{"id":"https://openalex.org/W3011892947","doi":"https://doi.org/10.1109/cdc40024.2019.9030099","title":"Monte Carlo tree search with optimal computing budget allocation","display_name":"Monte Carlo tree search with optimal computing budget allocation","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3011892947","doi":"https://doi.org/10.1109/cdc40024.2019.9030099","mag":"3011892947"},"language":"en","primary_location":{"id":"doi:10.1109/cdc40024.2019.9030099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9030099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101761583","display_name":"Yunchuan Li","orcid":"https://orcid.org/0000-0003-2716-6214"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunchuan Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering and the Institute for Systems Research, University of Maryland, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and the Institute for Systems Research, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000889975","display_name":"Michael C. Fu","orcid":"https://orcid.org/0000-0003-2105-4932"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Fu","raw_affiliation_strings":["Robert H. Smith School of Business and the Institute for Systems Research, University of Maryland, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robert H. Smith School of Business and the Institute for Systems Research, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075059198","display_name":"Jie Xu","orcid":"https://orcid.org/0000-0002-9422-6080"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Xu","raw_affiliation_strings":["Department of Systems Engineering and Operations Research, George Mason University, Fairfax, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Operations Research, George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"6332","last_page":"6337"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9991999864578247,"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":0.9991999864578247,"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/T11674","display_name":"Sports Analytics and Performance","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9968000054359436,"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":0.7475671768188477},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7314028739929199},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6486843824386597},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.629612922668457},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5218169093132019},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.512755274772644},{"id":"https://openalex.org/keywords/search-tree","display_name":"Search tree","score":0.4541144371032715},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.4449477195739746},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4443269371986389},{"id":"https://openalex.org/keywords/game-tree","display_name":"Game tree","score":0.43376338481903076},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.31278374791145325},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.27286088466644287},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.24270030856132507},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21969062089920044},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19187599420547485},{"id":"https://openalex.org/keywords/sequential-game","display_name":"Sequential game","score":0.16179487109184265},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11417970061302185}],"concepts":[{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.7475671768188477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7314028739929199},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6486843824386597},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.629612922668457},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5218169093132019},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.512755274772644},{"id":"https://openalex.org/C207024777","wikidata":"https://www.wikidata.org/wiki/Q621673","display_name":"Search tree","level":3,"score":0.4541144371032715},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4449477195739746},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4443269371986389},{"id":"https://openalex.org/C95815963","wikidata":"https://www.wikidata.org/wiki/Q1377033","display_name":"Game tree","level":4,"score":0.43376338481903076},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.31278374791145325},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.27286088466644287},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.24270030856132507},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21969062089920044},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19187599420547485},{"id":"https://openalex.org/C73795354","wikidata":"https://www.wikidata.org/wiki/Q287618","display_name":"Sequential game","level":3,"score":0.16179487109184265},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11417970061302185},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc40024.2019.9030099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9030099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1536615069","https://openalex.org/W1588577747","https://openalex.org/W1625390266","https://openalex.org/W1714211023","https://openalex.org/W1881419322","https://openalex.org/W1967181812","https://openalex.org/W2009551863","https://openalex.org/W2016647253","https://openalex.org/W2038110713","https://openalex.org/W2046282120","https://openalex.org/W2097416000","https://openalex.org/W2097955668","https://openalex.org/W2098432798","https://openalex.org/W2105066050","https://openalex.org/W2138016587","https://openalex.org/W2144304907","https://openalex.org/W2168405694","https://openalex.org/W2224586405","https://openalex.org/W2257979135","https://openalex.org/W2545898123","https://openalex.org/W2950433453","https://openalex.org/W4212953028","https://openalex.org/W4237029372","https://openalex.org/W4237697081","https://openalex.org/W4245448682","https://openalex.org/W6629459031","https://openalex.org/W6635205333","https://openalex.org/W6636578284","https://openalex.org/W6674624367","https://openalex.org/W6674675285","https://openalex.org/W6675713325","https://openalex.org/W6685283413","https://openalex.org/W6728832488","https://openalex.org/W6739435002"],"related_works":["https://openalex.org/W4383535542","https://openalex.org/W3193783858","https://openalex.org/W4386874825","https://openalex.org/W4383560925","https://openalex.org/W2523674799","https://openalex.org/W1973194029","https://openalex.org/W2102256448","https://openalex.org/W2978000411","https://openalex.org/W4327811054","https://openalex.org/W2188928203"],"abstract_inverted_index":{"We":[0,31],"analyze":[1],"a":[2,33,40,46,79],"tree":[3,35,72,76],"search":[4],"problem":[5],"with":[6,120],"an":[7],"underlying":[8],"Markov":[9],"decision":[10],"process,":[11],"in":[12,135],"which":[13],"the":[14,19,23,27,50,55,63,74,85,91,100,130,137,141],"goal":[15],"is":[16,94,105,126],"to":[17,44,62,83,117,128],"identify":[18],"best":[20,56,138],"action":[21,57,139],"at":[22,58,140],"root":[24],"that":[25,37,99],"achieves":[26],"highest":[28],"cumulative":[29],"reward.":[30],"present":[32],"new":[34,75],"policy":[36,77],"optimally":[38],"allocates":[39],"limited":[41],"computing":[42],"budget":[43,93],"maximize":[45],"lower":[47],"bound":[48],"on":[49],"probability":[51],"of":[52,71,102,132],"correctly":[53],"selecting":[54,136],"each":[59],"node.":[60],"Compared":[61],"widely":[64],"used":[65],"Upper":[66],"Confidence":[67],"Bound":[68],"(UCB)":[69],"type":[70],"policies,":[73],"presents":[78],"more":[80],"balanced":[81],"approach":[82],"manage":[84],"exploration":[86],"and":[87,113],"exploitation":[88],"trade-off":[89],"when":[90],"sampling":[92],"limited.":[95],"Furthermore,":[96],"UCB":[97],"assumes":[98],"support":[101],"reward":[103],"distribution":[104],"known,":[106],"whereas":[107],"our":[108,133],"algorithm":[109,134],"relaxes":[110],"this":[111],"assumption,":[112],"can":[114],"be":[115],"applied":[116],"game":[118],"trees":[119],"mild":[121],"modifications.":[122],"A":[123],"numerical":[124],"experiment":[125],"conducted":[127],"demonstrate":[129],"efficiency":[131],"root.":[142]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}