Hierarchical neural constructive solver for real-world TSP scenarios

• Main Authors: GOH, Yong Liang, CAO, Zhiguang, MA, Yining, DONG, Yanfei, DUPTY, Mohammed Haroon, LEE, Wee Sun
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2024
• 主題: neural constructive solver; traveling salesman problem; deep reinforcement learning; Databases and Information Systems; OS and Networks
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/9334; https://ink.library.smu.edu.sg/context/sis_research/article/10334/viewcontent/3637528.3672053.pdf

Existing neural constructive solvers for routing problems have predominantly employed transformer architectures, conceptualizing the route construction as a set-to-sequence learning task. However, their efficacy has primarily been demonstrated on entirely random problem instances that inadequately c...