Learning Improvement Heuristics for Solving Routing Problems

TL;DR

This paper introduces a deep reinforcement learning framework with a self-attention architecture to improve routing solutions, outperforming existing deep learning methods and generalizing across various problem sizes and datasets.

Contribution

It presents a novel deep RL approach with a self-attention network to learn improvement heuristics for routing problems, surpassing traditional hand-crafted rules.

Findings

Outperforms state-of-the-art deep learning approaches

Policies generalize well to different problem sizes and datasets

Enhancements via simple diversifying strategies improve performance

Abstract

Recent studies in using deep learning to solve routing problems focus on construction heuristics, the solutions of which are still far from optimality. Improvement heuristics have great potential to narrow this gap by iteratively refining a solution. However, classic improvement heuristics are all guided by hand-crafted rules which may limit their performance. In this paper, we propose a deep reinforcement learning framework to learn the improvement heuristics for routing problems. We design a self-attention based deep architecture as the policy network to guide the selection of next solution. We apply our method to two important routing problems, i.e. travelling salesman problem (TSP) and capacitated vehicle routing problem (CVRP). Experiments show that our method outperforms state-of-the-art deep learning based approaches. The learned policies are more effective than the traditional hand-crafted ones, and can be further enhanced by simple diversifying strategies. Moreover, the policies generalize well to different problem sizes, initial solutions and even real-world dataset.