{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T15:50:29Z","timestamp":1769269829455,"version":"3.49.0"},"publisher-location":"Berlin, Heidelberg","reference-count":15,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642341052","type":"print"},{"value":"9783642341069","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-34106-9_26","type":"book-chapter","created":{"date-parts":[[2012,10,1]],"date-time":"2012-10-01T05:56:27Z","timestamp":1349070987000},"page":"320-334","source":"Crossref","is-referenced-by-count":21,"title":["PAC Bounds for Discounted MDPs"],"prefix":"10.1007","author":[{"given":"Tor","family":"Lattimore","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcus","family":"Hutter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"26_CR1","first-page":"1563","volume":"99","author":"P. Auer","year":"2010","unstructured":"Auer, P., Jaksch, T., Ortner, R.: Near-optimal regret bounds for reinforcement learning. J. Mach. Learn. Res.\u00a099, 1563\u20131600 (2010)","journal-title":"J. Mach. Learn. Res."},{"key":"26_CR2","unstructured":"Azar, M., Munos, R., Kappen, B.: On the sample complexity of reinforcement learning with a generative model. In: Proceedings of the 29th International Conference on Machine Learning. ACM, New York (2012)"},{"key":"26_CR3","doi-asserted-by":"crossref","unstructured":"Auer, P., Ortner, R.: Logarithmic online regret bounds for undiscounted reinforcement learning. In: Advances in Neural Information Processing Systems 19, pp. 49\u201356. MIT Press (2007)","DOI":"10.7551\/mitpress\/7503.003.0011"},{"key":"26_CR4","unstructured":"Auer, P.: Upper confidence reinforcement learning. Unpublished, keynote at European Workshop of Reinforcement Learning (2011)"},{"key":"26_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/15427951.2006.10129115","volume":"3","author":"F. Chung","year":"2006","unstructured":"Chung, F., Lu, L.: Concentration inequalities and martingale inequalities a survey. Internet Mathematics\u00a03, 1 (2006)","journal-title":"Internet Mathematics"},{"key":"26_CR6","unstructured":"Kakade, S.: On The Sample Complexity of Reinforcement Learning. PhD thesis, University College London (2003)"},{"key":"26_CR7","unstructured":"Lattimore, T., Hutter, M.: PAC bounds for discounted MDPs. Technical report (2012), http:\/\/arxiv.org\/abs\/1202.3890"},{"issue":"1","key":"26_CR8","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/0196-8858(85)90002-8","volume":"6","author":"T. Lai","year":"1985","unstructured":"Lai, T., Robbins, H.: Asymptotically efficient adaptive allocation rules. Advances in Applied Mathematics\u00a06(1), 4\u201322 (1985)","journal-title":"Advances in Applied Mathematics"},{"key":"26_CR9","first-page":"623","volume":"5","author":"S. Mannor","year":"2004","unstructured":"Mannor, S., Tsitsiklis, J.: The sample complexity of exploration in the multi-armed bandit problem. J. Mach. Learn. Res.\u00a05, 623\u2013648 (2004)","journal-title":"J. Mach. Learn. Res."},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Strehl, A., Littman, M.: A theoretical analysis of model-based interval estimation. In: Proceedings of the 22nd International Conference on Machine Learning, ICML 2005, pp. 856\u2013863 (2005)","DOI":"10.1145\/1102351.1102459"},{"issue":"8","key":"26_CR11","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.1016\/j.jcss.2007.08.009","volume":"74","author":"A. Strehl","year":"2008","unstructured":"Strehl, A., Littman, M.: An analysis of model-based interval estimation for Markov decision processes. Journal of Computer and System Sciences\u00a074(8), 1309\u20131331 (2008)","journal-title":"Journal of Computer and System Sciences"},{"key":"26_CR12","first-page":"2413","volume":"10","author":"A. Strehl","year":"2009","unstructured":"Strehl, A., Li, L., Littman, M.: Reinforcement learning in finite MDPs: PAC analysis. J. Mach. Learn. Res.\u00a010, 2413\u20132444 (2009)","journal-title":"J. Mach. Learn. Res."},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Strehl, A., Li, L., Wiewiorac, E., Langford, J., Littman, M.: PAC model-free reinforcement learning. In: Proceedings of the 23rd International Conference on Machine Learning, ICML 2006, pp. 881\u2013888. ACM, New York (2006)","DOI":"10.1145\/1143844.1143955"},{"issue":"4","key":"26_CR14","doi-asserted-by":"publisher","first-page":"794","DOI":"10.2307\/3213832","volume":"19","author":"M. Sobel","year":"1982","unstructured":"Sobel, M.: The variance of discounted Markov decision processes. Journal of Applied Probability\u00a019(4), 794\u2013802 (1982)","journal-title":"Journal of Applied Probability"},{"key":"26_CR15","first-page":"1031","volume-title":"Proceedings of the 27th International Conference on Machine Learning","author":"I. Szita","year":"2010","unstructured":"Szita, I., Szepesv\u00e1ri, C.: Model-based reinforcement learning with nearly tight exploration complexity bounds. In: Proceedings of the 27th International Conference on Machine Learning, pp. 1031\u20131038. ACM, New York (2010)"}],"container-title":["Lecture Notes in Computer Science","Algorithmic Learning Theory"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-34106-9_26.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,29]],"date-time":"2024-04-29T22:48:51Z","timestamp":1714430931000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-34106-9_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642341052","9783642341069"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-34106-9_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012]]}}}