Heterogeneous attentions for solving pickup and delivery problem via deep reinforcement learning

• Main Authors: LI, Jingwen, XIN, Liang, CAO, Zhiguang, LIM, Andrew, SONG, Wen, ZHANG, Jie
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2022
• 主題: Reinforcement learning; Routing; Peer-to-peer computing; Heuristic algorithms; Deep learning; Decoding; Decision making; Heterogeneous attention; deep reinforcement learning; pickup and delivery problem; Artificial Intelligence and Robotics; Transportation
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/8127; https://ink.library.smu.edu.sg/context/sis_research/article/9130/viewcontent/2110.02634.pdf

Recently, there is an emerging trend to apply deep reinforcement learning to solve the vehicle routing problem (VRP), where a learnt policy governs the selection of next node for visiting. However, existing methods could not handle well the pairing and precedence relationships in the pickup and deli...