{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T03:21:10Z","timestamp":1772853670829,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":9,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540752240","type":"print"},{"value":"9783540752257","type":"electronic"}],"license":[{"start":{"date-parts":[[2007,1,1]],"date-time":"2007-01-01T00:00:00Z","timestamp":1167609600000},"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":[[2007]]},"DOI":"10.1007\/978-3-540-75225-7_15","type":"book-chapter","created":{"date-parts":[[2007,10,10]],"date-time":"2007-10-10T08:46:43Z","timestamp":1192006003000},"page":"150-165","source":"Crossref","is-referenced-by-count":64,"title":["Tuning Bandit Algorithms in Stochastic Environments"],"prefix":"10.1007","author":[{"given":"Jean-Yves","family":"Audibert","sequence":"first","affiliation":[]},{"given":"R\u00e9mi","family":"Munos","sequence":"additional","affiliation":[]},{"given":"Csaba","family":"Szepesv\u00e1ri","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"15_CR1","doi-asserted-by":"crossref","first-page":"1054","DOI":"10.2307\/1427934","volume":"27","author":"R. Agrawal","year":"1995","unstructured":"Agrawal, R.: Sample mean based index policies with O(logn) regret for the multi-armed bandit problem. Advances in Applied Probability\u00a027, 1054\u20131078 (1995)","journal-title":"Advances in Applied Probability"},{"key":"15_CR2","unstructured":"Audibert, J.-Y., Munos, R., Szepesv\u00e1ri,Cs.: Variance estimates and exploration function in multi-armed bandit. Research report 07-31, Certis - Ecole des Ponts (2007), \n                    \n                      http:\/\/cermics.enpc.fr\/~audibert\/RR0731.pdf"},{"issue":"2-3","key":"15_CR3","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(2-3), 235\u2013256 (2002)","journal-title":"Machine Learning"},{"key":"15_CR4","unstructured":"Auer, P., Cesa-Bianchi, N., Shawe-Taylor, J.: Exploration versus exploitation challenge. In: 2nd PASCAL Challenges Workshop. Pascal Network (2006)"},{"key":"15_CR5","unstructured":"Gittins, J.C.: Multi-armed Bandit Allocation Indices. In: Wiley-Interscience series in systems and optimization. Wiley, Chichester (1989)"},{"key":"15_CR6","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"},{"key":"15_CR7","doi-asserted-by":"publisher","first-page":"1199","DOI":"10.1109\/9.400491","volume":"40","author":"T.L. Lai","year":"1995","unstructured":"Lai, T.L., Yakowitz, S.: Machine learning and nonparametric bandit theory. IEEE Transactions on Automatic Control\u00a040, 1199\u20131209 (1995)","journal-title":"IEEE Transactions on Automatic Control"},{"key":"15_CR8","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_CR9","doi-asserted-by":"publisher","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\/978-3-540-75225-7_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,2,23]],"date-time":"2019-02-23T22:49:59Z","timestamp":1550962199000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-75225-7_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007]]},"ISBN":["9783540752240","9783540752257"],"references-count":9,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-75225-7_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2007]]}}}