{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:17:36Z","timestamp":1783610256623,"version":"3.55.0"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2018,12,1]],"date-time":"2018-12-01T00:00:00Z","timestamp":1543622400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2018,12,1]],"date-time":"2018-12-01T00:00:00Z","timestamp":1543622400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2018,12,1]],"date-time":"2018-12-01T00:00:00Z","timestamp":1543622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2018,12,1]],"date-time":"2018-12-01T00:00:00Z","timestamp":1543622400000},"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":["61629101"],"award-info":[{"award-number":["61629101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DMS-1622433"],"award-info":[{"award-number":["DMS-1622433"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["AST-1547436"],"award-info":[{"award-number":["AST-1547436"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["ECCS-1659025"],"award-info":[{"award-number":["ECCS-1659025"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1343155"],"award-info":[{"award-number":["CNS-1343155"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarships Council","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/jiot.2018.2848295","type":"journal-article","created":{"date-parts":[[2018,6,18]],"date-time":"2018-06-18T23:05:32Z","timestamp":1529363132000},"page":"4296-4307","source":"Crossref","is-referenced-by-count":125,"title":["Handover Control in Wireless Systems via Asynchronous Multiuser Deep Reinforcement Learning"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1095-9632","authenticated-orcid":false,"given":"Zhi","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihua","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8876-1389","authenticated-orcid":false,"given":"Hui","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2608-775X","authenticated-orcid":false,"given":"Shuguang","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref32","first-page":"2737","article-title":"Asynchronous parallel stochastic gradient for nonconvex optimization","author":"lian","year":"2015","journal-title":"Proc NIPS"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2727483"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1002\/wcm.72"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2016.2623298"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2014.031414.132731"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2015.2496958"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2017.7925950"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2005.01.025"},{"key":"ref15","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":"ref16","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc ICML"},{"key":"ref17","first-page":"1","article-title":"Learning to play in a day: Faster deep reinforcement learning by optimality tightening","author":"he","year":"2017","journal-title":"Proc ICLR"},{"key":"ref18","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc ICML"},{"key":"ref19","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc NIPS"},{"key":"ref28","article-title":"Training recurrent neural networks","author":"sutskever","year":"2013"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2013.022113.120506"},{"key":"ref27","first-page":"1054","article-title":"Safe and efficient off-policy reinforcement learning","author":"munos","year":"2016","journal-title":"Proc NIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2642538"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICECC.2011.6067552"},{"key":"ref29","first-page":"1","article-title":"End to end learning for self-driving cars","volume":"abs 1604 7316","author":"marius","year":"2017","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2015.2435451"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WCSP.2015.7341220"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICWMC.2010.17"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2016.2612038"},{"key":"ref9","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref1","year":"2017","journal-title":"Protocol Specifications Radio Resource Control V 14 2 2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2694140"},{"key":"ref22","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","author":"macqueen","year":"1966","journal-title":"Proc 5th Berkeley Symp Math Stat Probab"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2005.29"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1755743.1755745"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.35"},{"key":"ref26","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"1999","journal-title":"Proc ICML"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielaam\/6488907\/8614370\/8387430-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/8614370\/08387430.pdf?arnumber=8387430","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:54:00Z","timestamp":1649444040000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8387430\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":32,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2018.2848295","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12]]}}}