{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T20:50:18Z","timestamp":1782334218541,"version":"3.54.5"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1801925"],"award-info":[{"award-number":["CNS-1801925"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2029569"],"award-info":[{"award-number":["CNS-2029569"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"name":"JSPS KAKENHI","award":["JP19H02142"],"award-info":[{"award-number":["JP19H02142"]}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["EARS-1839818"],"award-info":[{"award-number":["EARS-1839818"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1717454"],"award-info":[{"award-number":["CNS-1717454"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1731424"],"award-info":[{"award-number":["CNS-1731424"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1702850"],"award-info":[{"award-number":["CNS-1702850"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1908308"],"award-info":[{"award-number":["CCF-1908308"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2022,12,1]]},"DOI":"10.1109\/tmc.2021.3085206","type":"journal-article","created":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T15:42:27Z","timestamp":1622562147000},"page":"4426-4438","source":"Crossref","is-referenced-by-count":52,"title":["Make Smart Decisions Faster: Deciding D2D Resource Allocation via Stackelberg Game Guided Multi-Agent Deep Reinforcement Learning"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9219-5516","authenticated-orcid":false,"given":"Dian","family":"Shi","sequence":"first","affiliation":[{"name":"Electrical and Computer Engineering Department, University of Houston, Houston, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3369-3571","authenticated-orcid":false,"given":"Liang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Cyber Engineering, Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3961-1426","authenticated-orcid":false,"given":"Tomoaki","family":"Ohtsuki","sequence":"additional","affiliation":[{"name":"Department of Information and Computer Science, Keio University, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2138-4413","authenticated-orcid":false,"given":"Miao","family":"Pan","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering Department, University of Houston, Houston, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6606-5822","authenticated-orcid":false,"given":"Zhu","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Houston, Houston, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2062-131X","authenticated-orcid":false,"given":"H. Vincent","family":"Poor","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Princeton University, Princeton, NJ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2019.2898944"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2014.2320074"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11586"},{"key":"ref32","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","author":"yang","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6226"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014213"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2867474"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2014.6807945"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2983741"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313433"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2897134"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2008.081002"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1049\/iet-com.2018.6028"},{"key":"ref12","first-page":"134","article-title":"Joint scheduling and resource allocation for device-to-device underlay communication","author":"wang","year":"2013","journal-title":"Proc IEEE Wireless Commun Netw Conf"},{"key":"ref13","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2965856"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2014.2363092"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2812731"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3028242"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11276-019-02176-3"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2016.2547395"},{"key":"ref28","first-page":"322","article-title":"Friend-or-foe Q-learning in general-sum games","author":"littman","year":"2001","journal-title":"Proc 18th Int Conf Mach Learn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.adhoc.2018.09.001"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/DDCLS.2017.8068163"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2931977"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2011.5935039"},{"key":"ref29","first-page":"1021","article-title":"Rational and convergent learning in stochastic games","author":"bowling","year":"2001","journal-title":"Proc 17th Int Joint Conf Artif Intell"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2873344"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2769644"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2876548"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/9781108277402"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933962"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2952354"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3031436"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2018.8377055"},{"key":"ref45","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2936849"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2961405"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2904261"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933973"},{"key":"ref24","first-page":"242","article-title":"Multiagent reinforcement learning: Theoretical framework and an algorithm","author":"hu","year":"1998","journal-title":"Proc 15th Int Conf Mach Learn"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2849755"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2962715"},{"key":"ref44","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":"ref26","first-page":"105","article-title":"Asymmetric multiagent reinforcement learning","volume":"2","author":"k\u00f6n\u00f6nen","year":"2004","journal-title":"Web Intell Agent Syst An Int J"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1162\/089976699300016070"},{"key":"ref25","first-page":"1039","article-title":"Nash Q-learning for general-sum stochastic games","volume":"4","author":"hu","year":"2003","journal-title":"J Mach Learn Res"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7755\/9937059\/9444840-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7755\/9937059\/09444840.pdf?arnumber=9444840","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T19:52:03Z","timestamp":1782330723000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9444840\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,1]]},"references-count":47,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2021.3085206","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,1]]}}}