{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T16:52:41Z","timestamp":1774716761434,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":14,"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_18","type":"book-chapter","created":{"date-parts":[[2012,10,1]],"date-time":"2012-10-01T01:56:27Z","timestamp":1349056587000},"page":"199-213","source":"Crossref","is-referenced-by-count":177,"title":["Thompson Sampling: An Asymptotically Optimal Finite-Time Analysis"],"prefix":"10.1007","author":[{"given":"Emilie","family":"Kaufmann","sequence":"first","affiliation":[]},{"given":"Nathaniel","family":"Korda","sequence":"additional","affiliation":[]},{"given":"R\u00e9mi","family":"Munos","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"18_CR1","unstructured":"Agrawal, S., Goyal, N.: Analysis of thompson sampling for the multi-armed bandit problem. In: Conference on Learning Theory, COLT (2012)"},{"key":"18_CR2","first-page":"2785","volume":"11","author":"J.-Y. Audibert","year":"2010","unstructured":"Audibert, J.-Y., Bubeck, S.: Regret bounds and minimax policies under partial monitoring. Journal of Machine Learning Research\u00a011, 2785\u20132836 (2010)","journal-title":"Journal of Machine Learning Research"},{"issue":"19","key":"18_CR3","doi-asserted-by":"publisher","first-page":"1876","DOI":"10.1016\/j.tcs.2009.01.016","volume":"410","author":"J.-Y. Audibert","year":"2009","unstructured":"Audibert, J.-Y., Munos, R., Szepesv\u00e1ri, C.: Exploration-exploitation trade-off using variance estimates in multi-armed bandits. Theoretical Computer Science\u00a0410(19), 1876\u20131902 (2009)","journal-title":"Theoretical Computer Science"},{"issue":"2","key":"18_CR4","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1023\/A:1013689704352","volume":"47","author":"P. Auer","year":"2002","unstructured":"Auer, P., Cesa-Bianchi, N., Fischer, P.: Finite-time analysis of the multiarmed bandit problem. Machine Learning\u00a047(2), 235\u2013256 (2002)","journal-title":"Machine Learning"},{"key":"18_CR5","unstructured":"Chapelle, O., Li, L.: An empirical evaluation of thompson sampling. In: NIPS (2011)"},{"key":"18_CR6","unstructured":"Garivier, A., Capp\u00e9, O.: The kl-ucb algorithm for bounded stochastic bandits and beyond. In: Conference on Learning Theory, COLT (2011)"},{"issue":"2","key":"18_CR7","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1108\/17563781011049179","volume":"3","author":"O.C. Granmo","year":"2010","unstructured":"Granmo, O.C.: Solving two-armed bernoulli bandit problems using a bayesian learning automaton. International Journal of Intelligent Computing and Cybernetics\u00a03(2), 207\u2013234 (2010)","journal-title":"International Journal of Intelligent Computing and Cybernetics"},{"key":"18_CR8","unstructured":"Honda, J., Takemura, A.: An asymptotically optimal bandit algorithm for bounded support models. In: Conference on Learning Theory, COLT (2010)"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Kaufmann, E., Garivier, A., Capp\u00e9, O.: On bayesian upper-confidence bounds for bandit problems. In: AISTATS (2012)","DOI":"10.1007\/978-3-642-24412-4_16"},{"issue":"1","key":"18_CR10","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/0196-8858(85)90002-8","volume":"6","author":"T.L. Lai","year":"1985","unstructured":"Lai, T.L., Robbins, H.: Asymptotically efficient adaptive allocation rules. Advances in Applied Mathematics\u00a06(1), 4\u201322 (1985)","journal-title":"Advances in Applied Mathematics"},{"key":"18_CR11","unstructured":"Maillard, O.-A., Munos, R., Stoltz, G.: A finite-time analysis of multi-armed bandits problems with kullback-leibler divergences. In: Conference on Learning Theory, COLT (2011)"},{"key":"18_CR12","first-page":"2069","volume":"13","author":"B.C. May","year":"2012","unstructured":"May, B.C., Korda, N., Lee, A., Leslie, D.: Optimistic bayesian sampling in contextual bandit problems. Journal of Machine Learning Research\u00a013, 2069\u20132106 (2012)","journal-title":"Journal of Machine Learning Research"},{"key":"18_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1007\/978-3-642-24412-4_15","volume-title":"Algorithmic Learning Theory","author":"A. Salomon","year":"2011","unstructured":"Salomon, A., Audibert, J.-Y.: Deviations of Stochastic Bandit Regret. In: Kivinen, J., Szepesv\u00e1ri, C., Ukkonen, E., Zeugmann, T. (eds.) ALT 2011. LNCS, vol.\u00a06925, pp. 159\u2013173. Springer, Heidelberg (2011)"},{"key":"18_CR14","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1093\/biomet\/25.3-4.285","volume":"25","author":"W.R. Thompson","year":"1933","unstructured":"Thompson, W.R.: On the likelihood that one unknown probability exceeds another in view of the evidence of two samples. Biometrika\u00a025, 285\u2013294 (1933)","journal-title":"Biometrika"}],"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_18.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,29]],"date-time":"2022-01-29T16:06:21Z","timestamp":1643472381000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-34106-9_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642341052","9783642341069"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-34106-9_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012]]}}}