Combining Reinforcement Learning with Lin-Kernighan-Helsgaun Algorithm for the Traveling Salesman Problem - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

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

, (1) , , (2) , (3, 4)
1
2
3
4

Résumé

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.
Fichier non déposé

Dates et versions

hal-03636413 , version 1 (10-04-2022)

Identifiants

  • HAL Id : hal-03636413 , version 1

Citer

Jiongzhi Zheng, Kun He, Jianrong Zhou, Yan Jin, Chu-Min Li. Combining Reinforcement Learning with Lin-Kernighan-Helsgaun Algorithm for the Traveling Salesman Problem. THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, Feb 2021, Vancouver, Canada. pp.12445-12452. ⟨hal-03636413⟩
42 Consultations
0 Téléchargements

Partager

Gmail Facebook Twitter LinkedIn More