{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T02:25:11Z","timestamp":1762050311861},"publisher-location":"Berlin, Heidelberg","reference-count":15,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642369063"},{"type":"electronic","value":"9783642369070"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-36907-0_7","type":"book-chapter","created":{"date-parts":[[2013,4,9]],"date-time":"2013-04-09T21:53:16Z","timestamp":1365544396000},"page":"100-115","source":"Crossref","is-referenced-by-count":3,"title":["Meta-learning of Exploration\/Exploitation Strategies: The Multi-armed Bandit Case"],"prefix":"10.1007","author":[{"given":"Francis","family":"Maes","sequence":"first","affiliation":[]},{"given":"Louis","family":"Wehenkel","sequence":"additional","affiliation":[]},{"given":"Damien","family":"Ernst","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"7_CR1","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 Mathematical Society\u00a058, 527\u2013536 (1952)","journal-title":"Bulletin of The American Mathematical Society"},{"key":"7_CR2","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/0196-8858(85)90002-8","volume":"6","author":"T. Lai","year":"1985","unstructured":"Lai, T., Robbins, H.: Asymptotically efficient adaptive allocation rules. Advances in Applied Mathematics\u00a06, 4\u201322 (1985)","journal-title":"Advances in Applied Mathematics"},{"key":"7_CR3","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"},{"key":"7_CR4","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1023\/A:1013689704352","volume":"47","author":"P. Auer","year":"2002","unstructured":"Auer, P., Fischer, P., Cesa-Bianchi, N.: Finite-time analysis of the multi-armed bandit problem. Machine Learning\u00a047, 235\u2013256 (2002)","journal-title":"Machine Learning"},{"key":"7_CR5","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1007\/978-3-540-75225-7_15","volume-title":"Algorithmic Learning Theory","author":"J.-Y. Audibert","year":"2007","unstructured":"Audibert, J.-Y., Munos, R., Szepesv\u00e1ri, C.: Tuning Bandit Algorithms in Stochastic Environments. In: Hutter, M., Servedio, R.A., Takimoto, E. (eds.) ALT 2007. LNCS (LNAI), vol.\u00a04754, pp. 150\u2013165. Springer, Heidelberg (2007)"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Audibert, J., Munos, R., Szepesvari, C.: Exploration-exploitation trade-off using variance estimates in multi-armed bandits. In: Theoretical Computer Science (2008)","DOI":"10.1016\/j.tcs.2009.01.016"},{"key":"7_CR7","unstructured":"Maes, F., Wehenkel, L., Ernst, D.: Learning to play K-armed bandit problems. In: Proc. of the 4th International Conference on Agents and Artificial Intelligence (2012)"},{"key":"7_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/978-3-642-29946-9_5","volume-title":"Recent Advances in Reinforcement Learning","author":"F. Maes","year":"2012","unstructured":"Maes, F., Wehenkel, L., Ernst, D.: Automatic Discovery of Ranking Formulas for Playing with Multi-armed Bandits. In: Sanner, S., Hutter, M. (eds.) EWRL 2011. LNCS, vol.\u00a07188, pp. 5\u201317. Springer, Heidelberg (2012)"},{"key":"7_CR9","unstructured":"Gonzalez, C., Lozano, J., Larra\u00f1aga, P.: Estimation of Distribution Algorithms. A New Tool for Evolutionary Computation. Kluwer Academic Publishers (2002)"},{"key":"7_CR10","unstructured":"Pelikan, M., M\u00fchlenbein, H.: Marginal distributions in evolutionary algorithms. In: Proceedings of the 4th International Conference on Genetic Algorithms (1998)"},{"key":"7_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/978-3-642-04414-4_7","volume-title":"Algorithmic Learning Theory","author":"S. Bubeck","year":"2009","unstructured":"Bubeck, S., Munos, R., Stoltz, G.: Pure Exploration in Multi-armed Bandits Problems. In: Gavald\u00e0, R., Lugosi, G., Zeugmann, T., Zilles, S. (eds.) ALT 2009. LNCS, vol.\u00a05809, pp. 23\u201337. Springer, Heidelberg (2009)"},{"key":"7_CR12","first-page":"1655","volume":"12","author":"S. Bubeck","year":"2011","unstructured":"Bubeck, S., Munos, R., Stoltz, G., Szepesv\u00e1ri, C.: X-armed bandits. Journal of Machine Learning Research\u00a012, 1655\u20131695 (2011)","journal-title":"Journal of Machine Learning Research"},{"key":"7_CR13","unstructured":"Garivier, A., Capp\u00e9, O.: The KL-UCB algorithm for bounded stochastic bandits and beyond. CoRR abs\/1102.2490 (2011)"},{"key":"7_CR14","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-4321-0","volume-title":"The cross-entropy method: a unified approach to combinatorial optimization, Monte-Carlo simluation, and machine learning","author":"R. Rubenstein","year":"2004","unstructured":"Rubenstein, R., Kroese, D.: The cross-entropy method: a unified approach to combinatorial optimization, Monte-Carlo simluation, and machine learning. Springer, New York (2004)"},{"key":"7_CR15","unstructured":"Castronovo, M., Maes, F., Fonteneau, R., Ernst, D.: Learning exploration\/exploitation strategies for single trajectory reinforcement learning. In: Proc. of 10th European Workshop on Reinforcement Learning (2012)"}],"container-title":["Communications in Computer and Information Science","Agents and Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-36907-0_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,12]],"date-time":"2019-05-12T01:42:24Z","timestamp":1557625344000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-36907-0_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642369063","9783642369070"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-36907-0_7","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2013]]}}}