{"id":"https://openalex.org/W2964934024","doi":"https://doi.org/10.1609/aaai.v33i01.33012157","title":"Variance Reduction in Monte Carlo Counterfactual Regret Minimization (VR-MCCFR) for Extensive Form Games Using Baselines","display_name":"Variance Reduction in Monte Carlo Counterfactual Regret Minimization (VR-MCCFR) for Extensive Form Games Using Baselines","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2964934024","doi":"https://doi.org/10.1609/aaai.v33i01.33012157","mag":"2964934024"},"language":"en","primary_location":{"id":"pmh:oai:ojs.aaai.org:article/4048","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"},"type":"article","indexed_in":[],"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/A5038602378","display_name":"Martin Schmid","orcid":"https://orcid.org/0000-0001-5341-9209"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Schmid, Martin","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018555885","display_name":"Neil Burch","orcid":"https://orcid.org/0000-0002-4596-3690"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Burch, Neil","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049659586","display_name":"Marc Lanctot","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lanctot, Marc","raw_affiliation_strings":["Deepmind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deepmind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004939505","display_name":"Matej Morav\u010d\u00edk","orcid":"https://orcid.org/0000-0001-5205-5378"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Moravcik, Matej","raw_affiliation_strings":["DeepMInd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMInd","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kadlec, Rudolf","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Kadlec, Rudolf","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081163135","display_name":"Michael Bowling","orcid":"https://orcid.org/0000-0003-2960-8418"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bowling, Michael","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.584,"has_fulltext":true,"cited_by_count":48,"citation_normalized_percentile":{"value":0.96514348,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9934999942779541,"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":0.9771999716758728,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/variance-reduction","display_name":"Variance reduction","score":0.7845065593719482},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.672587513923645},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.6313596963882446},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6296778917312622},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.580863356590271},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.579688549041748},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.5221312642097473},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5130788087844849},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5039929747581482},{"id":"https://openalex.org/keywords/magnitude","display_name":"Magnitude (astronomy)","score":0.4579635262489319},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.448317289352417},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.4408622980117798},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.43580538034439087},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.4352065920829773},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.41550254821777344},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4095602333545685},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3211287260055542},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.31625938415527344}],"concepts":[{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.7845065593719482},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.672587513923645},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.6313596963882446},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6296778917312622},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.580863356590271},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.579688549041748},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.5221312642097473},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5130788087844849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5039929747581482},{"id":"https://openalex.org/C126691448","wikidata":"https://www.wikidata.org/wiki/Q2028919","display_name":"Magnitude (astronomy)","level":2,"score":0.4579635262489319},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.448317289352417},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.4408622980117798},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.43580538034439087},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4352065920829773},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.41550254821777344},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4095602333545685},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3211287260055542},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.31625938415527344},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:ojs.aaai.org:article/4048","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1528676759","https://openalex.org/W1542941925","https://openalex.org/W1726776292","https://openalex.org/W1982039177","https://openalex.org/W2102509082","https://openalex.org/W2103315867","https://openalex.org/W2106975967","https://openalex.org/W2114793692","https://openalex.org/W2121863487","https://openalex.org/W2126776273","https://openalex.org/W2144274908","https://openalex.org/W2145901173","https://openalex.org/W2168356773","https://openalex.org/W2395326189","https://openalex.org/W2406828677","https://openalex.org/W2562174057","https://openalex.org/W2574978968","https://openalex.org/W2736601468","https://openalex.org/W2762117857","https://openalex.org/W2765775789","https://openalex.org/W2773381986","https://openalex.org/W2786303200","https://openalex.org/W2786887383","https://openalex.org/W2809013025","https://openalex.org/W2896791808","https://openalex.org/W2951301202","https://openalex.org/W2964043796","https://openalex.org/W2964319760","https://openalex.org/W4230563027","https://openalex.org/W4285364563","https://openalex.org/W4295150809","https://openalex.org/W4297789683","https://openalex.org/W4297810554"],"related_works":["https://openalex.org/W1983202944","https://openalex.org/W2802467175","https://openalex.org/W2022564137","https://openalex.org/W2132624896","https://openalex.org/W2035984254","https://openalex.org/W3046849046","https://openalex.org/W4252044174","https://openalex.org/W2118206667","https://openalex.org/W4291127980","https://openalex.org/W363903320"],"abstract_inverted_index":{"Learning":[0],"strategies":[1],"for":[2,17,160],"imperfect":[3],"information":[4],"games":[5],"from":[6,90,113],"samples":[7],"of":[8,52,67,100,126,143,154,176],"interaction":[9],"is":[10],"a":[11,41,65,121],"challenging":[12],"problem.":[13],"A":[14],"common":[15],"method":[16],"this":[18,37,55],"setting,":[19],"Monte":[20],"Carlo":[21],"Counterfactual":[22],"Regret":[23],"Minimization":[24],"(MCCFR),":[25],"can":[26,130],"have":[27],"slow":[28],"long-term":[29],"convergence":[30],"rates":[31],"due":[32],"to":[33,48,74,87,133,165,173],"high":[34],"variance.":[35],"In":[36],"paper,":[38],"we":[39,117],"introduce":[40],"variance":[42,125,149,158],"reduction":[43],"technique":[44],"(VR-MCCFR)":[45],"that":[46,119,138],"applies":[47],"any":[49],"sampling":[50],"variant":[51],"MCCFR.":[53],"Using":[54],"technique,":[56],"periteration":[57],"estimated":[58],"values":[59,69],"and":[60,70],"updates":[61],"are":[62],"reformulated":[63],"as":[64],"function":[66],"sampled":[68,104],"state-action":[71],"baselines,":[72],"similar":[73],"their":[75],"use":[76],"in":[77],"policy":[78],"gradient":[79],"reinforcement":[80],"learning.":[81],"The":[82,156],"new":[83],"formulation":[84],"allows":[85,159],"estimates":[86,92,107,129],"be":[88,131,166],"bootstrapped":[89],"other":[91,114],"within":[93],"the":[94,98,103,106,124,127,147,161,171],"same":[95],"episode,":[96],"propagating":[97],"benefits":[99],"baselines":[101],"along":[102],"trajectory;":[105],"remain":[108],"unbiased":[109],"even":[110],"when":[111],"bootstrapping":[112],"estimates.":[115],"Finally,":[116],"show":[118],"given":[120],"perfect":[122],"baseline,":[123],"value":[128],"reduced":[132],"zero.":[134],"Experimental":[135],"evaluation":[136],"shows":[137],"VR-MCCFR":[139],"brings":[140],"an":[141],"order":[142],"magnitude":[144],"speedup,":[145],"while":[146],"empirical":[148],"decreases":[150],"by":[151],"three":[152],"orders":[153,175],"magnitude.":[155,177],"decreased":[157],"first":[162],"time":[163],"CFR+":[164],"used":[167],"with":[168],"sampling,":[169],"increasing":[170],"speedup":[172],"two":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}