{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,30]],"date-time":"2024-07-30T05:49:22Z","timestamp":1722318562707},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2014,5,13]],"date-time":"2014-05-13T00:00:00Z","timestamp":1399939200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2014,6]]},"DOI":"10.1007\/s11432-013-4954-y","type":"journal-article","created":{"date-parts":[[2014,5,12]],"date-time":"2014-05-12T05:33:29Z","timestamp":1399872809000},"page":"1-10","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["A new self-learning optimal control laws for a class of discrete-time nonlinear systems based on ESN architecture"],"prefix":"10.1007","volume":"57","author":[{"given":"RuiZhuo","family":"Song","sequence":"first","affiliation":[]},{"given":"WenDong","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"ChangYin","family":"Sun","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2014,5,13]]},"reference":[{"key":"4954_CR1","doi-asserted-by":"crossref","first-page":"67","DOI":"10.7551\/mitpress\/4939.003.0007","volume-title":"A Menu of Designs for Reinforcement Learning Over Time, in Neural Networks for Control","author":"P J Werbos","year":"1991","unstructured":"Werbos P J. A Menu of Designs for Reinforcement Learning Over Time, in Neural Networks for Control. Massachusetts: MIT Press, 1991. 67\u201395"},{"key":"4954_CR2","volume-title":"Approximate Dynamic Programming for Real-Time Control and Neural Modeling, in Handbook of Intelligent Control: Neural, Fuzzy, and Adaptive Approaches","author":"P J Werbos","year":"1992","unstructured":"Werbos P J. Approximate Dynamic Programming for Real-Time Control and Neural Modeling, in Handbook of Intelligent Control: Neural, Fuzzy, and Adaptive Approaches. New York: Van Nostrand Reinhold, 1992."},{"key":"4954_CR3","doi-asserted-by":"crossref","first-page":"988","DOI":"10.1109\/TSMCB.2008.922019","volume":"38","author":"D Liu","year":"2008","unstructured":"Liu D, Javaherian H, Kovalenko O, et al. Adaptive critic learning techniques for engine torque and air-fuel ratio control. IEEE Trans Syst Man Cybern B Cybern, 2008, 38: 988\u2013993","journal-title":"IEEE Trans Syst Man Cybern B Cybern"},{"key":"4954_CR4","first-page":"990","volume":"2","author":"D Liu","year":"2001","unstructured":"Liu D, Xiong X, Zhang Y. Action-dependent adaptive critic designs. In: Proceedings of International Joint Conference on Neural Networks, Washington, 2001. 2: 990\u2013995","journal-title":"Proceedings of International Joint Conference on Neural Networks, Washington"},{"key":"4954_CR5","first-page":"21","volume":"10","author":"D Liu","year":"2005","unstructured":"Liu D, Zhang H. A neural dynamic programming approach for learning control of failure avoidance problems. Int J Intell Syst, 2005, 10: 21\u201332","journal-title":"Int J Intell Syst"},{"key":"4954_CR6","doi-asserted-by":"crossref","first-page":"1219","DOI":"10.1109\/TNN.2005.853408","volume":"16","author":"D Liu","year":"2005","unstructured":"Liu D, Zhang Y, Zhang H. A self-learning call admission control scheme for CDMA cellular networks. IEEE Trans Neural Netw, 2005, 16: 1219\u20131228","journal-title":"IEEE Trans Neural Netw"},{"key":"4954_CR7","volume-title":"Approximate Dynamic Programming: Solving the Curses of Dimensionality","author":"W B Powell","year":"2009","unstructured":"Powell W B. Approximate Dynamic Programming: Solving the Curses of Dimensionality. New York: Wiley, 2009"},{"key":"4954_CR8","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/TNN.2007.900227","volume":"19","author":"C Zheng","year":"2008","unstructured":"Zheng C, Jagannathan S. Generalized Hamilton-Jacobi-Bellman formulation-based neural network control of affine nonlinear discrete-time systems. IEEE Trans Neural Netw, 2008, 19: 90\u2013106","journal-title":"IEEE Trans Neural Netw"},{"key":"4954_CR9","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1109\/TSMCB.2006.883869","volume":"37","author":"P He","year":"2007","unstructured":"He P, Jagannathan S. Reinforcement learning neural-network-based controller for nonlinear discrete-time systems with input constraints. IEEE Trans Syst Man Cybern B Cybern, 2007, 37: 425\u2013436","journal-title":"IEEE Trans Syst Man Cybern B Cybern"},{"key":"4954_CR10","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1016\/j.automatica.2006.09.019","volume":"43","author":"A Al-Tamimi","year":"2007","unstructured":"Al-Tamimi A, Lewis F L, Abu-Khalaf M. Model-free Q-learning designs for linear discrete-time zero-sum games with application to H-infinity control. Automatica, 2007, 43: 473\u2013481","journal-title":"Automatica"},{"key":"4954_CR11","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, et al. Adaptive optimal control for continuous-time linear systems based on policy iteration. Automatica, 2009, 45: 477\u2013484","journal-title":"Automatica"},{"key":"4954_CR12","doi-asserted-by":"crossref","first-page":"878","DOI":"10.1016\/j.automatica.2010.02.018","volume":"46","author":"K G Vamvoudakis","year":"2010","unstructured":"Vamvoudakis K G, Lewis F L. Online actor-critic algorithm to solve the continuous-time infinite horizon optimal control problem. Automatica, 2010, 46: 878\u2013888","journal-title":"Automatica"},{"key":"4954_CR13","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 F L. Nearly optimal control laws for nonlinear systems withsaturating actuators using a neural network HJB approach. Automatica, 2005, 41: 779\u2013791","journal-title":"Automatica"},{"key":"4954_CR14","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1109\/TSMCC.2002.801727","volume":"32","author":"J J Murray","year":"2002","unstructured":"Murray J J, Cox C J, Lendaris G G, et al. Adaptive dynamic programming. IEEE Trans Syst Man Cybern C Appl Rev, 2002, 32: 140\u2013153","journal-title":"IEEE Trans Syst Man Cybern C Appl Rev"},{"key":"4954_CR15","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1109\/72.914523","volume":"12","author":"J Si","year":"2001","unstructured":"Si J, Wang Y T. On-line learning control by association and reinforcement. IEEE Trans Neural Netw, 2001, 12: 264\u2013276","journal-title":"IEEE Trans Neural Netw"},{"key":"4954_CR16","doi-asserted-by":"crossref","first-page":"929","DOI":"10.1109\/TNN.2003.813839","volume":"14","author":"R Enns","year":"2003","unstructured":"Enns R, Si J. Helicopter trimming and tracking control using direct neural dynamic programming. IEEE Trans Neural Netw, 2003, 14: 929\u2013939","journal-title":"IEEE Trans Neural Netw"},{"key":"4954_CR17","doi-asserted-by":"crossref","first-page":"937","DOI":"10.1109\/TSMCB.2008.920269","volume":"38","author":"H G Zhang","year":"2008","unstructured":"Zhang H G, Wei Q L, Luo Y H. A novel infinite-time optimal tracking control scheme for a class of discrete-time nonlinear systems via the greedy HDP iteration algorithm. IEEE Trans Syst Man Cybern B Cybern, 2008, 38: 937\u2013942","journal-title":"IEEE Trans Syst Man Cybern B Cybern"},{"key":"4954_CR18","doi-asserted-by":"crossref","first-page":"1490","DOI":"10.1109\/TNN.2009.2027233","volume":"20","author":"H G Zhang","year":"2009","unstructured":"Zhang H G, Luo Y H, Liu D R. Neural-network-based near-optimal control for a class of discrete-time affine nonlinear systems with control constraints. IEEE Trans Neural Netw, 2009, 20: 1490\u20131503","journal-title":"IEEE Trans Neural Netw"},{"key":"4954_CR19","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1109\/TNN.2010.2076370","volume":"22","author":"F Y Wang","year":"2011","unstructured":"Wang F Y, Jin N, Liu D R, et al. Adaptive dynamic programming for finite horizon optimal control of discrete-time nonlinear systems with \u025b-error bound. IEEE Trans Neural Netw, 2011, 22: 24\u201336","journal-title":"IEEE Trans Neural Netw"},{"key":"4954_CR20","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/j.automatica.2010.10.033","volume":"47","author":"H G Zhang","year":"2011","unstructured":"Zhang H G, Wei Q L, Liu D R. An iterative adaptive dynamic programming method for solving a class of nonlinear zero-sum differential games. Automatica, 2011, 47: 207\u2013214","journal-title":"Automatica"},{"key":"4954_CR21","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1016\/S0925-2312(01)00627-0","volume":"48","author":"W D Chang","year":"2002","unstructured":"Chang W D, Hwang R C, Hsieh J G. Stable direct adaptive neural controller of nonlinear systems based on single auto-tuning neuron. Neurocomputing, 2002, 48: 541\u2013554","journal-title":"Neurocomputing"},{"key":"4954_CR22","doi-asserted-by":"crossref","first-page":"2009","DOI":"10.1016\/j.neucom.2008.12.015","volume":"72","author":"H B Du","year":"2009","unstructured":"Du H B, Chen X C. NN-based output feedback adaptive variable structure control for a class of non-affine nonlinear systems: A nonseparation principle design. Neurocomputing, 2009, 72: 2009\u20132016","journal-title":"Neurocomputing"},{"key":"4954_CR23","doi-asserted-by":"crossref","first-page":"3020","DOI":"10.1016\/j.neucom.2010.07.005","volume":"73","author":"R Z Song","year":"2010","unstructured":"Song R Z, Zhang H G, Luo Y H, et al. Optimal control laws for time-delay systems with saturating actuators based on heuristic dynamic programming. Neurocomputing, 2010, 73: 3020\u20133027","journal-title":"Neurocomputing"},{"key":"4954_CR24","doi-asserted-by":"crossref","first-page":"1839","DOI":"10.1016\/j.neucom.2008.05.012","volume":"72","author":"Q L Wei","year":"2009","unstructured":"Wei Q L, Zhang H G, Dai J. Model-free multiobjective approximate dynamic programming for discrete-time nonlinear systems with general performance index functions. Neurocomputing, 2009, 72: 1839\u20131848","journal-title":"Neurocomputing"},{"key":"4954_CR25","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1007\/s11432-011-4194-y","volume":"54","author":"X Li","year":"2011","unstructured":"Li X, Xian B, Diao C, et al. Output feedback control of hypersonic vehicles based on neural network and high gain observer. Sci China Inf Sci, 2011, 54: 429\u2013447","journal-title":"Sci China Inf Sci"},{"key":"4954_CR26","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1007\/s11432-011-4189-8","volume":"54","author":"B Xu","year":"2011","unstructured":"Xu B, Gao D, Wang S. Adaptive neural control based on HGO for hypersonic flight vehicles. Sci China Inf Sci, 2011, 54: 511\u2013520","journal-title":"Sci China Inf Sci"},{"key":"4954_CR27","doi-asserted-by":"crossref","first-page":"800","DOI":"10.1007\/s11432-010-0075-z","volume":"53","author":"M Wang","year":"2010","unstructured":"Wang M, Zhang S, Chen B, et al. Direct adaptive neural control for stabilization of nonlinear time-delay systems. Sci China Inf Sci, 2010, 53: 800\u2013812","journal-title":"Sci China Inf Sci"},{"key":"4954_CR28","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1007\/s11432-010-4148-9","volume":"54","author":"Z Huang","year":"2011","unstructured":"Huang Z, Wang X, Sannay M. Self-excitation of neurons leads to multiperiodicity of discrete-time neural networks with distributed delays. Sci China Inf Sci, 2011, 54: 305\u2013317","journal-title":"Sci China Inf Sci"},{"key":"4954_CR29","volume-title":"A Tutorial on Training Recurrent Neural Networks, Covering BPPT, RTRL, EKF and the Echo State Network Approach","author":"H Jaeger","year":"2002","unstructured":"Jaeger H. A Tutorial on Training Recurrent Neural Networks, Covering BPPT, RTRL, EKF and the Echo State Network Approach. Bremen: International University Bremen, 2002"},{"key":"4954_CR30","first-page":"1479","volume":"14","author":"M \u010cer\u0148ansk\u00fd","year":"2005","unstructured":"\u010cer\u0148ansk\u00fd M. Feed-forward Echo State Networks. In: Proceedings of International Joint Conference on Neural Networks, Montreal, 2005. 14 1479\u2013148","journal-title":"Proceedings of International Joint Conference on Neural Networks, Montreal"},{"key":"4954_CR31","doi-asserted-by":"crossref","first-page":"1710","DOI":"10.1109\/TNN.2010.2054107","volume":"21","author":"Z Liu","year":"2010","unstructured":"Liu Z, Zhang H, Zhang Q. Novel stability analysis for recurrent neural networks with multiple delays via line integraltype L-K functional. IEEE Trans Neural Netw, 2010, 21: 1710\u20131718","journal-title":"IEEE Trans Neural Netw"},{"key":"4954_CR32","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1109\/TNN.2009.2034742","volume":"21","author":"H Zhang","year":"2010","unstructured":"Zhang H, Liu Z, Huang G, et al. Novel weighting-delay-based stability criteria for recurrent neural networks with time-varying delay. IEEE Trans Neural Netw, 2010, 21: 91\u2013106","journal-title":"IEEE Trans Neural Netw"},{"key":"4954_CR33","volume-title":"Time warping invariant echo state networks","author":"M Luko\u0161evi\u010dius","year":"2006","unstructured":"Luko\u0161evi\u010dius M, Popovici D, Jaeger H, et al. T Time warping invariant echo state networks, 2006. A Available form: http:\/\/jpubs.jacobs-university.de\/bitstream\/579\/149\/1\/twiesniubtechreport.pd"},{"key":"4954_CR34","first-page":"1010","volume-title":"Proceedings of the IEEE International Conference on Systems Man and Cybernetics, Istanbul","author":"P Koprinkova-Hristova","year":"2010","unstructured":"Koprinkova-Hristova P, Oubbati M, Palm G. Adaptive critic design with echo state network. In: Proceedings of the IEEE International Conference on Systems Man and Cybernetics, Istanbul, 2010. 1010\u20131015"},{"key":"4954_CR35","volume-title":"The Echo State Approach to Analysing and Training Recurrent Neural Networks. GMD Report 148, GMDGerman National Research Institute for Computer Science","author":"H Jaeger","year":"2001","unstructured":"Jaeger H. The Echo State Approach to Analysing and Training Recurrent Neural Networks. GMD Report 148, GMDGerman National Research Institute for Computer Science. 2001"},{"key":"4954_CR36","volume-title":"Short Term Memory in Echo State Networks. GMD Report 152, GMD-German National Research Institute for Computer Science","author":"H Jaeger","year":"2002","unstructured":"Jaeger H. Short Term Memory in Echo State Networks. GMD Report 152, GMD-German National Research Institute for Computer Science. 2002"},{"key":"4954_CR37","first-page":"1463","volume-title":"Proceedings of the International Joint Conference on Neural Networks, Montreal","author":"D Prokhorov","year":"2005","unstructured":"Prokhorov D. Echo state networks: appeal and challenges. In: Proceedings of the International Joint Conference on Neural Networks, Montreal, 2005. 1463\u20131466"},{"key":"4954_CR38","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1109\/TNN.2010.2089641","volume":"22","author":"A Rodan","year":"2011","unstructured":"Rodan A, Ti\u0148o P. Minimum complexity echo state network. IEEE Trans Neural Netw, 2011, 22: 131\u2013144","journal-title":"IEEE Trans Neural Netw"},{"key":"4954_CR39","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1109\/TNN.2010.2085444","volume":"22","author":"Y L Xia","year":"2011","unstructured":"Xia Y L, Jelfs B, van Hulle Marc M, et al. An augmented echo state network for nonlinear adaptive filtering of complex noncircular signals, IEEE Trans Neural Netw, 2011, 22: 74\u201383","journal-title":"IEEE Trans Neural Netw"},{"key":"4954_CR40","doi-asserted-by":"crossref","first-page":"2716","DOI":"10.1016\/j.automatica.2008.03.029","volume":"44","author":"W S Lin","year":"2008","unstructured":"Lin W S. Optimality and convergence of adaptive optimal control by reinforcement synthesis. Automatica, 2008, 44: 2716\u20132723","journal-title":"Automatica"},{"key":"4954_CR41","doi-asserted-by":"crossref","first-page":"1851","DOI":"10.1109\/TNN.2011.2172628","volume":"22","author":"H G Zhang","year":"2011","unstructured":"Zhang H G, Song R Z, Wei Q L, et al. Optimal tracking control for a class of nonlinear discrete-time systems with time delays based on heuristic dynamic programming. IEEE Trans Neural Netw, 2011, 22: 1851\u20131862","journal-title":"IEEE Trans Neural Netw"},{"key":"4954_CR42","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1109\/TSMCB.2008.926614","volume":"38","author":"A Al-Tamimi","year":"2007","unstructured":"Al-Tamimi A, Lewis F L. Discrete-time nonlinear HJB solution using approximate dynamic programming: convergence proof. IEEE Trans Syst Man Cybern B Cybern, 2007, 38: 943\u2013949","journal-title":"IEEE Trans Syst Man Cybern B Cybern"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-013-4954-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11432-013-4954-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-013-4954-y","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,26]],"date-time":"2024-05-26T16:01:21Z","timestamp":1716739281000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11432-013-4954-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,5,13]]},"references-count":42,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2014,6]]}},"alternative-id":["4954"],"URL":"https:\/\/doi.org\/10.1007\/s11432-013-4954-y","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,5,13]]}}}