{"id":"https://openalex.org/W10397790","doi":"https://doi.org/10.1007/978-3-319-14923-3_1","title":"Minimizing Simple and Cumulative Regret in Monte-Carlo Tree Search","display_name":"Minimizing Simple and Cumulative Regret in Monte-Carlo Tree Search","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W10397790","doi":"https://doi.org/10.1007/978-3-319-14923-3_1","mag":"10397790"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-14923-3_1","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Springer Nature","Springer Science+Business Media"],"type":"book series"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"book-chapter","type_crossref":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://mlanctot.info/files/papers/cgw14-hmcts.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036250489","display_name":"Tom Pepels","orcid":"https://orcid.org/0009-0007-1437-0693"},"institutions":[{"id":"https://openalex.org/I34352273","display_name":"Maastricht University","ror":"https://ror.org/02jz4aj89","country_code":"NL","type":"education","lineage":["https://openalex.org/I34352273"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Tom Pepels","raw_affiliation_strings":["Games and AI Group, Department of Knowledge Engineering, Faculty of Humanities and Sciences, Maastricht University, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Games and AI Group, Department of Knowledge Engineering, Faculty of Humanities and Sciences, Maastricht University, The Netherlands","institution_ids":["https://openalex.org/I34352273"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006305238","display_name":"Tristan Cazenave","orcid":"https://orcid.org/0000-0003-4669-9374"},"institutions":[{"id":"https://openalex.org/I56435720","display_name":"Universit\u00e9 Paris Dauphine-PSL","ror":"https://ror.org/052bz7812","country_code":"FR","type":"education","lineage":["https://openalex.org/I56435720"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Tristan Cazenave","raw_affiliation_strings":["LAMSADE - Universit\u00e9 Paris-Dauphine, France"],"affiliations":[{"raw_affiliation_string":"LAMSADE - Universit\u00e9 Paris-Dauphine, France","institution_ids":["https://openalex.org/I56435720"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013661099","display_name":"Mark H. M. Winands","orcid":"https://orcid.org/0000-0002-0125-0824"},"institutions":[{"id":"https://openalex.org/I34352273","display_name":"Maastricht University","ror":"https://ror.org/02jz4aj89","country_code":"NL","type":"education","lineage":["https://openalex.org/I34352273"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mark H. M. Winands","raw_affiliation_strings":["Games and AI Group, Department of Knowledge Engineering, Faculty of Humanities and Sciences, Maastricht University, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Games and AI Group, Department of Knowledge Engineering, Faculty of Humanities and Sciences, Maastricht University, The Netherlands","institution_ids":["https://openalex.org/I34352273"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049659586","display_name":"Marc Lanctot","orcid":null},"institutions":[{"id":"https://openalex.org/I34352273","display_name":"Maastricht University","ror":"https://ror.org/02jz4aj89","country_code":"NL","type":"education","lineage":["https://openalex.org/I34352273"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marc Lanctot","raw_affiliation_strings":["Games and AI Group, Department of Knowledge Engineering, Faculty of Humanities and Sciences, Maastricht University, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Games and AI Group, Department of Knowledge Engineering, Faculty of Humanities and Sciences, Maastricht University, The Netherlands","institution_ids":["https://openalex.org/I34352273"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.232,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.901981,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":89},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Game Artificial Intelligence Research","score":0.9999,"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":"Game Artificial Intelligence Research","score":0.9999,"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":"Optimization of Multi-Armed Bandit Problems","score":0.9947,"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 Algorithms","score":0.9931,"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/regret-analysis","display_name":"Regret Analysis","score":0.603123},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5787251},{"id":"https://openalex.org/keywords/bandit-optimization","display_name":"Bandit Optimization","score":0.551218},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo Tree Search","score":0.539322},{"id":"https://openalex.org/keywords/contextual-bandits","display_name":"Contextual Bandits","score":0.524631},{"id":"https://openalex.org/keywords/behavior-trees","display_name":"Behavior Trees","score":0.500912},{"id":"https://openalex.org/keywords/game-tree","display_name":"Game tree","score":0.44050336}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.9869349},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.8022187},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.67147666},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5787251},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.55500686},{"id":"https://openalex.org/C95815963","wikidata":"https://www.wikidata.org/wiki/Q1377033","display_name":"Game tree","level":4,"score":0.44050336},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.42889833},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4065557},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2505285},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1840555},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14618519},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.08076012},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.059589565},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C73795354","wikidata":"https://www.wikidata.org/wiki/Q287618","display_name":"Sequential game","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-14923-3_1","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Springer Nature","Springer Science+Business Media"],"type":"book series"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.711.8490","pdf_url":"http://mlanctot.info/files/papers/cgw14-hmcts.pdf","source":{"id":"https://openalex.org/S4306400349","display_name":"CiteSeer X (The Pennsylvania State University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130769515","host_organization_name":"Pennsylvania State University","host_organization_lineage":["https://openalex.org/I130769515"],"host_organization_lineage_names":["Pennsylvania State University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.711.8490","pdf_url":"http://mlanctot.info/files/papers/cgw14-hmcts.pdf","source":{"id":"https://openalex.org/S4306400349","display_name":"CiteSeer X (The Pennsylvania State University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130769515","host_organization_name":"Pennsylvania State University","host_organization_lineage":["https://openalex.org/I130769515"],"host_organization_lineage_names":["Pennsylvania State University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"score":0.59,"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":22,"referenced_works":["https://openalex.org/W1553290137","https://openalex.org/W1603772156","https://openalex.org/W1625390266","https://openalex.org/W1658022593","https://openalex.org/W1714211023","https://openalex.org/W176827212","https://openalex.org/W1881419322","https://openalex.org/W1968887996","https://openalex.org/W2065339974","https://openalex.org/W2080045911","https://openalex.org/W2086942358","https://openalex.org/W2102256448","https://openalex.org/W2108794978","https://openalex.org/W2112583639","https://openalex.org/W2126316555","https://openalex.org/W2126559945","https://openalex.org/W2152066132","https://openalex.org/W2168405694","https://openalex.org/W2204079010","https://openalex.org/W2949764112","https://openalex.org/W2949947343","https://openalex.org/W2950757557"],"related_works":["https://openalex.org/W4383560925","https://openalex.org/W4383535542","https://openalex.org/W4323526614","https://openalex.org/W3193783858","https://openalex.org/W2905819080","https://openalex.org/W2567165815","https://openalex.org/W2523674799","https://openalex.org/W2102256448","https://openalex.org/W1973194029","https://openalex.org/W10397790"],"abstract_inverted_index":{"Regret":[0],"minimization":[1],"is":[2,47],"important":[3],"in":[4,36,49,67,86,135],"both":[5,82],"the":[6,19,24,53,59,68,90,106,118,122,131],"Multi-Armed":[7],"Bandit":[8],"problem":[9],"and":[10,108,129,145],"Monte-Carlo":[11],"Tree":[12],"Search":[13],"(MCTS).":[14],"Recently,":[15],"simple":[16,103],"regret,":[17],"i.e.,":[18,38],"regret":[20,35,39,46,66,85,104,113],"of":[21,45,55,84,89,98,133],"not":[22],"recommending":[23],"best":[25],"action,":[26],"has":[27],"been":[28],"proposed":[29],"as":[30],"an":[31],"alternative":[32],"to":[33,101,110],"cumulative":[34,65,112],"MCTS,":[37],"accumulated":[40],"over":[41],"time.":[42],"Each":[43],"type":[44],"appropriate":[48],"different":[50,87],"contexts.":[51],"Although":[52],"majority":[54],"MCTS":[56,75,78],"research":[57],"applies":[58],"UCT":[60,109],"selection":[61],"policy":[62],"for":[63,124],"minimizing":[64],"tree,":[69],"this":[70,125],"paper":[71],"introduces":[72],"a":[73,95],"new":[74,126],"variant,":[76],"Hybrid":[77],"(H-MCTS),":[79],"which":[80],"minimizes":[81],"types":[83],"parts":[88],"tree.":[91,119],"H-MCTS":[92,134],"uses":[93],"SHOT,":[94],"recursive":[96],"version":[97],"Sequential":[99],"Halving,":[100],"minimize":[102,111],"near":[105],"root,":[107],"when":[114],"descending":[115],"further":[116],"down":[117],"We":[120],"discuss":[121],"motivation":[123],"search":[127],"technique,":[128],"show":[130],"performance":[132],"six":[136],"distinct":[137],"two-player":[138],"games:":[139],"Amazons,":[140],"AtariGo,":[141],"Ataxx,":[142],"Breakthrough,":[143],"NoGo,":[144],"Pentalath.":[146]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W10397790","counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":3}],"updated_date":"2024-10-07T23:13:21.370296","created_date":"2016-06-24"}
