{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,1,19]],"date-time":"2023-01-19T05:31:19Z","timestamp":1674106279160},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"3-4","license":[{"start":{"date-parts":[[2010,4,1]],"date-time":"2010-04-01T00:00:00Z","timestamp":1270080000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Ann Math Artif Intell"],"published-print":{"date-parts":[[2010,4]]},"DOI":"10.1007\/s10472-010-9201-2","type":"journal-article","created":{"date-parts":[[2010,6,28]],"date-time":"2010-06-28T09:39:50Z","timestamp":1277717990000},"page":"217-237","source":"Crossref","is-referenced-by-count":3,"title":["Reducing reinforcement learning to KWIK online regression"],"prefix":"10.1007","volume":"58","author":[{"given":"Lihong","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael L.","family":"Littman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2010,6,29]]},"reference":[{"key":"9201_CR1","unstructured":"Asmuth, J., Li, L., Littman, M. L., Nouri, A., Wingate, D.: A Bayesian sampling approach to exploration in reinforcement learning. In: Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence (UAI-09), pp. 19\u201326 (2009)"},{"key":"9201_CR2","first-page":"397","volume":"3","author":"P Auer","year":"2002","unstructured":"Auer, P.: Using confidence bounds for exploitation-exploration trade-offs. J. Mach. Learn. Res. 3, 397\u2013422 (2002)","journal-title":"J. Mach. Learn. Res."},{"issue":"NIPS-03","key":"9201_CR3","first-page":"831","volume":"16","author":"JA Bagnell","year":"2004","unstructured":"Bagnell, J.A., Kakade, S., Ng, A.Y., Schneider, J.: Policy search by dynamic programming. Adv. Neural Inf. Process. Syst. 16 (NIPS-03), 831\u2013838 (2004)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"9201_CR4","first-page":"369","volume":"7","author":"JA Boyan","year":"1995","unstructured":"Boyan, J.A., Moore, A.W.: Generalization in reinforcement learning: safely approximating the value function. Adv. Neural Inf. Process. Syst. 7, 369\u2013376 (1995)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"9201_CR5","first-page":"213","volume":"3","author":"RI Brafman","year":"2002","unstructured":"Brafman, R.I., Tennenholtz, M.: R-max\u2014a general polynomial time algorithm for near-optimal reinforcement learning. J. Mach. Learn. Res. 3, 213\u2013231 (2002)","journal-title":"J. Mach. Learn. Res."},{"key":"9201_CR6","doi-asserted-by":"crossref","unstructured":"Cesa-Bianchi, N., Lugosi, G.: Prediction, Learning, and Games. Cambridge University Press (2006)","DOI":"10.1017\/CBO9780511546921"},{"key":"9201_CR7","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1214\/aoms\/1177729330","volume":"23","author":"H Chernoff","year":"1952","unstructured":"Chernoff, H.: A measure of asymptotic efficiency for tests of a hypothesis based on the sum of observations. Ann. Math. Stat. 23, 493\u2013507 (1952)","journal-title":"Ann. Math. Stat."},{"key":"9201_CR8","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.: The complexity of dynamic programming. J. Complex. 5, 466\u2013488 (1989)","journal-title":"J. Complex."},{"key":"9201_CR9","unstructured":"Duff, M.O.: Optimal Learning: Computational Procedures for Bayes-adaptive Markov Decision Processes. Doctoral dissertation, University of Massachusetts, Amherst, MA (2002)"},{"key":"9201_CR10","doi-asserted-by":"crossref","unstructured":"Engel, Y., Mannor, S., Meir, R.: Reinforcement learning with Gaussian processes. In: Proceedings of the Twenty-Second International Conference on Machine Learning (ICML-05), pp. 201\u2013208 (2005)","DOI":"10.1145\/1102351.1102377"},{"key":"9201_CR11","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1613\/jair.1700","volume":"25","author":"A Fern","year":"2006","unstructured":"Fern, A., Yoon, S.W., Givan, R.: Approximate policy iteration with a policy language bias: solving relational Markov decision processes. J. Artif. Intell. Res. 25, 75\u2013118 (2006)","journal-title":"J. Artif. Intell. Res."},{"key":"9201_CR12","doi-asserted-by":"crossref","unstructured":"Fiechter, C.-N.: Efficient reinforcement learning. In: Proceedings of the Seventh Annual ACM Conference on Computational Learning Theory, pp. 88\u201397 (1994)","DOI":"10.1145\/180139.181019"},{"key":"9201_CR13","doi-asserted-by":"crossref","unstructured":"Geist, M., Pietquin, O., Fricout, G.: Kalman temporal differences: the deterministic case. In: Proceedings of the IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL-09), pp. 185\u2013192 (2009)","DOI":"10.1109\/ADPRL.2009.4927543"},{"key":"9201_CR14","doi-asserted-by":"crossref","unstructured":"Jong, N.K., Stone, P.: Model-based exploration in continuous state spaces. In: Proceedings of the Seventh International Symposium on Abstraction, Reformulation and Approximation (SARA-07), pp. 258\u2013272 (2007)","DOI":"10.1007\/978-3-540-73580-9_21"},{"key":"9201_CR15","unstructured":"Kakade, S.: On the Sample Complexity of Reinforcement Learning. Doctoral dissertation, University College London, UK (2003)"},{"key":"9201_CR16","unstructured":"Kakade, S., Kearns, M.J., Langford, J.: Exploration in metric state spaces. In: Proceedings of the Twentieth International Conference on Machine Learning, pp. 306\u2013312 (2003)"},{"key":"9201_CR17","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1023\/A:1017932429737","volume":"49","author":"MJ Kearns","year":"2002","unstructured":"Kearns, M.J., Mansour, Y., Ng, A.Y.: A sparse sampling algorithm for near-optimal planning in large Markov decision processes. Mach. Learn. 49, 193\u2013208 (2002)","journal-title":"Mach. Learn."},{"key":"9201_CR18","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1023\/A:1017984413808","volume":"49","author":"MJ Kearns","year":"2002","unstructured":"Kearns, M.J., Singh, S.P.: Near-optimal reinforcement learning in polynomial time. Mach. Learn. 49, 209\u2013232 (2002)","journal-title":"Mach. Learn."},{"key":"9201_CR19","doi-asserted-by":"crossref","unstructured":"Kearns, M.J., Vazirani, U.V.: An Introduction to Computational Learning Theory. MIT Press (1994)","DOI":"10.7551\/mitpress\/3897.001.0001"},{"key":"9201_CR20","first-page":"227","volume":"22","author":"S Koenig","year":"1996","unstructured":"Koenig, S., Simmons, R.G.: The effect of representation and knowledge on goal-directed exploration with reinforcement-learning algorithms. Mach. Learn. 22, 227\u2013250 (1996)","journal-title":"Mach. Learn."},{"key":"9201_CR21","doi-asserted-by":"crossref","unstructured":"Kolter, J.Z., Ng, A.Y.: Near Bayesian exploration in polynomial time. In: Proceedings of the Twenty-Sixth International Conference on Machine Learning (ICML-09), pp. 513\u2013520 (2009)","DOI":"10.1145\/1553374.1553441"},{"key":"9201_CR22","first-page":"1107","volume":"4","author":"MG Lagoudakis","year":"2003","unstructured":"Lagoudakis, M.G., Parr, R.: Least-squares policy iteration. J. Mach. Learn. Res. 4, 1107\u20131149 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"9201_CR23","unstructured":"Lagoudakis, M.G., Parr, R.: Reinforcement learning as classification: leveraging modern classifiers. In: Proceedings of the Twentieth International Conference on Machine Learning (ICML-03), pp. 424\u2013431 (2003)"},{"key":"9201_CR24","unstructured":"Langford, J., Zadrozny, B.: Reducing T-step reinforcement learning to classification. In: Proceedings of the Machine Learning Reductions Workshop. Chicago, IL (2003)"},{"key":"9201_CR25","doi-asserted-by":"crossref","unstructured":"Langford, J., Zadrozny, B.: Relating reinforcement learning performance to classification performance. In: Proceedings of the Twenty-Second International Conference on Machine Learning (ICML-05), pp. 473\u2013480 (2005)","DOI":"10.1145\/1102351.1102411"},{"key":"9201_CR26","unstructured":"Li, L.: Focus of Attention in Reinforcement Learning. Master\u2019s thesis, University of Alberta, Edmonton, AB, Canada (2004)"},{"key":"9201_CR27","unstructured":"Li, L.: A Unifying Framework for Computational Reinforcement Learning Theory. Doctoral dissertation, Rutgers University, New Brunswick, NJ (2009)"},{"key":"9201_CR28","first-page":"1246","volume":"13","author":"L Li","year":"2007","unstructured":"Li, L., Bulitko, V., Greiner, R.: Focus of attention in reinforcement learning. J. Univers. Comput. Sci. 13, 1246\u20131269 (2007)","journal-title":"J. Univers. Comput. Sci."},{"key":"9201_CR29","unstructured":"Li, L., Littman, M.L.: Efficient value-function approximation via online linear regression. In: Proceedings of the Tenth International Symposium on Artificial Intelligence and Mathematics (AMAI-08) (2008)"},{"key":"9201_CR30","unstructured":"Li, L., Littman, M.L., Mansley, C.R.: Online exploration in least-squares policy iteration. In: Proceedings of the Eighteenth International Conference on Agents and Multiagent Systems (AAMAS-09) (2009)"},{"key":"9201_CR31","doi-asserted-by":"crossref","unstructured":"Li, L., Littman, M.L., Walsh, T.J.: Knows what it knows: A framework for self-aware learning. In: Proceedings of the Twenty-Fifth International Conference on Machine Learning (ICML-08), pp. 568\u2013575 (2008)","DOI":"10.1145\/1390156.1390228"},{"key":"9201_CR32","doi-asserted-by":"crossref","unstructured":"Li, L., Littman, M.L., Walsh, T.J., Strehl, A.L.: Knows what it knows: a framework for self-aware learning. (2010, in submission)","DOI":"10.1007\/s10994-010-5225-4"},{"key":"9201_CR33","first-page":"1563","volume":"11","author":"R Ortner","year":"2010","unstructured":"Ortner, R., Auer, P., Jaksch, T.: Near-optimal regret bounds for reinforcement learning. J. Mach. Learn. Res. 11, 1563\u20131600 (2010)","journal-title":"J.Mach. Learn. Res."},{"key":"9201_CR34","doi-asserted-by":"crossref","unstructured":"Poupart, P., Vlassis, N., Hoey, J., Regan, K.: An analytic solution to discrete Bayesian reinforcement learning. In: Proceedings of the Twenty-Third International Conference on Machine Learning (ICML-06), pp. 697\u2013704 (2006)","DOI":"10.1145\/1143844.1143932"},{"key":"9201_CR35","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"ML Puterman","year":"1994","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley-Interscience, New York (1994)"},{"key":"9201_CR36","first-page":"2413","volume":"10","author":"AL Strehl","year":"2009","unstructured":"Strehl, A.L., Li, L., Littman, M.L.: Reinforcement learning in finite MDPs: PAC analysis. J. Mach. Learn. Res. 10, 2413\u20132444 (2009)","journal-title":"J. Mach. Learn. Res."},{"key":"9201_CR37","doi-asserted-by":"crossref","unstructured":"Strehl, A.L., Li, L., Wiewiora, E., Langford, J., Littman, M.L.: PAC model-free reinforcement learning. In: Proceedings of the Twenty-Third International Conference on Machine Learning, pp. 881\u2013888 (2006)","DOI":"10.1145\/1143844.1143955"},{"key":"9201_CR38","doi-asserted-by":"crossref","unstructured":"Strehl, A.L., Littman, M.L.: A theoretical analysis of model-based interval estimation. In: Proceedings of the Twenty-Second Conference on Machine Learning, pp. 857\u2013864 (2005)","DOI":"10.1145\/1102351.1102459"},{"key":"9201_CR39","first-page":"1417","volume":"20","author":"AL Strehl","year":"2008","unstructured":"Strehl, A.L., Littman, M.L.: Online linear regression and its application to model-based reinforcement learning. Adv. Neural Inf. Process. Syst. 20, 1417\u20131424 (2008)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"9201_CR40","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge, MA (1998)"},{"key":"9201_CR41","unstructured":"Thrun, S.: The role of exploration in learning control. In: White, D.A., Sofge, D.A. (eds.) Handbook of Intelligent Control: Neural, Fuzzy and Adaptive Approaches, pp. 527\u2013559. Van Nostrand Reinhold (1992)"}],"container-title":["Annals of Mathematics and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10472-010-9201-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10472-010-9201-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10472-010-9201-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,30]],"date-time":"2019-05-30T13:47:06Z","timestamp":1559224026000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10472-010-9201-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,4]]},"references-count":41,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2010,4]]}},"alternative-id":["9201"],"URL":"https:\/\/doi.org\/10.1007\/s10472-010-9201-2","relation":{},"ISSN":["1012-2443","1573-7470"],"issn-type":[{"value":"1012-2443","type":"print"},{"value":"1573-7470","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,4]]}}}