Learn to Design the Heuristics for Vehicle Routing Problem

TL;DR

This paper introduces a neural network-based approach to automatically learn local-search heuristics for the Vehicle Routing Problem, outperforming traditional methods and eliminating the need for handcrafted heuristics.

Contribution

It proposes a novel neural network architecture trained via actor-critic to learn destroy and repair heuristics for VRP, capable of handling large-scale instances.

Findings

Outperforms traditional heuristics on medium-scale VRP datasets.

Successfully tackles large-scale VRP instances with over 400 nodes.

Eliminates the need for expert-designed heuristics by learning them automatically.

Abstract

This paper presents an approach to learn the local-search heuristics that iteratively improves the solution of Vehicle Routing Problem (VRP). A local-search heuristics is composed of a destroy operator that destructs a candidate solution, and a following repair operator that rebuilds the destructed one into a new one. The proposed neural network, as trained through actor-critic framework, consists of an encoder in form of a modified version of Graph Attention Network where node embeddings and edge embeddings are integrated, and a GRU-based decoder rendering a pair of destroy and repair operators. Experiment results show that it outperforms both the traditional heuristics algorithms and the existing neural combinatorial optimization for VRP on medium-scale data set, and is able to tackle the large-scale data set (e.g., over 400 nodes) which is a considerable challenge in this area. Moreover, the need for expertise and handcrafted heuristics design is eliminated due to the fact that the proposed network learns to design the heuristics with a better performance. Our implementation is available online.