{"id":"https://openalex.org/W7123350440","doi":"https://doi.org/10.1109/cdc57313.2025.11312619","title":"Convergent Q-Learning for Infinite-Horizon General-Sum Markov Games through Behavioral Economics","display_name":"Convergent Q-Learning for Infinite-Horizon General-Sum Markov Games through Behavioral Economics","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123350440","doi":"https://doi.org/10.1109/cdc57313.2025.11312619"},"language":null,"primary_location":{"id":"doi:10.1109/cdc57313.2025.11312619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5048268146","display_name":"Yizhou Zhang","orcid":"https://orcid.org/0000-0002-5677-4748"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yizhou Zhang","raw_affiliation_strings":["California Institute of Technology,Department of Computing and Mathematical Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California Institute of Technology,Department of Computing and Mathematical Sciences","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5093925471","display_name":"Eric Mazumdar","orcid":null},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Mazumdar","raw_affiliation_strings":["California Institute of Technology,Department of Computing and Mathematical Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California Institute of Technology,Department of Computing and Mathematical Sciences","institution_ids":["https://openalex.org/I122411786"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I122411786"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62251498,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5899","last_page":"5904"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5580000281333923,"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":0.5580000281333923,"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":0.32600000500679016,"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/T11413","display_name":"Risk and Portfolio Optimization","score":0.009999999776482582,"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/bounded-rationality","display_name":"Bounded rationality","score":0.5947999954223633},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5347999930381775},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.4948999881744385},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4896000027656555},{"id":"https://openalex.org/keywords/stochastic-game","display_name":"Stochastic game","score":0.4864000082015991},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.4700999855995178},{"id":"https://openalex.org/keywords/uniqueness","display_name":"Uniqueness","score":0.44929999113082886},{"id":"https://openalex.org/keywords/lipschitz-continuity","display_name":"Lipschitz continuity","score":0.42500001192092896},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4097000062465668}],"concepts":[{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.598800003528595},{"id":"https://openalex.org/C58694771","wikidata":"https://www.wikidata.org/wiki/Q814385","display_name":"Bounded rationality","level":2,"score":0.5947999954223633},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5347999930381775},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.4948999881744385},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4896000027656555},{"id":"https://openalex.org/C22171661","wikidata":"https://www.wikidata.org/wiki/Q1074380","display_name":"Stochastic game","level":2,"score":0.4864000082015991},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.47620001435279846},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.4700999855995178},{"id":"https://openalex.org/C2777021972","wikidata":"https://www.wikidata.org/wiki/Q22976830","display_name":"Uniqueness","level":2,"score":0.44929999113082886},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4431999921798706},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.42500001192092896},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4097000062465668},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.3650999963283539},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3564999997615814},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.3077000081539154},{"id":"https://openalex.org/C202556891","wikidata":"https://www.wikidata.org/wiki/Q1584646","display_name":"Repeated game","level":3,"score":0.30649998784065247},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C189973286","wikidata":"https://www.wikidata.org/wiki/Q176695","display_name":"Markov property","level":4,"score":0.2913999855518341},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C11343654","wikidata":"https://www.wikidata.org/wiki/Q780008","display_name":"Solution concept","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C201717286","wikidata":"https://www.wikidata.org/wiki/Q938185","display_name":"Rationality","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.26159998774528503},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.25369998812675476},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7467854022979736,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Risk-aversion":[0],"and":[1,84,94,118,132,143,164,177],"bounded":[2,144,175],"rationality":[3,145],"are":[4],"two":[5],"key":[6],"characteristics":[7],"of":[8,28,44,66,82,121,140],"human":[9,29],"decision-making.":[10],"Risk-averse":[11],"quantal-response":[12,161],"equilibrium":[13],"(RQE)":[14],"is":[15],"a":[16,24,38,42,105,182],"solution":[17],"concept":[18],"that":[19,146],"incorporates":[20],"these":[21],"features,":[22],"providing":[23],"more":[25],"realistic":[26],"depiction":[27],"decision":[30],"making":[31],"in":[32,50,57,88],"various":[33],"strategic":[34],"environments":[35],"compared":[36],"to":[37,52,110,125],"Nash":[39],"equilibrium.":[40],"Furthermore":[41],"class":[43],"RQE":[45,83,122],"has":[46],"recently":[47],"been":[48],"shown":[49],"[1]":[51],"be":[53],"universally":[54],"computationally":[55],"tractable":[56],"all":[58,190],"finite-horizon":[59],"Markov":[60,97,155,193],"games,":[61],"allowing":[62,108],"for":[63,189],"the":[64,80,137,159,172],"development":[65],"multi-agent":[67],"reinforcement":[68],"learning":[69],"algorithms":[70],"with":[71,123,186],"convergence":[72,187],"guarantees.":[73],"In":[74],"this":[75],"paper,":[76],"we":[77,103],"expand":[78],"upon":[79],"study":[81],"analyze":[85],"their":[86],"computation":[87],"both":[89],"two-player":[90],"normal":[91,100],"form":[92,101],"games":[93,102],"discounted":[95,153],"infinite-horizon":[96,154,191],"games.":[98,156,194],"For":[99],"adopt":[104],"monotonicity-based":[106],"approach":[107],"us":[109],"generalize":[111],"previous":[112],"results.":[113],"We":[114,149,157],"first":[115],"show":[116],"uniqueness":[117],"Lipschitz":[119],"continuity":[120],"respect":[124],"player\u2019s":[126],"payoff":[127],"matrices":[128],"under":[129,168],"monotonicity":[130],"assumptions,":[131],"then":[133,150],"provide":[134],"conditions":[135,170],"on":[136,152,171],"players\u2019":[138,173],"degrees":[139],"risk":[141],"aversion":[142],"ensure":[147],"monotonicity.":[148],"focus":[151],"define":[158],"risk-averse":[160],"Bellman":[162],"operator":[163],"prove":[165],"its":[166],"contraction":[167],"further":[169],"risk-aversion,":[174],"rationality,":[176],"temporal":[178],"discounting.":[179],"This":[180],"yields":[181],"Q-learning":[183],"based":[184],"algorithm":[185],"guarantees":[188],"general-sum":[192]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-01-14T00:00:00"}