{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:26:22Z","timestamp":1779294382660,"version":"3.51.4"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"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":["61871096"],"award-info":[{"award-number":["61871096"]}],"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":["61972075"],"award-info":[{"award-number":["61972075"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["2018YFB2101300"],"award-info":[{"award-number":["2018YFB2101300"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"EU H2020 Research and Innovation Programme under the Marie Sklodowska-Curie","award":["752979"],"award-info":[{"award-number":["752979"]}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1109\/jiot.2020.2978830","type":"journal-article","created":{"date-parts":[[2020,3,6]],"date-time":"2020-03-06T23:15:16Z","timestamp":1583536516000},"page":"5449-5465","source":"Crossref","is-referenced-by-count":297,"title":["Deep-Reinforcement-Learning-Based Offloading Scheduling for Vehicular Edge Computing"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1851-7185","authenticated-orcid":false,"given":"Wenhan","family":"Zhan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9860-2901","authenticated-orcid":false,"given":"Chunbo","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1395-7314","authenticated-orcid":false,"given":"Geyong","family":"Min","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hancong","family":"Duan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingxin","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","first-page":"2171","article-title":"DEAP: Evolutionary algorithms made easy","volume":"13","author":"fortin","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref31","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref30","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc of USENIX Symp on Operating Systems Design and Implementation (OSDI)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2818111"},{"key":"ref11","author":"li","year":"2017","journal-title":"Deep reinforcement learning An overview"},{"key":"ref12","author":"sutton","year":"2011","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2019.1800971"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2018.8377343"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890685"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2876279"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9013982"},{"key":"ref18","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SURV.2013.062613.00160"},{"key":"ref28","author":"ba","year":"2016","journal-title":"Layer normalization"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2750180"},{"key":"ref27","first-page":"1","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2876298"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2014.2381227"},{"key":"ref29","author":"dulac-arnold","year":"2015","journal-title":"Deep reinforcement learning in large discrete action spaces"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2579198"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2015.2405539"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2016.2599530"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2017.2668838"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2016.7541539"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2018.2879647"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2017.2699660"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2016.2593486"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2316834"},{"key":"ref24","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"v hasselt","year":"2016","journal-title":"Proc AAAI Conf Artif Intell (AAAI)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref26","first-page":"179","article-title":"Off-policy actor–critic","author":"degris","year":"2012","journal-title":"Proc 29th Int Conf Mach Learn (ICML)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/9115800\/09026935.pdf?arnumber=9026935","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:25:47Z","timestamp":1651080347000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9026935\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6]]},"references-count":32,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2020.2978830","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6]]}}}