A Supervised Machine Learning Approach for the Vehicle Routing Problem

Sebastian Ammon, Frank Phillipson, Frank Phillipson, Rui Almeida

2024

Abstract

This paper expands on previous machine learning techniques applied to combinatorial optimisation problems, to approximately solve the capacitated vehicle routing problem (VRP). We leverage the versatility of graph neural networks (GNNs) and extend the application of graph convolutional neural networks, previously used for the Travelling Salesman Problem, to address the VRP. Our model employs a supervised learning technique, utilising solved instances from the OR-Tools solver for training. It learns to provide probabilistic representations of the VRP, generating final VRP tours via non-autoregressive decoding with beam search. This work shows that despite that reinforcement learning based autoregressive approaches have better performance, GNNs show great promise to solve complex optimisation problems, providing a valuable foundation for further refinement and study.

Paper Citation

in Harvard Style

Ammon S., Phillipson F. and Almeida R. (2024). A Supervised Machine Learning Approach for the Vehicle Routing Problem. In Proceedings of the 13th International Conference on Operations Research and Enterprise Systems - Volume 1: ICORES; ISBN 978-989-758-681-1, SciTePress, pages 364-371. DOI: 10.5220/0012430000003639

in Bibtex Style

@conference{icores24,
author={Sebastian Ammon and Frank Phillipson and Rui Almeida},
title={A Supervised Machine Learning Approach for the Vehicle Routing Problem},
booktitle={Proceedings of the 13th International Conference on Operations Research and Enterprise Systems - Volume 1: ICORES},
year={2024},
pages={364-371},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012430000003639},
isbn={978-989-758-681-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Operations Research and Enterprise Systems - Volume 1: ICORES
TI - A Supervised Machine Learning Approach for the Vehicle Routing Problem
SN - 978-989-758-681-1
AU - Ammon S.
AU - Phillipson F.
AU - Almeida R.
PY - 2024
SP - 364
EP - 371
DO - 10.5220/0012430000003639
PB - SciTePress