Optimising Stochastic Routing for Taxi Fleets with Model Enhanced Reinforcement Learning

TL;DR

This paper develops and compares model-based, model-free, and hybrid reinforcement learning algorithms to optimize vehicle routing in stochastic demand scenarios for ride-hailing services, demonstrating superior performance in simulations.

Contribution

It introduces a novel hybrid algorithm combining model-based and model-free reinforcement learning for vehicle routing in stochastic demand environments.

Findings

Hybrid algorithm accelerates learning process.

Reinforcement learning algorithms outperform traditional methods.

Effective in both artificial and real-world road networks.

Abstract

The future of mobility-as-a-Service (Maas)should embrace an integrated system of ride-hailing, street-hailing and ride-sharing with optimised intelligent vehicle routing in response to a real-time, stochastic demand pattern. We aim to optimise routing policies for a large fleet of vehicles for street-hailing services, given a stochastic demand pattern in small to medium-sized road networks. A model-based dispatch algorithm, a high performance model-free reinforcement learning based algorithm and a novel hybrid algorithm combining the benefits of both the top-down approach and the model-free reinforcement learning have been proposed to route the \emph{vacant} vehicles. We design our reinforcement learning based routing algorithm using proximal policy optimisation and combined intrinsic and extrinsic rewards to strike a balance between exploration and exploitation. Using a large-scale agent-based microscopic simulation platform to evaluate our proposed algorithms, our model-free reinforcement learning and hybrid algorithm show excellent performance on both artificial road network and community-based Singapore road network with empirical demands, and our hybrid algorithm can significantly accelerate the model-free learner in the process of learning.