{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,4]],"date-time":"2026-10-04T05:26:14Z","timestamp":1791091574570,"version":"4.1.0"},"reference-count":19,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2010,7,22]],"date-time":"2010-07-22T00:00:00Z","timestamp":1279756800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2010,10]]},"DOI":"10.1007\/s10994-010-5202-y","type":"journal-article","created":{"date-parts":[[2010,7,21]],"date-time":"2010-07-21T13:49:04Z","timestamp":1279720144000},"page":"85-98","source":"Crossref","is-referenced-by-count":19,"title":["Dimension reduction and its application to model-based exploration in continuous spaces"],"prefix":"10.1007","volume":"81","author":[{"given":"Ali","family":"Nouri","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael L.","family":"Littman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2010,7,22]]},"reference":[{"key":"5202_CR1","first-page":"213","volume":"3","author":"R. I. Brafman","year":"2002","unstructured":"Brafman, R. I., & Tennenholtz,\u00a0M. (2002). R-MAX\u2014a\u00a0general polynomial time algorithm for near-optimal reinforcement learning. Journal of Machine Learning Research, 3, 213\u2013231.","journal-title":"Journal of Machine Learning Research"},{"issue":"4","key":"5202_CR2","doi-asserted-by":"crossref","first-page":"466","DOI":"10.1016\/0885-064X(89)90021-6","volume":"5","author":"C. S. Chow","year":"1989","unstructured":"Chow, C. S., & Tsitsiklis, J. N. (1989). The complexity of dynamic programming. Journal of Complexity, 5(4), 466\u2013488.","journal-title":"Journal of Complexity"},{"key":"5202_CR3","doi-asserted-by":"crossref","first-page":"1871","DOI":"10.1214\/08-AOS637","volume":"37","author":"K. Fukumizu","year":"2009","unstructured":"Fukumizu,\u00a0K., Bach, F. R., & Jordan, M. I. (2009). Kernel dimension reduction in regression. Annals of Statistics, 37, 1871.","journal-title":"Annals of Statistics"},{"key":"5202_CR4","doi-asserted-by":"crossref","unstructured":"Gordon, G. J. (1995). Stable function approximation in dynamic programming. In Proceedings of the twelfth international conference on machine learning.","DOI":"10.1016\/B978-1-55860-377-6.50040-2"},{"key":"5202_CR5","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-1904-8","volume-title":"Principal component analysis","author":"I. Jolliffe","year":"1986","unstructured":"Jolliffe,\u00a0I. (1986). Principal component analysis. New York: Springer."},{"key":"5202_CR6","doi-asserted-by":"crossref","unstructured":"Jong, N. K., & Stone,\u00a0P. (2007). Model-based exploration in continuous state spaces. In The 7th symposium on abstraction, reformulation, and approximation.","DOI":"10.1007\/978-3-540-73580-9_21"},{"key":"5202_CR7","unstructured":"Kakade, S. M. (2003). On the sample complexity of reinforcement learning. PhD thesis, Gatsby Computational Neuroscience Unit, University College London."},{"key":"5202_CR8","doi-asserted-by":"crossref","unstructured":"Kolter, J. Z., & Ng, A. Y. (2009). Regularization and feature selection in least-squares temporal difference learning. In Proceedings of the 26th international conference on machine learning.","DOI":"10.1145\/1553374.1553442"},{"issue":"4","key":"5202_CR9","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1561\/2200000003","volume":"1","author":"S. Mahadevan","year":"2009","unstructured":"Mahadevan,\u00a0S. (2009). Learning representation and control in Markov decision processes: new frontiers. Foundations and Trends in Machine Learning, 1(4), 403\u2013565. http:\/\/dx.doi.org\/10.1561\/2200000003 .","journal-title":"Foundations and Trends in Machine Learning"},{"key":"5202_CR10","unstructured":"Nouri,\u00a0A., & Littman, M. L. (2008). Multi-resolution exploration in continuous spaces. In Proceedings of the 22nd neural information processing systems."},{"key":"5202_CR11","doi-asserted-by":"crossref","unstructured":"Parr,\u00a0R., Li,\u00a0L., Taylor,\u00a0G., Painter-Wakefield,\u00a0C., & Littman, M. L. (2008). 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.","DOI":"10.1145\/1390156.1390251"},{"key":"5202_CR12","unstructured":"Smart, W. D. (2004). Explicit manifold representations for value-function approximation in reinforcement learning. In Proceedings of the 8th international symposium on artificial intelligence and mathematics (pp.\u00a025\u20132004)."},{"key":"5202_CR13","doi-asserted-by":"crossref","unstructured":"Strehl, A. L. (2007). Model-based reinforcement learning in factored-state MDPs. In Proceedings of the 2007 IEEE international symposium on approximate dynamic programming and reinforcement learning.","DOI":"10.1109\/ADPRL.2007.368176"},{"key":"5202_CR14","unstructured":"Strehl, A. L., Diuk,\u00a0C., & Littman, M. L. (2007). Efficient structure learning in factored-state MDPs. In Proceedings of the 22nd national conference on artificial intelligence."},{"key":"5202_CR15","doi-asserted-by":"crossref","unstructured":"Sutton, R. S. (1990). Integrated architectures for learning, planning, and reacting based on approximating dynamic programming. In Proceedings of the 7th international conference on machine learning.","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"5202_CR16","unstructured":"Sutton, R. S. (1996). Generalization in reinforcement learning: successful examples using sparse coarse coding. In Proceedings of the 8th advances in neural information processing systems. Cambridge, MA."},{"key":"5202_CR17","volume-title":"Reinforcement learning: an introduction","author":"R. S. Sutton","year":"1998","unstructured":"Sutton, R. S., & Barto, A. G. (1998). Reinforcement learning: an introduction. Cambridge: MIT."},{"key":"5202_CR18","first-page":"527","volume-title":"Handbook of intelligent control: neural, fuzzy, and adaptive approaches","author":"S. B. Thrun","year":"1992","unstructured":"Thrun, S. B. (1992). The role of exploration in learning control. In Handbook of intelligent control: neural, fuzzy, and adaptive approaches (pp.\u00a0527\u2013559). New York: Van Nostrand Reinhold."},{"key":"5202_CR19","unstructured":"Weinberger, K. Q., & Tesauro,\u00a0G. (2007). Metric learning for kernel regression. In Proceedings of the 11th international conference on artificial intelligence and statistics."}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-010-5202-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10994-010-5202-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-010-5202-y","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,31]],"date-time":"2019-05-31T21:40:29Z","timestamp":1559338829000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10994-010-5202-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,7,22]]},"references-count":19,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2010,10]]}},"alternative-id":["5202"],"URL":"https:\/\/doi.org\/10.1007\/s10994-010-5202-y","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,7,22]]}}}