{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T23:37:33Z","timestamp":1780357053942,"version":"3.54.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"General Research Funding","award":["14209414"],"award-info":[{"award-number":["14209414"]}]},{"name":"General Research Funding","award":["14208107"],"award-info":[{"award-number":["14208107"]}]},{"name":"Research Grants Council of Hong Kong"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2020,9,1]]},"DOI":"10.1109\/tmc.2019.2922602","type":"journal-article","created":{"date-parts":[[2019,6,12]],"date-time":"2019-06-12T20:03:07Z","timestamp":1560369787000},"page":"2076-2087","source":"Crossref","is-referenced-by-count":76,"title":["DRAG: Deep Reinforcement Learning Based Base Station Activation in Heterogeneous Networks"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4031-6547","authenticated-orcid":false,"given":"Junhong","family":"Ye","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7304-6849","authenticated-orcid":false,"given":"Ying-Jun Angela","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Deep reinforcement learning in parameterized action space","author":"hausknecht","year":"2015","journal-title":"arXiv preprint arXiv 1511 05271"},{"key":"ref38","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"ref32","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":"ref31","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2769644"},{"key":"ref37","first-page":"-387i","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref36","article-title":"Deep reinforcement learning in large discrete action spaces","author":"dulac-arnold","year":"2015","journal-title":"arXiv preprint arXiv 1512 00327"},{"key":"ref35","article-title":"Parameter space noise for exploration","author":"plappert","year":"2017","journal-title":"arXiv preprint arXiv 1706 01905"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2013.130506"},{"key":"ref40","author":"abadi","year":"0"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2013.071613.122092"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2015.2434381"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2013.130503"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2013.072213.120588"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2014.2336249"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2331611"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2016.2544478"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2011.110903"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WOCC.2013.6676373"},{"key":"ref28","article-title":"On-line Q-learning using connectionist systems","author":"rummery","year":"1994"},{"key":"ref4","first-page":"1","article-title":"Optimal energy savings in cellular access networks","author":"marsan","year":"2009","journal-title":"Proc IEEE Int Conf Commun Workshops"},{"key":"ref27","article-title":"Learning from delayed rewards","author":"watkins","year":"1989"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2030613.2030628"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1186\/1687-1499-2012-142"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref5","first-page":"3264","article-title":"Reinforcement learning approach to dynamic activation of base station resources in wireless networks","author":"kong","year":"2013","journal-title":"Proc IEEE 24th Int Symp Pers Indoor Mobile Radio Commun"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIWDC.2013.6664207"},{"key":"ref7","article-title":"9900 wireless network guardian","year":"2012"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2014.022014.130840"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2015.2411737"},{"key":"ref1","year":"2007"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2012.120415"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1002\/ett.2565"},{"key":"ref21","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref24","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2011.5978418"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2011.2170565"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7755\/9158776\/08735834.pdf?arnumber=8735834","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T16:38:29Z","timestamp":1651077509000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8735834\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,1]]},"references-count":40,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2019.2922602","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,1]]}}}