{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:08:09Z","timestamp":1725685689037},"publisher-location":"Berlin, Heidelberg","reference-count":16,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642304477"},{"type":"electronic","value":"9783642304484"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-30448-4_23","type":"book-chapter","created":{"date-parts":[[2012,5,25]],"date-time":"2012-05-25T11:34:21Z","timestamp":1337945661000},"page":"182-189","source":"Crossref","is-referenced-by-count":0,"title":["An Online Kernel-Based Clustering Approach for Value Function Approximation"],"prefix":"10.1007","author":[{"given":"Nikolaos","family":"Tziortziotis","sequence":"first","affiliation":[]},{"given":"Konstantinos","family":"Blekas","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"23_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)"},{"key":"23_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 Inteligence Research\u00a04, 237\u2013285 (1996)","journal-title":"Journal of Artificial Inteligence Research"},{"issue":"1","key":"23_CR3","first-page":"9","volume":"3","author":"R. Sutton","year":"1988","unstructured":"Sutton, R.: Learning to predict by the method of temporal differences. Machine Learning\u00a03(1), 9\u201344 (1988)","journal-title":"Machine Learning"},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Boyan, J.A.: Technical update: Least-squares temporal difference learning. Machine Learning, 233\u2013246 (2002)","DOI":"10.1023\/A:1017936530646"},{"key":"23_CR5","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":"4","key":"23_CR6","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., Lu, X.: Kernel-based least squares policy iteration for reinforcement learning. IEEE Transactions on Neural Networks\u00a018(4), 973\u2013992 (2007)","journal-title":"IEEE Transactions on Neural Networks"},{"key":"23_CR7","unstructured":"Rasmussen, C.E., Kuss, M.: Gaussian processes in reinforcement learning. In: Advances in Neural Information Processing Systems 16, pp. 751\u2013759 (2004)"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Engel, Y., Mannor, S., Meir, R.: Reinforcement learning with gaussian process. In: International Conference on Machine Learning, pp. 201\u2013208 (2005)","DOI":"10.1145\/1102351.1102377"},{"key":"23_CR9","unstructured":"Farahmand, A.M., Ghavamzadeh, M., Szepesv\u00e1ri, C., Mannor, S.: Regularized policy iteration. In: NIPS, pp. 441\u2013448 (2008)"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Konidaris, G.D., Osentoski, S., Thomas, P.S.: Value function approximation in reinforcement learning using the fourier basis. In: AAAI Conf. on Artificial Intelligence, pp. 380\u2013385 (2011)","DOI":"10.1609\/aaai.v25i1.7903"},{"key":"23_CR11","unstructured":"Mahadevan, S.: Samuel meets amarel: Automating value function approximation using global state space analysis. In: AAAI (2005)"},{"key":"23_CR12","first-page":"2169","volume":"8","author":"S. Mahadevan","year":"2007","unstructured":"Mahadevan, S., Maggione, M.: Proto-value Functions: A Laplacian Framework for Learning Repersentation and Control in Markov Decision Porocesses. Journal of Machine Learning Research\u00a08, 2169\u20132231 (2007)","journal-title":"Journal of Machine Learning Research"},{"key":"23_CR13","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1007\/s10479-005-5732-z","volume":"134","author":"I. Menache","year":"2005","unstructured":"Menache, I., Mannor, S., Shimkin, N.: Basis Function Adaptation in Temporal Difference Reinforcement Learning. Annals of Operations Research\u00a0134, 215\u2013238 (2005)","journal-title":"Annals of Operations Research"},{"key":"23_CR14","unstructured":"Petrik, M.: An analysis of laplacian methods for value function approximation in mdps. In: International Joint Conference on Artificial Intelligence, pp. 2574\u20132579 (2007)"},{"issue":"5","key":"23_CR15","doi-asserted-by":"publisher","first-page":"1299","DOI":"10.1162\/089976698300017467","volume":"10","author":"B. Scholkopf","year":"1998","unstructured":"Scholkopf, B., Smola, A.J., Muller, K.-R.: Nonlinear component analysis as a kernel eigenvalue problem. Neural Computation\u00a010(5), 1299\u20131319 (1998)","journal-title":"Neural Computation"},{"issue":"7","key":"23_CR16","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1109\/TNN.2009.2019722","volume":"20","author":"G. Tzortzis","year":"2009","unstructured":"Tzortzis, G., Likas, A.: The Global Kernel k-Means Clustering Algorithm. IEEE Trans. on Neural Networks\u00a020(7), 1181\u20131194 (2009)","journal-title":"IEEE Trans. on Neural Networks"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence: Theories and Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-30448-4_23.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,22]],"date-time":"2023-06-22T19:18:10Z","timestamp":1687461490000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-30448-4_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642304477","9783642304484"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-30448-4_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}