Learning to solve multiple-TSP with time window and rejections via deep reinforcement learning

• المؤلفون الرئيسيون: ZHANG, Rongkai, ZHANG, Cong, CAO, Zhiguang, SONG, Wen, TAN, Puay Siew, ZHANG, Jie, WEN, Bihan, DAUWELS, Justin
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2022
• الموضوعات: Travelling Salesman Problem; Graph Neural Network; Deep Reinforcement Learning; Artificial Intelligence and Robotics; Transportation
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/sis_research/8128; https://ink.library.smu.edu.sg/context/sis_research/article/9131/viewcontent/2209.06094.pdf

We propose a manager-worker framework (the implementation of our model is publically available at: https://github.com/zcaicaros/manager-worker-mtsptwr) based on deep reinforcement learning to tackle a hard yet nontrivial variant of Travelling Salesman Problem (TSP), i.e. multiple-vehicle TSP with ti...