Where to go: Agent Guidance with Deep Reinforcement Learning in A City-Scale Online Ride-Hailing Service

TL;DR

This paper introduces a deep reinforcement learning approach with action masking to optimize taxi dispatching in city-scale ride-hailing services, significantly improving efficiency and customer satisfaction.

Contribution

It proposes a novel AM-DQN method with action masking for faster, more efficient agent learning in large-scale ride-hailing scenarios, outperforming existing heuristics and learning methods.

Findings

AM-DQN achieves lowest failure rate

Reduces customer waiting time

Decreases idle search time for taxis

Abstract

Online ride-hailing services have become a prevalent transportation system across the world. In this paper, we study a challenging problem of how to direct vacant taxis around a city such that supplies and demands can be balanced in online ride-hailing services. We design a new reward scheme that considers multiple performance metrics of online ride-hailing services. We also propose a novel deep reinforcement learning method named Deep-Q-Network with Action Mask (AM-DQN) masking off unnecessary actions in various locations such that agents can learn much faster and more efficiently. We conduct extensive experiments using a city-scale dataset from Chicago. Several popular heuristic and learning methods are also implemented as baselines for comparison. The results of the experiments show that the AM-DQN attains the best performances of all methods with respect to average failure rate, average waiting time for customers, and average idle search time for vacant taxis.