{"id":"https://openalex.org/W4285605424","doi":"https://doi.org/10.24963/ijcai.2022/55","title":"Modelling the Dynamics of Multi-Agent Q-learning: The Stochastic Effects of Local Interaction and Incomplete Information","display_name":"Modelling the Dynamics of Multi-Agent Q-learning: The Stochastic Effects of Local Interaction and Incomplete Information","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285605424","doi":"https://doi.org/10.24963/ijcai.2022/55"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/55","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/55","pdf_url":"https://www.ijcai.org/proceedings/2022/0055.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0055.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110838463","display_name":"Chin-Wing Leung","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chin-wing Leung","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052387391","display_name":"Shuyue Hu","orcid":"https://orcid.org/0000-0002-1908-1344"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuyue Hu","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022683388","display_name":"Ho-fung Leung","orcid":"https://orcid.org/0000-0003-4914-2934"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ho-fung Leung","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"384","last_page":"390"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11764","display_name":"Evolution and Genetic Dynamics","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11764","display_name":"Evolution and Genetic Dynamics","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11270","display_name":"Complex Systems and Time Series Analysis","score":0.9767000079154968,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9763000011444092,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.7090079188346863},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6706137657165527},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5692269802093506},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.5596308708190918},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5460004210472107},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.4549311399459839},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.43889370560646057},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.4257742762565613},{"id":"https://openalex.org/keywords/stochastic-differential-equation","display_name":"Stochastic differential equation","score":0.41808658838272095},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4139779806137085},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4057202935218811},{"id":"https://openalex.org/keywords/statistical-physics","display_name":"Statistical physics","score":0.34916138648986816},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.34820085763931274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3469046354293823},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.24474498629570007},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22708916664123535},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.1732339859008789},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14800533652305603},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09438508749008179}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7090079188346863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6706137657165527},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5692269802093506},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.5596308708190918},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5460004210472107},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.4549311399459839},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.43889370560646057},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.4257742762565613},{"id":"https://openalex.org/C51955184","wikidata":"https://www.wikidata.org/wiki/Q1545585","display_name":"Stochastic differential equation","level":2,"score":0.41808658838272095},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4139779806137085},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4057202935218811},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.34916138648986816},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34820085763931274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3469046354293823},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.24474498629570007},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22708916664123535},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.1732339859008789},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14800533652305603},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09438508749008179},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2022/55","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/55","pdf_url":"https://www.ijcai.org/proceedings/2022/0055.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/55","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/55","pdf_url":"https://www.ijcai.org/proceedings/2022/0055.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285605424.pdf","grobid_xml":"https://content.openalex.org/works/W4285605424.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W92376239","https://openalex.org/W1192553058","https://openalex.org/W1595172192","https://openalex.org/W2031098375","https://openalex.org/W2037200286","https://openalex.org/W2156060009","https://openalex.org/W2172193467","https://openalex.org/W2214696221","https://openalex.org/W2571381988","https://openalex.org/W2594794854","https://openalex.org/W2740242815","https://openalex.org/W2903845856","https://openalex.org/W2921919225","https://openalex.org/W2971327495","https://openalex.org/W2997338169","https://openalex.org/W3132236529","https://openalex.org/W3195846754","https://openalex.org/W4233253704","https://openalex.org/W4287600873","https://openalex.org/W4287870504","https://openalex.org/W4297789683"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W3087814763","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W4376605461","https://openalex.org/W4400868993","https://openalex.org/W2361647908","https://openalex.org/W2952356279"],"abstract_inverted_index":{"The":[0],"theoretical":[1,42],"underpinnings":[2],"of":[3,60,75,82,96,101,114,127],"multiagent":[4],"reinforcement":[5],"learning":[6,21],"has":[7],"recently":[8],"attracted":[9],"much":[10],"attention.":[11],"In":[12,130],"this":[13,49],"work,":[14],"we":[15,70,91,132],"focus":[16],"on":[17,88],"the":[18,34,45,58,72,89,93,97,104,112,136,148],"generalized":[19],"social":[20],"(GSL)":[22],"protocol":[23,28],"---":[24],"an":[25,40],"agent":[26,78],"interaction":[27],"that":[29,52,66,134,155,160],"is":[30,145,156],"widely":[31],"adopted":[32],"in":[33,103],"literature,":[35],"and":[36,63,143,164],"aim":[37],"to":[38,56,152],"develop":[39],"accurate":[41],"model":[43,71,116],"for":[44],"Q-learning":[46],"dynamics":[47,74],"under":[48],"protocol.":[50],"Noting":[51],"previous":[53],"models":[54],"fail":[55],"characterize":[57],"effects":[59],"local":[61],"interactions":[62,137,163],"incomplete":[64],"information":[65,144],"arise":[67],"from":[68],"GSL,":[69],"Q-values":[73,102],"each":[76],"individual":[77],"as":[79,135],"a":[80,107,153],"system":[81],"stochastic":[83],"differential":[84],"equations":[85],"(SDE).":[86],"Based":[87],"SDE,":[90],"express":[92],"time":[94],"evolution":[95],"probability":[98],"density":[99],"function":[100],"population":[105,149],"with":[106,120,161],"Fokker-Planck":[108],"equation.":[109],"We":[110],"validate":[111],"correctness":[113],"our":[115],"through":[117],"extensive":[118],"comparisons":[119],"agent-based":[121],"simulation":[122],"results":[123],"across":[124],"different":[125,158],"types":[126],"symmetric":[128],"games.":[129],"addition,":[131],"show":[133],"between":[138],"agents":[139],"are":[140],"more":[141],"limited":[142],"less":[146],"complete,":[147],"can":[150],"converge":[151],"outcome":[154],"qualitatively":[157],"than":[159],"global":[162],"complete":[165],"information.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}