{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:56:25Z","timestamp":1771959385677,"version":"3.50.1"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2018,1,12]],"date-time":"2018-01-12T00:00:00Z","timestamp":1515715200000},"content-version":"tdm","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":["61433004"],"award-info":[{"award-number":["61433004"]}],"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":["61627809"],"award-info":[{"award-number":["61627809"]}],"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":["61621004"],"award-info":[{"award-number":["61621004"]}],"id":[{"id":"10.13039\/501100001809","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":[[2018,6]]},"DOI":"10.1007\/s10462-017-9603-1","type":"journal-article","created":{"date-parts":[[2018,1,12]],"date-time":"2018-01-12T16:17:53Z","timestamp":1515773873000},"page":"75-91","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":62,"title":["Iterative ADP learning algorithms for discrete-time multi-player games"],"prefix":"10.1007","volume":"50","author":[{"given":"He","family":"Jiang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2375-9824","authenticated-orcid":false,"given":"Huaguang","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,1,12]]},"reference":[{"issue":"1","key":"9603_CR1","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1109\/TSMCB.2006.880135","volume":"37","author":"A Al-Tamimi","year":"2007","unstructured":"Al-Tamimi A, Abu-Khalaf M, Lewis FL (2007) Adaptive critic designs for discrete-time zero-sum games with application to \n                    \n                      \n                    \n                    $$H_{\\infty }$$\n                    \n                      \n                        \n                          H\n                          \u221e\n                        \n                      \n                    \n                   control. IEEE Trans Syst Man Cybern B Cybern 37(1):240\u2013247","journal-title":"IEEE Trans Syst Man Cybern B Cybern"},{"issue":"3","key":"9603_CR2","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1016\/j.automatica.2006.09.019","volume":"43","author":"A Al-Tamimi","year":"2007","unstructured":"Al-Tamimi A, Lewis FL, Abu-Khalaf M (2007) Model-free Q-learning designs for linear discrete-time zero-sum games with application to \n                    \n                      \n                    \n                    $$H_{\\infty }$$\n                    \n                      \n                        \n                          H\n                          \u221e\n                        \n                      \n                    \n                   control. Automatica 43(3):473\u2013481","journal-title":"Automatica"},{"issue":"4","key":"9603_CR3","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1109\/TSMCB.2008.926614","volume":"38","author":"A Al-Tamimi","year":"2008","unstructured":"Al-Tamimi A, Lewis FL, Abu-Khalaf M (2008) Discrete-time nonlinear HJB solution using approximate dynamic programming: convergence proof. IEEE Trans Syst Man Cybern Part B Cybern 38(4):943\u2013949","journal-title":"IEEE Trans Syst Man Cybern Part B Cybern"},{"key":"9603_CR4","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.neucom.2017.05.086","volume":"1\u20138","author":"H Jiang","year":"2017","unstructured":"Jiang H, Zhang H, Xiao G, Cui X (2017) Data-based approximate optimal control for nonzero-sum games of multi-player systems using adaptive dynamic programming. Neurocomputing 1\u20138:12. \n                    https:\/\/doi.org\/10.1016\/j.neucom.2017.05.086","journal-title":"Neurocomputing"},{"key":"9603_CR5","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1016\/j.neucom.2016.11.041","volume":"237","author":"H Jiang","year":"2017","unstructured":"Jiang H, Zhang H, Luo Y, Cui X (2017) \n                    \n                      \n                    \n                    $$H_\\infty $$\n                    \n                      \n                        \n                          H\n                          \u221e\n                        \n                      \n                    \n                   control with constrained input for completely unknown nonlinear systems using data-driven reinforcement learning method. Neurocomputing 237:226\u2013234","journal-title":"Neurocomputing"},{"issue":"3","key":"9603_CR6","doi-asserted-by":"publisher","first-page":"1645","DOI":"10.1109\/TNNLS.2014.2350835","volume":"1","author":"M Johnson","year":"2015","unstructured":"Johnson M, Kamalapurkar R, Bhasin S, Dixon WE (2015) Approximate \n                    \n                      \n                    \n                    $$N$$\n                    \n                      \n                        N\n                      \n                    \n                  -player nonzero-sum game solution for an uncertain continuous nonlinear system. IEEE Trans Neural Netw Learn Syst 1(3):1645\u20131658","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"3","key":"9603_CR7","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1109\/JAS.2014.7004681","volume":"1","author":"R Kamalapurkar","year":"2014","unstructured":"Kamalapurkar R, Klotz J, Dixon WE (2014) Concurrent learning-based online approximate feedback Nash equilibrium solution of \n                    \n                      \n                    \n                    $$N$$\n                    \n                      \n                        N\n                      \n                    \n                  -player nonzero-sum differential games. IEEE\/CAA J Autom Sin 1(3):239\u2013247","journal-title":"IEEE\/CAA J Autom Sin"},{"issue":"3","key":"9603_CR8","doi-asserted-by":"publisher","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":"3","key":"9603_CR9","doi-asserted-by":"publisher","first-page":"628","DOI":"10.1109\/TASE.2012.2198057","volume":"9","author":"D Liu","year":"2012","unstructured":"Liu D, Wang D, Zhao D, Wei Q, Jin N (2012) Neural-network-based optimal control for a class of unknown discrete-time nonlinear systems using globalized dual heuristic programming. IEEE Trans Autom Sci Eng 9(3):628\u2013634","journal-title":"IEEE Trans Autom Sci Eng"},{"key":"9603_CR10","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1016\/j.neunet.2012.02.005","volume":"32","author":"F Liu","year":"2012","unstructured":"Liu F, Sun J, Si J, Guo W, Mei S (2012) A boundedness result for the direct heuristic dynamic programming. Neural Netw 32:229\u2013235","journal-title":"Neural Netw"},{"key":"9603_CR11","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.neucom.2012.11.021","volume":"110","author":"D Liu","year":"2013","unstructured":"Liu D, Li H, Wang D (2013) Neural-network-based zero-sum game for discrete-time nonlinear systems via iterative adaptive dynamic programming algorithm. Neurocomputing 110:92\u2013100","journal-title":"Neurocomputing"},{"issue":"8","key":"9603_CR12","doi-asserted-by":"publisher","first-page":"1015","DOI":"10.1109\/TSMC.2013.2295351","volume":"44","author":"D Liu","year":"2014","unstructured":"Liu D, Li H, Wang D (2014) Online synchronous approximate optimal learning algorithm for multi-player non-zero-sum games with unknown dynamics. IEEE Trans Syst Man Cybern Syst 44(8):1015\u20131027","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"issue":"7","key":"9603_CR13","doi-asserted-by":"publisher","first-page":"1372","DOI":"10.1109\/TCYB.2015.2417170","volume":"45","author":"D Liu","year":"2015","unstructured":"Liu D, Yang X, Wang D, Wei Q (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"},{"issue":"12","key":"9603_CR14","doi-asserted-by":"publisher","first-page":"3281","DOI":"10.1016\/j.automatica.2014.10.056","volume":"50","author":"B Luo","year":"2014","unstructured":"Luo B, Wu HN, Huang T, Liu D (2014) Data-based approximate policy iteration for affine nonlinear continuous-time optimal control design. Automatica 50(12):3281\u20133290","journal-title":"Automatica"},{"key":"9603_CR15","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1016\/j.neunet.2015.08.007","volume":"71","author":"B Luo","year":"2015","unstructured":"Luo B, Wu HN, Huang T, Liu D (2015) Reinforcement learning solution for HJB equation arising in constrained optimal control problem. Neural Netw 71:150\u2013158","journal-title":"Neural Netw"},{"issue":"1","key":"9603_CR16","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1109\/TCYB.2014.2319577","volume":"45","author":"B Luo","year":"2015","unstructured":"Luo B, Wu HN, Huang T (2015) Off-policy reinforcement learning for \n                    \n                      \n                    \n                    $$H_\\infty $$\n                    \n                      \n                        \n                          H\n                          \u221e\n                        \n                      \n                    \n                   control design. IEEE Trans Cybern 45(1):65\u201376","journal-title":"IEEE Trans Cybern"},{"issue":"10","key":"9603_CR17","doi-asserted-by":"publisher","first-page":"2134","DOI":"10.1109\/TNNLS.2016.2585520","volume":"27","author":"B Luo","year":"2016","unstructured":"Luo B, Liu D, Huang T, Wang D (2016) Model-free optimal tracking control via critic-only Q-learning. IEEE Trans Neural Netw Learn Syst 27(10):2134\u20132144","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"6","key":"9603_CR18","doi-asserted-by":"publisher","first-page":"1641","DOI":"10.1109\/TSMCB.2012.2227253","volume":"43","author":"S Mehraeen","year":"2013","unstructured":"Mehraeen S, Dierks T, Jagannathan S (2013) Zero-sum two-player game theoretic formulation of affine nonlinear discrete-time systems using neural networks. IEEE Trans Cybern 43(6):1641\u20131655","journal-title":"IEEE Trans Cybern"},{"issue":"2","key":"9603_CR19","doi-asserted-by":"publisher","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 Part C Appl Rev 32(2):140\u2013153","journal-title":"IEEE Trans Syst Man Cybern Part C Appl Rev"},{"key":"9603_CR20","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1016\/j.automatica.2015.06.001","volume":"59","author":"Y Sokolov","year":"2015","unstructured":"Sokolov Y, Kozma R, Werbos L, Werbos P (2015) Complete stability analysis of a heuristic approximate dynamic programming control design. Automatica 59:9\u201318","journal-title":"Automatica"},{"issue":"4","key":"9603_CR21","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1109\/TNNLS.2015.2399020","volume":"26","author":"R Song","year":"2015","unstructured":"Song R, Lewis FL, Wei Q, Zhang H, Jiang ZP, Levine D (2015) Multiple actor-critic structures for continuous-time optimal control using input-output data. IEEE Trans Neural Netw Learn Syst 26(4):851\u2013865","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"3","key":"9603_CR22","doi-asserted-by":"publisher","first-page":"704","DOI":"10.1109\/TNNLS.2016.2582849","volume":"28","author":"R Song","year":"2017","unstructured":"Song R, Lewis FL, Wei Q (2017) Off-policy integral reinforcement learning method to solve nonlinear continuous-time multiplayer nonzero-sum games. IEEE Trans Neural Netw Learn Syst 28(3):704\u2013713","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"5","key":"9603_CR23","doi-asserted-by":"publisher","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":"9603_CR24","doi-asserted-by":"publisher","first-page":"1556","DOI":"10.1016\/j.automatica.2011.03.005","volume":"47","author":"KG Vamvoudakis","year":"2011","unstructured":"Vamvoudakis KG, Lewis FL (2011) Multi-player non-zero-sum games: Online adaptive learning solution of coupled Hamilton-Jacobi equations. Automatica 47(8):1556\u20131569","journal-title":"Automatica"},{"issue":"2","key":"9603_CR25","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1109\/MCI.2009.932261","volume":"4","author":"FY Wang","year":"2009","unstructured":"Wang FY, Zhang H, Liu D (2009) Adaptive dynamic programming: an introduction. IEEE Comput Intell Mag 4(2):39\u201347","journal-title":"IEEE Comput Intell Mag"},{"key":"9603_CR26","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.ins.2014.05.050","volume":"282","author":"D Wang","year":"2014","unstructured":"Wang D, Liu D, Li H, Ma H (2014) Neural-network-based robust optimal control design for a class of uncertain nonlinear systems via adaptive dynamic programming. Inf Sci 282:167\u2013179","journal-title":"Inf Sci"},{"issue":"5","key":"9603_CR27","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1109\/TSMC.2015.2466191","volume":"46","author":"D Wang","year":"2016","unstructured":"Wang D, Liu D, Li H, Luo B, Ma H (2016) An approximate optimal control approach for robust stabilization of a class of discrete-time nonlinear systems with uncertainties. IEEE Trans Syst Man Cybern Syst 46(5):713\u2013717","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"issue":"11","key":"9603_CR28","doi-asserted-by":"publisher","first-page":"1544","DOI":"10.1109\/TSMC.2015.2492941","volume":"46","author":"D Wang","year":"2016","unstructured":"Wang D, Liu D, Zhang Q, Zhao D (2016) Data-based adaptive critic designs for nonlinear robust optimal control with uncertain dynamics. IEEE Trans Syst Man Cybern Syst 46(11):1544\u20131555","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"issue":"10","key":"9603_CR29","doi-asserted-by":"publisher","first-page":"3429","DOI":"10.1109\/TCYB.2017.2712188","volume":"47","author":"D Wang","year":"2017","unstructured":"Wang D, He H, Liu D (2017) Adaptive critic nonlinear robust control: a survey. IEEE Trans Cybern 47(10):3429\u20133451","journal-title":"IEEE Trans Cybern"},{"key":"9603_CR30","first-page":"1","volume":"99","author":"D Wang","year":"2017","unstructured":"Wang D, Mu C, Liu D, Ma H (2017) On mixed data and event driven design for adaptive-critic-based nonlinear \n                    \n                      \n                    \n                    $$H_{\\infty }$$\n                    \n                      \n                        \n                          H\n                          \u221e\n                        \n                      \n                    \n                   control. IEEE Trans Neural Netw Learn Syst 99:1\u201313","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"6","key":"9603_CR31","doi-asserted-by":"publisher","first-page":"4935","DOI":"10.1109\/TIE.2017.2674633","volume":"64","author":"D Wang","year":"2017","unstructured":"Wang D, He H, Mu C, Liu D (2017) Intelligent critic control with disturbance attenuation for affine dynamics including an application to a microgrid system. IEEE Trans Ind Electron 64(6):4935\u20134944","journal-title":"IEEE Trans Ind Electron"},{"issue":"12","key":"9603_CR32","doi-asserted-by":"publisher","first-page":"2820","DOI":"10.1109\/TCYB.2014.2354377","volume":"44","author":"Q Wei","year":"2014","unstructured":"Wei Q, Wang FY, Liu D, Yang X (2014) Finite-approximation-error based discrete-time iterative adaptive dynamic programming. IEEE Trans Cybern 44(12):2820\u20132833","journal-title":"IEEE Trans Cybern"},{"issue":"4","key":"9603_CR33","doi-asserted-by":"publisher","first-page":"866","DOI":"10.1109\/TNNLS.2015.2401334","volume":"26","author":"Q Wei","year":"2015","unstructured":"Wei Q, Liu D, Yang X (2015) Infinite horizon self-learning optimal control of nonaffine discrete-time nonlinear systems. IEEE Trans Neural Netw Learn Syst 26(4):866\u2013879","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"3","key":"9603_CR34","doi-asserted-by":"publisher","first-page":"840","DOI":"10.1109\/TCYB.2015.2492242","volume":"46","author":"Q Wei","year":"2016","unstructured":"Wei Q, Liu D, Lin H (2016) Value iteration adaptive dynamic programming for optimal control of discrete-time nonlinear systems. IEEE Trans Cybern 46(3):840\u2013853","journal-title":"IEEE Trans Cybern"},{"key":"9603_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TSMC.2016.2623766","volume":"99","author":"Q Wei","year":"2016","unstructured":"Wei Q, Lewis FL, Liu D, Song R, Lin H (2016) Discrete-time local value iteration adaptive dynamic programming: convergence analysis. IEEE Trans Syst Man Cybern Syst 99:1\u201317","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"9603_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TNNLS.2017.2696582","volume":"99","author":"Q Wei","year":"2017","unstructured":"Wei Q, Liu D, Qiao L, Song R (2017) Adaptive dynamic programming for discrete-time zero-sum games. IEEE Trans Neural Netw Learn Syst 99:1\u201313","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"6","key":"9603_CR37","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 Yearb 22(6):25\u201338","journal-title":"Gen Syst Yearb"},{"key":"9603_CR38","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1016\/j.neucom.2015.08.119","volume":"198","author":"X Yang","year":"2016","unstructured":"Yang X, Liu D, Wei Q, Wang D (2016) Guaranteed cost neural tracking control for a class of uncertain nonlinear systems using adaptive dynamic programming. Neurocomputing 198:80\u201390","journal-title":"Neurocomputing"},{"key":"9603_CR39","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1016\/j.ins.2015.09.001","volume":"328","author":"X Yang","year":"2016","unstructured":"Yang X, Liu D, Ma H, Xu Y (2016) Online approximate solution of HJI equation for unknown constrained-input nonlinear continuous-time systems. Inf Sci 328:435\u2013454","journal-title":"Inf Sci"},{"issue":"1","key":"9603_CR40","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1109\/TSMCB.2012.2203336","volume":"43","author":"H Zhang","year":"2013","unstructured":"Zhang H, Cui L, Luo Y (2013) Near-optimal control for nonzero-sum differential games of continuous-time nonlinear systems using single-network ADP. IEEE Trans Cybern 43(1):206\u2013216","journal-title":"IEEE Trans Cybern"},{"issue":"12","key":"9603_CR41","doi-asserted-by":"publisher","first-page":"2706","DOI":"10.1109\/TCYB.2014.2313915","volume":"44","author":"H Zhang","year":"2014","unstructured":"Zhang H, Qin C, Jiang B, Luo Y (2014) Online adaptive policy learning algorithm for \n                    \n                      \n                    \n                    $$H_ {\\infty }$$\n                    \n                      \n                        \n                          H\n                          \u221e\n                        \n                      \n                    \n                   state feedback control of unknown affine nonlinear discrete-time systems. IEEE Trans Cybern 44(12):2706\u20132718","journal-title":"IEEE Trans Cybern"},{"key":"9603_CR42","first-page":"1","volume":"99","author":"H Zhang","year":"2016","unstructured":"Zhang H, Jiang H, Luo C, Xiao G (2016) Discrete-time nonzero-sum games for multiplayer using policy iteration-based adaptive dynamic programming algorithms. IEEE Trans Cybern 99:1\u201310","journal-title":"IEEE Trans Cybern"},{"key":"9603_CR43","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TNNLS.2017.2705113","volume":"99","author":"H Zhang","year":"2017","unstructured":"Zhang H, Cui X, Luo Y, Jiang H (2017) Finite-horizon \n                    \n                      \n                    \n                    $$H_\\infty $$\n                    \n                      \n                        \n                          H\n                          \u221e\n                        \n                      \n                    \n                   tracking control for unknown nonlinear systems with saturating actuators. IEEE Trans Neural Netw Learn Syst 99:1\u201313","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"2","key":"9603_CR44","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1109\/TNNLS.2014.2371046","volume":"26","author":"D Zhao","year":"2015","unstructured":"Zhao D, Zhu Y (2015) MEC\u2014a near-optimal online reinforcement learning algorithm for continuous deterministic systems. IEEE Trans Neural Netw Learn Syst 26(2):346\u2013356","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"4","key":"9603_CR45","doi-asserted-by":"publisher","first-page":"1461","DOI":"10.1109\/TASE.2014.2348991","volume":"12","author":"D Zhao","year":"2015","unstructured":"Zhao D, Xia Z, Wang D (2015) Model-free optimal control for affine nonlinear systems with convergence analysis. IEEE Trans Autom Sci Eng 12(4):1461\u20131468","journal-title":"IEEE Trans Autom Sci Eng"},{"issue":"3","key":"9603_CR46","doi-asserted-by":"publisher","first-page":"854","DOI":"10.1109\/TCYB.2015.2488680","volume":"46","author":"D Zhao","year":"2016","unstructured":"Zhao D, Zhang Q, Wang D, Zhu Y (2016) Experience replay for optimal control of nonzero-sum game systems with unknown dynamics. IEEE Trans Cybern 46(3):854\u2013865","journal-title":"IEEE Trans Cybern"},{"issue":"12","key":"9603_CR47","doi-asserted-by":"publisher","first-page":"1339","DOI":"10.1049\/iet-cta.2015.0769","volume":"10","author":"Y Zhu","year":"2016","unstructured":"Zhu Y, Zhao D, Li X (2016) Using reinforcement learning techniques to solve continuous-time non-linear optimal tracking problem without system dynamics. IET Control Theory Appl 10(12):1339\u20131347","journal-title":"IET Control Theory Appl"},{"issue":"5","key":"9603_CR48","doi-asserted-by":"publisher","first-page":"4101","DOI":"10.1109\/TIE.2016.2597763","volume":"64","author":"Y Zhu","year":"2017","unstructured":"Zhu Y, Zhao D, He H, Ji J (2017) Event-triggered optimal control for partially-unknown constrained-input systems via adaptive dynamic programming. IEEE Trans Ind Electron 64(5):4101\u20134109","journal-title":"IEEE Trans Ind Electron"},{"key":"9603_CR49","doi-asserted-by":"publisher","unstructured":"Zhu Y, Zhao D (2017) Comprehensive comparison of online ADP algorithms for continuous-time optimal control. Artif Intell Rev 1-17. \n                    https:\/\/doi.org\/10.1007\/s10462-017-9548-4","DOI":"10.1007\/s10462-017-9548-4"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10462-017-9603-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-017-9603-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-017-9603-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,1,11]],"date-time":"2019-01-11T19:05:53Z","timestamp":1547233553000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10462-017-9603-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,1,12]]},"references-count":49,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2018,6]]}},"alternative-id":["9603"],"URL":"https:\/\/doi.org\/10.1007\/s10462-017-9603-1","relation":{},"ISSN":["0269-2821","1573-7462"],"issn-type":[{"value":"0269-2821","type":"print"},{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,1,12]]},"assertion":[{"value":"12 January 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}