on both autonomous vehicles and mobility on demand systems, to the best of our knowledge, this is the first work that shows how to manage autonomous mobility on demand systems for better passenger experience. We introduce the Expand and Target algorithm which can be easily integrated with three different scheduling strategies for dispatching autonomous vehicles. We implement an agent-based simulation platform and empirically evaluate the proposed approaches with the New York City taxi data. Experimental results demonstrate that the algorithm significantly improve passengers' experience by reducing the average passenger waiting time by up to 29.82% and increasing the trip success rate by up to 7.65%.