Complex Vehicle Routing with Memory Augmented Neural Networks

TL;DR

This paper explores using deep learning models with explicit memory components to tackle complex vehicle routing problems, aiming for scalable, interpretable solutions that outperform traditional heuristics.

Contribution

It introduces a novel approach combining deep learning with memory modules for solving capacitated vehicle routing problems at scale.

Findings

Memory-augmented models improve solution quality.

Enhanced interpretability of routing decisions.

Potential for industrial-scale application.

Abstract

Complex real-life routing challenges can be modeled as variations of well-known combinatorial optimization problems. These routing problems have long been studied and are difficult to solve at scale. The particular setting may also make exact formulation difficult. Deep Learning offers an increasingly attractive alternative to traditional solutions, which mainly revolve around the use of various heuristics. Deep Learning may provide solutions which are less time-consuming and of higher quality at large scales, as it generally does not need to generate solutions in an iterative manner, and Deep Learning models have shown a surprising capacity for solving complex tasks in recent years. Here we consider a particular variation of the Capacitated Vehicle Routing (CVRP) problem and investigate the use of Deep Learning models with explicit memory components. Such memory components may help in gaining insight into the model's decisions as the memory and operations on it can be directly inspected at any time, and may assist in scaling the method to such a size that it becomes viable for industry settings.