{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T17:16:27Z","timestamp":1772644587492,"version":"3.50.1"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"TELUS Canada and the National Science and Engineering Research Council, Canada through its Collaborative Research and Development (CRD) Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Wireless Commun."],"published-print":{"date-parts":[[2020,12]]},"DOI":"10.1109\/twc.2020.3022705","type":"journal-article","created":{"date-parts":[[2020,9,16]],"date-time":"2020-09-16T20:42:36Z","timestamp":1600288956000},"page":"8410-8426","source":"Crossref","is-referenced-by-count":53,"title":["Centralized and Distributed Deep Reinforcement Learning Methods for Downlink Sum-Rate Optimization"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7057-6361","authenticated-orcid":false,"given":"Ahmad Ali","family":"Khan","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0224-2209","authenticated-orcid":false,"given":"Raviraj S.","family":"Adve","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCW.2018.8403662"},{"key":"ref32","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","author":"omidshafiei","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","article-title":"Emergent tool use from multi-agent autocurricula","author":"baker","year":"2019","journal-title":"arXiv 1909 07528"},{"key":"ref34","author":"bishop","year":"2016","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCW.2013.6649246"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2010.12.101635"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CAMSAP45676.2019.9022520"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC.2019.8815516"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933973"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3001736"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2769644"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2938514"},{"key":"ref18","first-page":"22","article-title":"Constrained policy optimization","author":"achiam","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref28","first-page":"3562","article-title":"Learn what not to learn: Action elimination with deep reinforcement learning","author":"zahavy","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2011.2147784"},{"key":"ref27","first-page":"1531","article-title":"A natural policy gradient","author":"kakade","year":"2002","journal-title":"Proc Adv Neu Inf Proc Sys"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2866382"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOMW.2018.8644119"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1718942115"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2812733"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2015.7248971"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.2200\/S00330ED1V01Y201101CNT009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2012.031212.111585"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1109\/JSTSP.2007.914876","article-title":"Dynamic spectrum management: Complexity and duality","volume":"2","author":"luo","year":"2008","journal-title":"IEEE J Sel Topics Signal Process"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2762289"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref22","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2957482"},{"key":"ref23","article-title":"Algorithms for multi-armed bandit problems","author":"kuleshov","year":"2014","journal-title":"arXiv 1402 6028"},{"key":"ref26","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"arXiv 1506 02438 [cs]"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2908906"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7693\/9289043\/09199126.pdf?arnumber=9199126","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T16:27:07Z","timestamp":1651076827000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9199126\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12]]},"references-count":34,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/twc.2020.3022705","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12]]}}}