{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:56:27Z","timestamp":1771959387741,"version":"3.50.1"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,8,7]],"date-time":"2021-08-07T00:00:00Z","timestamp":1628294400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,8,7]],"date-time":"2021-08-07T00:00:00Z","timestamp":1628294400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61803371"],"award-info":[{"award-number":["61803371"]}],"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":["61903028"],"award-info":[{"award-number":["61903028"]}],"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":["61973330"],"award-info":[{"award-number":["61973330"]}],"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":["61773075"],"award-info":[{"award-number":["61773075"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"beijing natural science foundation","award":["4212038"],"award-info":[{"award-number":["4212038"]}]},{"name":"open research project of the state key laboratory of management and control for complex systems","award":["20210108"],"award-info":[{"award-number":["20210108"]}]},{"name":"open research project of the state key laboratory of industrial control technology","award":["ICT2021B48"],"award-info":[{"award-number":["ICT2021B48"]}]},{"DOI":"10.13039\/501100012226","name":"fundamental research funds for the central universities","doi-asserted-by":"publisher","award":["2019NTST25"],"award-info":[{"award-number":["2019NTST25"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011248","name":"state key laboratory of synthetical automation for process industries","doi-asserted-by":"publisher","award":["2019-KF-23-03"],"award-info":[{"award-number":["2019-KF-23-03"]}],"id":[{"id":"10.13039\/501100011248","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Intell Rev"],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1007\/s10462-021-10045-9","type":"journal-article","created":{"date-parts":[[2021,8,7]],"date-time":"2021-08-07T05:03:18Z","timestamp":1628312598000},"page":"23-58","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["Sparse online kernelized actor-critic Learning in reproducing kernel Hilbert space"],"prefix":"10.1007","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3144-8604","authenticated-orcid":false,"given":"Yongliang","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1031-9475","authenticated-orcid":false,"given":"Hufei","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9747-391X","authenticated-orcid":false,"given":"Qichao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7684-7342","authenticated-orcid":false,"given":"Bo","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0877-6829","authenticated-orcid":false,"given":"Zhenning","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9726-9051","authenticated-orcid":false,"given":"Donald C.","family":"Wunsch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,8,7]]},"reference":[{"key":"10045_CR35","volume-title":"Optimal control: linear quadratic methods","author":"BD Anderson","year":"2007","unstructured":"Anderson BD, Moore JB (2007) Optimal control: linear quadratic methods. Courier Corporation, HH"},{"issue":"3731","key":"10045_CR32","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1126\/science.153.3731.34","volume":"153","author":"R Bellman","year":"1966","unstructured":"Bellman R (1966) Dynamic programming. Science 153(3731):34\u201337","journal-title":"Science"},{"key":"10045_CR44","volume-title":"Reproducing kernel Hilbert spaces in probability and statistics","author":"A Berlinet","year":"2011","unstructured":"Berlinet A, Thomas-Agnan C (2011) Reproducing kernel Hilbert spaces in probability and statistics. Springer Science & Business Media, Berlin"},{"key":"10045_CR2","volume-title":"Pattern recognition and machine learning","author":"CM Bishop","year":"2006","unstructured":"Bishop CM (2006) Pattern recognition and machine learning. Springer, Berlin"},{"key":"10045_CR51","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511804441","volume-title":"Convex optimization","author":"S Boyd","year":"2004","unstructured":"Boyd S, Boyd SP, Vandenberghe L (2004) Convex optimization. Cambridge University Press, Cambridge"},{"issue":"3","key":"10045_CR11","first-page":"273","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes C, Vapnik V (1995) Support-vector networks. Mach learn 20(3):273\u2013297","journal-title":"Mach learn"},{"issue":"5","key":"10045_CR8","first-page":"2135","volume":"36","author":"P Hall","year":"2008","unstructured":"Hall P, Park BU, Samworth RJ et al (2008) Choice of neighbor order in nearest-neighbor classification. Annals Stat 36(5):2135\u20132152","journal-title":"Annals Stat"},{"key":"10045_CR3","doi-asserted-by":"crossref","unstructured":"H\u00e4rdle W, Simar L (2015) \u201cApplied multivariate statistical analysis course,\u201d","DOI":"10.1007\/978-3-662-45171-7"},{"key":"10045_CR4","unstructured":"Haykin SS (2009) \u201cNeural networks and learning machines,\u201d"},{"key":"10045_CR14","volume-title":"Robust adaptive control","author":"PA Ioannou","year":"2012","unstructured":"Ioannou PA, Sun J (2012) Robust adaptive control. Courier Corporation, HH"},{"issue":"11","key":"10045_CR41","doi-asserted-by":"crossref","first-page":"2917","DOI":"10.1109\/TAC.2015.2414811","volume":"60","author":"Y Jiang","year":"2015","unstructured":"Jiang Y, Jiang Z-P (2015) Global adaptive dynamic programming for continuous-time nonlinear systems. IEEE Trans Autom Control 60(11):2917\u20132929","journal-title":"IEEE Trans Autom Control"},{"key":"10045_CR15","volume-title":"Nonlinear systems","author":"HK Khalil","year":"2002","unstructured":"Khalil HK, Grizzle JW (2002) Nonlinear systems. Prentice hall Upper Saddle River, NJ"},{"issue":"7","key":"10045_CR46","doi-asserted-by":"crossref","first-page":"1130","DOI":"10.1109\/TNNLS.2012.2198889","volume":"23","author":"HA Kingravi","year":"2012","unstructured":"Kingravi HA, Chowdhary G, Vela PA, Johnson EN (2012) Reproducing kernel Hilbert space approach for the online update of radial bases in neuro-adaptive control. IEEE Trans Neural Netw Learn Syst 23(7):1130\u20131141","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"10045_CR12","volume-title":"Nonlinear and adaptive control design","author":"M Krstic","year":"1995","unstructured":"Krstic M, Kokotovic PV, Kanellakopoulos I (1995) Nonlinear and adaptive control design. John Wiley & Sons Inc, Hoboken"},{"key":"10045_CR49","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781139176224","volume-title":"Kernel methods and machine learning","author":"SY Kung","year":"2014","unstructured":"Kung SY (2014) Kernel methods and machine learning. Cambridge University Press, Cambridge"},{"key":"10045_CR42","volume-title":"Reinforcement learning and approximate dynamic programming for feedback control","author":"FL Lewis","year":"2013","unstructured":"Lewis FL, Liu D (2013) Reinforcement learning and approximate dynamic programming for feedback control. John Wiley & Sons, Hoboken"},{"key":"10045_CR16","volume-title":"Neural network control of robot manipulators and nonlinear systems","author":"FL Lewis","year":"1998","unstructured":"Lewis FL, Yesildirak A, Jagannathan S (1998) Neural network control of robot manipulators and nonlinear systems. Taylor & Francis Inc, USA"},{"key":"10045_CR36","doi-asserted-by":"crossref","DOI":"10.1002\/9781118122631","volume-title":"Optimal control","author":"FL Lewis","year":"2012","unstructured":"Lewis FL, Vrabie D, Syrmos VL (2012) Optimal control. John Wiley & Sons, Hoboken"},{"issue":"11","key":"10045_CR26","doi-asserted-by":"crossref","first-page":"3972","DOI":"10.1109\/TSMC.2019.2907991","volume":"50","author":"M Liang","year":"2020","unstructured":"Liang M, Wang D, Liu D (2020) Neuro-optimal control for discrete stochastic processes via a novel policy iteration algorithm. IEEE Trans Syst Man Cybern Syst 50(11):3972\u20133985","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"10045_CR34","doi-asserted-by":"crossref","DOI":"10.2307\/j.ctvcm4g0s","volume-title":"Calculus of variations and optimal control theory","author":"D Liberzon","year":"2011","unstructured":"Liberzon D (2011) Calculus of variations and optimal control theory. Princeton university press, Princeton, NJ, USA"},{"issue":"4","key":"10045_CR28","doi-asserted-by":"crossref","first-page":"954","DOI":"10.1109\/JAS.2020.1003225","volume":"7","author":"H Lin","year":"2020","unstructured":"Lin H, Zhao B, Liu D, Alippi C (2020) Data-based fault tolerant control for affine nonlinear systems through particle swarm optimized neural networks. IEEE\/CAA J Automatica Sinica 7(4):954\u2013964","journal-title":"IEEE\/CAA J Automatica Sinica"},{"issue":"3","key":"10045_CR38","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1109\/TNNLS.2013.2281663","volume":"25","author":"D Liu","year":"2014","unstructured":"Liu D, Wei Q (2014) Policy iteration adaptive dynamic programming algorithm for discrete-time nonlinear systems. IEEE Trans Neural Netw Learn Syst 25(3):621\u2013634","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"12","key":"10045_CR39","doi-asserted-by":"crossref","first-page":"2834","DOI":"10.1109\/TCYB.2014.2357896","volume":"44","author":"D Liu","year":"2014","unstructured":"Liu D, Wang D, Wang F, Li H, Yang X (2014) Neural-network-based online hjb solution for optimal robust guaranteed cost control of continuous-time uncertain nonlinear systems. IEEE Trans Cybern 44(12):2834\u20132847","journal-title":"IEEE Trans Cybern"},{"issue":"1","key":"10045_CR18","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1109\/TSMC.2020.3042876","volume":"51","author":"D Liu","year":"2021","unstructured":"Liu D, Xue S, Zhao B, Luo B, Wei Q (2021) Adaptive dynamic programming for control: a survey and recent advances. IEEE Trans Syst Man Cybern Syst 51(1):142\u2013160","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"10045_CR45","doi-asserted-by":"crossref","unstructured":"Nguyen-Tuong D, Sch\u00f6lkopf B, Peters J (2009) \u201cSparse online model learning for robot control with support vector regression,\u201d in 2009 IEEE\/RSJ International Conference on Intelligent Robots and Systems. IEEE, pp. 3121\u20133126","DOI":"10.1109\/IROS.2009.5354609"},{"key":"10045_CR43","doi-asserted-by":"crossref","unstructured":"Poggio T, Girosi F (1990) Networks for approximation and learning. Proceedings of the IEEE 78(9):1481\u20131497","DOI":"10.1109\/5.58326"},{"key":"10045_CR40","doi-asserted-by":"crossref","unstructured":"Prajna S, Papachristodoulou A, Parrilo PA (2002) \u201cIntroducing sostools: A general purpose sum of squares programming solver,\u201d in Proceedings of the 41st IEEE Conference on Decision and Control, 2002., vol.\u00a01. IEEE, pp. 741\u2013746","DOI":"10.1109\/CDC.2002.1184594"},{"key":"10045_CR1","volume-title":"Artificial intelligence: a modern approach","author":"S Russell","year":"2002","unstructured":"Russell S, Norvig P (2002) Artificial intelligence: a modern approach. Prentice Hall, Upper Saddle River, New Jersey, USA"},{"key":"10045_CR17","doi-asserted-by":"crossref","DOI":"10.1201\/9781420015454","volume-title":"Neural network control of nonlinear discrete-time systems","author":"J Sarangapani","year":"2018","unstructured":"Sarangapani J (2018) Neural network control of nonlinear discrete-time systems. CRC Press, Cambridge"},{"key":"10045_CR37","volume-title":"Constructive nonlinear control","author":"R Sepulchre","year":"2012","unstructured":"Sepulchre R, Jankovic M, Kokotovic PV (2012) Constructive nonlinear control. Springer Science & Business Media, HH"},{"key":"10045_CR33","doi-asserted-by":"crossref","unstructured":"Speyer JL, Jacobson DH (2010) Primer on optimal control theory. SIAM","DOI":"10.1137\/1.9780898718560"},{"key":"10045_CR13","volume-title":"Adaptive control of systems with actuator and sensor nonlinearities","author":"G Tao","year":"1996","unstructured":"Tao G, Kokotovic PV (1996) Adaptive control of systems with actuator and sensor nonlinearities. John Wiley & Sons Inc, Hoboken"},{"issue":"5","key":"10045_CR48","doi-asserted-by":"crossref","first-page":"878","DOI":"10.1016\/j.automatica.2010.02.018","volume":"46","author":"KG Vamvoudakis","year":"2010","unstructured":"Vamvoudakis KG, Lewis FL (2010) Online actor-critic algorithm to solve the continuous-time infinite horizon optimal control problem. Automatica 46(5):878\u2013888","journal-title":"Automatica"},{"issue":"8","key":"10045_CR20","doi-asserted-by":"crossref","first-page":"1598","DOI":"10.1016\/j.automatica.2012.05.074","volume":"48","author":"KG Vamvoudakis","year":"2012","unstructured":"Vamvoudakis KG, Lewis FL, Hudas GR (2012) Multi-agent differential graphical games: Online adaptive learning solution for synchronization with optimality. Automatica 48(8):1598\u20131611","journal-title":"Automatica"},{"issue":"2","key":"10045_CR50","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1109\/MCI.2009.932261","volume":"4","author":"F-Y Wang","year":"2009","unstructured":"Wang F-Y, Zhang H, Liu D (2009) Adaptive dynamic programming: an introduction. IEEE Comput Intell Magazine 4(2):39\u201347","journal-title":"IEEE Comput Intell Magazine"},{"issue":"11","key":"10045_CR47","doi-asserted-by":"crossref","first-page":"1804","DOI":"10.1109\/TNN.2010.2073719","volume":"21","author":"M Wang","year":"2010","unstructured":"Wang M, Ge SS, Hong K (2010) Approximation-based adaptive tracking control of pure-feedback nonlinear systems with multiple unknown time-varying delays. IEEE Trans Neural Netw 21(11):1804\u20131816","journal-title":"IEEE Trans Neural Netw"},{"issue":"1","key":"10045_CR10","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1145\/507338.507355","volume":"31","author":"IH Witten","year":"2002","unstructured":"Witten IH, Frank E (2002) Data mining: practical machine learning tools and techniques with java implementations. Acm Sigmod Record 31(1):76\u201377","journal-title":"Acm Sigmod Record"},{"issue":"1","key":"10045_CR9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10115-007-0114-2","volume":"14","author":"X Wu","year":"2008","unstructured":"Wu X, Kumar V, Quinlan JR, Ghosh J, Yang Q, Motoda H, McLachlan GJ, Ng A, Liu B, Philip SY et al (2008) Top 10 algorithms in data mining. Knowledge Inform Syst 14(1):1\u201337","journal-title":"Knowledge Inform Syst"},{"issue":"9","key":"10045_CR56","doi-asserted-by":"crossref","first-page":"3189","DOI":"10.1109\/TSMC.2018.2852810","volume":"50","author":"S Xue","year":"2020","unstructured":"Xue S, Luo B, Liu D (2020a) Event-triggered adaptive dynamic programming for zero-sum game of partially unknown continuous-time nonlinear systems. IEEE Trans Syst Man Cybern Syst 50(9):3189\u20133199","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"10045_CR53","doi-asserted-by":"publisher","unstructured":"Xue S, Luo B, Liu D, Yang Y (2020b) Constrained event-triggered H$$_\\infty $$ control based on adaptive dynamic programming with concurrent learning. In: IEEE Transactions on Systems, Man, and Cybernetics: Systems. https:\/\/doi.org\/10.1109\/TSMC.2020.2997559","DOI":"10.1109\/TSMC.2020.2997559"},{"key":"10045_CR7","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2020.3021714","author":"Y Yang","year":"2020","unstructured":"Yang Y, Xu C-Z (2020) Adaptive fuzzy leader-follower synchronization of constrained heterogeneous multiagent systems. IEEE Trans Fuzzy Syst. https:\/\/doi.org\/10.1109\/TFUZZ.2020.3021714","journal-title":"IEEE Trans Fuzzy Syst"},{"issue":"8","key":"10045_CR22","doi-asserted-by":"crossref","first-page":"1929","DOI":"10.1109\/TNNLS.2017.2654324","volume":"28","author":"Y Yang","year":"2017","unstructured":"Yang Y, Wunsch D, Yin Y (2017) Hamiltonian-driven adaptive dynamic programming for continuous nonlinear dynamical systems. IEEE Trans Neural Netw Learn Syst 28(8):1929\u20131940","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"6","key":"10045_CR21","doi-asserted-by":"crossref","first-page":"2139","DOI":"10.1109\/TNNLS.2018.2803059","volume":"29","author":"Y Yang","year":"2018","unstructured":"Yang Y, Modares H, Wunsch DC, Yin Y (2018) Leader-follower output synchronization of linear heterogeneous systems with active leader using reinforcement learning. IEEE Trans Neural Netw Learn Syst 29(6):2139\u20132153","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"3","key":"10045_CR19","doi-asserted-by":"crossref","first-page":"1228","DOI":"10.1109\/TCST.2018.2794336","volume":"27","author":"Y Yang","year":"2019","unstructured":"Yang Y, Modares H, Wunsch DC, Yin Y (2019) Optimal containment control of unknown heterogeneous systems with active leaders. IEEE Trans Control Syst Technol 27(3):1228\u20131236","journal-title":"IEEE Trans Control Syst Technol"},{"issue":"6","key":"10045_CR25","doi-asserted-by":"crossref","first-page":"3316","DOI":"10.1016\/j.jfranklin.2019.12.017","volume":"357","author":"Y Yang","year":"2020","unstructured":"Yang Y, Ding D-W, Xiong H, Yin Y, Wunsch DC (2020a) Online barrier-actor-critic learning for H$$_\\infty $$ control with full-state constraints and input saturation. J Franklin Inst 357(6):3316\u20133344","journal-title":"J Franklin Inst"},{"issue":"12","key":"10045_CR31","doi-asserted-by":"crossref","first-page":"5441","DOI":"10.1109\/TNNLS.2020.2967871","volume":"31","author":"Y Yang","year":"2020","unstructured":"Yang Y, Vamvoudakis KG, Modares H, Yin Y, Wunsch DC (2020b) Safe intermittent reinforcement learning with static and dynamic event generators. IEEE Trans Neural Netw Learn Syst 31(12):5441\u20135455","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"10045_CR54","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2962103","author":"Y Yang","year":"2020","unstructured":"Yang Y, Vamvoudakis KG, Modares H, Yin Y, Wunsch DC (2020c) Hamiltonian-driven hybrid adaptive dynamic programming. IEEE Trans Syst Man Cybern Syst. https:\/\/doi.org\/10.1109\/TSMC.2019.2962103","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"10045_CR6","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2021.3075501","author":"Y Yang","year":"2021","unstructured":"Yang Y, Gao W, Modares H, Xu C-Z (2021a) Robust actor-critic learning for continuous-time nonlinear systems with unmodeled dynamics. IEEE Trans Fuzzy Syst. https:\/\/doi.org\/10.1109\/TFUZZ.2021.3075501","journal-title":"IEEE Trans Fuzzy Syst"},{"issue":"6","key":"10045_CR52","doi-asserted-by":"crossref","first-page":"1941","DOI":"10.1002\/rnc.5341","volume":"31","author":"Y Yang","year":"2021","unstructured":"Yang Y, Mazouchi M, Modares H (2021b) Hamiltonian-driven adaptive dynamic programming for mixed H$$_2$$\/H$$_\\infty $$ performance using sum-of-squares. Int J Robust Nonlinear Control 31(6):1941\u20131963","journal-title":"Int J Robust Nonlinear Control"},{"issue":"4","key":"10045_CR55","doi-asserted-by":"crossref","first-page":"3054","DOI":"10.1109\/TIE.2019.2914571","volume":"67","author":"B Zhao","year":"2020","unstructured":"Zhao B, Liu D (2020) Event-triggered decentralized tracking control of modular reconfigurable robots through adaptive dynamic programming. IEEE Trans Indus Electron 67(4):3054\u20133064","journal-title":"IEEE Trans Indus Electron"},{"key":"10045_CR29","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.ins.2016.12.016","volume":"384","author":"B Zhao","year":"2017","unstructured":"Zhao B, Liu D, Li Y (2017) Observer based adaptive dynamic programming for fault tolerant control of a class of nonlinear systems. Inform Sci 384:21\u201333","journal-title":"Inform Sci"},{"issue":"10","key":"10045_CR27","doi-asserted-by":"crossref","first-page":"1725","DOI":"10.1109\/TSMC.2017.2690665","volume":"48","author":"B Zhao","year":"2018","unstructured":"Zhao B, Wang D, Shi G, Liu D, Li Y (2018) Decentralized control for large-scale nonlinear systems with unknown mismatched interconnections via policy iteration. IEEE Trans Syst Man Cybern Syst 48(10):1725\u20131735","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"issue":"10","key":"10045_CR30","doi-asserted-by":"crossref","first-page":"4330","DOI":"10.1109\/TNNLS.2019.2954983","volume":"31","author":"B Zhao","year":"2020","unstructured":"Zhao B, Liu D, Luo C (2020) Reinforcement learning-based optimal stabilization for unknown nonlinear systems subject to inputs with uncertain constraints. IEEE Trans Neural Netw Learn Syst 31(10):4330\u20134340","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"10045_CR5","volume-title":"Fuzzy modeling and fuzzy control","author":"H Zhang","year":"2006","unstructured":"Zhang H, Liu D (2006) Fuzzy modeling and fuzzy control. Springer, Berlin"},{"issue":"8","key":"10045_CR24","doi-asserted-by":"crossref","first-page":"2874","DOI":"10.1109\/TCYB.2018.2830820","volume":"49","author":"Q Zhang","year":"2019","unstructured":"Zhang Q, Zhao D (2019) Data-based reinforcement learning for nonzero-sum games with unknown drift dynamics. IEEE Trans Cybern 49(8):2874\u20132885","journal-title":"IEEE Trans Cybern"},{"issue":"7","key":"10045_CR23","doi-asserted-by":"crossref","first-page":"1071","DOI":"10.1109\/TSMC.2016.2531680","volume":"47","author":"Q Zhang","year":"2017","unstructured":"Zhang Q, Zhao D, Zhu Y (2017) Event-triggered $${H}_\\infty $$ control for continuous-time nonlinear system via concurrent learning. IEEE Trans Syst Man Cybern Syst 47(7):1071\u20131081","journal-title":"IEEE Trans Syst Man Cybern Syst"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-021-10045-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10462-021-10045-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-021-10045-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,29]],"date-time":"2022-01-29T07:22:54Z","timestamp":1643440974000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10462-021-10045-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,7]]},"references-count":56,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,1]]}},"alternative-id":["10045"],"URL":"https:\/\/doi.org\/10.1007\/s10462-021-10045-9","relation":{},"ISSN":["0269-2821","1573-7462"],"issn-type":[{"value":"0269-2821","type":"print"},{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,7]]},"assertion":[{"value":"7 August 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}