{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T05:02:25Z","timestamp":1773810145823,"version":"3.50.1"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2016,3,1]],"date-time":"2016-03-01T00:00:00Z","timestamp":1456790400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2016,3,1]],"date-time":"2016-03-01T00:00:00Z","timestamp":1456790400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2016,3,1]],"date-time":"2016-03-01T00:00:00Z","timestamp":1456790400000},"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":["61273136"],"award-info":[{"award-number":["61273136"]}],"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":["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"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61304086"],"award-info":[{"award-number":["61304086"]}],"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":[[2016,3]]},"DOI":"10.1109\/tcyb.2015.2488680","type":"journal-article","created":{"date-parts":[[2015,10,26]],"date-time":"2015-10-26T18:50:48Z","timestamp":1445885448000},"page":"854-865","source":"Crossref","is-referenced-by-count":217,"title":["Experience Replay for Optimal Control of Nonzero-Sum Game Systems With Unknown Dynamics"],"prefix":"10.1109","volume":"46","author":[{"given":"Dongbin","family":"Zhao","sequence":"first","affiliation":[{"name":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Qichao","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Ding","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Yuanheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/srep03055"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2014.7004681"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.88.042145"},{"key":"ref34","first-page":"1","article-title":"Reinforcement learning and neural networks for multi-agent nonzero-sum games of nonlinear constrained-input systems","author":"yasini","year":"2014","journal-title":"Int J Mach Learn Cybern"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/16\/3\/033041"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973242"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/srep02470"},{"key":"ref36","volume":"200","author":"basar","year":"1995","journal-title":"Dynamic Noncooperative Game Theory"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2010.5717148"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2011.2106494"},{"key":"ref11","author":"morris","year":"2012","journal-title":"Introduction to Game Theory"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.09.043"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/87.974344"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2276571"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.02.027"},{"key":"ref1","author":"lewis","year":"2013","journal-title":"Reinforcement Learning and Approximate Dynamic Programming for Feedback Control"},{"key":"ref17","author":"engwerda","year":"1995","journal-title":"The Open-Loop Nash Equilibrium in LQ-Games Revisited"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF00929443"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2004.11.034"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1137\/0307013"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2350835"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"916","DOI":"10.1109\/TNNLS.2014.2328590","article-title":"Integral reinforcement learning for continuous-time input-affine nonlinear systems with simultaneous invariant explorations","volume":"26","author":"lee","year":"2015","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2010.5718152"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2014.2348991"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2014.2300532"},{"key":"ref20","author":"friedman","year":"2013","journal-title":"Differential Games"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2012.2203336"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2011.03.005"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2013.2295351"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.1989.4790360"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.03.007"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2281663"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2013.11.055"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2013.2247071"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"988","DOI":"10.1109\/TSMCB.2008.922019","article-title":"Adaptive critic learning techniques for engine torque and air–fuel ratio control","volume":"38","author":"liu","year":"2008","journal-title":"IEEE Trans Syst Man Cybern B Cybern"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2012.09.034"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2011.2122257"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2002.801727"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/7406788\/07307153.pdf?arnumber=7307153","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T21:18:44Z","timestamp":1682630324000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7307153\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":38,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2015.2488680","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,3]]}}}