Work

Diversity Optimization for Travelling Salesman Problem via Deep Reinforcement Learning

Year: 2025

Type: conference-paper

Abstract: Existing neural methods for the Travelling Salesman Problem (TSP) mostly aim at finding a single optimal solution. To discover diverse yet high-quality solutions for Multi-Solution TSP (MSTSP), we propose a novel deep reinforcement learning based neural solver, which is primarily featured by an encoder-decoder structured policy. Concretely, on the one hand, a Relativization Filter (RF) is designed to enhance the robustness of the encoder to affine transformations of the instances, so as to potentially improve the quality of the found solutions. On the other hand, a Multi-Attentive Adaptive Active Search (MA3S) is tailored to allow the decoders to strike a balance between the optimality and diversity. Experimental evaluations on benchmark instances demonstrate the superiority of our method over recent neural baselines across different metrics, and its competitive performance against state-of-the-art traditional heuristics with significantly reduced computational time, ranging from 1.3× to 15× faster. Furthermore, we demonstrate that our method can also be applied to the Capacitated Vehicle Routing Problem (CVRP).

Source: ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)

DOI: 10.1145/3690624.3709181

Authors: Qi Li, Zhiguang Cao, Yining Ma, Yaoxin Wu, Yue-Jiao Gong

Institutions: South China University of Technology, Singapore Management University, Massachusetts Institute of Technology, Eindhoven University of Technology

Language: English

Topic: Vehicle Routing Optimization Methods

Subfield: Industrial and Manufacturing Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: green

Funders: National Research Foundation, National Research Foundation Singapore, National Natural Science Foundation of China, Natural Science Foundation of Guangdong Province

Awards: G3621338742, G6790837365, G8336759129