{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:04:09Z","timestamp":1780052649879,"version":"3.53.1"},"publisher-location":"Berlin, Heidelberg","reference-count":18,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642244117","type":"print"},{"value":"9783642244124","type":"electronic"}],"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_14","type":"book-chapter","created":{"date-parts":[[2011,10,6]],"date-time":"2011-10-06T00:41:17Z","timestamp":1317861677000},"page":"144-158","source":"Crossref","is-referenced-by-count":20,"title":["Lipschitz Bandits without the Lipschitz Constant"],"prefix":"10.1007","author":[{"given":"S\u00e9bastien","family":"Bubeck","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gilles","family":"Stoltz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia Yuan","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"14_CR1","first-page":"2635","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, 2635\u20132686 (2010)","journal-title":"Journal of Machine Learning Research"},{"key":"14_CR2","unstructured":"Audibert, J.-Y., Bubeck, S., Lugosi, G.: Minimax policies for combinatorial prediction games. In: Proceedings of the 24th Annual Conference on Learning Theory. Omnipress (2011)"},{"issue":"2-3","key":"14_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 Journal\u00a047(2-3), 235\u2013256 (2002)","journal-title":"Machine Learning Journal"},{"issue":"1","key":"14_CR4","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1137\/S0097539701398375","volume":"32","author":"P. Auer","year":"2002","unstructured":"Auer, P., Cesa-Bianchi, N., Freund, Y., Schapire, R.: The non-stochastic multi-armed bandit problem. SIAM Journal on Computing\u00a032(1), 48\u201377 (2002)","journal-title":"SIAM Journal on Computing"},{"key":"14_CR5","doi-asserted-by":"publisher","first-page":"1926","DOI":"10.1137\/S0363012992237273","volume":"33","author":"R. Agrawal","year":"1995","unstructured":"Agrawal, R.: The continuum-armed bandit problem. SIAM Journal on Control and Optimization\u00a033, 1926\u20131951 (1995)","journal-title":"SIAM Journal on Control and Optimization"},{"key":"14_CR6","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"454","DOI":"10.1007\/978-3-540-72927-3_33","volume-title":"Learning Theory","author":"P. Auer","year":"2007","unstructured":"Auer, P., Ortner, R., Szepesv\u00e1ri, C.: Improved rates for the stochastic continuum-armed bandit problem. In: Bshouty, N.H., Gentile, C. (eds.) COLT. LNCS (LNAI), vol.\u00a04539, pp. 454\u2013468. Springer, Heidelberg (2007)"},{"key":"14_CR7","unstructured":"Bubeck, S., Munos, R.: Open-loop optimistic planning. In: Proceedings of the 23rd Annual Conference on Learning Theory. Omnipress (2010)"},{"key":"14_CR8","first-page":"1655","volume":"12","author":"S. Bubeck","year":"2011","unstructured":"Bubeck, S., Munos, R., Stoltz, G., Szepesv\u00e1ri, C.: \n                    \n                      \n                    \n                    $\\mathcal{X}$\n                  \u2013armed bandits. Journal of Machine Learning Research\u00a012, 1655\u20131695 (2011)","journal-title":"Journal of Machine Learning Research"},{"key":"14_CR9","unstructured":"Bubeck, S., Stoltz, G., Yu, J.Y.: Lipschitz bandits without the lipschitz constant (2011), \n                    \n                      http:\/\/arxiv.org\/pdf\/1105.5041"},{"issue":"6","key":"14_CR10","doi-asserted-by":"publisher","first-page":"1243","DOI":"10.1109\/TAC.2009.2019797","volume":"54","author":"E. Cope","year":"2009","unstructured":"Cope, E.: Regret and convergence bounds for immediate-reward reinforcement learning with continuous action spaces. IEEE Transactions on Automatic Control\u00a054(6), 1243\u20131253 (2009)","journal-title":"IEEE Transactions on Automatic Control"},{"key":"14_CR11","unstructured":"Dani, V., Hayes, T.P., Kakade, S.M.: Stochastic linear optimization under bandit feedback. In: Proceedings of the 21st Annual Conference on Learning Theory, pp. 355\u2013366. Omnipress (2008)"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Horn, M.: Optimal algorithms for global optimization in case of unknown Lipschitz constant. Journal of Complexity\u00a022(1) (2006)","DOI":"10.1016\/j.jco.2005.06.006"},{"issue":"1","key":"14_CR13","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/BF00941892","volume":"79","author":"D.R. Jones","year":"1993","unstructured":"Jones, D.R., Perttunen, C.D., Stuckman, B.E.: Lipschitzian optimization without the Lipschitz constant. Journal of Optimization Theory and Applications\u00a079(1), 157\u2013181 (1993)","journal-title":"Journal of Optimization Theory and Applications"},{"key":"14_CR14","unstructured":"Kleinberg, R.: Nearly tight bounds for the continuum-armed bandit problem. In: Advances in Neural Information Processing Systems, pp. 697\u2013704 (2004)"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Kleinberg, R., Slivkins, A., Upfal, E.: Multi-armed bandits in metric spaces. In: Proceedings of the 40th ACM Symposium on Theory of Computing (2008)","DOI":"10.1145\/1374376.1374475"},{"key":"14_CR16","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":"14_CR17","unstructured":"Wang, Y., Audibert, J.Y., Munos, R.: Algorithms for infinitely many-armed bandits. In: Advances in Neural Information Processing Systems, pp. 1729\u20131736 (2009)"},{"key":"14_CR18","unstructured":"Yu, J.Y., Mannor, S.: Unimodal bandits. In: Proceedings of the 28th International Conference on Machine Learning (2011)"}],"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_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,4,9]],"date-time":"2019-04-09T23:50:25Z","timestamp":1554853825000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-24412-4_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642244117","9783642244124"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-24412-4_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011]]}}}