{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T06:57:04Z","timestamp":1760597824433},"publisher-location":"Cham","reference-count":12,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319943060"},{"type":"electronic","value":"9783319943077"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-94307-7_5","type":"book-chapter","created":{"date-parts":[[2018,6,19]],"date-time":"2018-06-19T09:28:33Z","timestamp":1529400513000},"page":"55-67","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Reinforcement Learning with Monte Carlo Sampling in Imperfect Information Problems"],"prefix":"10.1007","author":[{"given":"Jiajia","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Hong","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,6,20]]},"reference":[{"key":"5_CR1","unstructured":"Bampton, H.J.: Solving imperfect information games using the Monte Carlo heuristic, Master dissertation. University of Tennessee, USA (1994b)"},{"key":"5_CR2","unstructured":"Brown, N., Sandholm, T.: Safe and nested subgame solving for imperfect-information games (2017)"},{"key":"5_CR3","unstructured":"Billings, D., Papp, D., Schaeffer, J. (eds.): Opponent modeling in poker. In: Association for the Advancement of Artificial Intelligence, pp. 493\u2013499. AAAI Press (1998)"},{"issue":"7587","key":"5_CR4","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., Huang, A., Maddison, C.J., et al.: Mastering the game of Go with deep neural networks and tree search. Nature 529(7587), 484 (2016)","journal-title":"Nature"},{"issue":"7676","key":"5_CR5","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., Schrittwieser, J., Simonyan, K., et al.: Mastering the game of Go without human knowledge. Nature 550(7676), 354 (2017)","journal-title":"Nature"},{"key":"5_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1007\/978-3-540-75538-8_7","volume-title":"Computers and Games","author":"R Coulom","year":"2007","unstructured":"Coulom, R.: Efficient selectivity and backup operators in monte-carlo tree search. In: van den Herik, H.J., Ciancarini, P., Donkers, H.H.L.M.J. (eds.) CG 2006. LNCS, vol. 4630, pp. 72\u201383. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-75538-8_7"},{"key":"5_CR7","unstructured":"http:\/\/www.computerpokercompetition.org\/index.php\/competitions\/results\/125-2017-results"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Long, J., Sturtevant, N., Buro, M.: Understanding the success of perfect information monte carlo sampling in game tree search. In: Proceedings of AAAI-10, pp. 134\u2013140 (2010)","DOI":"10.1609\/aaai.v24i1.7562"},{"key":"5_CR9","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). https:\/\/doi.org\/10.1007\/11871842_29"},{"key":"5_CR10","unstructured":"Zhang, J., Wang, X., Yao, L., Li, L., Shen, X.: Using Kullback-Leibler divergence to model opponents in poker. In: 28th AAAI Conference on Artificial Intelligence (AAAI 2014) Workshop: Computer Poker and Imperfect Information, QuebecCity, Canada, pp. 50\u201357 (2014)"},{"key":"5_CR11","unstructured":"Van der Kleij, A.A.J.: Monte Carlo Tree Search and Opponent Modeling through Player Clustering in no-limit Texas Hold\u2019em Poker. Master dissertation, University of Groningen, The Netherlands (2010b)"},{"key":"5_CR12","unstructured":"https:\/\/tonybet.com\/sport"}],"container-title":["Lecture Notes in Computer Science","Cognitive Computing \u2013 ICCC 2018"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-94307-7_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,3]],"date-time":"2023-09-03T03:28:04Z","timestamp":1693711684000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-94307-7_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319943060","9783319943077"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-94307-7_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}