{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T16:44:20Z","timestamp":1778345060029,"version":"3.51.4"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":["61971366"],"award-info":[{"award-number":["61971366"]}],"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":["61671396"],"award-info":[{"award-number":["61671396"]}],"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":["61901403"],"award-info":[{"award-number":["61901403"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["20720190034"],"award-info":[{"award-number":["20720190034"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["20720190029"],"award-info":[{"award-number":["20720190029"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008081","name":"Southeast University","doi-asserted-by":"publisher","award":["2018D08"],"award-info":[{"award-number":["2018D08"]}],"id":[{"id":"10.13039\/501100008081","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["2019J05001"],"award-info":[{"award-number":["2019J05001"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-0939370"],"award-info":[{"award-number":["CCF-0939370"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1513915"],"award-info":[{"award-number":["CCF-1513915"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Wireless Commun."],"published-print":{"date-parts":[[2020,1]]},"DOI":"10.1109\/twc.2019.2945951","type":"journal-article","created":{"date-parts":[[2019,10,14]],"date-time":"2019-10-14T19:26:23Z","timestamp":1571081183000},"page":"423-434","source":"Crossref","is-referenced-by-count":83,"title":["Reinforcement Learning-Based Downlink Interference Control for Ultra-Dense Small Cells"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2402-611X","authenticated-orcid":false,"given":"Liang","family":"Xiao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1550-4119","authenticated-orcid":false,"given":"Hailu","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yilin","family":"Xiao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4808-7443","authenticated-orcid":false,"given":"Xiaoyue","family":"Wan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5710-0446","authenticated-orcid":false,"given":"Sicong","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7883-6217","authenticated-orcid":false,"given":"Li-Chun","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2062-131X","authenticated-orcid":false,"given":"H. Vincent","family":"Poor","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299173"},{"key":"ref38","first-page":"4863","article-title":"Is Q-learning provably efficient?","author":"jin","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","first-page":"369","article-title":"Dynamic analysis of multiagent Q-learning with \n$\\varepsilon$\n-greedy exploration","author":"gomes","year":"2009","journal-title":"Proc 26th Annu Int Conf Mach Learn (ICML)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2017.2737968"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2002.804034"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2018.8648136"},{"key":"ref37","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2844878"},{"key":"ref35","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":"ref34","article-title":"What do we understand about convolutional networks?","author":"hadji","year":"2018","journal-title":"arXiv 1803 08834"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2664832"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2856854"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2011.100611.101684"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2018.2851755"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2018.2842113"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2016.2646346"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2016.2545539"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2799568"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2013.060513.120959"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2015.7248841"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2014.2374237"},{"key":"ref28","article-title":"A multi-agent deep reinforcement learning based spectrum allocation framework for D2D communications","author":"li","year":"2019","journal-title":"arXiv 1904 06615"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/VTCFall.2016.7880924"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WCSP.2019.8927868"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2013.6549291"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2017.2720898"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761431"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2782726"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2009.2035627"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2017.1700052"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2014.6845056"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2016.2628821"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2013.2273503"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2015.2393496"},{"key":"ref22","first-page":"170","article-title":"A cooperative reinforcement learning approach for inter-cell interference coordination in OFDMA cellular networks","author":"dirani","year":"2010","journal-title":"Proc 8th Int Symp Modeling Optim Mobile Ad Hoc Wireless Netw (WiOpt)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904365"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487486"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2871020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7997440"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2900035"},{"key":"ref43","article-title":"Neural episodic control","author":"pritzel","year":"2017","journal-title":"arXiv 1703 01988"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2769644"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7693\/8952731\/08868117.pdf?arnumber=8868117","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T16:25:50Z","timestamp":1651076750000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8868117\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1]]},"references-count":43,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/twc.2019.2945951","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,1]]}}}