{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T23:05:10Z","timestamp":1725750310100},"publisher-location":"Berlin, Heidelberg","reference-count":17,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642409349"},{"type":"electronic","value":"9783642409356"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-40935-6_17","type":"book-chapter","created":{"date-parts":[[2013,9,27]],"date-time":"2013-09-27T05:14:50Z","timestamp":1380258890000},"page":"234-248","source":"Crossref","is-referenced-by-count":11,"title":["An Efficient Algorithm for Learning with Semi-bandit Feedback"],"prefix":"10.1007","author":[{"given":"Gergely","family":"Neu","sequence":"first","affiliation":[]},{"given":"G\u00e1bor","family":"Bart\u00f3k","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"17_CR1","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/11894841_20","volume-title":"Algorithmic Learning Theory","author":"C. Allenberg","year":"2006","unstructured":"Allenberg, C., Auer, P., Gy\u00f6rfi, L., Ottucs\u00e1k, G.: Hannan consistency in on-line learning in case of unbounded losses under partial monitoring. In: Balc\u00e1zar, J.L., Long, P.M., Stephan, F. (eds.) ALT 2006. LNCS (LNAI), vol.\u00a04264, pp. 229\u2013243. Springer, Heidelberg (2006)"},{"key":"17_CR2","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":"17_CR3","doi-asserted-by":"crossref","unstructured":"Audibert, J.Y., Bubeck, S., Lugosi, G.: Regret in online combinatorial optimization. To appear in Mathematics of Operations Research (2013)","DOI":"10.1287\/moor.2013.0598"},{"issue":"1","key":"17_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.E.: The nonstochastic multiarmed bandit problem. SIAM J. Comput.\u00a032(1), 48\u201377 (2002)","journal-title":"SIAM J. Comput."},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Awerbuch, B., Kleinberg, R.D.: Adaptive routing with end-to-end feedback: distributed learning and geometric approaches. In: Proceedings of the 36th ACM Symposium on Theory of Computing, pp. 45\u201353 (2004)","DOI":"10.1145\/1007352.1007367"},{"key":"17_CR6","unstructured":"Bubeck, S., Cesa-Bianchi, N., Kakade, S.M.: Towards minimax policies for online linear optimization with bandit feedback. In: Proceedings of the 25th Annual Conference on Learning Theory (COLT), pp. 1\u201314 (2012)"},{"key":"17_CR7","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546921","volume-title":"Prediction, Learning, and Games","author":"N. Cesa-Bianchi","year":"2006","unstructured":"Cesa-Bianchi, N., Lugosi, G.: Prediction, Learning, and Games. Cambridge University Press, New York (2006)"},{"key":"17_CR8","doi-asserted-by":"publisher","first-page":"1404","DOI":"10.1016\/j.jcss.2012.01.001","volume":"78","author":"N. Cesa-Bianchi","year":"2012","unstructured":"Cesa-Bianchi, N., Lugosi, G.: Combinatorial bandits. Journal of Computer and System Sciences\u00a078, 1404\u20131422 (2012)","journal-title":"Journal of Computer and System Sciences"},{"key":"17_CR9","unstructured":"Dani, V., Hayes, T., Kakade, S.: The price of bandit information for online optimization. In: Advances in Neural Information Processing Systems (NIPS), vol.\u00a020, pp. 345\u2013352 (2008)"},{"key":"17_CR10","first-page":"2369","volume":"8","author":"A. Gy\u00f6rgy","year":"2007","unstructured":"Gy\u00f6rgy, A., Linder, T., Lugosi, G., Ottucs\u00e1k, G.: The on-line shortest path problem under partial monitoring. Journal of Machine Learning Research\u00a08, 2369\u20132403 (2007)","journal-title":"Journal of Machine Learning Research"},{"key":"17_CR11","first-page":"97","volume":"3","author":"J. Hannan","year":"1957","unstructured":"Hannan, J.: Approximation to Bayes risk in repeated play. Contributions to the Theory of Games\u00a03, 97\u2013139 (1957)","journal-title":"Contributions to the Theory of Games"},{"key":"17_CR12","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1016\/j.jcss.2004.10.016","volume":"71","author":"A. Kalai","year":"2005","unstructured":"Kalai, A., Vempala, S.: Efficient algorithms for online decision problems. Journal of Computer and System Sciences\u00a071, 291\u2013307 (2005)","journal-title":"Journal of Computer and System Sciences"},{"key":"17_CR13","unstructured":"Koolen, W., Warmuth, M., Kivinen, J.: Hedging structured concepts. In: Proceedings of the 23rd Annual Conference on Learning Theory (COLT), pp. 93\u2013105 (2010)"},{"key":"17_CR14","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/978-3-540-27819-1_8","volume-title":"Learning Theory","author":"H.B. McMahan","year":"2004","unstructured":"McMahan, H.B., Blum, A.: Online geometric optimization in the bandit setting against an adaptive adversary. In: Shawe-Taylor, J., Singer, Y. (eds.) COLT 2004. LNCS (LNAI), vol.\u00a03120, pp. 109\u2013123. Springer, Heidelberg (2004)"},{"key":"17_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1007\/11571155_7","volume-title":"Stochastic Algorithms: Foundations and Applications","author":"J. Poland","year":"2005","unstructured":"Poland, J.: FPL analysis for adaptive bandits. In: Lupanov, O.B., Kasim-Zade, O.M., Chaskin, A.V., Steinh\u00f6fel, K. (eds.) SAGA 2005. LNCS, vol.\u00a03777, pp. 58\u201369. Springer, Heidelberg (2005)"},{"key":"17_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1007\/978-3-642-34106-9_22","volume-title":"Algorithmic Learning Theory","author":"D. Suehiro","year":"2012","unstructured":"Suehiro, D., Hatano, K., Kijima, S., Takimoto, E., Nagano, K.: Online prediction under submodular constraints. In: Bshouty, N.H., Stoltz, G., Vayatis, N., Zeugmann, T. (eds.) ALT 2012. LNCS, vol.\u00a07568, pp. 260\u2013274. Springer, Heidelberg (2012)"},{"key":"17_CR17","first-page":"773","volume":"4","author":"E. Takimoto","year":"2003","unstructured":"Takimoto, E., Warmuth, M.: Paths kernels and multiplicative updates. Journal of Machine Learning Research\u00a04, 773\u2013818 (2003)","journal-title":"Journal of Machine Learning Research"}],"container-title":["Lecture Notes in Computer Science","Algorithmic Learning Theory"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-40935-6_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,17]],"date-time":"2019-05-17T15:19:24Z","timestamp":1558106364000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-40935-6_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642409349","9783642409356"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-40935-6_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}