English

Optimizing Large-Scale Fleet Management on a Road Network using Multi-Agent Deep Reinforcement Learning with Graph Neural Network

Machine Learning 2021-08-09 v2 Systems and Control Systems and Control

Abstract

We propose a novel approach to optimize fleet management by combining multi-agent reinforcement learning with graph neural network. To provide ride-hailing service, one needs to optimize dynamic resources and demands over spatial domain. While the spatial structure was previously approximated with a regular grid, our approach represents the road network with a graph, which better reflects the underlying geometric structure. Dynamic resource allocation is formulated as multi-agent reinforcement learning, whose action-value function (Q function) is approximated with graph neural networks. We use stochastic policy update rule over the graph with deep Q-networks (DQN), and achieve superior results over the greedy policy update. We design a realistic simulator that emulates the empirical taxi call data, and confirm the effectiveness of the proposed model under various conditions.

Keywords

Cite

@article{arxiv.2011.06175,
  title  = {Optimizing Large-Scale Fleet Management on a Road Network using Multi-Agent Deep Reinforcement Learning with Graph Neural Network},
  author = {Juhyeon Kim and Kihyun Kim},
  journal= {arXiv preprint arXiv:2011.06175},
  year   = {2021}
}

Comments

7 pages, 4 figures

R2 v1 2026-06-23T20:07:04.549Z