{"id":"https://openalex.org/W2083884861","doi":"https://doi.org/10.1109/cca.2013.6662854","title":"Stability of the Nash equilibrium under gradient ascent learning algorithms in two-agent two-action games","display_name":"Stability of the Nash equilibrium under gradient ascent learning algorithms in two-agent two-action games","publication_year":2013,"publication_date":"2013-08-01","ids":{"openalex":"https://openalex.org/W2083884861","doi":"https://doi.org/10.1109/cca.2013.6662854","mag":"2083884861"},"language":"en","primary_location":{"id":"doi:10.1109/cca.2013.6662854","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cca.2013.6662854","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Control Applications (CCA)","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/A5042509798","display_name":"Amit Bhaya","orcid":"https://orcid.org/0000-0002-3144-1242"},"institutions":[{"id":"https://openalex.org/I122140584","display_name":"Universidade Federal do Rio de Janeiro","ror":"https://ror.org/03490as77","country_code":"BR","type":"education","lineage":["https://openalex.org/I122140584"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Amit Bhaya","raw_affiliation_strings":["Department of Electrical Engineering, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil","Dept. of Electr. Eng., Fed. Univ. of Rio de Janeiro, Rio de Janeiro, Brazil"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil","institution_ids":["https://openalex.org/I122140584"]},{"raw_affiliation_string":"Dept. of Electr. Eng., Fed. Univ. of Rio de Janeiro, Rio de Janeiro, Brazil","institution_ids":["https://openalex.org/I122140584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058862335","display_name":"Rodrigo Brandolt Sodre de Macedo","orcid":null},"institutions":[{"id":"https://openalex.org/I122140584","display_name":"Universidade Federal do Rio de Janeiro","ror":"https://ror.org/03490as77","country_code":"BR","type":"education","lineage":["https://openalex.org/I122140584"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Rodrigo Brandolt Sodre de Macedo","raw_affiliation_strings":["Department of Electrical Engineering, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil","Dept. of Electr. Eng., Fed. Univ. of Rio de Janeiro, Rio de Janeiro, Brazil"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil","institution_ids":["https://openalex.org/I122140584"]},{"raw_affiliation_string":"Dept. of Electr. Eng., Fed. Univ. of Rio de Janeiro, Rio de Janeiro, Brazil","institution_ids":["https://openalex.org/I122140584"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080947010","display_name":"Lucas Shiguemitsu Shigueoka","orcid":null},"institutions":[{"id":"https://openalex.org/I122140584","display_name":"Universidade Federal do Rio de Janeiro","ror":"https://ror.org/03490as77","country_code":"BR","type":"education","lineage":["https://openalex.org/I122140584"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Lucas Shiguemitsu Shigueoka","raw_affiliation_strings":["Department of Electrical Engineering, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil","Dept. of Electr. Eng., Fed. Univ. of Rio de Janeiro, Rio de Janeiro, Brazil"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil","institution_ids":["https://openalex.org/I122140584"]},{"raw_affiliation_string":"Dept. of Electr. Eng., Fed. Univ. of Rio de Janeiro, Rio de Janeiro, Brazil","institution_ids":["https://openalex.org/I122140584"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5042509798"],"corresponding_institution_ids":["https://openalex.org/I122140584"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1012182,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"20","issue":null,"first_page":"837","last_page":"842"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T11031","display_name":"Game Theory and Applications","score":0.9962000250816345,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/nash-equilibrium","display_name":"Nash equilibrium","score":0.8770469427108765},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6072720289230347},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6050946712493896},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5675480961799622},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.5667502284049988},{"id":"https://openalex.org/keywords/best-response","display_name":"Best response","score":0.5657917261123657},{"id":"https://openalex.org/keywords/epsilon-equilibrium","display_name":"Epsilon-equilibrium","score":0.48922061920166016},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.46336719393730164},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.46068528294563293},{"id":"https://openalex.org/keywords/equilibrium-selection","display_name":"Equilibrium selection","score":0.4505760967731476},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.4395427107810974},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4211941957473755},{"id":"https://openalex.org/keywords/solution-concept","display_name":"Solution concept","score":0.4163525700569153},{"id":"https://openalex.org/keywords/correlated-equilibrium","display_name":"Correlated equilibrium","score":0.416057825088501},{"id":"https://openalex.org/keywords/sequential-equilibrium","display_name":"Sequential equilibrium","score":0.41416677832603455},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3824641704559326},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37124574184417725},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.31663787364959717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29307857155799866},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19984319806098938},{"id":"https://openalex.org/keywords/repeated-game","display_name":"Repeated game","score":0.16475346684455872},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.08606156706809998},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.0691620409488678}],"concepts":[{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.8770469427108765},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6072720289230347},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6050946712493896},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5675480961799622},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.5667502284049988},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.5657917261123657},{"id":"https://openalex.org/C141824439","wikidata":"https://www.wikidata.org/wiki/Q307521","display_name":"Epsilon-equilibrium","level":4,"score":0.48922061920166016},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.46336719393730164},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.46068528294563293},{"id":"https://openalex.org/C164407509","wikidata":"https://www.wikidata.org/wiki/Q5384490","display_name":"Equilibrium selection","level":4,"score":0.4505760967731476},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.4395427107810974},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4211941957473755},{"id":"https://openalex.org/C11343654","wikidata":"https://www.wikidata.org/wiki/Q780008","display_name":"Solution concept","level":3,"score":0.4163525700569153},{"id":"https://openalex.org/C163630976","wikidata":"https://www.wikidata.org/wiki/Q964667","display_name":"Correlated equilibrium","level":5,"score":0.416057825088501},{"id":"https://openalex.org/C201364048","wikidata":"https://www.wikidata.org/wiki/Q2897085","display_name":"Sequential equilibrium","level":5,"score":0.41416677832603455},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3824641704559326},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37124574184417725},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.31663787364959717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29307857155799866},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19984319806098938},{"id":"https://openalex.org/C202556891","wikidata":"https://www.wikidata.org/wiki/Q1584646","display_name":"Repeated game","level":3,"score":0.16475346684455872},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.08606156706809998},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0691620409488678},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cca.2013.6662854","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cca.2013.6662854","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Control Applications (CCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5099999904632568,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1504193820","https://openalex.org/W1607392272","https://openalex.org/W1990042683","https://openalex.org/W1999403616","https://openalex.org/W2051838070","https://openalex.org/W2105643086","https://openalex.org/W2120327309","https://openalex.org/W2120846115","https://openalex.org/W2166565318","https://openalex.org/W2497819203","https://openalex.org/W2951054971","https://openalex.org/W3105048218","https://openalex.org/W4255047891","https://openalex.org/W4302379208","https://openalex.org/W6636288269","https://openalex.org/W6676014644"],"related_works":["https://openalex.org/W1553185561","https://openalex.org/W4221157020","https://openalex.org/W4299590005","https://openalex.org/W2953375265","https://openalex.org/W4302558842","https://openalex.org/W2025767136","https://openalex.org/W2097226409","https://openalex.org/W2408729172","https://openalex.org/W2952611531","https://openalex.org/W2097264194"],"abstract_inverted_index":{"This":[0],"paper":[1],"provides":[2],"a":[3,55,61,67,97,118,132,167],"unified":[4,62],"view":[5],"and":[6,34,36,42,59,90,101,152],"stability":[7,70,119],"analysis":[8,108],"of":[9,69,71,106,109,116,157,162,173],"reinforcement":[10],"learning":[11,28,79],"algorithms":[12,29],"for":[13,121],"general":[14],"sum":[15],"games":[16,138],"that":[17,125,144],"have":[18],"been":[19],"proposed":[20,30,39],"in":[21,135,139],"the":[22,25,37,51,72,76,103,110,126,141,158,171,174],"literature.":[23],"Specifically,":[24],"gradient":[26],"ascent":[27],"by":[31,40,88],"Singh,":[32],"Kearns":[33],"Mansour,":[35],"variant":[38],"Bowling":[41],"Veloso":[43],"are":[44],"shown":[45],"to":[46,48,50,130],"lead":[47],"convergence":[49],"Nash":[52,73,133,175],"equilibrium,":[53],"using":[54,96],"switching":[56],"control":[57],"viewpoint":[58],"providing":[60,117],"Lyapunov":[63],"function":[64,99],"analysis.":[65],"Furthermore,":[66],"proof":[68,120],"equilibrium":[74,112,134],"under":[75],"weighted":[77],"policy":[78],"(WPL)":[80],"algorithm,":[81],"which":[82,140],"was":[83],"proposed,":[84],"without":[85],"formal":[86],"proof,":[87],"Abdallah":[89],"Lesser,":[91],"is":[92,124,148],"also":[93],"arrived":[94],"at":[95],"Liapunov":[98],"approach":[100],"involves":[102],"novel":[104],"feature":[105],"an":[107,145],"virtual":[111],"points.":[113],"The":[114],"importance":[115],"WPL":[122],"dynamics":[123],"latter":[127],"allows":[128],"agents":[129],"reach":[131],"two-agent,":[136],"two-action":[137],"only":[142],"feedback":[143],"agent":[146,154],"needs":[147],"its":[149],"own":[150],"reward,":[151],"no":[153],"uses":[155],"knowledge":[156],"rewards":[159],"or":[160,165],"actions":[161],"other":[163],"agents,":[164],"any":[166],"priori":[168],"information":[169],"on":[170],"location":[172],"equilibrium.":[176]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}