{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T04:31:19Z","timestamp":1775017879995,"version":"3.50.1"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2017,5,1]],"date-time":"2017-05-01T00:00:00Z","timestamp":1493596800000},"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":["61433004"],"award-info":[{"award-number":["61433004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"IAPI Fundamental Research Funds","award":["2013ZCX14"],"award-info":[{"award-number":["2013ZCX14"]}]},{"name":"Development Project of Key Laboratory of Liaoning province"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Ind. Electron."],"published-print":{"date-parts":[[2017,5]]},"DOI":"10.1109\/tie.2016.2542134","type":"journal-article","created":{"date-parts":[[2016,3,15]],"date-time":"2016-03-15T18:16:00Z","timestamp":1458065760000},"page":"4091-4100","source":"Crossref","is-referenced-by-count":386,"title":["Data-Driven Optimal Consensus Control for Discrete-Time Multi-Agent Systems With Unknown Dynamics Using Reinforcement Learning Method"],"prefix":"10.1109","volume":"64","author":[{"given":"Huaguang","family":"Zhang","sequence":"first","affiliation":[]},{"given":"He","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Yanhong","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Geyang","family":"Xiao","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2013.6760804"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.05.074"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2006.884959"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2013.2257806"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"2173","DOI":"10.1109\/TNN.2011.2176141","article-title":"Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems","volume":"22","author":"hou","year":"2011","journal-title":"IEEE Trans Neural Netw"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"1136","DOI":"10.23919\/ACC.1989.4790360","article-title":"neural network control of unknown nonlinear systems","author":"li","year":"1989","journal-title":"1989 American Control Conference ACC"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2350511"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2012.2203336"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2012.11.021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.1760"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2010.2090575"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2305841"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.06.014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2004.834433"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2012.2219061"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.920269"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2358227"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2011.03.058"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2441749"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.05.011"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2013.06.037"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3724\/SP.J.1004.2010.00121"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.02.005"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2015.06.001"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2014.2310238"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.09.043"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11768-015-3203-x"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2014.2301770"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2014.2388198"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2014.2303139"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2004.11.034"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2009.2027233"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2276571"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2004.834113"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2012.2215715"},{"key":"ref6","first-page":"1859","article-title":"A survey of consensus problems in multi-agent coordination","volume":"3","author":"ren","year":"0","journal-title":"Proc Amer Control Conf"},{"key":"ref5","author":"lesser","year":"2012","journal-title":"Distributed Sensor Networks A Multiagent Perspective"},{"key":"ref8","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":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2013.2273480"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/72.914523"},{"key":"ref46","doi-asserted-by":"crossref","DOI":"10.1007\/978-93-86279-17-0","author":"tijs","year":"2003","journal-title":"Introduction to Game Thoery"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2009.2014057"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.02.018"},{"key":"ref47","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":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.10.047"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2015.04.044"},{"key":"ref44","author":"vrabie","year":"2013","journal-title":"Optimal Adaptive Control and Differential Games by Reinforcement Learning Principles"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2013.6580483"}],"container-title":["IEEE Transactions on Industrial Electronics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/41\/7895231\/07434032.pdf?arnumber=7434032","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:20:28Z","timestamp":1642004428000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7434032\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5]]},"references-count":49,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tie.2016.2542134","relation":{},"ISSN":["0278-0046","1557-9948"],"issn-type":[{"value":"0278-0046","type":"print"},{"value":"1557-9948","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,5]]}}}