{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T10:20:46Z","timestamp":1725618046367},"publisher-location":"Berlin, Heidelberg","reference-count":19,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642244117"},{"type":"electronic","value":"9783642244124"}],"license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011]]},"DOI":"10.1007\/978-3-642-24412-4_15","type":"book-chapter","created":{"date-parts":[[2011,10,6]],"date-time":"2011-10-06T04:41:17Z","timestamp":1317876077000},"page":"159-173","source":"Crossref","is-referenced-by-count":6,"title":["Deviations of Stochastic Bandit Regret"],"prefix":"10.1007","author":[{"given":"Antoine","family":"Salomon","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jean-Yves","family":"Audibert","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"2-3","key":"15_CR1","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. Mach. Learn.\u00a047(2-3), 235\u2013256 (2002)","journal-title":"Mach. Learn."},{"key":"15_CR2","first-page":"1054","volume":"27","author":"R. Agrawal","year":"1995","unstructured":"Agrawal, R.: Sample mean based index policies with o(log n) regret for the multi-armed bandit problem. Advances in Applied Mathematics\u00a027, 1054\u20131078 (1995)","journal-title":"Advances in Applied Mathematics"},{"issue":"19","key":"15_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 tradeoff using variance estimates in multi-armed bandits. Theoretical Computer Science\u00a0410(19), 1876\u20131902 (2009)","journal-title":"Theoretical Computer Science"},{"key":"15_CR4","unstructured":"Bubeck, S., Munos, R., Stoltz, G., Szepesvari, C.: Online optimization in X-armed bandits. In: Advances in Neural Information Processing Systems, vol.\u00a021, pp. 201\u2013208 (2009)"},{"key":"15_CR5","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1145\/1566374.1566386","volume-title":"Proceedings of the Tenth ACM Conference on Electronic Commerce","author":"M. Babaioff","year":"2009","unstructured":"Babaioff, M., Sharma, Y., Slivkins, A.: Characterizing truthful multi-armed bandit mechanisms: extended abstract. In: Proceedings of the Tenth ACM Conference on Electronic Commerce, pp. 79\u201388. ACM, New York (2009)"},{"key":"15_CR6","volume-title":"The New Palgrave Dictionary of Economics","author":"D. Bergemann","year":"2008","unstructured":"Bergemann, D., Valimaki, J.: Bandit problems. In: The New Palgrave Dictionary of Economics, 2nd edn. Macmillan Press, Basingstoke (2008)","edition":"2"},{"key":"15_CR7","unstructured":"Coquelin, P.A., Munos, R.: Bandit algorithms for tree search. In: Uncertainty in Artificial Intelligence (2007)"},{"key":"15_CR8","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/1566374.1566388","volume-title":"Proceedings of the Tenth ACM Conference on Electronic Commerce","author":"N.R. Devanur","year":"2009","unstructured":"Devanur, N.R., Kakade, S.M.: The price of truthfulness for pay-per-click auctions. In: Proceedings of the Tenth ACM Conference on Electronic Commerce, pp. 99\u2013106. ACM, New York (2009)"},{"key":"15_CR9","unstructured":"Gelly, S., Wang, Y.: Exploration exploitation in go: UCT for Monte-Carlo go. In: Online trading between exploration and exploitation Workshop, Twentieth Annual Conference on Neural Information Processing Systems, NIPS 2006 (2006)"},{"key":"15_CR10","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/1090.001.0001","volume-title":"Adaptation in natural and artificial systems","author":"J.H. Holland","year":"1992","unstructured":"Holland, J.H.: Adaptation in natural and artificial systems. MIT Press, Cambridge (1992)"},{"key":"15_CR11","unstructured":"Kleinberg, R.D.: Nearly tight bounds for the continuum-armed bandit problem. In: Advances in Neural Information Processing Systems, vol.\u00a017, pp. 697\u2013704 (2005)"},{"key":"15_CR12","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/11871842_29","volume-title":"Machine Learning: ECML 2006","author":"L. Kocsis","year":"2006","unstructured":"Kocsis, L., Szepesv\u00e1ri, C.: Bandit based Monte-Carlo planning. In: F\u00fcrnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol.\u00a04212, pp. 282\u2013293. Springer, Heidelberg (2006)"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Kleinberg, R., Slivkins, A., Upfal, E.: Multi-armed bandits in metric spaces. In: Proceedings of the 40th Annual ACM Symposium on Theory of Computing, pp. 681\u2013690 (2008)","DOI":"10.1145\/1374376.1374475"},{"issue":"3","key":"15_CR14","doi-asserted-by":"publisher","first-page":"1424","DOI":"10.1214\/105051604000000350","volume":"14","author":"D. Lamberton","year":"2004","unstructured":"Lamberton, D., Pag\u00e8s, G., Tarr\u00e8s, P.: When can the two-armed bandit algorithm be trusted? Annals of Applied Probability\u00a014(3), 1424\u20131454 (2004)","journal-title":"Annals of Applied Probability"},{"key":"15_CR15","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, 4\u201322 (1985)","journal-title":"Advances in Applied Mathematics"},{"issue":"3","key":"15_CR16","doi-asserted-by":"publisher","first-page":"1269","DOI":"10.1214\/aop\/1176990746","volume":"18","author":"P. Massart","year":"1990","unstructured":"Massart, P.: The tight constant in the Dvoretzky-Kiefer-Wolfowitz inequality. The Annals of Probability\u00a018(3), 1269\u20131283 (1990)","journal-title":"The Annals of Probability"},{"key":"15_CR17","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1090\/S0002-9904-1952-09620-8","volume":"58","author":"H. Robbins","year":"1952","unstructured":"Robbins, H.: Some aspects of the sequential design of experiments. Bulletin of the American Mathematics Society\u00a058, 527\u2013535 (1952)","journal-title":"Bulletin of the American Mathematics Society"},{"key":"15_CR18","volume-title":"Real and complex analysis","author":"W. Rudin","year":"1986","unstructured":"Rudin, W.: Real and complex analysis, 3rd edn. McGraw-Hill Inc., New York (1986)","edition":"3"},{"key":"15_CR19","volume-title":"Reinforcement Learning: An Introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"}],"container-title":["Lecture Notes in Computer Science","Algorithmic Learning Theory"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-24412-4_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,4,10]],"date-time":"2019-04-10T03:21:57Z","timestamp":1554866517000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-24412-4_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642244117","9783642244124"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-24412-4_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2011]]}}}