{"id":"https://openalex.org/W1916578716","doi":"https://doi.org/10.1109/cig.2015.7317923","title":"Regulation of exploration for simple regret minimization in Monte-Carlo tree search","display_name":"Regulation of exploration for simple regret minimization in Monte-Carlo tree search","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W1916578716","doi":"https://doi.org/10.1109/cig.2015.7317923","mag":"1916578716"},"language":"en","primary_location":{"id":"doi:10.1109/cig.2015.7317923","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cig.2015.7317923","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Conference on Computational Intelligence and Games (CIG)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045301572","display_name":"Yun-Ching Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yun-Ching Liu","raw_affiliation_strings":["Graduate School of Engineering University of Tokyo","Graduate school of Engineering, University of Tokyo"],"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering University of Tokyo","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate school of Engineering, University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064113904","display_name":"Yoshimasa Tsuruoka","orcid":"https://orcid.org/0000-0002-0707-1077"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshimasa Tsuruoka","raw_affiliation_strings":["Graduate School of Engineering University of Tokyo","Graduate school of Engineering, University of Tokyo"],"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering University of Tokyo","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate school of Engineering, University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5045301572"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":1.7804,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88389152,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"30","issue":null,"first_page":"35","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.7865293025970459},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.6649753451347351},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.6562356352806091},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.6290127038955688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6060782074928284},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.6002883315086365},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4901898503303528},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.46602770686149597},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35387030243873596},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2879408597946167},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1654166281223297},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13254526257514954},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.11828359961509705}],"concepts":[{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.7865293025970459},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.6649753451347351},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.6562356352806091},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6290127038955688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6060782074928284},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.6002883315086365},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4901898503303528},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.46602770686149597},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35387030243873596},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2879408597946167},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1654166281223297},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13254526257514954},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.11828359961509705},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cig.2015.7317923","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cig.2015.7317923","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Conference on Computational Intelligence and Games (CIG)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.707.6512","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.707.6512","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.logos.t.u-tokyo.ac.jp/%7Etsuruoka/papers/cig2015liu.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W10397790","https://openalex.org/W1500868819","https://openalex.org/W1501823362","https://openalex.org/W1625390266","https://openalex.org/W1881419322","https://openalex.org/W1975779216","https://openalex.org/W1977989560","https://openalex.org/W1997840820","https://openalex.org/W2048751428","https://openalex.org/W2086942358","https://openalex.org/W2121863487","https://openalex.org/W2126316555","https://openalex.org/W2126559945","https://openalex.org/W2158319693","https://openalex.org/W2168405694","https://openalex.org/W2204079010","https://openalex.org/W2963736810","https://openalex.org/W2963750583","https://openalex.org/W4214717370","https://openalex.org/W4300077424","https://openalex.org/W6630117878","https://openalex.org/W6639331779","https://openalex.org/W6678664249","https://openalex.org/W6687944646"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W2101991911","https://openalex.org/W2174986909","https://openalex.org/W2527791220","https://openalex.org/W2155070487","https://openalex.org/W4311589891","https://openalex.org/W10397790","https://openalex.org/W2905819080"],"abstract_inverted_index":{"The":[0],"application":[1,201],"of":[2,14,58,62,96,113,117,149,176,193,202],"multi-armed":[3],"bandit":[4,30,40,46,75,141],"(MAB)":[5],"algorithms":[6,41,124],"was":[7],"a":[8,56,91],"critical":[9],"step":[10],"in":[11,65,68,93,132],"the":[12,23,28,52,72,78,94,111,114,118,137,150,154,161,174,191,200],"development":[13],"Monte-Carlo":[15],"tree":[16,98],"search":[17],"(MCTS).":[18],"One":[19],"example":[20],"would":[21],"be":[22,90,196],"UCT":[24,172],"algorithm,":[25],"which":[26,48,88,109],"applies":[27],"UCB":[29,120,122,151],"algorithm.":[31],"Various":[32],"research":[33],"has":[34,77,143,167,182],"been":[35,61],"conducted":[36],"on":[37,84,153,173],"applying":[38],"other":[39],"to":[42,50,80,125],"MCTS.":[43,133],"Simple":[44],"regret":[45,74,130],"algorithms,":[47],"aim":[49],"identify":[51],"optimal":[53],"arm":[54],"after":[55],"number":[57],"trials,":[59],"have":[60],"great":[63],"interest":[64],"various":[66],"fields":[67],"recent":[69],"years.":[70],"However,":[71],"simple":[73,129],"algorithm":[76,142,152],"tendency":[79],"spend":[81],"more":[82],"time":[83],"sampling":[85],"suboptimal":[86],"arms,":[87],"may":[89],"problem":[92],"context":[95],"game":[97,175],"search.":[99],"In":[100],"this":[101],"research,":[102],"we":[103],"will":[104,135,158,187],"propose":[105],"combined":[106,138,162],"confidence":[107,115,139,163],"bounds,":[108],"utilize":[110],"characteristics":[112],"bounds":[116,140,164],"improved":[119],"and":[121,181],"\u221a\u00b7":[123],"regulate":[126],"exploration":[127],"for":[128],"minimization":[131],"We":[134,157,186],"demonstrate":[136],"better":[144,168],"empirical":[145],"performance":[146,169,192],"than":[147],"that":[148,160,190],"MAB":[155],"problem.":[156],"show":[159,189],"MCTS":[165],"(CCB-MCTS)":[166],"over":[170],"plain":[171],"9":[177,179],"\u00d7":[178],"Go,":[180],"shown":[183],"good":[184],"scalability.":[185],"also":[188],"CCB-MCTS":[194],"can":[195],"further":[197],"enhanced":[198],"with":[199],"all-moves-as-first":[203],"(AMAF)":[204],"heuristic.":[205]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}