{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T18:07:45Z","timestamp":1732039665618},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"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":["61672136","61828202"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Plan","award":["2018AAA0103203"]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2021,3,1]]},"DOI":"10.1109\/jiot.2020.3025015","type":"journal-article","created":{"date-parts":[[2020,9,18]],"date-time":"2020-09-18T20:38:58Z","timestamp":1600461538000},"page":"3576-3586","source":"Crossref","is-referenced-by-count":63,"title":["Cloud Resource Scheduling With Deep Reinforcement Learning and Imitation Learning"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-0744-5745","authenticated-orcid":false,"given":"Wenxia","family":"Guo","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-5551-9796","authenticated-orcid":false,"given":"Wenhong","family":"Tian","sequence":"additional","affiliation":[]},{"given":"Yufei","family":"Ye","sequence":"additional","affiliation":[]},{"given":"Lingxiao","family":"Xu","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-2069-0032","authenticated-orcid":false,"given":"Kui","family":"Wu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","year":"2018","journal-title":"Alibaba-Cluster-Trace-2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref33","first-page":"45","article-title":"Q-learning algorithm for joint computation offloading and resource allocation in edge cloud","author":"dab","year":"2019","journal-title":"Proc IFIP\/IEEE Symp Integr Netw Serv Manag (IM)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2019.1800386"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSET.2018.8336194"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMMST.2018.8632064"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-014-1131-z"},{"key":"ref36","author":"bojarski","year":"2016","journal-title":"End to End Learning for Self-Driving Cars"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1613\/jair.898"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MCC.2018.1081063"},{"key":"ref40","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref11","author":"sutton","year":"2011","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref12","article-title":"Learning from delayed rewards","author":"watkins","year":"1989"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref14","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid.2012.112"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.1867"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2017.2679738"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2740070.2626334"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-018-1062-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cdt.2019.0092"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1137\/0403025"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/PDP.2014.109"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11276-018-1743-y"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2009.77"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1137\/0211053"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2017.03.008"},{"key":"ref9","first-page":"1","article-title":"Deep reinforcement learning for resource allocation in V2V communications","author":"ye","year":"2018","journal-title":"Proc IEEE Int Conf Commun (ICC)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.suscom.2018.05.011"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2012.240"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/NCCA.2012.29"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2018.12.021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2894851"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2014.012614.130747"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3233\/IDT-190007"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2018.11.012"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/9358034\/09200455.pdf?arnumber=9200455","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:51Z","timestamp":1652194431000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9200455\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,1]]},"references-count":40,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2020.3025015","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,1]]}}}