{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T10:31:13Z","timestamp":1725532273608},"publisher-location":"Berlin, Heidelberg","reference-count":13,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642015090"},{"type":"electronic","value":"9783642015106"}],"license":[{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009]]},"DOI":"10.1007\/978-3-642-01510-6_46","type":"book-chapter","created":{"date-parts":[[2009,5,20]],"date-time":"2009-05-20T03:38:37Z","timestamp":1242790717000},"page":"398-407","source":"Crossref","is-referenced-by-count":0,"title":["Reordering Sparsification of Kernel Machines in Approximate Policy Iteration"],"prefix":"10.1007","author":[{"given":"Chunming","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinze","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengcheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"46_CR1","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning. MIT Press, Cambridge (1998)"},{"key":"46_CR2","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"L.P. Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement Learning: A Survey. Journal of Artificial Intelligence Research\u00a04, 237\u2013285 (1996)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"46_CR3","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1109\/TNN.2007.899161","volume":"18","author":"X. Xu","year":"2007","unstructured":"Xu, X., Hu, D.W., Lu, X.C.: Kernel Based Least-squares Policy Iteration. IEEE Transactions on Neural Networks\u00a018, 973\u2013992 (2007)","journal-title":"IEEE Transactions on Neural Networks"},{"key":"46_CR4","unstructured":"Bertsekas, D.P., Tsitsiklis, J.N.: Neurodynamic Programming. Athena Scientific, Belmont (1996)"},{"key":"46_CR5","doi-asserted-by":"publisher","first-page":"875","DOI":"10.1109\/72.935097","volume":"12","author":"J. Moody","year":"2001","unstructured":"Moody, J., Saffell, M.: Learning to Trade Via Direct Reinforcement. IEEE Transactions on Neural Networks\u00a012, 875\u2013889 (2001)","journal-title":"IEEE Transactions on Neural Networks"},{"key":"46_CR6","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1613\/jair.806","volume":"15","author":"J. Baxter","year":"2001","unstructured":"Baxter, J., Bartlett, P.L.: Infinite-horizon Policy-gradient Estimation. Journal of Artificial Intelligence Research\u00a015, 319\u2013350 (2001)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"46_CR7","first-page":"835","volume":"13","author":"A.G. Barto","year":"1983","unstructured":"Barto, A.G., Sutton, R.S., Anderson, C.W.: Neuronlike Adaptive Elements that Can Solve Difficult Learning Control Problems. IEEE Transactions on System, Man, and Cybernetics\u00a013, 835\u2013846 (1983)","journal-title":"IEEE Transactions on System, Man, and Cybernetics"},{"key":"46_CR8","unstructured":"Konda, V.R., Tsitsiklis, J.N.: Actor-Critic Algorithm. In: Advances in Neural Information Processing Systems. MIT Press, Cambridge (2000)"},{"key":"46_CR9","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1613\/jair.946","volume":"16","author":"X. Xu","year":"2002","unstructured":"Xu, X., He, H.G., Hu, D.W.: 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":"46_CR10","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. Machine Learning\u00a049, 233\u2013246 (2002)","journal-title":"Machine Learning"},{"key":"46_CR11","first-page":"1107","volume":"4","author":"M.G. Lagoudakis","year":"2003","unstructured":"Lagoudakis, M.G., Parr, P.: Least-squares Policy Iteration. Journal of Machine Learning Research\u00a04, 1107\u20131149 (2003)","journal-title":"Journal of Machine Learning Research"},{"key":"46_CR12","doi-asserted-by":"publisher","first-page":"2275","DOI":"10.1109\/TSP.2004.830985","volume":"52","author":"Y. Engel","year":"2004","unstructured":"Engel, Y., Mannor, S., Meir, R.: The Kernel Recursive Least-squares Algorithm. IEEE Transactions on Signal Processing\u00a052, 2275\u20132285 (2004)","journal-title":"IEEE Transactions on Signal Processing"},{"key":"46_CR13","unstructured":"Vapnik, V.: Statistical Learning Theory. Wiley Interscience, NewYork (1998)"}],"container-title":["Lecture Notes in Computer Science","Advances in Neural Networks \u2013 ISNN 2009"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-01510-6_46","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,3,8]],"date-time":"2019-03-08T01:09:20Z","timestamp":1552007360000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-01510-6_46"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783642015090","9783642015106"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-01510-6_46","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2009]]}}}