{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T02:16:56Z","timestamp":1778638616889,"version":"3.51.4"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100006602","name":"Air Force Research Laboratory (AFRL) and the Office of undersecretary of Defense (OSD) for sponsoring this research","doi-asserted-by":"publisher","award":["FA8750-15-2-0116"],"award-info":[{"award-number":["FA8750-15-2-0116"]}],"id":[{"id":"10.13039\/100006602","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3102230","type":"journal-article","created":{"date-parts":[[2021,8,9]],"date-time":"2021-08-09T20:25:56Z","timestamp":1628540756000},"page":"110601-110613","source":"Crossref","is-referenced-by-count":15,"title":["Antenna Beamwidth Optimization in Directional Device-to-Device Communication Using Multi-Agent Deep Reinforcement Learning"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6278-0645","authenticated-orcid":false,"given":"Niloofar","family":"Bahadori","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3059-7912","authenticated-orcid":false,"given":"Mahmoud","family":"Nabil","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1179-3221","authenticated-orcid":false,"given":"Abdollah","family":"Homaifar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933973"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933962"},{"key":"ref30","article-title":"Learning from delayed rewards","author":"watkins","year":"1989"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2019.8885670"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2882635"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2020.3005138"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2979446"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000057"},{"key":"ref16","first-page":"780","article-title":"Predicting and preventing coordination problems in cooperative q-learning systems","author":"fulda","year":"2007","journal-title":"Proc IJCAI"},{"key":"ref17","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","volume":"70","author":"foerster","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2673248"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2016.2551690"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2017.2699360"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2015.7248501"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2017.2767041"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2013.2260813"},{"key":"ref6","first-page":"1","article-title":"Beamwidth optimization in millimeter wave small cell networks with relay nodes: A swarm intelligence approach","author":"perfecto","year":"2016","journal-title":"Proc 22th Eur Wireless Conf"},{"key":"ref29","first-page":"2","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","author":"claus","year":"1998","journal-title":"Proc AAAI\/IAAI"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2901593"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2869151"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2017.2719998"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2015.7010536"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2019.8904251"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2014.2319555"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2897134"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2879433"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2894138"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2019.2958814"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2015.2434384"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2015.7421171"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09509379.pdf?arnumber=9509379","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:57:22Z","timestamp":1639771042000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9509379\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3102230","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}