Where to go: Agent Guidance with Deep Reinforcement Learning in A City-Scale Online Ride-Hailing Service
This addresses inefficiencies in ride-hailing services for providers and customers, but it is incremental as it builds on existing reinforcement learning techniques with a novel action-masking approach.
The paper tackles the problem of directing vacant taxis to balance supply and demand in city-scale online ride-hailing services, proposing a deep reinforcement learning method (AM-DQN) that achieves the best performance in reducing failure rates, customer waiting times, and taxi idle search times compared to baselines.
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.