{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T16:09:15Z","timestamp":1775750955134,"version":"3.50.1"},"reference-count":244,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2018AAA0100203"],"award-info":[{"award-number":["2018AAA0100203"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62073085"],"award-info":[{"award-number":["62073085"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Introducing Innovative and Enterpreneurial Teams of \u201cThe Pearl River Talent Recruitment Program\u201d","award":["2019ZT08X340"],"award-info":[{"award-number":["2019ZT08X340"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2021,1]]},"DOI":"10.1109\/tsmc.2020.3042876","type":"journal-article","created":{"date-parts":[[2020,12,24]],"date-time":"2020-12-24T20:57:16Z","timestamp":1608843436000},"page":"142-160","source":"Crossref","is-referenced-by-count":632,"title":["Adaptive Dynamic Programming for Control: A Survey and Recent Advances"],"prefix":"10.1109","volume":"51","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3715-4778","authenticated-orcid":false,"given":"Derong","family":"Liu","sequence":"first","affiliation":[]},{"given":"Shan","family":"Xue","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7684-7342","authenticated-orcid":false,"given":"Bo","family":"Zhao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3353-2586","authenticated-orcid":false,"given":"Biao","family":"Luo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7002-9800","authenticated-orcid":false,"given":"Qinglai","family":"Wei","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2305841"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2541020"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2401334"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.01.004"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.11.032"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2017.2772162"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2011.2166384"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2890046"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2821369"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.05.049"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2013.2280974"},{"key":"ref39","doi-asserted-by":"crossref","DOI":"10.1002\/9780470182963","author":"powell","year":"2007","journal-title":"Approximate Dynamic Programming Solving the Curses of Dimensionality"},{"key":"ref38","article-title":"ADP: Goals, opportunities and principles","author":"werbos","year":"2004","journal-title":"Handbook of Learning and Approximate Dynamic Programming"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1960.1105018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2017.03.022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2592682"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/49.824797"},{"key":"ref37","first-page":"847","article-title":"Suboptimal control of nonlinear stochastic systems","volume":"10","author":"saridis","year":"1994","journal-title":"Control Theory Adv Technol"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1992.371109"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1137\/0305004"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1965.1098127"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2011.2172628"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2011.03.058"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.02.015"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2012.07.047"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2017.2698413"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2358227"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2585520"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2013.09.069"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2013.2284545"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.03.008"},{"key":"ref28","first-page":"21","article-title":"A neural dynamic programming approach for learning control of failure avoidance problems","volume":"10","author":"liu","year":"2005","journal-title":"Int J Intell Control Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1049\/ip-cta:20041119"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2384016"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/3468.823480"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.1080.0305"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1995.478953"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/nature14540"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/9780470544785"},{"key":"ref25","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2563982"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2011.05.031"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2898370"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2899594"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2548662"},{"key":"ref155","first-page":"2085","article-title":"Adaptive and optimal output feedback control of linear systems: An adaptive dynamic programming approach","author":"gao","year":"2014","journal-title":"Proc 11th World Congr Intell Control Autom"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2586303"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2017.2774602"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2017.2698377"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2453320"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.3587"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2523878"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2016.2597763"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2236354"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.02.005"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/72.914523"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2548941"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.04.092"},{"key":"ref54","doi-asserted-by":"crossref","first-page":"2038","DOI":"10.1109\/TNNLS.2013.2271454","article-title":"Goal representation heuristic dynamic programming on maze navigation","volume":"24","author":"ni","year":"2013","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2490698"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2247627"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368190"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2761718"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.04.008"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2014.1325"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2905215"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2317301"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2014.2322778"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2850520"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.06.096"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1049\/ree.1976.0044"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.23.11.1248"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2002.801727"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(94)00011-O"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.18.5.265"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2014.0186"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0037-6_19"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2542923"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2019.108549"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1987.289329"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.2013.790562"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.1989.4790360"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.01.020"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2014.2361485"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2322116"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.924139"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2013.04.006"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2015.2505327"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.10.056"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2281663"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.1760"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2008.08.017"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.926614"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2402203"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2606479"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2017.2690665"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2492242"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.06.059"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2015.2414811"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2009.932261"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2016.7510262"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref64","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1109\/MCS.2012.2214134","article-title":"Reinforcement learning and feedback control: Using natural decision methods to design optimal adaptive controllers","volume":"32","author":"lewis","year":"2012","journal-title":"IEEE Control Syst Mag"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2712188"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-017-9548-4"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-4757-2"},{"key":"ref68","author":"lewis","year":"2013","journal-title":"Reinforcement Learning and Approximate Dynamic Programming for Feedback Control"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50815-3"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2012.2186716"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2011.03.005"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2013.2295351"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/9.256331"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/9.159566"},{"key":"ref195","author":"ba?ar","year":"1995","journal-title":"H? optimal control and related minimax design problems"},{"key":"ref196","author":"burl","year":"1998","journal-title":"Linear Optimal Control H2 and H? Method"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2354377"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2011.0783"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.07.001"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2661865"},{"key":"ref191","author":"ba?ar","year":"1982","journal-title":"Dynamic Noncooperative Game Theory"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2417510"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2362334"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2623859"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2017.2771516"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.12.009"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-014-1533-0"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2017.05.005"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2623766"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2593743"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2006.878720"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2755501"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2586082"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2421338"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1049\/ip-cta:20050094"},{"key":"ref86","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1109\/TSMCB.2012.2216523","article-title":"Finite-approximation-error-based optimal control approach for discrete-time nonlinear systems","volume":"43","author":"liu","year":"2013","journal-title":"IEEE Trans Cybern"},{"key":"ref87","first-page":"2794","article-title":"Policy approximation in policy iteration approximate dynamic programming for discrete-time nonlinear systems","volume":"29","author":"guo","year":"2018","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.3018"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2014.7004681"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2012.03.004"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2898389"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(88)90013-1"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1080\/00207721.2019.1599463"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1049\/el.2016.4756"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2015.08.017"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-018-9602-1"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2019.01.025"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2007.904544"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2810117"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2018.8628851"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.07.082"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2280013"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.06.020"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2837899"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.05.005"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-014-1534-z"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1080\/00207721.2020.1803439"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1007\/s11071-014-1347-8"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.12.063"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.09.029"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1080\/00207721.2017.1296982"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-016-0711-5"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.10.058"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2819695"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2788819"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.12.079"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2492941"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2011.2160968"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2019.2914571"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.2018.1466059"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2477810"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.05.017"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1142\/S2301385016400069"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2015.08.007"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2761841"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582849"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2618926"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2010.5717148"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.03.007"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2832025"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2319577"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.2997559"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3009015"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.07.016"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2852810"},{"key":"ref239","first-page":"1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2638863"},{"key":"ref234","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1109\/MCS.2016.2621461","article-title":"Game theory-based control system algorithms with real-time reinforcement learning: How to solve multiplayer games online","volume":"37","author":"vamvoudakis","year":"2017","journal-title":"IEEE Control Syst Mag"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2818878"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2751018"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2488680"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(90)90005-6"},{"key":"ref137","author":"\u00e5str\u00f6m","year":"2013","journal-title":"Adaptive Control"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2954983"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2006.08.010"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.09.019"},{"key":"ref142","author":"khalil","year":"1996","journal-title":"Nonlinear Systems"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2642128"},{"key":"ref2","article-title":"Adaptive dynamic programming and inventory control","author":"papachristos","year":"1977"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2007.904277"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2307\/1885258"},{"key":"ref145","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1109\/JAS.2014.7004686","article-title":"Event-triggered optimal adaptive control algorithm for continuous-time nonlinear systems","volume":"1","author":"vamvoudakis","year":"2014","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2016.2614675"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2965208"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2076370"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.02.027"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927869"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2012.07.006"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.09.043"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2869462"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.09.097"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2771256"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2357896"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2251747"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2013.0472"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.2013.848292"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2276571"},{"key":"ref10","first-page":"25","article-title":"Advanced forecasting methods for global crisis warning and models of intelligence","volume":"22","author":"werbos","year":"1977","journal-title":"Gen Syst Yearbook"},{"key":"ref11","article-title":"A menu of designs for reinforcement learning over time","author":"werbos","year":"1990","journal-title":"Neural Networks for Control"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(90)90088-3"},{"key":"ref13","article-title":"Approximate dynamic programming for real-time control and neural modeling","author":"werbos","year":"1992","journal-title":"Handbook of Intelligent Control Neural Fuzzy and Adaptive Approaches"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(95)00042-9"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/72.623201"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2016.12.016"},{"key":"ref17","article-title":"Reinforcement learning and adaptive critic methods","author":"barto","year":"1992","journal-title":"Handbook of Intelligent Control Neural Fuzzy and Adaptive Approaches"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2015.1105"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref19","article-title":"Learning from delayed rewards","author":"watkins","year":"1989"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.10.041"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-014-0300-y"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.05.011"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2914160"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2853091"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1007\/s11071-018-4309-8"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2946857"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2020.1003225"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2441749"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221021\/9321226\/09306903.pdf?arnumber=9306903","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:15Z","timestamp":1652194395000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9306903\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":244,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2020.3042876","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1]]}}}