{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T16:35:05Z","timestamp":1761323705105},"publisher-location":"Berlin, Heidelberg","reference-count":19,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642158797"},{"type":"electronic","value":"9783642158803"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-15880-3_36","type":"book-chapter","created":{"date-parts":[[2010,8,17]],"date-time":"2010-08-17T14:08:53Z","timestamp":1282054133000},"page":"474-489","source":"Crossref","is-referenced-by-count":13,"title":["Feature Selection for Reinforcement Learning: Evaluating Implicit State-Reward Dependency via Conditional Mutual Information"],"prefix":"10.1007","author":[{"given":"Hirotaka","family":"Hachiya","sequence":"first","affiliation":[]},{"given":"Masashi","family":"Sugiyama","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"36_CR1","volume-title":"Reinforcement Learning: An Introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, G.A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"36_CR2","doi-asserted-by":"publisher","first-page":"1107","DOI":"10.1162\/jmlr.2003.4.6.1107","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"},{"key":"36_CR3","first-page":"229","volume":"8","author":"R.J. Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning\u00a08, 229\u2013256 (1992)","journal-title":"Machine Learning"},{"issue":"2","key":"36_CR4","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1162\/neco.1997.9.2.271","volume":"9","author":"P. Dayan","year":"1997","unstructured":"Dayan, P., Hinton, G.E.: Using expectation-maximization for reinforcement learning. Neural Computation\u00a09(2), 271\u2013278 (1997)","journal-title":"Neural Computation"},{"key":"36_CR5","first-page":"1531","volume":"14","author":"S. Kakade","year":"2002","unstructured":"Kakade, S.: A natural policy gradient. Advances in Neural Information Processing Systems\u00a014, 1531\u20131538 (2002)","journal-title":"Advances in Neural Information Processing Systems"},{"key":"36_CR6","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1162\/153244303322753616","volume":"3","author":"I. Guyon","year":"2003","unstructured":"Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. Journal of Machine Learning Research\u00a03, 1157\u20131182 (2003)","journal-title":"Journal of Machine Learning Research"},{"key":"36_CR7","doi-asserted-by":"crossref","unstructured":"Keller, P.W., Mannor, S., Precup, D.: Automatic basis function construction for approximate dynamic programming and reinforcement learning. In: Proceedings of the 23rd International Conference on Machine learning, pp. 449\u2013456 (2006)","DOI":"10.1145\/1143844.1143901"},{"key":"36_CR8","doi-asserted-by":"crossref","unstructured":"Parr, R., Painter, C.W., Li, L., Littman, L.M.: Analyzing feature generation for value-function approximation. In: Proceedings of the 24th International Conference on Machine Learning, pp. 737\u2013744 (2007)","DOI":"10.1145\/1273496.1273589"},{"key":"36_CR9","doi-asserted-by":"crossref","unstructured":"Parr, R., Li, L., Taylor, G., Painter, C.W., Littman, L.M.: An analysis of linear models, linear value-function approximation, and feature selection for reinforcement learning. In: Proceedings of the 25th International Conference on Machine Learning, pp. 752\u2013759 (2008)","DOI":"10.1145\/1390156.1390251"},{"key":"36_CR10","first-page":"513","volume-title":"Advances in Neural Information Processing Systems","author":"J. Goldberger","year":"2005","unstructured":"Goldberger, J., Roweis, S., Hinton, G., Salakhutdinov, R.: Neighbourhood components analysis. In: Saul, L.K., Weiss, Y., Bottou, L. (eds.) Advances in Neural Information Processing Systems, vol.\u00a017, pp. 513\u2013520. MIT Press, Cambridge (2005)"},{"key":"36_CR11","doi-asserted-by":"crossref","unstructured":"Morimoto, J., Hyon, S., Atkeson, C.G., Cheng, G.: Low-dimensional feature extraction for humaniod locomotion using kernel dimension reduction. In: Proceedings of 2007 IEEE International Conference on Robotics and Automation, pp. 2711\u20132716 (2008)","DOI":"10.1109\/ROBOT.2008.4543621"},{"key":"36_CR12","doi-asserted-by":"crossref","unstructured":"Kroon, M., Whiteson, S.: Automatic feature selection for model-based reinforcement learning in factored mdps. In: Proceedings of the 2009 International Conference on Machine Learning and Applications, pp. 324\u2013330 (2009)","DOI":"10.1109\/ICMLA.2009.71"},{"issue":"4","key":"36_CR13","doi-asserted-by":"publisher","first-page":"1871","DOI":"10.1214\/08-AOS637","volume":"37","author":"K. Fukumizu","year":"2009","unstructured":"Fukumizu, K., Bach, F.R., Jordan, M.I.: Kernel dimension reduction in regression. Annals of Statistics\u00a037(4), 1871\u20131905 (2009)","journal-title":"Annals of Statistics"},{"key":"36_CR14","volume-title":"Information Theory, Inference, and Learning Algorithms","author":"D.J.C. MacKay","year":"2003","unstructured":"MacKay, D.J.C.: Information Theory, Inference, and Learning Algorithms. Cambridge University Press, Cambridge (2003)"},{"issue":"1","key":"36_CR15","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1186\/1471-2105-10-S1-S52","volume":"10","author":"T. Suzuki","year":"2009","unstructured":"Suzuki, T., Sugiyama, M., Kanamori, T., Sese, J.: Mutual information estimation reveals global associations between stimuli and biological processes. BMC Bioinformatics\u00a010(1), S52 (2009)","journal-title":"BMC Bioinformatics"},{"key":"36_CR16","volume-title":"Statistical Learning Theory","author":"V.N. Vapnik","year":"1998","unstructured":"Vapnik, V.N.: Statistical Learning Theory. Wiley, New York (1998)"},{"key":"36_CR17","first-page":"1391","volume":"10","author":"T. Kanamori","year":"2009","unstructured":"Kanamori, T., Hido, S., Sugiyama, M.: A least-squares approach to direct importance estimation. Journal of Machine Learning Research\u00a010, 1391\u20131445 (2009)","journal-title":"Journal of Machine Learning Research"},{"key":"36_CR18","unstructured":"Kanamori, T., Suzuki, T., Sugiyama, M.: Condition number analysis of kernel-based density ratio estimation. Technical report, arXiv (2009), http:\/\/www.citebase.org\/abstract?id=oai:arXiv.org:0912.2800"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Song, L., Smola, A., Gretton, A., Borgwardt, K., Bedo, J.: Supervised feature selection via dependence estimation. In: Proceedings of the 24th International Conference on Machine Learning, pp. 823\u2013830 (2007)","DOI":"10.1145\/1273496.1273600"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-15880-3_36.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,24]],"date-time":"2020-11-24T02:42:02Z","timestamp":1606185722000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-15880-3_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642158797","9783642158803"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-15880-3_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}