{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:29:01Z","timestamp":1783700941617,"version":"3.55.0"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2014,12,1]],"date-time":"2014-12-01T00:00:00Z","timestamp":1417392000000},"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":["61034005"],"award-info":[{"award-number":["61034005"]}],"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":["61104010"],"award-info":[{"award-number":["61104010"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National High Technology Research and Development Program of China","award":["2012AA040104"],"award-info":[{"award-number":["2012AA040104"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/tcyb.2014.2313915","type":"journal-article","created":{"date-parts":[[2014,7,28]],"date-time":"2014-07-28T18:28:34Z","timestamp":1406572114000},"page":"2706-2718","source":"Crossref","is-referenced-by-count":226,"title":["Online Adaptive Policy Learning Algorithm for $H_{\\infty }$  State Feedback Control of Unknown Affine Nonlinear Discrete-Time Systems"],"prefix":"10.1109","volume":"44","author":[{"given":"Huaguang","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunbin","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanhong","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2000204"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.10.033"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.02.018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2008.08.017"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1016\/j.automatica.2004.11.034","article-title":"Nearly optimal control laws for nonlinear systems with saturating actuators using a neural network HJB approach","volume":"41","author":"abu-khalaf","year":"2005","journal-title":"Automatica"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2002.801727"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2010.5717676"},{"key":"ref36","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":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2234133"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.automatica.2012.09.019","article-title":"A novel actor-critic-identifier architecture for approximate optimal control of uncertain nonlinear systems","volume":"49","author":"bhasin","year":"2013","journal-title":"Automatica"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2011.03.058"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2012.01.025"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2196708"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/9.489271"},{"key":"ref1","author":"zhou","year":"1997","journal-title":"Essentials of Robust Control"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2009.932261"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.926614"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2009.2027233"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MED.2009.5164741"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.920269"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2076370"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2009.5399697"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2012.11.021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2012.2227253"},{"key":"ref57","author":"lewis","year":"1999","journal-title":"Neural Network Control of Robot Manipulators and Nonlinear Systems"},{"key":"ref56","author":"khalil","year":"2002","journal-title":"Nonlinear System"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1002\/0471459100"},{"key":"ref54","author":"jagannathan","year":"2006","journal-title":"Neuarl Network Control of Nonlinear Discrete-Time Systems"},{"key":"ref53","first-page":"1","article-title":"Viscosity solutions of Hamilton–Jacobi equations arising in nonlinear \\(H_{\\infty }\\) -control","volume":"6","author":"ball","year":"1996","journal-title":"J Math Syst Estimat Control"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-4755-1"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1109\/TSMCB.2012.2185842","article-title":"\\(H_{\\infty }\\) state estimation for discrete-time chaotic systems based on a unified model","volume":"42","author":"liu","year":"2012","journal-title":"IEEE Trans Syst Man Cybern B Cybern"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.1760"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2011.2165729"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1080\/002071798221542","article-title":"Successive Galerkin approximation algorithms for nonlinear optimal and robust control","volume":"71","author":"beard","year":"1998","journal-title":"Int J Control"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2006.884959"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2006108"},{"key":"ref15","first-page":"493","article-title":"Approximate dynamic programming for real-time control and neural modeling","author":"werbos","year":"1992","journal-title":"Handbook of Intelligent Control"},{"key":"ref16","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/72.623201"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1002\/9780470182963"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/9.256331"},{"key":"ref3","author":"basar","year":"1995","journal-title":"\\( H _ \\infty \\) Optimal Conrol and Related Minimax Design Problems A Dynamic Game Approach"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2009.2037009"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF00276493"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/002071799221398"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.2514\/3.21495"},{"key":"ref49","first-page":"3056","article-title":"\\(H_{\\infty }\\) control of unknown discrete-time nonlinear systems with control constraints using adaptive dynamic programming","author":"liu","year":"2012","journal-title":"Proc IEEE World Congr Comput Intell"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.927267"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.05.002"},{"key":"ref45","first-page":"682","article-title":"Model-free Q-learning designs for linear discrete-time zero-sum games with application to H-infinity control","volume":"43","author":"al-tamimi","year":"2010","journal-title":"Automatica"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596761"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2011.5967351"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2012.08.012"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11768-011-0166-4"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3724\/SP.J.1004.2009.00682"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2006.880135"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/6936410\/06866861.pdf?arnumber=6866861","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:00:35Z","timestamp":1642003235000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6866861\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":57,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2014.2313915","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,12]]}}}