{"id":"https://openalex.org/W4386120402","doi":"https://doi.org/10.1137/22m1515112","title":"Satisficing Paths and Independent Multiagent Reinforcement Learning in Stochastic Games","display_name":"Satisficing Paths and Independent Multiagent Reinforcement Learning in Stochastic Games","publication_year":2023,"publication_date":"2023-08-24","ids":{"openalex":"https://openalex.org/W4386120402","doi":"https://doi.org/10.1137/22m1515112"},"language":"en","primary_location":{"id":"doi:10.1137/22m1515112","is_oa":true,"landing_page_url":"https://doi.org/10.1137/22m1515112","pdf_url":null,"source":{"id":"https://openalex.org/S4210229561","display_name":"SIAM Journal on Mathematics of Data Science","issn_l":"2577-0187","issn":["2577-0187"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Mathematics of Data Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1137/22m1515112","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017866507","display_name":"Bora Yongacoglu","orcid":null},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Bora Yongacoglu","raw_affiliation_strings":["Department of Mathematics and Statistics, Queen\u2019s University, Kingston, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Statistics, Queen\u2019s University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072860374","display_name":"G\u00fcrdal Arslan","orcid":"https://orcid.org/0000-0002-8295-1509"},"institutions":[{"id":"https://openalex.org/I117965899","display_name":"University of Hawai\u02bbi at M\u0101noa","ror":"https://ror.org/01wspgy28","country_code":"US","type":"education","lineage":["https://openalex.org/I117965899"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G\u00fcrdal Arslan","raw_affiliation_strings":["Department of Electrical Engineering, University of Hawaii at Manoa, Honolulu, HI 96822 USA"],"raw_orcid":"https://orcid.org/0000-0002-8295-1509","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Hawaii at Manoa, Honolulu, HI 96822 USA","institution_ids":["https://openalex.org/I117965899"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005401257","display_name":"Serdar Y\u00fcksel","orcid":"https://orcid.org/0000-0001-6099-5001"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Serdar Y\u00fcksel","raw_affiliation_strings":["Department of Mathematics and Statistics, Queen\u2019s University, Kingston, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Statistics, Queen\u2019s University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7737,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.92257705,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"5","issue":"3","first_page":"745","last_page":"773"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9973999857902527,"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/T11182","display_name":"Auction Theory and Applications","score":0.9957000017166138,"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/satisficing","display_name":"Satisficing","score":0.9928493499755859},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6994453072547913},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.588842511177063},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.5641268491744995},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5203613638877869},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4275052547454834},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.42583024501800537},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3035023510456085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29899823665618896},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.29211074113845825}],"concepts":[{"id":"https://openalex.org/C94822996","wikidata":"https://www.wikidata.org/wiki/Q1777902","display_name":"Satisficing","level":2,"score":0.9928493499755859},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6994453072547913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.588842511177063},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.5641268491744995},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5203613638877869},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4275052547454834},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.42583024501800537},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3035023510456085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29899823665618896},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.29211074113845825},{"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:10.1137/22m1515112","is_oa":true,"landing_page_url":"https://doi.org/10.1137/22m1515112","pdf_url":null,"source":{"id":"https://openalex.org/S4210229561","display_name":"SIAM Journal on Mathematics of Data Science","issn_l":"2577-0187","issn":["2577-0187"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Mathematics of Data Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1137/22m1515112","is_oa":true,"landing_page_url":"https://doi.org/10.1137/22m1515112","pdf_url":null,"source":{"id":"https://openalex.org/S4210229561","display_name":"SIAM Journal on Mathematics of Data Science","issn_l":"2577-0187","issn":["2577-0187"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Mathematics of Data Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1967250398","https://openalex.org/W1983321045","https://openalex.org/W1987420866","https://openalex.org/W1989388297","https://openalex.org/W1990873282","https://openalex.org/W1995158831","https://openalex.org/W1996013982","https://openalex.org/W2011696174","https://openalex.org/W2024612830","https://openalex.org/W2038686546","https://openalex.org/W2060247189","https://openalex.org/W2075099603","https://openalex.org/W2096145798","https://openalex.org/W2116395276","https://openalex.org/W2120327309","https://openalex.org/W2121863487","https://openalex.org/W2124666512","https://openalex.org/W2135608404","https://openalex.org/W2145339207","https://openalex.org/W2149254401","https://openalex.org/W2176451521","https://openalex.org/W2257979135","https://openalex.org/W2570514057","https://openalex.org/W2618428225","https://openalex.org/W2736601468","https://openalex.org/W2766447205","https://openalex.org/W2773381986","https://openalex.org/W2793538878","https://openalex.org/W2794998369","https://openalex.org/W2962990479","https://openalex.org/W2991046523","https://openalex.org/W3024488175","https://openalex.org/W3043098219","https://openalex.org/W3092557414","https://openalex.org/W3099277320","https://openalex.org/W3102463202","https://openalex.org/W3122272342","https://openalex.org/W3123073578","https://openalex.org/W3133570404","https://openalex.org/W3209754935","https://openalex.org/W4211095127","https://openalex.org/W4294576339"],"related_works":["https://openalex.org/W3118038935","https://openalex.org/W2486197377","https://openalex.org/W2672066981","https://openalex.org/W2025499279","https://openalex.org/W96070519","https://openalex.org/W2079941411","https://openalex.org/W3147748563","https://openalex.org/W2898650285","https://openalex.org/W4252791283","https://openalex.org/W2030091197"],"abstract_inverted_index":{"In":[0],"multiagent":[1],"reinforcement":[2],"learning,":[3],"independent":[4,31,49,140],"learners":[5,32,50],"are":[6,89],"those":[7],"that":[8,33,67],"do":[9],"not":[10,72],"observe":[11],"the":[12,18,22,41,69,81,84,117,166],"actions":[13],"of":[14,24,43,83,94,119,152,170],"other":[15],"agents":[16],"in":[17,54,124],"system.":[19],"Due":[20],"to":[21,29,36,47,51,71,80,91,107,154],"decentralization":[23],"information,":[25],"it":[26,77],"is":[27,64,78,160],"challenging":[28],"design":[30],"drive":[34],"play":[35],"equilibrium.":[37],"This":[38,158],"paper":[39],"investigates":[40],"feasibility":[42],"using":[44,162],"satisficing":[45],"dynamics":[46],"guide":[48],"approximate":[52],"equilibrium":[53],"stochastic":[55,131],"games.":[56],"For":[57],",":[58],"an":[59,139],"-satisficing":[60,87,103,120,171],"policy":[61,75,104],"update":[62,105],"rule":[63,66,106],"any":[65],"instructs":[68],"agent":[70,100],"change":[73],"its":[74,109],"when":[76,98],"-best-responding":[79],"policies":[82,96],"remaining":[85],"players;":[86],"paths":[88,121],"defined":[90],"be":[92],"sequences":[93],"joint":[95],"obtained":[97],"each":[99],"uses":[101],"some":[102],"select":[108],"next":[110],"policy.":[111],"We":[112,136],"establish":[113],"structural":[114],"results":[115],"on":[116],"existence":[118],"into":[122],"-equilibrium":[123,155],"both":[125],"symmetric":[126,145],"-player":[127,144],"games":[128,132,146],"and":[129,147],"general":[130],"with":[133],"two":[134],"players.":[135],"then":[137],"present":[138],"learning":[141],"algorithm":[142],"for":[143],"give":[148],"high":[149],"probability":[150],"guarantees":[151],"convergence":[153],"under":[156],"self-play.":[157],"guarantee":[159],"made":[161],"symmetry":[163],"alone,":[164],"leveraging":[165],"previously":[167],"unexploited":[168],"structure":[169],"paths.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2023-08-25T00:00:00"}