{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T16:03:39Z","timestamp":1788019419082,"version":"build-2784847793"},"publisher-location":"Berlin, Heidelberg","reference-count":14,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540453758","type":"print"},{"value":"9783540460565","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11871842_29","type":"book-chapter","created":{"date-parts":[[2006,9,18]],"date-time":"2006-09-18T04:28:47Z","timestamp":1158553727000},"page":"282-293","source":"Crossref","is-referenced-by-count":1315,"title":["Bandit Based Monte-Carlo Planning"],"prefix":"10.1007","author":[{"given":"Levente","family":"Kocsis","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Csaba","family":"Szepesv\u00e1ri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"issue":"2-3","key":"29_CR1","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":"29_CR2","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 Journal on Computing\u00a032, 48\u201377 (2002)","journal-title":"SIAM Journal on Computing"},{"key":"29_CR3","unstructured":"Barto, A.G., Bradtke, S.J., Singh, S.P.: Real-time learning and control using asynchronous dynamic programming. Technical report 91-57, Computer Science Department, University of Massachusetts (1991)"},{"key":"29_CR4","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1016\/S0004-3702(01)00130-8","volume":"134","author":"D. Billings","year":"2002","unstructured":"Billings, D., Davidson, A., Schaeffer, J., Szafron, D.: The challenge of poker. Artificial Intelligence\u00a0134, 201\u2013240 (2002)","journal-title":"Artificial Intelligence"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Bouzy, B., Helmstetter, B.: Monte Carlo Go developments. In: van den Herik, H.J., Iida, H., Heinz, E.A. (eds.) Advances in Computer Games 10, pp. 159\u2013174 (2004)","DOI":"10.1007\/978-0-387-35706-5_11"},{"issue":"1","key":"29_CR6","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1287\/opre.1040.0145","volume":"53","author":"H.S. Chang","year":"2005","unstructured":"Chang, H.S., Fu, M., Hu, J., Marcus, S.I.: An adaptive sampling algorithm for solving Markov decision processes. Operations Research\u00a053(1), 126\u2013139 (2005)","journal-title":"Operations Research"},{"key":"29_CR7","unstructured":"Chung, M., Buro, M., Schaeffer, J.: Monte Carlo planning in RTS games. In: CIG 2005, Colchester, UK (2005)"},{"key":"29_CR8","unstructured":"Kearns, M., Mansour, Y., Ng, A.Y.: A sparse sampling algorithm for near-optimal planning in large Markovian decisi on processes. In: Proceedings of IJCAI 1999, pp. 1324\u20131331 (1999)"},{"key":"29_CR9","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":"29_CR10","unstructured":"P\u00e9ret, L., Garcia, F.: On-line search for solving Markov decision processes via heuristic sampling. In: de M\u00e1ntaras, R.L., Saitta, L. (eds.) ECAI, pp. 530\u2013534 (2004)"},{"issue":"1\u20132","key":"29_CR11","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1016\/S0004-3702(01)00166-7","volume":"134","author":"B. Sheppard","year":"2002","unstructured":"Sheppard, B.: World-championship-caliber Scrabble. Artificial Intelligence\u00a0134(1\u20132), 241\u2013275 (2002)","journal-title":"Artificial Intelligence"},{"key":"29_CR12","unstructured":"Smith, S.J.J., Nau, D.S.: An analysis of forward pruning. In: AAAI, pp. 1386\u20131391 (1994)"},{"key":"29_CR13","unstructured":"Tesauro, G., Galperin, G.R.: On-line policy improvement using Monte-Carlo search. In: Mozer, M.C., Jordan, M.I., Petsche, T. (eds.) NIPS 9, pp. 1068\u20131074 (1997)"},{"key":"29_CR14","unstructured":"Vanderbei, R.: Optimal sailing strategies, statistics and operations research program. University of Princeton (1996), \n                    \n                      http:\/\/www.sor.princeton.edu\/~rvdb\/sail\/sail.html"}],"container-title":["Lecture Notes in Computer Science","Machine Learning: ECML 2006"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11871842_29.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T03:24:09Z","timestamp":1619493849000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11871842_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540453758","9783540460565"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/11871842_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2006]]}}}