{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T15:22:02Z","timestamp":1725895322586},"publisher-location":"Berlin, Heidelberg","reference-count":10,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642313455"},{"type":"electronic","value":"9783642313462"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-31346-2_28","type":"book-chapter","created":{"date-parts":[[2012,7,21]],"date-time":"2012-07-21T02:42:07Z","timestamp":1342838527000},"page":"246-255","source":"Crossref","is-referenced-by-count":0,"title":["A Novel Feature Sparsification Method for Kernel-Based Approximate Policy Iteration"],"prefix":"10.1007","author":[{"given":"Zhenhua","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanqiang","family":"Lian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"28_CR1","volume-title":"Reinforcement learning:an introduction","author":"R. Sutton","year":"1998","unstructured":"Sutton, R., Barto, A.: Reinforcement learning:an introduction. MIT Press, Cambridge (1998)"},{"issue":"2-3","key":"28_CR2","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1023\/A:1017936530646","volume":"49","author":"J. Boyan","year":"2002","unstructured":"Boyan, J.: Technical update: Least-squares temporal difference learning. Mach. Learn.\u00a049(2-3), 233\u2013246 (2002)","journal-title":"Mach. Learn."},{"key":"28_CR3","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1109\/TNN.2007.899161","volume":"18","author":"X. Xu","year":"2007","unstructured":"Xu, X., et al.: Kernel-based Least-Squares Policy Iteration for Reinforcement Learning. IEEE Trans. on Neural Networks\u00a018, 973\u2013992 (2007)","journal-title":"IEEE Trans. on Neural Networks"},{"key":"28_CR4","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1613\/jair.946","volume":"16","author":"X. Xu","year":"2002","unstructured":"Xu, X., et al.: Efficient Reinforcement Learning Using Recursive Least-Squares Methods. Journal of Artificial Intelligence Research\u00a016, 259\u2013292 (2002)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"28_CR5","volume-title":"An Introduction to Support Vector Machines","author":"N. Cristianini","year":"2000","unstructured":"Cristianini, N., Shawe-Taylor, J.: An Introduction to Support Vector Machines. Cambridge Univ. Press, Cambridge (2000)"},{"key":"28_CR6","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"L.P. Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., et al.: Reinforcement learning: A survey. J. Artif. Intell. Res.\u00a04, 237\u2013285 (1996)","journal-title":"J. Artif. Intell. Res."},{"key":"28_CR7","first-page":"1107","volume":"4","author":"M.G. Lagoudakis","year":"2003","unstructured":"Lagoudakis, M.G., Parr, R.: Least-squares policy iteration. J.Mach. Learn. Res.\u00a04, 1107\u20131149 (2003)","journal-title":"J.Mach. Learn. Res."},{"issue":"2","key":"28_CR8","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1023\/A:1017928328829","volume":"49","author":"S.. Ormoneit","year":"2002","unstructured":"Ormoneit, S.: Kernel-based reinforcement learning. Machine Learning\u00a049(2), 161\u2013178 (2002)","journal-title":"Machine Learning"},{"key":"28_CR9","volume-title":"Learning With Kernels","author":"B. Sch\u00f6lkopf","year":"2002","unstructured":"Sch\u00f6lkopf, B., Smola, A.: Learning With Kernels. MIT Press, Cambridge (2002)"},{"issue":"5","key":"28_CR10","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1109\/9.580874","volume":"42","author":"J.N. Tsitsiklis","year":"1997","unstructured":"Tsitsiklis, J.N., Roy, B.V.: An analysis of temporal difference learning with function approximation. IEEE Trans. Autom. Control.\u00a042(5), 674\u2013690 (1997)","journal-title":"IEEE Trans. Autom. Control."}],"container-title":["Lecture Notes in Computer Science","Advances in Neural Networks \u2013 ISNN 2012"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-31346-2_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,4]],"date-time":"2019-05-04T04:22:11Z","timestamp":1556943731000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-31346-2_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642313455","9783642313462"],"references-count":10,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-31346-2_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}