{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T17:49:18Z","timestamp":1793987358963,"version":"4.8.0"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72171172"],"award-info":[{"award-number":["72171172"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92367101"],"award-info":[{"award-number":["92367101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004750","name":"Aeronautical Science Foundation of China","doi-asserted-by":"publisher","award":["2023Z066038001"],"award-info":[{"award-number":["2023Z066038001"]}],"id":[{"id":"10.13039\/501100004750","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Natural Science Foundation of China Basic Science Research Center Program","award":["62088101"],"award-info":[{"award-number":["62088101"]}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0100"],"award-info":[{"award-number":["2021SHZDZX0100"]}]},{"name":"Chinese Academy of Engineering, Strategic Research and Consulting Program","award":["2023-XZ-65"],"award-info":[{"award-number":["2023-XZ-65"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Veh. Technol."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tvt.2025.3555594","type":"journal-article","created":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T19:33:34Z","timestamp":1743449614000},"page":"13013-13028","source":"Crossref","is-referenced-by-count":8,"title":["Deep Reinforcement Learning for Dynamic Task Scheduling in Data Relay Satellite Networks"],"prefix":"10.1109","volume":"74","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9839-9757","authenticated-orcid":false,"given":"Kunhao","family":"Chen","sequence":"first","affiliation":[{"name":"College of Electronic and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7018-4763","authenticated-orcid":false,"given":"Qingyun","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5097-9972","authenticated-orcid":false,"given":"Li","family":"Li","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2449-9793","authenticated-orcid":false,"given":"Jie","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.omega.2015.01.001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2022.3188405"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s43684-023-00054-6"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2020.2997050"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3046304"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2021.3115587"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3233358"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3590163"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121723"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106208"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2020.106799"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2763150"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2903737"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3045140"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3317783"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-023-01227-9"},{"key":"ref17","first-page":"486","article-title":"A theoretical analysis of deep Q-learning","volume-title":"Proc. 2nd Conf. Learn. Dyn. Control","author":"Fan","year":"2020"},{"key":"ref18","article-title":"Attention, learn to solve routing problems!","author":"Kool","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.105677"},{"key":"ref20","first-page":"31226","article-title":"Learning generalizable models for vehicle routing problems via knowledge distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bi","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00468-6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref24","first-page":"21188","article-title":"POMO: Policy optimization with multiple optima for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kwon","year":"2020"},{"key":"ref25","first-page":"1936","article-title":"Sym-NCO: Leveraging symmetricity for neural combinatorial optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2024.3411640"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2024.3379169"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3345928"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2023.101233"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2024.3371964"},{"issue":"12","key":"ref31","first-page":"2715","article-title":"Survey on models, algorithms and general techniques for spacecraft mission scheduling","volume":"47","author":"Xing","year":"2021","journal-title":"Acta Automatica Sinica"},{"key":"ref32","first-page":"48485","article-title":"Winner takes it all: Training performant RL populations for combinatorial optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Grinsztajn","year":"2023"},{"key":"ref33","article-title":"RL4CO: A unified reinforcement learning for combinatorial optimization library","volume-title":"Proc. NeurIPS 2023 Workshop: New Front. Graph Learn.","author":"Berto","year":"2023"},{"key":"ref34","volume-title":"NASA Systems Engineering Handbook","author":"Kapurch","year":"2010"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.23919\/CCC58697.2023.10241198"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2020.06.005"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-28451-9_18"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119338"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3111082"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3352143"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-3559-4_32"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2011.02.002"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2021.100888"},{"key":"ref44","article-title":"Neural combinatorial optimization algorithms for solving vehicle routing problems: A comprehensive survey with perspectives","author":"Wu","year":"2024"}],"container-title":["IEEE Transactions on Vehicular Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/25\/11119234\/10944576.pdf?arnumber=10944576","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:43:14Z","timestamp":1755546194000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10944576\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":44,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tvt.2025.3555594","relation":{},"ISSN":["0018-9545","1939-9359"],"issn-type":[{"value":"0018-9545","type":"print"},{"value":"1939-9359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}