{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T17:30:18Z","timestamp":1760549418791},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2013,9,1]],"date-time":"2013-09-01T00:00:00Z","timestamp":1377993600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput. Intell. AI Games"],"published-print":{"date-parts":[[2013,9]]},"DOI":"10.1109\/tciaig.2013.2239295","type":"journal-article","created":{"date-parts":[[2013,9,11]],"date-time":"2013-09-11T19:26:22Z","timestamp":1378927582000},"page":"201-213","source":"Crossref","is-referenced-by-count":8,"title":["Monte Carlo Search Algorithm Discovery for Single-Player Games"],"prefix":"10.1109","volume":"5","author":[{"given":"Francis","family":"Maes","sequence":"first","affiliation":[]},{"given":"David Lupien","family":"St-Pierre","sequence":"additional","affiliation":[]},{"given":"Damien","family":"Ernst","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"5","article-title":"Automatic discovery of ranking formulas for playing with multi-armed bandits","author":"maes","year":"2011","journal-title":"Proc 1st European Workshop on Reinforcement Learning EWRL-1"},{"key":"ref38","author":"cazenave","year":"2007","journal-title":"?Evolving Monte Carlo tree search algorithms ?"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-13800-3_9"},{"key":"ref32","article-title":"Parameter tuning by simple regret algorithms and multiple simultaneous hypothesis testing","author":"bourki","year":"2010","journal-title":"Proc Int Conf Inf Control Autom Robot"},{"key":"ref31","first-page":"2249","article-title":"An empirical evaluation of Thompson sampling","author":"chapelle","year":"2011","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-29946-9_20"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2186810"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1007\/978-3-642-31866-5_25","volume":"7168","author":"st-pierre","year":"2012","journal-title":"Advances in Computer Games"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1142\/9789812709677_0246"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273531"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553468"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(01)00130-8"},{"key":"ref11","first-page":"7","article-title":"Meta Monte Carlo tree search for automatic opening book generation","author":"chaslot","year":"2009","journal-title":"Proc Workshop General Intell Game Playing Agents"},{"key":"ref12","article-title":"Learning to play <formula formulatype=\"inline\"> <tex Notation=\"TeX\">$K$<\/tex><\/formula>-armed bandit problems","author":"maes","year":"2012","journal-title":"Proc 3rd Int Conf Agents Artif Intell"},{"key":"ref13","article-title":"Meta-learning of exploration\/exploitation strategies: The multi-armed bandit case","author":"maes","year":"2012","journal-title":"Proc 3rd Int Conf Agents Artif Intell"},{"key":"ref14","article-title":"Learning exploration\/exploitation strategies for single trajectory reinforcement learning","author":"castronovo","year":"2012","journal-title":"10th Eur Workshop Reinforcement Learn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33492-4_6"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/978-3-642-04414-4_7","article-title":"Pure exploration in multi-armed bandits problems","author":"bubeck","year":"2009","journal-title":"Proc Algorithmic Learn Theory"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-28356-0_5"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref19","article-title":"Bandit algorithms for tree search","author":"coquelin","year":"2007","journal-title":"Proc Uncertainty Artif Intell"},{"key":"ref28","article-title":"Parameter tuning by the cross-entropy method","author":"chaslot","year":"2008","journal-title":"10th Eur Workshop Reinforcement Learn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2010.2088123"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2012.6374162"},{"key":"ref3","first-page":"456","article-title":"Nested Monte Carlo search","author":"cazenave","year":"2009","journal-title":"Proc 21st Int Joint Conf Artif Intell"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-31866-5_13"},{"key":"ref5","first-page":"1068","article-title":"On-line policy improvement using Monte Carlo search","volume":"96","author":"tesauro","year":"1996","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref8","first-page":"91","article-title":"Monte-Carlo tree search in production management problems","author":"chaslot","year":"2006","journal-title":"Proc BeNeLux Conf Artif Intell"},{"key":"ref7","first-page":"165","article-title":"Reflexive Monte Carlo search","author":"cazenave","year":"2007","journal-title":"Proc Comput Games Workshop"},{"key":"ref2","first-page":"72","article-title":"Efficient selectivity and backup operators in Monte Carlo tree search","author":"coulom","year":"2006","journal-title":"Proc 5th Int Conf Comput Games"},{"key":"ref1","first-page":"282","article-title":"Bandit based Monte Carlo planning","author":"kocsis","year":"2006","journal-title":"Proc 17th Eur Conf Mach Learn"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/978-3-540-87608-3_1","volume":"5131","author":"schadd","year":"2008","journal-title":"Proceedings of Computers and Games (CG)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12148-7_23"},{"key":"ref22","first-page":"1057","article-title":"Nested Monte Carlo expression discovery","author":"cazenave","year":"2010","journal-title":"Proc Eur Conf Artif Intell"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74819-9_46"},{"key":"ref24","author":"boyer","year":"2012"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10710-010-9121-2"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2007.4424460"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s00224-005-1240-4"},{"key":"ref25","first-page":"649","article-title":"Nested rollout policy adaptation for Monte Carlo tree search","author":"rosin","year":"2011","journal-title":"Proc 22nd Int Joint Conf Artif Intell"}],"container-title":["IEEE Transactions on Computational Intelligence and AI in Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4804728\/6595579\/06409426.pdf?arnumber=6409426","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:02:38Z","timestamp":1642003358000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6409426\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,9]]},"references-count":41,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tciaig.2013.2239295","relation":{},"ISSN":["1943-068X","1943-0698"],"issn-type":[{"value":"1943-068X","type":"print"},{"value":"1943-0698","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,9]]}}}