Combining Reinforcement Learning with Lin-Kernighan-Helsgaun Algorithm for the Traveling Salesman Problem

Authors

  • Jiongzhi Zheng Huazhong University of Science and Technology
  • Kun He Huazhong University of Science and Technology
  • Jianrong Zhou Huazhong University of Science and Technology
  • Yan Jin Huazhong University of Science and Technology
  • Chu-Min Li MIS, University of Picardie Jules Verne Huazhong University of Science and Technology

Keywords:

Heuristic Search, Reinforcement Learning

Abstract

We address the Traveling Salesman Problem (TSP), a famous NP-hard combinatorial optimization problem. And we propose a variable strategy reinforced approach, denoted as VSR-LKH, which combines three reinforcement learning methods (Q-learning, Sarsa and Monte Carlo) with the well-known TSP algorithm, called Lin-Kernighan-Helsgaun (LKH). VSR-LKH replaces the inflexible traversal operation in LKH, and lets the program learn to make choice at each search step by reinforcement learning. Experimental results on 111 TSP benchmarks from the TSPLIB with up to 85,900 cities demonstrate the excellent performance of the proposed method.

Downloads

Published

2021-05-18

How to Cite

Zheng, J., He, K., Zhou, J., Jin, Y., & Li, C.-M. (2021). Combining Reinforcement Learning with Lin-Kernighan-Helsgaun Algorithm for the Traveling Salesman Problem. Proceedings of the AAAI Conference on Artificial Intelligence, 35(14), 12445-12452. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17476

Issue

Section

AAAI Technical Track on Search and Optimization