{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T20:28:07Z","timestamp":1771705687824,"version":"3.50.1"},"reference-count":47,"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":"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":[{"name":"National Key Research and Development Plan","award":["2016YFB0101000"],"award-info":[{"award-number":["2016YFB0101000"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61573353"],"award-info":[{"award-number":["61573353"]}],"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":["61533017"],"award-info":[{"award-number":["61533017"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2019,8]]},"DOI":"10.1109\/tcyb.2018.2830820","type":"journal-article","created":{"date-parts":[[2018,5,16]],"date-time":"2018-05-16T19:01:59Z","timestamp":1526497319000},"page":"2874-2885","source":"Crossref","is-referenced-by-count":109,"title":["Data-Based Reinforcement Learning for Nonzero-Sum Games With Unknown Drift Dynamics"],"prefix":"10.1109","volume":"49","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9747-391X","authenticated-orcid":false,"given":"Qichao","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8218-9633","authenticated-orcid":false,"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2461023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2561300"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2011.2168538"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2013.2295351"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2350835"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2488680"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2014.2300532"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2294968"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2441749"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2421338"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/BF00929443"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582849"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.2307\/1969529"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-017-9548-4"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2317880"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2585520"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2016.2597763"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2653800"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2654324"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2011.03.005"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-014-0300-y"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2017.03.022"},{"key":"ref4","volume":"15","author":"j\u00f8rgensen","year":"2012","journal-title":"Differential Games in Marketing"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2014.7004681"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S1574-0005(05)80055-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2531680"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2424971"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2011.2161577"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.01.076"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2643687"},{"key":"ref2","author":"friedman","year":"2013","journal-title":"Differential Games"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2464080"},{"key":"ref1","author":"morris","year":"2012","journal-title":"Introduction to Game Theory"},{"key":"ref46","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2006.08.010"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2004.11.034"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.03.008"},{"key":"ref47","first-page":"1","article-title":"Q-Prop: Sample-efficient policy gradient with an off-policy critic","author":"gu","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2012.2203336"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2249668"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11768-011-0166-4"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2017.2670463"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"1884","DOI":"10.1109\/TNNLS.2012.2217349","article-title":"Neural network based online simultaneous policy update algorithm for solving the HJI equation in nonlinear \n${H}_\\infty $\n control","volume":"23","author":"wu","year":"2012","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2015.0769"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2010.5718152"},{"key":"ref43","volume":"200","author":"basar","year":"1995","journal-title":"Dynamic Noncooperative Game Theory"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2319577"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/8708695\/08360036.pdf?arnumber=8360036","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:54:01Z","timestamp":1657745641000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8360036\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":47,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2018.2830820","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8]]}}}