{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:10:13Z","timestamp":1772554213336,"version":"3.50.1"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"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":["U1936201"],"award-info":[{"award-number":["U1936201"]}],"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":["62072229"],"award-info":[{"award-number":["62072229"]}],"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":["62071220"],"award-info":[{"award-number":["62071220"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"State Key Laboratory of Air Traffic Management System and Technology","award":["SKLATM202109"],"award-info":[{"award-number":["SKLATM202109"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Wireless Commun."],"published-print":{"date-parts":[[2022,11]]},"DOI":"10.1109\/twc.2022.3170308","type":"journal-article","created":{"date-parts":[[2022,5,6]],"date-time":"2022-05-06T19:51:34Z","timestamp":1651866694000},"page":"8889-8904","source":"Crossref","is-referenced-by-count":20,"title":["A Proactive Eavesdropping Game in MIMO Systems Based on Multiagent Deep Reinforcement Learning"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8725-6804","authenticated-orcid":false,"given":"Delin","family":"Guo","sequence":"first","affiliation":[{"name":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China"}]},{"given":"Hui","family":"Ding","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Air Traffic Management Systems and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1646-8455","authenticated-orcid":false,"given":"Lan","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4181-580X","authenticated-orcid":false,"given":"Xinggan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1474-1806","authenticated-orcid":false,"given":"Lvxi","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2671-5090","authenticated-orcid":false,"given":"Ying-Chang","family":"Liang","sequence":"additional","affiliation":[{"name":"Center for Intelligent Networking and Communications (CINC), University of Electronic Science and Technology of China (UESTC), Chengdu, China"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2837037"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2016.2613860"},{"key":"ref33","article-title":"Deep reinforcement learning from self-play in imperfect-information games","author":"heinrich","year":"2016","journal-title":"arXiv 1603 01121"},{"key":"ref32","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"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2016.2548987"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2015.2419634"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8848100"},{"key":"ref35","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume":"80","author":"haarnoja","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref34","first-page":"805","article-title":"Fictitious self-play in extensive-form games","volume":"37","author":"heinrich","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref60","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref61","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","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":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2785414"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00121-2"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2008.060848"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2011.5751298"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSIPN.2015.2506038"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2016.2645679"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2868900"},{"key":"ref24","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10918"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2856854"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2779508"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref59","year":"2014","journal-title":"The Space of Continuous Functions"},{"key":"ref58","first-page":"129","article-title":"Mixed-policy asynchronous deep Q-learning","author":"sim\u00f5es","year":"2017","journal-title":"Proc Iberian Robot Conf"},{"key":"ref57","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref56","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume":"32","author":"silver","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref55","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume":"70","author":"haarnoja","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1111\/1468-0262.00069"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2048445"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2004.825029"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2863287"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2843285"},{"key":"ref40","first-page":"374","article-title":"Iterative solution of games by fictitious play","volume":"13","author":"brown","year":"1951","journal-title":"Activ Anal Prod Allocat"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2696305"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2700379"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2016.2600519"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2865305"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2012.020712.111298"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2011.060711.101155"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2012.2222386"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2015.2498934"},{"key":"ref4","first-page":"5983","article-title":"Power allocation for artificial-noise secure MIMO precoding systems","volume":"59","author":"tsai","year":"2011","journal-title":"IEEE Trans Signal Process"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2269049"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2883144"},{"key":"ref5","first-page":"1","article-title":"Performance analysis on anti-jamming technique of smart antennas","volume":"2","author":"xu","year":"2011","journal-title":"Commun Syst Inf Technol"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2015.2498610"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2666138"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2010.5757643"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2727045"},{"key":"ref46","first-page":"1","article-title":"Off-policy actor-critic","author":"degris","year":"2012","journal-title":"Proc 29th Int Conf Mach Learn"},{"key":"ref45","first-page":"1","article-title":"Neural fictitious self-play on ELF mini-rts","author":"kawamura","year":"2019","journal-title":"Proc 33rd AAAI Conf Artif Intell"},{"key":"ref48","first-page":"3479","article-title":"Mitigation of loopback self-interference in full-duplex MIMO relays","volume":"62","author":"riihonen","year":"2014","journal-title":"IEEE Trans Signal Process"},{"key":"ref47","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.4310\/CMS.2021.v19.n2.a2"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2930247"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500450"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.geb.2005.08.005"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7693\/9944944\/09770395.pdf?arnumber=9770395","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T19:46:41Z","timestamp":1670874401000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9770395\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11]]},"references-count":61,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/twc.2022.3170308","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11]]}}}