{"id":"https://openalex.org/W4407127594","doi":"https://doi.org/10.1109/tac.2025.3538807","title":"On the Convergence Rate of MCTS for the Optimal Value Estimation in Markov Decision Processes","display_name":"On the Convergence Rate of MCTS for the Optimal Value Estimation in Markov Decision Processes","publication_year":2025,"publication_date":"2025-02-04","ids":{"openalex":"https://openalex.org/W4407127594","doi":"https://doi.org/10.1109/tac.2025.3538807"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2025.3538807","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2025.3538807","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/A5041693183","display_name":"Hyeong Soo Chang","orcid":"https://orcid.org/0000-0003-3298-0018"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hyeong Soo Chang","raw_affiliation_strings":["Department of Computer Science and Engineering, Sogang University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sogang University, Seoul, South Korea","institution_ids":["https://openalex.org/I148751991"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5041693183"],"corresponding_institution_ids":["https://openalex.org/I148751991"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00831662,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"70","issue":"7","first_page":"4788","last_page":"4793"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9987000226974487,"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":0.9968000054359436,"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/markov-decision-process","display_name":"Markov decision process","score":0.7026117444038391},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6054402589797974},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5993621349334717},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5243445038795471},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5140310525894165},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.5128803253173828},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4741220772266388},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.46786120533943176},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.42282089591026306},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37248313426971436},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.22480875253677368},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20270046591758728},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0968458354473114},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.0819055438041687}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7026117444038391},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6054402589797974},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5993621349334717},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5243445038795471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5140310525894165},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.5128803253173828},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4741220772266388},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.46786120533943176},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.42282089591026306},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37248313426971436},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.22480875253677368},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20270046591758728},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0968458354473114},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0819055438041687},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2025.3538807","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2025.3538807","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":[{"score":0.47999998927116394,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1625390266","https://openalex.org/W1714211023","https://openalex.org/W1941445455","https://openalex.org/W2009551863","https://openalex.org/W2016647253","https://openalex.org/W2088705090","https://openalex.org/W2108794978","https://openalex.org/W2126316555","https://openalex.org/W2168405694","https://openalex.org/W4213251304","https://openalex.org/W4214650739","https://openalex.org/W4285796263","https://openalex.org/W4302608015"],"related_works":["https://openalex.org/W1660242800","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W4236062181","https://openalex.org/W2315999538","https://openalex.org/W2367222340","https://openalex.org/W187740018","https://openalex.org/W2162286586"],"abstract_inverted_index":{"A":[0],"recent":[1],"theoretical":[2,213],"analysis":[3],"of":[4,32,39,54,56,92,111,138,150,159,188,202],"a":[5,24,29,78,104],"Monte-Carlo":[6],"tree":[7],"search":[8],"(MCTS)":[9],"method":[10],"properly":[11],"modified":[12],"from":[13,36,114],"the":[14,49,57,70,90,109,115,120,147,151,172,178,186,189,193,198],"\u201cupper":[15,124],"confidence":[16,125],"bound":[17,126],"applied":[18],"to":[19,28,61,145,211],"trees\u201d":[20],"(UCT)":[21],"algorithm":[22],"established":[23],"surprising":[25],"result,":[26],"due":[27],"great":[30],"deal":[31],"empirical":[33],"successes":[34],"reported":[35],"heuristic":[37],"usage":[38],"UCT":[40],"with":[41],"relevant":[42],"adjustments":[43],"for":[44,129,215],"various":[45],"problem":[46],"domains":[47],"in":[48,68,77,108,175,192],"literature,":[50],"that":[51,119,171,183],"its":[52,216],"rate":[53],"convergence":[55,99],"expected":[58],"absolute":[59],"error":[60],"zero":[62],"is":[63,89],"<inline-formula":[64,85,160],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[65,86,161],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[66,87,162],"notation=\"LaTeX\">$O(1/\\sqrt{n})$</tex-math></inline-formula>":[67],"estimating":[69],"optimal":[71],"value":[72],"at":[73],"an":[74,136,155],"initial":[75],"state":[76,190],"finite-horizon":[79],"Markov":[80],"decision":[81],"process":[82],"(MDP),":[83],"where":[84],"notation=\"LaTeX\">$n$</tex-math></inline-formula>":[88],"number":[91],"simulations.":[93],"We":[94,167],"strengthen":[95],"this":[96],"dispiriting":[97],"slow":[98],"result":[100],"by":[101,140],"arguing":[102],"within":[103],"simpler":[105,121],"algorithmic":[106],"framework":[107],"perspective":[110],"MDP,":[112,153],"apart":[113],"usual":[116],"MCTS":[117,139,174,208],"description,":[118],"strategy,":[122],"called":[123],"1\u201d":[127],"(UCB1)":[128],"multiarmed":[130],"bandit":[131],"problems,":[132],"when":[133],"employed":[134],"as":[135],"instance":[137],"setting":[141],"UCB1\u2019s":[142],"arm":[143],"set":[144,149],"be":[146],"policy":[148],"underlying":[152],"has":[154,177,209],"asymptotically":[156],"faster":[157],"convergence-rate":[158],"notation=\"LaTeX\">$O(\\ln":[163],"n":[164],"/":[165],"n)$</tex-math></inline-formula>.":[166],"also":[168],"point":[169],"out":[170],"UCT-based":[173,207],"general":[176],"time":[179],"and":[180],"space":[181,191],"complexities":[182],"depend":[184],"on":[185],"size":[187],"worst":[194],"case,":[195],"which":[196],"contradicts":[197],"original":[199],"design":[200],"spirit":[201],"MCTS.":[203],"Unless":[204],"heuristically":[205],"used,":[206],"yet":[210],"have":[212],"supports":[214],"applicabilities.":[217]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}