{"id":"https://openalex.org/W4385767510","doi":"https://doi.org/10.24963/ijcai.2023/16","title":"Beyond Strict Competition: Approximate Convergence of Multi-agent Q-Learning Dynamics","display_name":"Beyond Strict Competition: Approximate Convergence of Multi-agent Q-Learning Dynamics","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767510","doi":"https://doi.org/10.24963/ijcai.2023/16"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/16","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/16","pdf_url":"https://www.ijcai.org/proceedings/2023/0016.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0016.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050036888","display_name":"Aamal Hussain","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Aamal Hussain","raw_affiliation_strings":["Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055883955","display_name":"Francesco Belardinelli","orcid":"https://orcid.org/0000-0002-7768-1794"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Francesco Belardinelli","raw_affiliation_strings":["Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079969658","display_name":"Georgios Piliouras","orcid":"https://orcid.org/0000-0002-6236-3566"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Georgios Piliouras","raw_affiliation_strings":["Singapore University of Technology and Design"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050036888"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09369986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"135","last_page":"143"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9976000189781189,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9921000003814697,"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/zero-sum-game","display_name":"Zero-sum game","score":0.7226227521896362},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.641568660736084},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5987732410430908},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5837280750274658},{"id":"https://openalex.org/keywords/neighbourhood","display_name":"Neighbourhood (mathematics)","score":0.5585520267486572},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5101445317268372},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.49043747782707214},{"id":"https://openalex.org/keywords/repeated-game","display_name":"Repeated game","score":0.48245078325271606},{"id":"https://openalex.org/keywords/fictitious-play","display_name":"Fictitious play","score":0.46481212973594666},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.45392367243766785},{"id":"https://openalex.org/keywords/potential-game","display_name":"Potential game","score":0.4498150646686554},{"id":"https://openalex.org/keywords/sequential-game","display_name":"Sequential game","score":0.44292381405830383},{"id":"https://openalex.org/keywords/extensive-form-game","display_name":"Extensive-form game","score":0.4355798363685608},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.4348655343055725},{"id":"https://openalex.org/keywords/equilibrium-point","display_name":"Equilibrium point","score":0.42141997814178467},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3576102554798126},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3415510058403015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3124937415122986},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.10264185070991516}],"concepts":[{"id":"https://openalex.org/C136356330","wikidata":"https://www.wikidata.org/wiki/Q156612","display_name":"Zero-sum game","level":3,"score":0.7226227521896362},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.641568660736084},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5987732410430908},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5837280750274658},{"id":"https://openalex.org/C161677786","wikidata":"https://www.wikidata.org/wiki/Q2478475","display_name":"Neighbourhood (mathematics)","level":2,"score":0.5585520267486572},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5101445317268372},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.49043747782707214},{"id":"https://openalex.org/C202556891","wikidata":"https://www.wikidata.org/wiki/Q1584646","display_name":"Repeated game","level":3,"score":0.48245078325271606},{"id":"https://openalex.org/C145071142","wikidata":"https://www.wikidata.org/wiki/Q1411116","display_name":"Fictitious play","level":3,"score":0.46481212973594666},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.45392367243766785},{"id":"https://openalex.org/C2778079155","wikidata":"https://www.wikidata.org/wiki/Q288500","display_name":"Potential game","level":3,"score":0.4498150646686554},{"id":"https://openalex.org/C73795354","wikidata":"https://www.wikidata.org/wiki/Q287618","display_name":"Sequential game","level":3,"score":0.44292381405830383},{"id":"https://openalex.org/C146930158","wikidata":"https://www.wikidata.org/wiki/Q656416","display_name":"Extensive-form game","level":4,"score":0.4355798363685608},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.4348655343055725},{"id":"https://openalex.org/C94766913","wikidata":"https://www.wikidata.org/wiki/Q1530271","display_name":"Equilibrium point","level":3,"score":0.42141997814178467},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3576102554798126},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3415510058403015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3124937415122986},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.10264185070991516},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C78045399","wikidata":"https://www.wikidata.org/wiki/Q11214","display_name":"Differential equation","level":2,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/16","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/16","pdf_url":"https://www.ijcai.org/proceedings/2023/0016.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/16","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/16","pdf_url":"https://www.ijcai.org/proceedings/2023/0016.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1575777884","display_name":null,"funder_award_id":"NRF-NRFF2018-07","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G3063805291","display_name":null,"funder_award_id":"NRF2019-NRF-ANR095","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G3447883985","display_name":null,"funder_award_id":"NRF2019-NRF-ANR095 ALIAS grant","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G3917087662","display_name":null,"funder_award_id":"AISG2-RP-2020-016","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G4161133441","display_name":null,"funder_award_id":"AISG Award No: AISG2-RP-2020-016","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G4269887845","display_name":null,"funder_award_id":"EP/S023356/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"},{"id":"https://openalex.org/G4441651082","display_name":null,"funder_award_id":"NRF-NRFF2018-07","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G563338929","display_name":null,"funder_award_id":"NRF 2018 Fellowship NRF-NRFF2018-07","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G6960108870","display_name":null,"funder_award_id":"A20H6b0151","funder_id":"https://openalex.org/F4320320696","funder_display_name":"Agency for Science, Technology and Research"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767510.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W568318363","https://openalex.org/W2020341805","https://openalex.org/W2031098375","https://openalex.org/W2060284899","https://openalex.org/W2067393629","https://openalex.org/W2108212877","https://openalex.org/W2128797809","https://openalex.org/W2156006942","https://openalex.org/W2170109092","https://openalex.org/W2264897026","https://openalex.org/W2288719682","https://openalex.org/W2508573783","https://openalex.org/W2563524224","https://openalex.org/W2777662428","https://openalex.org/W2944311505","https://openalex.org/W2949531204","https://openalex.org/W3046546065","https://openalex.org/W3092962099","https://openalex.org/W3113152939","https://openalex.org/W3131743709","https://openalex.org/W3144118612","https://openalex.org/W3175070592","https://openalex.org/W3178113021","https://openalex.org/W3197270551","https://openalex.org/W4211108990","https://openalex.org/W4226217272","https://openalex.org/W4242216908","https://openalex.org/W4287113916","https://openalex.org/W4287127022","https://openalex.org/W4298859366"],"related_works":["https://openalex.org/W4287266326","https://openalex.org/W3137345903","https://openalex.org/W2949401733","https://openalex.org/W4248264387","https://openalex.org/W2736271402","https://openalex.org/W1988057242","https://openalex.org/W2069444266","https://openalex.org/W2910530315","https://openalex.org/W1967575524","https://openalex.org/W3126427555"],"abstract_inverted_index":{"The":[0,112],"behaviour":[1,26],"of":[2,15,27,63,114,132,170],"multi-agent":[3],"learning":[4,28,33,68],"in":[5,91,165],"competitive":[6,47],"settings":[7],"is":[8,24,117],"often":[9,36],"considered":[10],"under":[11,20],"the":[12,25,52,72,84,115,120,123,129,133,149,172],"restrictive":[13],"assumption":[14],"a":[16,60,65,106,109,141],"zero-sum":[17,53,98,124,152],"game.":[18],"Only":[19],"this":[21,89],"strict":[22],"requirement":[23],"well":[29,127],"understood;":[30],"beyond":[31],"this,":[32,57],"dynamics":[34,69,173],"can":[35,154],"display":[37],"non-convergent":[38],"behaviours":[39],"which":[40,70,93],"prevent":[41],"fixed-point":[42],"analysis.":[43],"Nonetheless,":[44],"many":[45],"relevant":[46],"games":[48,92,99],"do":[49],"not":[50],"satisfy":[51],"assumption.":[54],"Motivated":[55],"by":[56,119,139],"we":[58],"study":[59],"smooth":[61],"variant":[62],"Q-Learning,":[64],"popular":[66],"reinforcement":[67],"balances":[71],"agents'":[73],"tendency":[74],"to":[75,82,96,105,122],"maximise":[76],"their":[77,80],"payoffs":[78],"with":[79],"propensity":[81],"explore":[83],"state":[85],"space.":[86],"We":[87,135],"examine":[88],"dynamic":[90],"are":[94,162],"`close'":[95],"network":[97,147,151],"and":[100],"find":[101],"that":[102],"Q-Learning":[103],"converges":[104],"neighbourhood":[107,116],"around":[108],"unique":[110],"equilibrium.":[111],"size":[113],"determined":[118],"`distance'":[121],"game,":[125,148],"as":[126,128],"exploration":[130],"rates":[131],"agents.":[134],"complement":[136],"these":[137],"results":[138],"providing":[140],"method":[142],"whereby,":[143],"given":[144],"an":[145,176],"arbitrary":[146],"`nearest'":[150],"game":[153,167],"be":[155],"found":[156],"efficiently.":[157],"Importantly,":[158],"our":[159],"theoretical":[160],"guarantees":[161],"widely":[163],"applicable":[164],"different":[166],"settings,":[168],"regardless":[169],"whether":[171],"ultimately":[174],"reach":[175],"equilibrium,":[177],"or":[178],"remain":[179],"non":[180],"convergent.":[181]},"counts_by_year":[],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2025-10-10T00:00:00"}