{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T03:42:14Z","timestamp":1773373334231,"version":"3.50.1"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2017,3,1]],"date-time":"2017-03-01T00:00:00Z","timestamp":1488326400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"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\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["Z141101001814094"],"award-info":[{"award-number":["Z141101001814094"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013148","name":"Science and Technology Foundation of State Grid Corporation of China","doi-asserted-by":"crossref","award":["DG71-14-032"],"award-info":[{"award-number":["DG71-14-032"]}],"id":[{"id":"10.13039\/501100013148","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2017,3]]},"DOI":"10.1109\/tnnls.2016.2561300","type":"journal-article","created":{"date-parts":[[2016,5,27]],"date-time":"2016-05-27T14:16:23Z","timestamp":1464358583000},"page":"714-725","source":"Crossref","is-referenced-by-count":115,"title":["Iterative Adaptive Dynamic Programming for Solving Unknown Nonlinear Zero-Sum Game Based on Online Data"],"prefix":"10.1109","volume":"28","author":[{"given":"Yuanheng","family":"Zhu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8218-9633","authenticated-orcid":false,"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Xiangjun","family":"Li","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1109\/TNNLS.2013.2281663","article-title":"Policy iteration adaptive dynamic programming algorithm for discrete-time nonlinear systems","volume":"25","author":"liu","year":"2014","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.926614"},{"key":"ref33","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2313915"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2012.11.021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2006.09.019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2004.11.034"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2015.0769"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2371046"},{"key":"ref34","author":"busoniu","year":"2010","journal-title":"Reinforcement Learning and Dynamic Programming Using Function Approximators"},{"key":"ref60","article-title":"Constrained nonlinear optimal control: A converse HJB approach","author":"nevisti?","year":"1996"},{"key":"ref62","first-page":"503","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"ernst","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2236354"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1002\/acs.2485"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.2814"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2006.880135"},{"key":"ref2","author":"bertsekas","year":"1995","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref1","author":"lewis","year":"1995","journal-title":"Optimal Control"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2006.884959"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.10.033"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2000204"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.1760"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2010.5717676"},{"key":"ref26","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 $H_{\\infty }$ control","volume":"23","author":"wu","year":"2012","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.02.018"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11768-011-0166-4"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2014.2300532"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719468"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1137\/050624935"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(90)90005-6"},{"key":"ref55","author":"finlayson","year":"1990","journal-title":"The Method of Weighted Residuals and Variational Principles"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.2307\/2316909"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/BF02547750"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2441749"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1080\/002071798221542"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2196708"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"1556","DOI":"10.1016\/j.automatica.2011.03.005","article-title":"Multi-player non-zero-sum games: Online adaptive learning solution of coupled Hamilton–Jacobi equations","volume":"47","author":"vamvoudakis","year":"2011","journal-title":"Automatica"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2014.2348991"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2305841"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2354377"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2329942"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2009.932261"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1002\/9780470182963"},{"key":"ref19","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/9.376058"},{"key":"ref3","author":"zhou","year":"1996","journal-title":"Robust and Optimal Control"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1007\/978-93-86279-17-0","author":"tijs","year":"2003","journal-title":"Introduction to Game Theory"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1007\/3-540-76074-1","author":"van der schaft","year":"1996","journal-title":"$L_ 2 $ -gain and passivity techniques in nonlinear control"},{"key":"ref8","author":"basar","year":"1999","journal-title":"Dynamic Noncooperative Game Theory"},{"key":"ref7","author":"ba?ar","year":"1995","journal-title":"$H^\\infty$ -Optimal Control and Related Minimax Design Problems"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejcon.2013.05.017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.2514\/3.21495"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2013.2295351"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2276571"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2012.6426987"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.05.049"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2488680"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2012.2203336"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-014-0085-5"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2011.6160778"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/7857118\/07480425.pdf?arnumber=7480425","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:38:40Z","timestamp":1641987520000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7480425\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3]]},"references-count":62,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2016.2561300","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,3]]}}}