{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T20:54:41Z","timestamp":1785185681269,"version":"3.55.0"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":["61501178"],"award-info":[{"award-number":["61501178"]}],"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":["61571100"],"award-info":[{"award-number":["61571100"]}],"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":["61631005"],"award-info":[{"award-number":["61631005"]}],"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":["61628103"],"award-info":[{"award-number":["61628103"]}],"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":["61771187"],"award-info":[{"award-number":["61771187"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","award":["2018CFB698"],"award-info":[{"award-number":["2018CFB698"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","award":["2018CFB698"],"award-info":[{"award-number":["2018CFB698"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Wireless Commun."],"published-print":{"date-parts":[[2019,11]]},"DOI":"10.1109\/twc.2019.2933417","type":"journal-article","created":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T20:05:06Z","timestamp":1565726706000},"page":"5141-5152","source":"Crossref","is-referenced-by-count":447,"title":["Deep Reinforcement Learning for User Association and Resource Allocation in Heterogeneous Cellular Networks"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4738-5684","authenticated-orcid":false,"given":"Nan","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2671-5090","authenticated-orcid":false,"given":"Ying-Chang","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7442-7416","authenticated-orcid":false,"given":"Dusit","family":"Niyato","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9915-8697","authenticated-orcid":false,"given":"Yiyang","family":"Pei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minghu","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunhao","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref38","author":"osborne","year":"2004","journal-title":"An Introduction to Game Theory"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2018.2809722"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2017.2687918"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2782726"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2871020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-010-0189-2"},{"key":"ref36","article-title":"Deep reinforcement learning for distributed dynamic power allocation in wireless networks","author":"nasir","year":"2018","journal-title":"arXiv 1808 00490"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2879433"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1700246"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2014.2339313"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2017.8254853"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2015.2416990"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2013.2268923"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2012.6503987"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2865951"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2017.2762668"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2017.04.025"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1016\/j.jnca.2011.08.007","article-title":"Reinforcement learning for context awareness and intelligence in wireless networks: Review, new features and open issues","volume":"35","author":"yau","year":"2011","journal-title":"J Netw Comput Appl"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1002\/ett.2800"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2897134"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2013.040413.120676"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2769644"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2015.7143323"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2012.121112.120018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7997286"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2014.2328143"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2015.2452953"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2015.2417011"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s41650-017-0002-1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2016.2533559"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2018.8647611"},{"key":"ref46","first-page":"26","article-title":"Lecture 6.5 RmsProp: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Netw Mach Learn"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2016.2593468"},{"key":"ref45","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2015","journal-title":"arXiv 1511 06581"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7997440"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2709462"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref24","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":"ref41","first-page":"871","article-title":"Extending Q-learning to general adaptive multi-agent systems","author":"tesauro","year":"2004","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422826"},{"key":"ref44","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2015","journal-title":"arXiv 1509 06461 [cs]"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2831240"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1162\/089976699300016070"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2829773"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7693\/8894903\/08796358.pdf?arnumber=8796358","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:08:45Z","timestamp":1657746525000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8796358\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":46,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/twc.2019.2933417","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,11]]}}}