Accelerating the Genetic Algorithm for Large-scale Traveling Salesman Problems by Cooperative Coevolutionary Pointer Network with Reinforcement Learning

TL;DR

This paper introduces CCPNRL-GA, a two-stage optimization method combining clustering, Pointer Networks, and genetic algorithms to efficiently solve large-scale Traveling Salesman Problems, demonstrating significant acceleration over traditional methods.

Contribution

The paper proposes a novel two-stage approach integrating cooperative coevolution, pointer networks, and reinforcement learning to improve large-scale TSP optimization.

Findings

Accelerates convergence of LSTSP solutions

Outperforms traditional evolutionary algorithms

Shows broad applicability to large-scale TSPs

Abstract

In this paper, we propose a two-stage optimization strategy for solving the Large-scale Traveling Salesman Problems (LSTSPs) named CCPNRL-GA. First, we hypothesize that the participation of a well-performed individual as an elite can accelerate the convergence of optimization. Based on this hypothesis, in the first stage, we cluster the cities and decompose the LSTSPs into multiple subcomponents, and each subcomponent is optimized with a reusable Pointer Network (PtrNet). After subcomponents optimization, we combine all sub-tours to form a valid solution, this solution joins the second stage of optimization with GA. We validate the performance of our proposal on 10 LSTSPs and compare it with traditional EAs. Experimental results show that the participation of an elite individual can greatly accelerate the optimization of LSTSPs, and our proposal has broad prospects for dealing with LSTSPs.