{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T07:53:38Z","timestamp":1743062018725,"version":"3.40.3"},"publisher-location":"Cham","reference-count":13,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319279916"},{"type":"electronic","value":"9783319279923"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"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":[[2015]]},"DOI":"10.1007\/978-3-319-27992-3_6","type":"book-chapter","created":{"date-parts":[[2015,12,24]],"date-time":"2015-12-24T12:24:21Z","timestamp":1450959861000},"page":"53-64","source":"Crossref","is-referenced-by-count":1,"title":["Adapting Improved Upper Confidence Bounds for Monte-Carlo Tree Search"],"prefix":"10.1007","author":[{"given":"Yun-Ching","family":"Liu","sequence":"first","affiliation":[]},{"given":"Yoshimasa","family":"Tsuruoka","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,12,25]]},"reference":[{"issue":"1","key":"6_CR1","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/0196-8858(85)90002-8","volume":"6","author":"TL Lai","year":"1985","unstructured":"Lai, T.L., Robbins, H.: Asymptotically efficient adaptive allocation rules. Adv. Appl. Math. 6(1), 4 (1985)","journal-title":"Adv. Appl. Math."},{"key":"6_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10998-010-3055-6","volume":"61","author":"P Auer","year":"2010","unstructured":"Auer, P., Ortner, R.: UCB revisited: improved regret bounds for the stochastic multi-armed bandit problem. Periodica Math. Hung. 61, 1\u20132 (2010)","journal-title":"Periodica Math. Hung."},{"key":"6_CR3","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/11871842_29","volume-title":"Machine Learning: ECML 2006","author":"L Kocsis","year":"2006","unstructured":"Kocsis, L., Szepesv\u00e1ri, C.: Bandit based monte-carlo planning. In: F\u00fcrnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol. 4212, pp. 282\u2013293. Springer, Heidelberg (2006)"},{"issue":"2\u20133","key":"6_CR4","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. Mach. Learn. 47(2\u20133), 235\u2013256 (2002)","journal-title":"Mach. Learn."},{"key":"6_CR5","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge, MA (1998)"},{"issue":"1","key":"6_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TCIAIG.2012.2186810","volume":"4","author":"CB Browne","year":"2012","unstructured":"Browne, C.B., Powley, E., Whitehouse, D., Lucas, S.M., Cowling, P.I., Rohlfshagen, P., Tavener, S., Perez, D., Samothrakis, S., Colton, S.: A survey of monte carlo tree search methods. IEEE Trans. Comput. Intell. AI Games 4(1), 1\u201343 (2012)","journal-title":"IEEE Trans. Comput. Intell. AI Games"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Tolpin, D., Shimony, S.E.: MCTS based on simple regret. In: Proceedings of the 26th AAAI Conference on Artificial Intelligence, pp. 570\u2013576 (2012)","DOI":"10.1609\/aaai.v26i1.8126"},{"key":"6_CR8","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1109\/TCIAIG.2014.2317737","volume":"7","author":"T Cazenave","year":"2014","unstructured":"Cazenave, T.: Sequential halving applied to trees. IEEE Trans. Comput. Intell. AI Games 7, 102\u2013105 (2014)","journal-title":"IEEE Trans. Comput. Intell. AI Games"},{"key":"6_CR9","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-319-14923-3_1","volume-title":"Computer Games","author":"T Pepels","year":"2014","unstructured":"Pepels, T., Cazenave, T., Winands, M.H.M., Lanctot, M.: Minimizing simple and cumulative regret in monte-carlo tree search. In: Cazenave, T., Winands, M.H.M., Bj\u00f6rnsson, Y. (eds.) CGW 2014. CCIS, vol. 504, pp. 1\u201315. Springer, Heidelberg (2014)"},{"key":"6_CR10","unstructured":"Imagawa, T., Kaneko, T.: Applying multi armed bandit algorithms to MCTS and those analysis. In: Proceedings of the 19th Game Programming Workshop (GPW-14), pp. 145\u2013150 (2014)"},{"key":"6_CR11","unstructured":"Karnin, Z., Koren, T., Oren, S.: Almost optimal exploration in multi-armed bandits. In: Proceedings of the 30th International Conference on Machine Learning (ICML\u201913), pp. 1238\u20131246 (2013)"},{"key":"6_CR12","unstructured":"Garivier, A., Cappe, A.: The KL-UCB algorithm for bounded stochastic bandits and beyond. In: Proceedings of 24th Annual Conference on Learning Theory (COLT \u201911), pp. 359\u2013376 (2011)"},{"key":"6_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1007\/978-3-642-34106-9_18","volume-title":"Algorithmic Learning Theory","author":"E Kaufmann","year":"2012","unstructured":"Kaufmann, E., Korda, N., Munos, R.: Thompson sampling: an asymptotically optimal finite-time analysis. In: Bshouty, N.H., Stoltz, G., Vayatis, N., Zeugmann, T. (eds.) ALT 2012. LNCS, vol. 7568, pp. 199\u2013213. Springer, Heidelberg (2012)"}],"container-title":["Lecture Notes in Computer Science","Advances in Computer Games"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-27992-3_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,16]],"date-time":"2023-08-16T08:28:44Z","timestamp":1692174524000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-27992-3_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319279916","9783319279923"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-27992-3_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]}}}