{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:05:06Z","timestamp":1740096306460,"version":"3.37.3"},"publisher-location":"Berlin, Heidelberg","reference-count":14,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642420412"},{"type":"electronic","value":"9783642420429"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-42042-9_31","type":"book-chapter","created":{"date-parts":[[2013,10,29]],"date-time":"2013-10-29T10:08:03Z","timestamp":1383041283000},"page":"242-249","source":"Crossref","is-referenced-by-count":1,"title":["Online Model-Free RLSPI Algorithm for Nonlinear Discrete-Time Non-affine Systems"],"prefix":"10.1007","author":[{"given":"Yuanheng","family":"Zhu","sequence":"first","affiliation":[]},{"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"31_CR1","volume-title":"Reinforcement Learning: An Introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"issue":"2","key":"31_CR2","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1109\/MCI.2009.932261","volume":"4","author":"F. Wang","year":"2009","unstructured":"Wang, F., Zhang, H., Liu, D.: Adaptive Dynamic Programming: An Introduction. IEEE Comput. Intell. Mag.\u00a04(2), 39\u201347 (2009)","journal-title":"IEEE Comput. Intell. Mag."},{"issue":"3","key":"31_CR3","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1109\/MCAS.2009.933854","volume":"9","author":"F.L. Lewis","year":"2009","unstructured":"Lewis, F.L., Vrabie, D.: Reinforcement Learning and Adaptive Dynamic Programming for Feedback Control. IEEE Circuits Syst. Mag.\u00a09(3), 32\u201350 (2009)","journal-title":"IEEE Circuits Syst. Mag."},{"key":"31_CR4","volume-title":"Dynamic Programming and Markov Processes","author":"R. Howard","year":"1960","unstructured":"Howard, R.: Dynamic Programming and Markov Processes. MIT Press, Cambridge (1960)"},{"key":"31_CR5","volume-title":"Neuro-Dynamic Programming","author":"D.P. Bertsekas","year":"1996","unstructured":"Bertsekas, D.P., Tsitsiklis, J.N.: Neuro-Dynamic Programming. Athena Scientific, Belmont (1996)"},{"key":"31_CR6","first-page":"59","volume":"22","author":"J.N. Tsitsiklis","year":"1996","unstructured":"Tsitsiklis, J.N., Van Roy, B.: Feature-Based Methods for Large Scale Dynamic Programming. Machine Learning\u00a022, 59\u201394 (1996)","journal-title":"Machine Learning"},{"issue":"5","key":"31_CR7","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1109\/9.580874","volume":"42","author":"J.N. Tsitsiklis","year":"1997","unstructured":"Tsitsiklis, J.N., Van Roy, B.: An Analysis of Temporal Difference Learning with Function Approximation. IEEE Trans. Automat. Contr.\u00a042(5), 674\u2013690 (1997)","journal-title":"IEEE Trans. Automat. Contr."},{"issue":"4","key":"31_CR8","doi-asserted-by":"publisher","first-page":"990","DOI":"10.1109\/TITS.2011.2122257","volume":"12","author":"D.B. Zhao","year":"2011","unstructured":"Zhao, D.B., Bai, X.R., Wang, F.Y., Xu, J., Yu, W.S.: DHP Method for Ramp Metering of Freeway Traffic. IEEE Transactions on Intelligent Transportation Systems\u00a012(4), 990\u2013999 (2011)","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"Zhao, D.B., Hu, Z.H., Xia, Z.P., Alippi, C., Wang, D.: A Human-Like Full Range Adaptive Cruise Control Based on Supervised Adaptive Dynamic Programming. Neurocomputing (in press), \n                  \n                    http:\/\/dx.doi.org\/10.1016\/j.neucom.2012.09.034","DOI":"10.1016\/j.neucom.2012.09.034"},{"issue":"2","key":"31_CR10","doi-asserted-by":"publisher","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.\u00a012(2), 264\u2013276 (2001)","journal-title":"IEEE Trans. Neural Netw."},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Busoniu, L., Ernst, D., De Schutter, B., Babuska, R.: Online Least-Squares Policy Iteration for Reinforcement Learning Control. In: Proc. 2010 American Control Conf. (ACC 2010), pp. 486\u2013491 (2010)","DOI":"10.1109\/ACC.2010.5530856"},{"key":"31_CR12","first-page":"1107","volume":"4","author":"M.G. Lagoudakis","year":"2003","unstructured":"Lagoudakis, M.G., Parr, R.: Least-Squares Policy Iteration. Journal of Machine Learning Research\u00a04, 1107\u20131149 (2003)","journal-title":"Journal of Machine Learning Research"},{"issue":"5","key":"31_CR13","doi-asserted-by":"publisher","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 with Saturating Actuators Using a Neural Network HJB Approach. Automatica\u00a041(5), 779\u2013791 (2005)","journal-title":"Automatica"},{"issue":"9","key":"31_CR14","doi-asserted-by":"publisher","first-page":"1490","DOI":"10.1109\/TNN.2009.2027233","volume":"20","author":"H. Zhang","year":"2009","unstructured":"Zhang, H., Luo, Y., Liu, D.: Neural-Network-Based Near-Optimal Control for a Class of Discrete-Time Affine Nonlinear Systems with Control Constraints. IEEE Trans. Neural Netw.\u00a020(9), 1490\u20131503 (2009)","journal-title":"IEEE Trans. Neural Netw."}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-42042-9_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,23]],"date-time":"2019-05-23T21:11:58Z","timestamp":1558645918000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-42042-9_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642420412","9783642420429"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-42042-9_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}