{"id":"https://openalex.org/W4391022051","doi":"https://doi.org/10.1109/cdc49753.2023.10383668","title":"Episodic Logit-Q Dynamics for Efficient Learning in Stochastic Teams","display_name":"Episodic Logit-Q Dynamics for Efficient Learning in Stochastic Teams","publication_year":2023,"publication_date":"2023-12-13","ids":{"openalex":"https://openalex.org/W4391022051","doi":"https://doi.org/10.1109/cdc49753.2023.10383668"},"language":"en","primary_location":{"id":"doi:10.1109/cdc49753.2023.10383668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10383668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-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/A5033592879","display_name":"Onur Unlu","orcid":"https://orcid.org/0000-0002-7410-7981"},"institutions":[{"id":"https://openalex.org/I168864056","display_name":"Bilkent University","ror":"https://ror.org/02vh8a032","country_code":"TR","type":"education","lineage":["https://openalex.org/I168864056"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Onur Unlu","raw_affiliation_strings":["Bilkent University,Department of Electrical & Electronics Engineering,Ankara,Turkey,06800"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bilkent University,Department of Electrical & Electronics Engineering,Ankara,Turkey,06800","institution_ids":["https://openalex.org/I168864056"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081851582","display_name":"Muhammed O. Sayin","orcid":"https://orcid.org/0000-0001-5779-3986"},"institutions":[{"id":"https://openalex.org/I168864056","display_name":"Bilkent University","ror":"https://ror.org/02vh8a032","country_code":"TR","type":"education","lineage":["https://openalex.org/I168864056"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Muhammed O. Sayin","raw_affiliation_strings":["Bilkent University,Department of Electrical & Electronics Engineering,Ankara,Turkey,06800"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bilkent University,Department of Electrical & Electronics Engineering,Ankara,Turkey,06800","institution_ids":["https://openalex.org/I168864056"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I168864056"],"apc_list":null,"apc_paid":null,"fwci":0.6452,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76270359,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1985","last_page":"1990"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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":0.998199999332428,"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/T11031","display_name":"Game Theory and Applications","score":0.9979000091552734,"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/convergence","display_name":"Convergence (economics)","score":0.719871997833252},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6882312893867493},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5107064247131348},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4920148551464081},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.4702887535095215},{"id":"https://openalex.org/keywords/logit","display_name":"Logit","score":0.45543891191482544},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4415791928768158},{"id":"https://openalex.org/keywords/stochastic-process","display_name":"Stochastic process","score":0.4214855432510376},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.382440984249115},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2189790904521942},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11448943614959717},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.10226759314537048}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.719871997833252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6882312893867493},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5107064247131348},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4920148551464081},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.4702887535095215},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.45543891191482544},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4415791928768158},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.4214855432510376},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.382440984249115},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2189790904521942},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11448943614959717},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.10226759314537048},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc49753.2023.10383668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10383668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1907356258","https://openalex.org/W1972645710","https://openalex.org/W1973039793","https://openalex.org/W2001007182","https://openalex.org/W2024612830","https://openalex.org/W2032200533","https://openalex.org/W2145067550","https://openalex.org/W2885549115","https://openalex.org/W2991046523","https://openalex.org/W3043098219","https://openalex.org/W3092557414","https://openalex.org/W3209754935","https://openalex.org/W4254547512","https://openalex.org/W4285092776","https://openalex.org/W4389775604","https://openalex.org/W4391022051","https://openalex.org/W6681342480","https://openalex.org/W6804306786"],"related_works":["https://openalex.org/W2803931294","https://openalex.org/W2282604764","https://openalex.org/W2500870930","https://openalex.org/W2218535193","https://openalex.org/W4389370903","https://openalex.org/W2468739564","https://openalex.org/W1554758635","https://openalex.org/W4302558842","https://openalex.org/W2171981925","https://openalex.org/W2955320052"],"abstract_inverted_index":{"We":[0,131],"present":[1],"new":[2],"learning":[3,8],"dynamics":[4,22,53],"combining":[5],"(independent)":[6],"log-linear":[7,121],"and":[9,90,103],"value":[10],"iteration":[11],"for":[12],"stochastic":[13,36],"games":[14],"within":[15],"the":[16,26,39,58,85,97,104,107,116,129,133,136,141,149,152],"auxiliary":[17],"stage":[18],"game":[19],"framework.":[20],"The":[21,52,93,120],"presented":[23],"provably":[24],"attain":[25],"efficient":[27],"equilibrium":[28,102],"(also":[29],"known":[30],"as":[31],"optimal":[32],"equilibrium)":[33],"in":[34,57,84,127,139],"identical-interest":[35],"games,":[37],"beyond":[38],"recent":[40],"concentration":[41],"of":[42,81,88,106,118,151],"progress":[43],"on":[44],"provable":[45],"convergence":[46,98],"to":[47,69,99,115],"some":[48],"(possibly":[49],"inefficient)":[50],"equilibrium.":[51,76],"are":[54,96],"also":[55],"independent":[56],"sense":[59],"that":[60],"agents":[61,142],"take":[62],"actions":[63],"consistent":[64],"with":[65],"their":[66,144],"local":[67],"viewpoint":[68,113],"a":[70,110],"reasonable":[71],"extent":[72],"rather":[73],"than":[74],"seeking":[75],"These":[77],"aspects":[78],"can":[79],"be":[80],"practical":[82],"interest":[83],"control":[86],"applications":[87],"intelligent":[89],"autonomous":[91],"systems.":[92],"key":[94],"challenges":[95],"an":[100,124],"inefficient":[101],"non-stationarity":[105],"environment":[108],"from":[109],"single":[111],"agent's":[112],"due":[114],"adaptation":[117],"others.":[119],"update":[122,143],"plays":[123],"important":[125],"role":[126],"addressing":[128],"former.":[130],"address":[132],"latter":[134],"through":[135],"play-in-episodes":[137],"scheme":[138],"which":[140],"Q-function":[145],"estimates":[146],"only":[147],"at":[148],"end":[150],"episodes.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}