{"id":"https://openalex.org/W3167334575","doi":"https://doi.org/10.1109/tac.2021.3088792","title":"An Optimal Computing Budget Allocation Tree Policy for Monte Carlo Tree Search","display_name":"An Optimal Computing Budget Allocation Tree Policy for Monte Carlo Tree Search","publication_year":2021,"publication_date":"2021-06-14","ids":{"openalex":"https://openalex.org/W3167334575","doi":"https://doi.org/10.1109/tac.2021.3088792","mag":"3167334575"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2021.3088792","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2021.3088792","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-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/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":"https://orcid.org/0000-0003-2716-6214","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 C. Fu","raw_affiliation_strings":["R. H. Smith School of Business and the Institute for Systems Research, University of Maryland, College Park, MD, USA"],"raw_orcid":"https://orcid.org/0000-0003-2105-4932","affiliations":[{"raw_affiliation_string":"R. 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":"https://orcid.org/0000-0002-9422-6080","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":2.3202,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.90057718,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"67","issue":"6","first_page":"2685","last_page":"2699"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9986000061035156,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9977999925613403,"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/computer-science","display_name":"Computer science","score":0.6704510450363159},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6594756245613098},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6567339301109314},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.6565756797790527},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5885060429573059},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.46883314847946167},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4599522650241852},{"id":"https://openalex.org/keywords/search-tree","display_name":"Search tree","score":0.44107598066329956},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.3862440288066864},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.2560211718082428},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24906855821609497},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23140740394592285},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12698233127593994},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08518049120903015}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6704510450363159},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6594756245613098},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6567339301109314},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.6565756797790527},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5885060429573059},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.46883314847946167},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4599522650241852},{"id":"https://openalex.org/C207024777","wikidata":"https://www.wikidata.org/wiki/Q621673","display_name":"Search tree","level":3,"score":0.44107598066329956},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.3862440288066864},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.2560211718082428},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24906855821609497},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23140740394592285},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12698233127593994},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08518049120903015},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2021.3088792","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2021.3088792","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/17"}],"awards":[{"id":"https://openalex.org/G3747973309","display_name":null,"funder_award_id":"FA95502010211","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G4355153667","display_name":null,"funder_award_id":"N660011824024","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G4554390172","display_name":null,"funder_award_id":"FA9550-19-1-0383","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G8717510076","display_name":null,"funder_award_id":"DMS-1923145","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G8805755233","display_name":null,"funder_award_id":"CMMI-1434419","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1536615069","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/W2049934117","https://openalex.org/W2097416000","https://openalex.org/W2097955668","https://openalex.org/W2098432798","https://openalex.org/W2105066050","https://openalex.org/W2106663919","https://openalex.org/W2126316555","https://openalex.org/W2138016587","https://openalex.org/W2168405694","https://openalex.org/W2224586405","https://openalex.org/W2257979135","https://openalex.org/W2401855953","https://openalex.org/W2484571116","https://openalex.org/W2524229012","https://openalex.org/W2545898123","https://openalex.org/W2606614575","https://openalex.org/W2804342876","https://openalex.org/W2950433453","https://openalex.org/W2963653944","https://openalex.org/W2972635416","https://openalex.org/W3011892947","https://openalex.org/W3086574084","https://openalex.org/W4212953028","https://openalex.org/W4237029372","https://openalex.org/W4237697081","https://openalex.org/W6674624367","https://openalex.org/W6674675285","https://openalex.org/W6675713325","https://openalex.org/W6676362848","https://openalex.org/W6678102440","https://openalex.org/W6685283413","https://openalex.org/W6689048836","https://openalex.org/W6728832488","https://openalex.org/W6739435002","https://openalex.org/W6752125625","https://openalex.org/W6775321880"],"related_works":["https://openalex.org/W4386874825","https://openalex.org/W2162286586","https://openalex.org/W4327811054","https://openalex.org/W2978000411","https://openalex.org/W4255368532","https://openalex.org/W2770627170","https://openalex.org/W4206302813","https://openalex.org/W2491631281","https://openalex.org/W2967025328","https://openalex.org/W1785631772"],"abstract_inverted_index":{"We":[0,31],"analyze":[1],"a":[2,33,40,46,76],"tree":[3,35,69,73],"search":[4],"problem":[5],"with":[6],"an":[7],"underlying":[8],"Markov":[9],"decision":[10],"process,":[11],"in":[12,118],"which":[13],"the":[14,19,23,27,50,55,71,82,88,97,113,120,124],"goal":[15],"is":[16,91,102],"to":[17,44,62,80],"identify":[18],"best":[20,56,121],"action":[21,57,122],"at":[22,58,123],"root":[24],"that":[25,37,96],"achieves":[26],"highest":[28],"cumulative":[29],"reward.":[30],"present":[32],"new":[34,72],"policy":[36,74],"optimally":[38],"allocates":[39],"limited":[41],"computing":[42],"budget":[43,90],"maximize":[45],"lower":[47],"bound":[48,67],"on":[49],"probability":[51],"of":[52,99,115],"correctly":[53],"selecting":[54,119],"each":[59],"node.":[60],"Compared":[61],"widely":[63],"used":[64],"upper":[65],"confidence":[66],"(UCB)":[68],"policies,":[70],"presents":[75],"more":[77],"balanced":[78],"approach":[79],"manage":[81],"exploration":[83],"and":[84],"exploitation":[85],"tradeoff":[86],"when":[87],"sampling":[89],"limited.":[92],"Furthermore,":[93],"UCB":[94],"assumes":[95],"support":[98],"reward":[100],"distribution":[101],"known,":[103],"whereas":[104],"our":[105,116],"algorithm":[106,117],"relaxes":[107],"this":[108],"assumption.":[109],"Numerical":[110],"experiments":[111],"demonstrate":[112],"efficiency":[114],"root.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}