{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T09:10:19Z","timestamp":1782983419809,"version":"3.54.5"},"reference-count":11,"publisher":"Springer Science and Business Media LLC","issue":"1-2","license":[{"start":{"date-parts":[[2010,9,1]],"date-time":"2010-09-01T00:00:00Z","timestamp":1283299200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Period Math Hung"],"published-print":{"date-parts":[[2010,9]]},"DOI":"10.1007\/s10998-010-3055-6","type":"journal-article","created":{"date-parts":[[2010,9,30]],"date-time":"2010-09-30T14:24:21Z","timestamp":1285856661000},"page":"55-65","source":"Crossref","is-referenced-by-count":119,"title":["UCB revisited: Improved regret bounds for the stochastic multi-armed bandit problem"],"prefix":"10.1007","volume":"61","author":[{"given":"Peter","family":"Auer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ronald","family":"Ortner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2010,10,1]]},"reference":[{"key":"3055_CR1","doi-asserted-by":"crossref","first-page":"1054","DOI":"10.2307\/1427934","volume":"27","author":"R. Agrawal","year":"1995","unstructured":"Rajeev Agrawal, Sample mean based index policies with O(log n) regret for the multi-armed bandit problem, Adv. in Appl. Probab., 27 (1995), 1054\u20131078.","journal-title":"Adv. in Appl. Probab."},{"key":"3055_CR2","unstructured":"Jean-Yves Audibert and S\u00e9bastien Bubeck, Minimax policies for adversarial and stochastic bandits, Proceedings of the 22nd Annual Conference on Learning Theory (COLT2009), 2009, 217\u2013226."},{"key":"3055_CR3","doi-asserted-by":"crossref","first-page":"1876","DOI":"10.1016\/j.tcs.2009.01.016","volume":"410","author":"J.-Y. Audibert","year":"2009","unstructured":"Jean-Yves Audibert, R\u00e9mi Munos and Csaba Szepesv\u00e1ri, Exploration-exploitation tradeoff using variance estimates in multi-armed bandits, Theor. Comput. Sci., 410 (2009), 1876\u20131902.","journal-title":"Theor. Comput. Sci."},{"key":"3055_CR4","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1023\/A:1013689704352","volume":"47","author":"P. Auer","year":"2002","unstructured":"Peter Auer, Nicol\u00f2 Cesa-Bianchi and Paul Fischer, Finite-Time Analysis of the Multi-Armed Bandit Problem, Mach. Learn., 47 (2002), 235\u2013256.","journal-title":"Mach. Learn."},{"key":"3055_CR5","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1137\/S0097539701398375","volume":"32","author":"P. Auer","year":"2002","unstructured":"Peter Auer, Nicol\u00f2 Cesa-Bianchi, Yoav Freund and Robert E. Schapire, The Nonstochastic Multiarmed Bandit Problem, SIAM J. Comput., 32 (2002), 48\u201377.","journal-title":"SIAM J. Comput."},{"key":"3055_CR6","first-page":"1079","volume":"7","author":"E. Even-Dar","year":"2006","unstructured":"Eyal Even-Dar, Shie Mannor and Yishay Mansour, Action Elimination and Stopping Conditions for the Multi-Armed Bandit and Reinforcement Learning Problems, J. Mach. Learn. Res., 7 (2006), 1079\u20131105.","journal-title":"J. Mach. Learn. Res."},{"key":"3055_CR7","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1080\/01621459.1963.10500830","volume":"58","author":"W. Hoeffding","year":"1963","unstructured":"Wassily Hoeffding, Probability inequalities for sums of bounded random variables, J. Amer. Statist. Assoc., 58 (1963), 13\u201330.","journal-title":"J. Amer. Statist. Assoc."},{"key":"3055_CR8","unstructured":"Robert D. Kleinberg, Nearly Tight Bounds for the Continuum-Armed Bandit Problem, Advances in Neural Information Processing Systems 17, MIT Press, 2005, 697\u2013704."},{"key":"3055_CR9","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1016\/0196-8858(85)90002-8","volume":"6","author":"T. L. Lai","year":"1985","unstructured":"Tze Leung Lai and Herbert Robbins, Asymptotically Efficient Adaptive Allocation Rules, Adv. in Appl. Math., 6 (1985), 4\u201322.","journal-title":"Adv. in Appl. Math."},{"key":"3055_CR10","first-page":"623","volume":"5","author":"S. Mannor","year":"2004","unstructured":"Shie Mannor and John N. Tsitsiklis, The Sample Complexity of Exploration in the Multi-Armed Bandit Problem, J. Mach. Learn. Res., 5 (2004), 623\u2013648.","journal-title":"J. Mach. Learn. Res."},{"key":"3055_CR11","doi-asserted-by":"crossref","unstructured":"Richard S. Sutton and Andrew G. Barto, Reinforcement Learning: An Introduction, MIT Press, 1998.","DOI":"10.1109\/TNN.1998.712192"}],"container-title":["Periodica Mathematica Hungarica"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10998-010-3055-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10998-010-3055-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10998-010-3055-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,5]],"date-time":"2019-06-05T04:50:48Z","timestamp":1559710248000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10998-010-3055-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,9]]},"references-count":11,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2010,9]]}},"alternative-id":["3055"],"URL":"https:\/\/doi.org\/10.1007\/s10998-010-3055-6","relation":{},"ISSN":["0031-5303","1588-2829"],"issn-type":[{"value":"0031-5303","type":"print"},{"value":"1588-2829","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,9]]}}}