{"id":"https://openalex.org/W2996609870","doi":"https://doi.org/10.1142/s0217595919400098","title":"Simulation-Based Algorithms for Markov Decision Processes: Monte Carlo Tree Search from AlphaGo to AlphaZero","display_name":"Simulation-Based Algorithms for Markov Decision Processes: Monte Carlo Tree Search from AlphaGo to AlphaZero","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W2996609870","doi":"https://doi.org/10.1142/s0217595919400098","mag":"2996609870"},"language":"en","primary_location":{"id":"doi:10.1142/s0217595919400098","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0217595919400098","pdf_url":null,"source":{"id":"https://openalex.org/S1254427","display_name":"Asia Pacific Journal of Operational Research","issn_l":"0217-5959","issn":["0217-5959","1793-7019"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Asia-Pacific Journal of Operational Research","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/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":true,"raw_author_name":"Michael C. Fu","raw_affiliation_strings":["Robert H. Smith School of Business & Institute for Systems Research, University of Maryland, College Park, Maryland 20742, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robert H. Smith School of Business & Institute for Systems Research, University of Maryland, College Park, Maryland 20742, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5000889975"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":0.9883,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.82792837,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"36","issue":"06","first_page":"1940009","last_page":"1940009"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9976000189781189,"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":0.9962999820709229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.8817360997200012},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.639146089553833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.583525538444519},{"id":"https://openalex.org/keywords/champion","display_name":"Champion","score":0.558427631855011},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.5182023644447327},{"id":"https://openalex.org/keywords/game-tree","display_name":"Game tree","score":0.4414524435997009},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42835038900375366},{"id":"https://openalex.org/keywords/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.4202454686164856},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.4173271358013153},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.35155996680259705},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3361820876598358},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.3246641159057617},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.29020488262176514},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.2091275155544281},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.1797327995300293},{"id":"https://openalex.org/keywords/sequential-game","display_name":"Sequential game","score":0.17179065942764282},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14046034216880798},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.13035252690315247},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09442025423049927}],"concepts":[{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.8817360997200012},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.639146089553833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.583525538444519},{"id":"https://openalex.org/C2780465443","wikidata":"https://www.wikidata.org/wiki/Q852061","display_name":"Champion","level":2,"score":0.558427631855011},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.5182023644447327},{"id":"https://openalex.org/C95815963","wikidata":"https://www.wikidata.org/wiki/Q1377033","display_name":"Game tree","level":4,"score":0.4414524435997009},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42835038900375366},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.4202454686164856},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.4173271358013153},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.35155996680259705},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3361820876598358},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.3246641159057617},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.29020488262176514},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.2091275155544281},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.1797327995300293},{"id":"https://openalex.org/C73795354","wikidata":"https://www.wikidata.org/wiki/Q287618","display_name":"Sequential game","level":3,"score":0.17179065942764282},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14046034216880798},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.13035252690315247},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09442025423049927},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1142/s0217595919400098","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0217595919400098","pdf_url":null,"source":{"id":"https://openalex.org/S1254427","display_name":"Asia Pacific Journal of Operational Research","issn_l":"0217-5959","issn":["0217-5959","1793-7019"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Asia-Pacific Journal of Operational Research","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:wsi:apjorx:v:36:y:2019:i:06:n:s0217595919400098","is_oa":false,"landing_page_url":"http://www.worldscientific.com/doi/abs/10.1142/S0217595919400098","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6833004606","display_name":null,"funder_award_id":"CMMI-1434419","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1536615069","https://openalex.org/W1625390266","https://openalex.org/W2000080679","https://openalex.org/W2009551863","https://openalex.org/W2016647253","https://openalex.org/W2024780670","https://openalex.org/W2098432798","https://openalex.org/W2100857832","https://openalex.org/W2122272911","https://openalex.org/W2126316555","https://openalex.org/W2131600418","https://openalex.org/W2168405694","https://openalex.org/W2257979135","https://openalex.org/W2295012269","https://openalex.org/W2401135644","https://openalex.org/W2505159842","https://openalex.org/W2541018735","https://openalex.org/W2574978968","https://openalex.org/W2762403641","https://openalex.org/W2766447205","https://openalex.org/W2773381986","https://openalex.org/W2787259794","https://openalex.org/W2902907165","https://openalex.org/W2960876848","https://openalex.org/W2963653944","https://openalex.org/W4214717370","https://openalex.org/W4237029372","https://openalex.org/W4247855592","https://openalex.org/W4252019227","https://openalex.org/W4298215580","https://openalex.org/W4302608015","https://openalex.org/W4307347247"],"related_works":["https://openalex.org/W2152117070","https://openalex.org/W4383535542","https://openalex.org/W3193783858","https://openalex.org/W4383560925","https://openalex.org/W1973194029","https://openalex.org/W2523674799","https://openalex.org/W2102256448","https://openalex.org/W4323526614","https://openalex.org/W2567165815","https://openalex.org/W2999703182"],"abstract_inverted_index":{"AlphaGo":[0,4,37,84,243],"and":[1,6,32,73,146,166,213,240,258,281],"its":[2,259],"successors":[3],"Zero":[5],"AlphaZero":[7,116],"made":[8],"international":[9],"headlines":[10],"with":[11],"their":[12,168],"incredible":[13],"successes":[14],"in":[15,33,52,55,71,77,106,109,113,138,201,205,234,261,275,298],"game":[16,81],"playing,":[17],"which":[18],"have":[19],"been":[20],"touted":[21],"as":[22],"further":[23],"evidence":[24],"of":[25,29,103,163,242,248],"the":[26,39,78,91,101,118,123,238,246,263,270,299],"immense":[27],"potential":[28],"artificial":[30],"intelligence,":[31],"particular,":[34],"machine":[35],"learning.":[36],"defeated":[38],"reigning":[40],"human":[41],"world":[42,120],"champion":[43],"Go":[44,95,104],"player":[45,96],"Lee":[46],"Sedol":[47],"4":[48],"games":[49,145],"to":[50,187,253],"1,":[51],"March":[53],"2016":[54],"Seoul,":[56],"Korea,":[57],"an":[58,188],"achievement":[59],"that":[60,266],"surpassed":[61],"previous":[62],"computer":[63,125],"game-playing":[64],"program":[65,127],"milestones":[66],"by":[67,74,89,121,142],"IBM\u2019s":[68,75],"Deep":[69],"Blue":[70],"chess":[72,119,126],"Watson":[76],"U.S.":[79],"TV":[80],"show":[82],"Jeopardy.":[83],"then":[85],"followed":[86],"this":[87],"up":[88],"defeating":[90],"world\u2019s":[92],"number":[93],"one":[94],"Ke":[97],"Jie":[98],"3-0":[99],"at":[100],"Future":[102],"Summit":[105],"Wuzhen,":[107],"China":[108],"May":[110],"2017.":[111],"Then,":[112],"December":[114],"2017,":[115],"stunned":[117],"dominating":[122],"top":[124],"Stockfish":[128],"(which":[129],"has":[130],"a":[131,139,173],"far":[132],"higher":[133],"rating":[134],"than":[135],"any":[136],"human)":[137],"100-game":[140],"match":[141],"winning":[143],"28":[144],"losing":[147],"none":[148],"(72":[149],"draws)":[150],"after":[151],"training":[152,262],"from":[153],"scratch":[154],"for":[155,195,221,256],"just":[156],"four":[157],"hours!":[158],"The":[159],"deep":[160],"neural":[161,264],"networks":[162,265],"AlphaGo,":[164],"AlphaZero,":[165,245],"all":[167],"incarnations":[169],"are":[170,250],"trained":[171],"using":[172],"technique":[174],"called":[175],"Monte":[176],"Carlo":[177],"tree":[178],"search":[179],"(MCTS),":[180],"whose":[181],"roots":[182],"can":[183],"be":[184],"traced":[185,251],"back":[186,204,252],"adaptive":[189,218],"multistage":[190],"sampling":[191,219],"(AMS)":[192],"simulation-based":[193,254],"algorithm":[194,220],"Markov":[196,223],"decision":[197,224],"processes":[198],"(MDPs)":[199],"published":[200],"Operations":[202,226],"Research":[203],"2005":[206],"[Chang,":[207],"HS,":[208],"MC":[209],"Fu,":[210],"J":[211],"Hu":[212],"SI":[214],"Marcus":[215],"(2005).":[216],"An":[217],"solving":[222],"processes.":[225],"Research,":[227],"53,":[228],"126\u2013139.]":[229],"(and":[230],"introduced":[231],"even":[232],"earlier":[233],"2002).":[235],"After":[236],"reviewing":[237],"history":[239],"background":[241],"through":[244],"origins":[247],"MCTS":[249],"algorithms":[255],"MDPs,":[257],"role":[260],"essentially":[267],"carry":[268],"out":[269],"value/policy":[271],"function":[272],"approximation":[273],"used":[274],"approximate":[276],"dynamic":[277],"programming,":[278],"reinforcement":[279],"learning,":[280],"neuro-dynamic":[282],"programming":[283],"is":[284],"discussed,":[285],"including":[286],"some":[287],"recently":[288],"proposed":[289],"enhancements":[290],"building":[291],"on":[292],"statistical":[293],"ranking":[294],"&":[295],"selection":[296],"research":[297,301],"operations":[300],"simulation":[302],"community.":[303]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}