{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T18:37:42Z","timestamp":1784399862286,"version":"3.55.0"},"reference-count":12,"publisher":"Springer Science and Business Media LLC","issue":"2-3","license":[{"start":{"date-parts":[[2002,5,1]],"date-time":"2002-05-01T00:00:00Z","timestamp":1020211200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2002,5,1]],"date-time":"2002-05-01T00:00:00Z","timestamp":1020211200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Learning"],"published-print":{"date-parts":[[2002,5]]},"DOI":"10.1023\/a:1013689704352","type":"journal-article","created":{"date-parts":[[2002,12,23]],"date-time":"2002-12-23T17:11:47Z","timestamp":1040663507000},"page":"235-256","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3830,"title":["Finite-time Analysis of the Multiarmed Bandit Problem"],"prefix":"10.1007","volume":"47","author":[{"given":"Peter","family":"Auer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicol\u00f2","family":"Cesa-Bianchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Fischer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"391590_CR1","doi-asserted-by":"crossref","first-page":"1054","DOI":"10.2307\/1427934","volume":"27","author":"R. Agrawal","year":"1995","unstructured":"Agrawal, R. (1995). Sample mean based index policies with O(log n) regret for the multi-armed bandit problem. Advances in Applied Probability, 27, 1054\u20131078.","journal-title":"Advances in Applied Probability"},{"key":"391590_CR2","doi-asserted-by":"crossref","DOI":"10.1007\/978-94-015-3711-7","volume-title":"Bandit problems","author":"D. Berry","year":"1985","unstructured":"Berry, D., & Fristedt, B. (1985). Bandit problems. London: Chapman and Hall."},{"issue":"2","key":"391590_CR3","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1006\/aama.1996.0007","volume":"17","author":"A. Burnetas","year":"1996","unstructured":"Burnetas, A., & Katehakis, M. (1996). Optimal adaptive policies for sequential allocation problems. Advances in Applied Mathematics, 17:2, 122\u2013142.","journal-title":"Advances in Applied Mathematics"},{"key":"391590_CR4","doi-asserted-by":"crossref","unstructured":"Duff, M. (1995). Q-learning for bandit problems. In Proceedings of the 12th International Conference on Machine Learning (pp. 209-217).","DOI":"10.1016\/B978-1-55860-377-6.50034-7"},{"key":"391590_CR5","series-title":"Wiley-Interscience series in Systems and Optimization","volume-title":"Multi-armed bandit allocation indices","author":"J. Gittins","year":"1989","unstructured":"Gittins, J. (1989). Multi-armed bandit allocation indices, Wiley-Interscience series in Systems and Optimization. New York: John Wiley and Sons."},{"key":"391590_CR6","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/1090.001.0001","volume-title":"Adaptation in natural and artificial systems","author":"J. Holland","year":"1992","unstructured":"Holland, J. (1992). Adaptation in natural and artificial systems. Cambridge: MIT Press\/Bradford Books."},{"issue":"1","key":"391590_CR7","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1007\/BF02191765","volume":"83","author":"T. Ishikida","year":"1994","unstructured":"Ishikida, T., & Varaiya, P. (1994). Multi-armed bandit problem revisited. Journal of Optimization Theory and Applications, 83:1, 113\u2013154.","journal-title":"Journal of Optimization Theory and Applications"},{"key":"391590_CR8","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1016\/0196-8858(85)90002-8","volume":"6","author":"T. Lai","year":"1985","unstructured":"Lai, T., & Robbins, H. (1985). Asymptotically efficient adaptive allocation rules. Advances in Applied Mathematics, 6, 4\u201322.","journal-title":"Advances in Applied Mathematics"},{"key":"391590_CR9","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4612-5254-2","volume-title":"Convergence of stochastic processes","author":"D. Pollard","year":"1984","unstructured":"Pollard, D. (1984). Convergence of stochastic processes. Berlin: Springer."},{"key":"391590_CR10","volume-title":"Reinforcement learning, an introduction","author":"R. Sutton","year":"1998","unstructured":"Sutton, R., & Barto, A. (1998). Reinforcement learning, an introduction. Cambridge: MIT Press\/Bradford Books."},{"key":"391590_CR11","volume-title":"Matematical statistics","author":"S. Wilks","year":"1962","unstructured":"Wilks, S. (1962). Matematical statistics. New York: John Wiley and Sons."},{"key":"391590_CR12","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1007\/BF02055587","volume":"28","author":"S. Yakowitz","year":"1991","unstructured":"Yakowitz, S., & Lowe, W. (1991). Nonparametric bandit methods. Annals of Operations Research, 28, 297\u2013312.","journal-title":"Annals of Operations Research"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1013689704352.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1013689704352\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1013689704352.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T11:38:46Z","timestamp":1752147526000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1013689704352"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2002,5]]},"references-count":12,"journal-issue":{"issue":"2-3","published-print":{"date-parts":[[2002,5]]}},"alternative-id":["391590"],"URL":"https:\/\/doi.org\/10.1023\/a:1013689704352","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2002,5]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}