{"id":"https://openalex.org/W4414247892","doi":"https://doi.org/10.1145/3719545.3719553","title":"Variational Stochastic Games","display_name":"Variational Stochastic Games","publication_year":2024,"publication_date":"2024-12-18","ids":{"openalex":"https://openalex.org/W4414247892","doi":"https://doi.org/10.1145/3719545.3719553"},"language":"en","primary_location":{"id":"doi:10.1145/3719545.3719553","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3719545.3719553","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3719545.3719553","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Sixth International Conference on Distributed Artificial Intelligences","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3719545.3719553","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhiyu Zhao","orcid":"https://orcid.org/0009-0004-2201-0733"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"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/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiyu Zhao","raw_affiliation_strings":["The Institute of Automation of the Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of the Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-2201-0733","affiliations":[{"raw_affiliation_string":"The Institute of Automation of the Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210112150","https://openalex.org/I4210094879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106976846","display_name":"Haifeng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"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/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Zhang","raw_affiliation_strings":["The Institute of Automation of the Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of the Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-4502-1760","affiliations":[{"raw_affiliation_string":"The Institute of Automation of the Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210112150","https://openalex.org/I4210094879"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210100255","https://openalex.org/I4210112150"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35972829,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"46","last_page":"57"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.982200026512146,"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"}},"topics":[{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.982200026512146,"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/T12137","display_name":"Economic theories and models","score":0.9732999801635742,"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/T11031","display_name":"Game Theory and Applications","score":0.9697999954223633,"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/convergence","display_name":"Convergence (economics)","score":0.7146000266075134},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6445000171661377},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.6105999946594238},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5853999853134155},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5414000153541565},{"id":"https://openalex.org/keywords/cognitive-reframing","display_name":"Cognitive reframing","score":0.5198000073432922},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.49549999833106995},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.435699999332428},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.4350999891757965}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7146000266075134},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6445000171661377},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.6105999946594238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5975000262260437},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5853999853134155},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5414000153541565},{"id":"https://openalex.org/C187029079","wikidata":"https://www.wikidata.org/wiki/Q958679","display_name":"Cognitive reframing","level":2,"score":0.5198000073432922},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.49549999833106995},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.48399999737739563},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.435699999332428},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.4350999891757965},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.3853999972343445},{"id":"https://openalex.org/C167729594","wikidata":"https://www.wikidata.org/wiki/Q17736","display_name":"Axiom","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3140000104904175},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C205875254","wikidata":"https://www.wikidata.org/wiki/Q17156857","display_name":"Decentralised system","level":3,"score":0.30720001459121704},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29840001463890076},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2937999963760376},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.2791000008583069},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.27619999647140503},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.2734000086784363},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C141824439","wikidata":"https://www.wikidata.org/wiki/Q307521","display_name":"Epsilon-equilibrium","level":4,"score":0.25679999589920044},{"id":"https://openalex.org/C2780432614","wikidata":"https://www.wikidata.org/wiki/Q864213","display_name":"Conservative extension","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3719545.3719553","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3719545.3719553","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3719545.3719553","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Sixth International Conference on Distributed Artificial Intelligences","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3719545.3719553","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3719545.3719553","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3719545.3719553","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Sixth International Conference on Distributed Artificial Intelligences","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414247892.pdf","grobid_xml":"https://content.openalex.org/works/W4414247892.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2105934661","https://openalex.org/W2107464055","https://openalex.org/W2123157758","https://openalex.org/W2225156818","https://openalex.org/W2610740441","https://openalex.org/W2946045694","https://openalex.org/W2963390138","https://openalex.org/W2965922694","https://openalex.org/W3035478219","https://openalex.org/W4206742934","https://openalex.org/W4252284432","https://openalex.org/W4254547512"],"related_works":[],"abstract_inverted_index":{"The":[0],"Control":[1],"as":[2,17],"Inference":[3],"(CAI)":[4],"framework":[5,52,58],"has":[6],"successfully":[7],"transformed":[8],"single-agent":[9],"reinforcement":[10],"learning":[11],"(RL)":[12],"by":[13,63],"reframing":[14],"control":[15],"tasks":[16],"probabilistic":[18],"inference":[19,51],"problems.However,":[20],"the":[21,60,71,84],"extension":[22],"of":[23],"CAI":[24],"to":[25,54,94],"multi-agent,":[26],"general-sum":[27],"stochastic":[28],"games":[29],"(SGs)":[30],"remains":[31],"underexplored,":[32],"particularly":[33],"in":[34],"decentralized":[35,55,86],"settings":[36],"where":[37],"agents":[38],"operate":[39],"independently":[40],"without":[41],"centralized":[42],"coordination.In":[43],"this":[44,88],"paper,":[45],"we":[46,78,90],"propose":[47],"a":[48],"novel":[49],"variational":[50],"tailored":[53],"multi-agent":[56],"systems.Our":[57],"addresses":[59],"challenges":[61],"posed":[62],"non-stationarity":[64],"and":[65,102],"unaligned":[66],"agent":[67],"objectives,":[68],"proving":[69],"that":[70],"resulting":[72],"policies":[73],"form":[74],"an":[75],"-Nash":[76],"equilibrium.Additionally,":[77],"demonstrate":[79],"theoretical":[80,107],"convergence":[81,108],"guarantees":[82],"for":[83,96],"proposed":[85],"algorithms.Leveraging":[87],"framework,":[89],"instantiate":[91],"multiple":[92],"algorithms":[93],"solve":[95],"Nash":[97,100],"equilibrium,":[98,101,104],"mean-field":[99],"correlated":[103],"with":[105],"rigorous":[106],"analysis.":[109]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}