{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T16:27:42Z","timestamp":1780072062540,"version":"3.54.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,7,3]],"date-time":"2019-07-03T00:00:00Z","timestamp":1562112000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,7,3]],"date-time":"2019-07-03T00:00:00Z","timestamp":1562112000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61473202"],"award-info":[{"award-number":["61473202"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1007\/s11063-019-10072-2","type":"journal-article","created":{"date-parts":[[2019,7,3]],"date-time":"2019-07-03T11:03:21Z","timestamp":1562151801000},"page":"2963-2989","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Optimal Output Feedback Control of Nonlinear Partially-Unknown Constrained-Input Systems Using Integral Reinforcement Learning"],"prefix":"10.1007","volume":"50","author":[{"given":"Ling","family":"Ren","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0994-5468","authenticated-orcid":false,"given":"Guoshan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaoxu","family":"Mu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,7,3]]},"reference":[{"key":"10072_CR1","doi-asserted-by":"crossref","DOI":"10.1002\/9781118122631","volume-title":"Optimal control","author":"FL Lewis","year":"2012","unstructured":"Lewis FL, Vrabie DL, Syrmos VL (2012) Optimal control, 3rd edn. Wiley & Sons, Hoboken","edition":"3"},{"key":"10072_CR2","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1016\/j.neunet.2015.05.006","volume":"69","author":"YY Wu","year":"2015","unstructured":"Wu YY, Cao JD, Alofi A, Al-Mazrooei A, Elaiw A (2015) Finite-time boundedness and stabilization of uncertain switched neural networks with time-varying delay. Neural Netw 69:135\u2013143","journal-title":"Neural Netw"},{"key":"10072_CR3","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.neunet.2016.10.007","volume":"85","author":"YY Wu","year":"2017","unstructured":"Wu YY, Cao JD, Li QB, Alsaedi A, Alsaadi FE (2017) Finite-time synchronization of uncertain coupled switched neural networks under asynchronous switching. Neural Netw 85:128\u2013139","journal-title":"Neural Netw"},{"issue":"6","key":"10072_CR4","doi-asserted-by":"publisher","first-page":"2495","DOI":"10.1109\/TAC.2018.2867161","volume":"64","author":"Qingling Wang","year":"2019","unstructured":"Wang QL, Psillakis HE, Sun CY (2018) Cooperative control of multiple agents with unknown high-frequency gain signs under unbalanced and switching topologies. IEEE Trans Autom Control. \nhttps:\/\/doi.org\/10.1109\/TAC.2018.2867161","journal-title":"IEEE Transactions on Automatic Control"},{"key":"10072_CR5","doi-asserted-by":"publisher","unstructured":"Wang QL, Sun CY (2018) Adaptive consensus of multi-agent systems with unknown high-frequency gain signs under directed graphs. IEEE Trans Syst Man Cybern Syst. \nhttps:\/\/doi.org\/10.1109\/TSMC.2018.2810089","DOI":"10.1109\/TSMC.2018.2810089"},{"issue":"3","key":"10072_CR6","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1007\/s11424-018-8141-5","volume":"32","author":"Qingbo Li","year":"2018","unstructured":"Li QB, Guo J, Sun CY, Wu YY, Ding ZT (2018) Finite-time synchronization for a class of dynamical complex networks with nonidentical nodes and uncertain disturbance. J Syst Sci Complex. \nhttps:\/\/doi.org\/10.1007\/s11424-018-8141-5","journal-title":"Journal of Systems Science and Complexity"},{"issue":"6","key":"10072_CR7","first-page":"25","volume":"22","author":"PJ Werbos","year":"1977","unstructured":"Werbos PJ (1977) Advanced forecasting methods for global crisis warning and models of intelligence. Gen Syst Year b 22(6):25\u201338","journal-title":"Gen Syst Year b"},{"issue":"4","key":"10072_CR8","doi-asserted-by":"crossref","first-page":"898","DOI":"10.1109\/TSMCB.2008.924139","volume":"38","author":"PJ Werbos","year":"2008","unstructured":"Werbos PJ (2008) ADP: the key direction for future research in intelligent control and understanding brain intelligence. IEEE Trans Syst Man Cybern Part B Cybern 38(4):898\u2013900","journal-title":"IEEE Trans Syst Man Cybern Part B Cybern"},{"key":"10072_CR9","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1016\/j.automatica.2017.03.022","volume":"81","author":"CX Mu","year":"2017","unstructured":"Mu CX, Wang D, He HB (2017) Novel iterative neural dynamic programming for data-based approximate optimal control design. Automatica 81:240\u2013252","journal-title":"Automatica"},{"issue":"6","key":"10072_CR10","first-page":"1687","volume":"27","author":"DP Bertsekas","year":"1996","unstructured":"Bertsekas DP, Tsitsiklis JN (1996) Neuro-dynamic programming. Athena Sci 27(6):1687\u20131692","journal-title":"Athena Sci"},{"key":"10072_CR11","volume-title":"Approximate dynamic programming: solving the curses of dimensionality","author":"PM Pardalos","year":"2009","unstructured":"Pardalos PM (2009) Approximate dynamic programming: solving the curses of dimensionality. Wiley, New York"},{"issue":"2","key":"10072_CR12","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1109\/72.914523","volume":"12","author":"J Si","year":"2001","unstructured":"Si J, Wang YT (2001) Online learning control by association and reinforcement. IEEE Trans Neural Netw 12(2):264\u2013276","journal-title":"IEEE Trans Neural Netw"},{"issue":"C","key":"10072_CR13","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1016\/j.neucom.2015.04.014","volume":"166","author":"X Fang","year":"2015","unstructured":"Fang X, Zheng DZ, He HB, Ni Z (2015) Data-driven heuristic dynamic programming with virtual reality. Neurocomputing 166(C):244\u2013255","journal-title":"Neurocomputing"},{"key":"10072_CR14","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1007\/s11063-016-9536-8","volume":"45","author":"CX Ding","year":"2017","unstructured":"Ding CX, Sun Y, Zhu YG (2017) A NN-based hybrid intelligent algorithm for a discrete nonlinear uncertain optimal control problem. Neural Process Lett 45:457\u2013473","journal-title":"Neural Process Lett"},{"key":"10072_CR15","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1016\/j.neucom.2013.04.006","volume":"121","author":"D Wang","year":"2013","unstructured":"Wang D, Liu DR (2013) Neural-optimal control for a class of unknown nonlinear dynamic systems using SN-DHP technique. Neurocomputing 121:218\u2013225","journal-title":"Neurocomputing"},{"issue":"8","key":"10072_CR16","doi-asserted-by":"crossref","first-page":"839","DOI":"10.1109\/TASE.2014.2303139","volume":"121","author":"HG Zhang","year":"2014","unstructured":"Zhang HG, Qin CB, Luo YH (2014) Nerual-network-based constrained optimal control scheme for discrete-time switched systems using dual heuristic programming. IEEE Trans Autom Sci Eng 121(8):839\u2013849","journal-title":"IEEE Trans Autom Sci Eng"},{"issue":"8","key":"10072_CR17","first-page":"839","volume":"121","author":"Z Ni","year":"2014","unstructured":"Ni Z, He HB, Zhao DB, Xu X, Prokhorov DV (2014) GrDHP: a general utility function representation for dual heuristic dynamic programming. IEEE Trans Neural Netw Learn Syst 121(8):839\u2013849","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"10072_CR18","first-page":"493","volume-title":"Approximate dynamic programming for real-time control and neural modeling. Handbook of intelligent control","author":"PJ Werbos","year":"1992","unstructured":"Werbos PJ (1992) Approximate dynamic programming for real-time control and neural modeling. Handbook of intelligent control. Van Nostrand, New York, pp 493\u2013525"},{"issue":"2","key":"10072_CR19","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1016\/0893-6080(90)90088-3","volume":"3","author":"PJ Werbos","year":"1990","unstructured":"Werbos PJ (1990) Consistency of HDP applied to a simple reinforcement learning problem. Neural Netw 3(2):179\u2013189","journal-title":"Neural Netw"},{"issue":"2","key":"10072_CR20","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1109\/TSMCC.2002.801727","volume":"32","author":"JJ Murray","year":"2002","unstructured":"Murray JJ, Cox CJ, Lendaris GG, Saeks R (2002) Adaptive dynamic programming. IEEE Trans Syst Man Cybern 32(2):140\u2013153","journal-title":"IEEE Trans Syst Man Cybern"},{"issue":"11","key":"10072_CR21","doi-asserted-by":"crossref","first-page":"2850","DOI":"10.1016\/j.automatica.2012.06.008","volume":"48","author":"JY Lee","year":"2012","unstructured":"Lee JY, Park JB, Choi YH (2012) Integral Q-learning and explorized policy iteration for adaptive optimal control of continuous-time linear systems. Automatica 48(11):2850\u20132859","journal-title":"Automatica"},{"issue":"10","key":"10072_CR22","doi-asserted-by":"crossref","first-page":"2699","DOI":"10.1016\/j.automatica.2012.06.096","volume":"48","author":"Y Jiang","year":"2012","unstructured":"Jiang Y, Jiang ZP (2012) Computational adaptive optimal control for continuous-time linear systems with completely unknown dynamics. Automatica 48(10):2699\u20132704","journal-title":"Automatica"},{"issue":"3","key":"10072_CR23","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1109\/TNNLS.2013.2281663","volume":"25","author":"DR Liu","year":"2014","unstructured":"Liu DR, Wei QL (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"},{"key":"10072_CR24","doi-asserted-by":"crossref","first-page":"432","DOI":"10.1016\/j.neucom.2017.04.043","volume":"260","author":"CX Mu","year":"2017","unstructured":"Mu CX, Sun CY, Wang D, Song AG (2017) Adaptive tracking control for a class of continuous-time uncertain nonlinear systems using the approximate solution of HJB equation. Neurocomputing 260:432\u2013442","journal-title":"Neurocomputing"},{"issue":"5","key":"10072_CR25","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1016\/j.automatica.2004.11.034","volume":"41","author":"M Abu-Khalaf","year":"2005","unstructured":"Abu-Khalaf M, Lewis FL (2005) Nearly optimal control laws for nonlinear systems with saturating actuators using a neural network HJB approach. Automatica 41(5):779\u2013791","journal-title":"Automatica"},{"key":"10072_CR26","first-page":"73","volume":"CDC08","author":"D Vrabie","year":"2008","unstructured":"Vrabie D, Lewis FL (2008) Adaptive optimal control algorithm for continuous-time nonlinear systems based on policy iteration. IEEE Proc CDC08:73\u201379","journal-title":"IEEE Proc"},{"issue":"2","key":"10072_CR27","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1016\/j.automatica.2008.08.017","volume":"45","author":"D Vrabie","year":"2009","unstructured":"Vrabie D, Pastravanu O, Abu-Khalaf M, Lewis FL (2009) Adaptive optimal control for continuous-time linear systems based on policy iteration. Automatica 45(2):477\u2013484","journal-title":"Automatica"},{"key":"10072_CR28","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1016\/j.neunet.2009.03.008","volume":"22","author":"D Vrabie","year":"2009","unstructured":"Vrabie D, Lewis FL (2009) Neural network approach to continuous-time direct adaptive optimal control for partially unknown nonlinear systems. Neural Netw 22:237\u2013246","journal-title":"Neural Netw"},{"issue":"5","key":"10072_CR29","doi-asserted-by":"crossref","first-page":"916","DOI":"10.1109\/TNNLS.2014.2328590","volume":"26","author":"JY Lee","year":"2015","unstructured":"Lee JY, Park JB, Choi YH (2015) Integral reinforcement learning for continuous-time input-affine nonlinear systems with simultaneous invariant explorations. IEEE Trans Neural Netw Learn Syst 26(5):916\u2013932","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"10072_CR30","doi-asserted-by":"crossref","first-page":"731","DOI":"10.1016\/j.ins.2016.07.051","volume":"369","author":"X Yang","year":"2016","unstructured":"Yang X, Liu DR, Luo B, Li C (2016) Data-based robust adaptive control for a class of unknown nonlinear constrained-input systems via integral reinforcement learning. Inf Sci 369:731\u2013747","journal-title":"Inf Sci"},{"key":"10072_CR31","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 46:878\u2013888","journal-title":"Automatica"},{"key":"10072_CR32","doi-asserted-by":"crossref","first-page":"878","DOI":"10.1002\/rnc.3018","volume":"24","author":"KG Vamvoudakis","year":"2014","unstructured":"Vamvoudakis KG, Vrabie D, Lewis FL (2014) Online adaptive algorithm for optimal control with integral reinforcement learning. Int J Robust Nonlinear Control 24:878\u2013888","journal-title":"Int J Robust Nonlinear Control"},{"key":"10072_CR33","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/j.automatica.2013.09.043","volume":"50","author":"H Modares","year":"2014","unstructured":"Modares H, Lewis FL, Naghibi-Sistani MB (2014) Integral reinforcement learning and experience replay for adaptive optimal control of partially-unknown constrained-input continuous-time systems. Automatica 50:193\u2013202","journal-title":"Automatica"},{"issue":"7","key":"10072_CR34","doi-asserted-by":"crossref","first-page":"1372","DOI":"10.1109\/TCYB.2015.2417170","volume":"45","author":"DR Liu","year":"2015","unstructured":"Liu DR, Yang X, Wang D, Wei QL (2015) Reinforcement-learning-based robust controller design for continuous-time uncertain nonlinear systems subject to input constraints. IEEE Trans Cybern 45(7):1372\u20131385","journal-title":"IEEE Trans Cybern"},{"key":"10072_CR35","doi-asserted-by":"crossref","first-page":"848","DOI":"10.1016\/j.neucom.2016.07.002","volume":"214","author":"D Wang","year":"2016","unstructured":"Wang D, Mu CX, Zhang QC, Liu DR (2016) Event-based input-constrained nonlinear $$H_\\infty $$ state feedback with adaptive critic and neural implementation. Neurocomputing 214:848\u2013856","journal-title":"Neurocomputing"},{"key":"10072_CR36","first-page":"1","volume":"99","author":"W Sun","year":"2018","unstructured":"Sun W, Wu YQ, Xia JW, Nguyen VT (2018) Adaptive fuzzy control with high-order barrier Lyapunov functions for high-order uncertain nonlinear systems with full-state constraints. IEEE Trans Cybern 99:1\u20139","journal-title":"IEEE Trans Cybern"},{"issue":"1","key":"10072_CR37","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1109\/TCST.2014.2322778","volume":"23","author":"LM Zhu","year":"2015","unstructured":"Zhu LM, Modares H, Peen GO, Lewis FL, Yue BZ (2015) Adaptive suboptimal output-feedback control for linear systems using integral reinforcement learning. IEEE Trans Control Syst Technol 23(1):264\u2013273","journal-title":"IEEE Trans Control Syst Technol"},{"key":"10072_CR38","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1016\/j.neucom.2017.03.053","volume":"247","author":"TC Wang","year":"2017","unstructured":"Wang TC, Sui S, Tong SC (2017) Data-based adaptive neural network optimal output feedback control for nonlinear systems with actuator saturation. Neurocomputing 247:192\u2013201","journal-title":"Neurocomputing"},{"issue":"1","key":"10072_CR39","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1109\/TNN.2005.863458","volume":"17","author":"F Abdollahi","year":"2006","unstructured":"Abdollahi F, Talebi HA, Patel RV (2006) A stable neural network-based observer with application to flexible-joint manipulators. IEEE Trans Neural Netw 17(1):118\u2013129","journal-title":"IEEE Trans Neural Netw"},{"issue":"3","key":"10072_CR40","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1049\/iet-cta.2016.0966","volume":"11","author":"YZ Huang","year":"2017","unstructured":"Huang YZ (2017) Neuro-observer based online finite-horizon optimal control for uncertain non-linear continuous-time systems. IET Control Theory Appl 11(3):401\u2013410","journal-title":"IET Control Theory Appl"},{"key":"10072_CR41","volume-title":"The handbook of brain theory and neural networks","author":"MA Arbib","year":"2003","unstructured":"Arbib MA (2003) The handbook of brain theory and neural networks. MIT Press, Cambridge"},{"key":"10072_CR42","doi-asserted-by":"crossref","first-page":"3339","DOI":"10.1007\/s00521-017-2911-1","volume":"30","author":"MM Yan","year":"2018","unstructured":"Yan MM, Qiu JL, Chen XY, Chen X, Yang CD, Zhang AC (2018) Almost periodic dynamics of the delayed complex-valued recurrent neural networks with discontinuous activation functions. Neural Comput Appl 30:3339\u20133352","journal-title":"Neural Comput Appl"},{"key":"10072_CR43","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1007\/s11063-017-9736-x","volume":"48","author":"MM Yan","year":"2018","unstructured":"Yan MM, Qiu JL, Chen XY, Chen X, Yang CD, Zhang AC, Alsaadi F (2018) Almost periodic dynamics of the delayed complex-valued recurrent neural networks with discontinuous activation functions. Neural Process Lett 48:577\u2013601","journal-title":"Neural Process Lett"},{"key":"10072_CR44","series-title":"SIAM Adaptive Control Tutorial","volume-title":"Advances in design and control","author":"P Ioannou","year":"2006","unstructured":"Ioannou P, Fidan B (2006) Advances in design and control. SIAM Adaptive Control Tutorial. SIAM, PA"},{"key":"10072_CR45","volume-title":"Aircraft control and simulation","author":"BL Stevens","year":"2003","unstructured":"Stevens BL, Frank FL (2003) Aircraft control and simulation. Wiley, New York"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-019-10072-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11063-019-10072-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-019-10072-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T23:46:32Z","timestamp":1593647192000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11063-019-10072-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,3]]},"references-count":45,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["10072"],"URL":"https:\/\/doi.org\/10.1007\/s11063-019-10072-2","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"value":"1370-4621","type":"print"},{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7,3]]},"assertion":[{"value":"3 July 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}