{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T18:30:33Z","timestamp":1778351433971,"version":"3.51.4"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1642865"],"award-info":[{"award-number":["1642865"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NASA ULI","award":["NNX17AJ94A"],"award-info":[{"award-number":["NNX17AJ94A"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Wireless Commun."],"published-print":{"date-parts":[[2019,8]]},"DOI":"10.1109\/twc.2019.2919611","type":"journal-article","created":{"date-parts":[[2019,6,5]],"date-time":"2019-06-05T20:00:21Z","timestamp":1559764821000},"page":"3933-3947","source":"Crossref","is-referenced-by-count":75,"title":["Reinforcement Learning for Self Organization and Power Control of Two-Tier Heterogeneous Networks"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6373-121X","authenticated-orcid":false,"given":"Roohollah","family":"Amiri","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2467-9583","authenticated-orcid":false,"given":"Mojtaba Ahmadi","family":"Almasi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9115-5088","authenticated-orcid":false,"given":"Jeffrey G.","family":"Andrews","sequence":"additional","affiliation":[]},{"given":"Hani","family":"Mehrpouyan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref38","first-page":"1","article-title":"Learning rates for Q-learning","volume":"5","author":"even-dar","year":"2004","journal-title":"J Mach Learn Res"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2866382"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCW.2018.8403515"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2006.879347"},{"key":"ref30","first-page":"840","article-title":"Reward function and initial values: Better choices for accelerated goal-directed reinforcement learning","author":"matignon","year":"2006","journal-title":"Proc ICANN"},{"key":"ref37","first-page":"227","article-title":"Coordinated reinforcement learning","author":"guestrin","year":"2002","journal-title":"Proc ICML"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2010.111910.091238"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/VTCFall.2018.8690565"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1613\/jair.575"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2009.081386"},{"key":"ref40","first-page":"996","article-title":"Finite-sample convergence rates for Q-learning and indirect algorithms","volume":"11","author":"kearns","year":"1999","journal-title":"Proc NIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2012.157"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2007.4394515"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/GSMM.2018.8439323"},{"key":"ref14","article-title":"Deep reinforcement learning for distributed dynamic power allocation in wireless networks","author":"nasir","year":"2018","journal-title":"arXiv 1808 00490"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2014.141213"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2017.2698260"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952825"},{"key":"ref18","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2010.2043124"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2011.08.007"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2014.2328098"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2014.2384510"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2018.07.015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2016.2532458"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2013.6515045"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2014.6963801"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2727878"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SURV.2012.021312.00116"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2017.1600304WC"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422864"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/VTCFall.2012.6399230"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1963.10500830"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2013.060513.120959"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/VTCFall.2013.6692057"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2011.2179817"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2016.2535461"},{"key":"ref41","year":"2010","journal-title":"Evolved Universal Terrestrial Radio Access (E-UTRA) Further Advancements for E-UTRA Physical Layer Aspects ’ 3rd Generation Partnership Project (3GPP) Technical Specification (TS)"},{"key":"ref23","first-page":"625","article-title":"A Q-learning-based downlink resource scheduling method for capacity optimization in LTE femtocells","author":"wen","year":"2014","journal-title":"Proc 9th Int Conf Comput Sci Educ"},{"key":"ref44","first-page":"2413","article-title":"Reinforcement learning in finite MDPs: PAC analysis","volume":"10","author":"strehl","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2009.5425693"},{"key":"ref43","first-page":"1","article-title":"Cross-layer interference modeling for 5G mm-Wave networks in the presence of blockage","author":"niknam","year":"2018","journal-title":"Proc IEEE Veh Technol Conf"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCW.2015.7247475"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielaam\/7693\/8794662\/8731967-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7693\/8794662\/08731967.pdf?arnumber=8731967","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\/8731967\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":45,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/twc.2019.2919611","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8]]}}}