{"id":"https://openalex.org/W4407951578","doi":"https://doi.org/10.1109/cdc56724.2024.10886868","title":"Policy Optimization finds Nash Equilibrium in Regularized General-Sum LQ Games","display_name":"Policy Optimization finds Nash Equilibrium in Regularized General-Sum LQ Games","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4407951578","doi":"https://doi.org/10.1109/cdc56724.2024.10886868"},"language":"en","primary_location":{"id":"doi:10.1109/cdc56724.2024.10886868","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10886868","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"article","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/A5053458868","display_name":"Muhammad Aneeq Uz Zaman","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Muhammad Aneeq Uz Zaman","raw_affiliation_strings":["University of Illinois Urbana-Champaign,Coordinated Science Laboratory,Urbana,IL,USA,61801"],"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,Coordinated Science Laboratory,Urbana,IL,USA,61801","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019129928","display_name":"Shubham Aggarwal","orcid":"https://orcid.org/0000-0002-9424-246X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shubham Aggarwal","raw_affiliation_strings":["University of Illinois Urbana-Champaign,Coordinated Science Laboratory,Urbana,IL,USA,61801"],"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,Coordinated Science Laboratory,Urbana,IL,USA,61801","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000544057","display_name":"Melih Ba\u015ftop\u00e7u","orcid":"https://orcid.org/0000-0001-5122-0642"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Melih Bastopcu","raw_affiliation_strings":["University of Illinois Urbana-Champaign,Coordinated Science Laboratory,Urbana,IL,USA,61801"],"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,Coordinated Science Laboratory,Urbana,IL,USA,61801","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019604570","display_name":"Tamer Ba\u015far","orcid":"https://orcid.org/0000-0003-4406-7875"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tamer Ba\u015far","raw_affiliation_strings":["University of Illinois Urbana-Champaign,Coordinated Science Laboratory,Urbana,IL,USA,61801"],"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,Coordinated Science Laboratory,Urbana,IL,USA,61801","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5053458868"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33921017,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3384","last_page":"3389"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.984000027179718,"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/T11031","display_name":"Game Theory and Applications","score":0.984000027179718,"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":0.9804999828338623,"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/T13825","display_name":"Economic Policies and Impacts","score":0.9309999942779541,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.7896325588226318},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.6345908641815186},{"id":"https://openalex.org/keywords/best-response","display_name":"Best response","score":0.5357578992843628},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.505584716796875},{"id":"https://openalex.org/keywords/epsilon-equilibrium","display_name":"Epsilon-equilibrium","score":0.46460336446762085},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.41275161504745483},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.40972697734832764},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.40082746744155884}],"concepts":[{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.7896325588226318},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.6345908641815186},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.5357578992843628},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.505584716796875},{"id":"https://openalex.org/C141824439","wikidata":"https://www.wikidata.org/wiki/Q307521","display_name":"Epsilon-equilibrium","level":4,"score":0.46460336446762085},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.41275161504745483},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40972697734832764},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.40082746744155884}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc56724.2024.10886868","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10886868","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320316514","display_name":"Arm","ror":"https://ror.org/04mmhzs81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2011000015","https://openalex.org/W2038686546","https://openalex.org/W2492629073","https://openalex.org/W2498694880","https://openalex.org/W2896280943","https://openalex.org/W2991046523","https://openalex.org/W3037286161","https://openalex.org/W3038093235","https://openalex.org/W3110347183","https://openalex.org/W3119173266","https://openalex.org/W3157937972","https://openalex.org/W3216656735","https://openalex.org/W4214597064","https://openalex.org/W4285093350","https://openalex.org/W4294692096","https://openalex.org/W4367359634","https://openalex.org/W4392972206","https://openalex.org/W4402354108","https://openalex.org/W6728155968","https://openalex.org/W6754297394","https://openalex.org/W6756650885","https://openalex.org/W6762982123","https://openalex.org/W6765239642","https://openalex.org/W6770404689","https://openalex.org/W6790511988","https://openalex.org/W6799255795","https://openalex.org/W6802266127","https://openalex.org/W6802528643","https://openalex.org/W6802970913","https://openalex.org/W6803111450","https://openalex.org/W6842723896","https://openalex.org/W6852865817","https://openalex.org/W6858014027","https://openalex.org/W6863068607","https://openalex.org/W6863465575","https://openalex.org/W6869665510"],"related_works":["https://openalex.org/W4302558842","https://openalex.org/W1554758635","https://openalex.org/W4389370903","https://openalex.org/W2282604764","https://openalex.org/W2803931294","https://openalex.org/W2500870930","https://openalex.org/W1721270588","https://openalex.org/W2010679956","https://openalex.org/W2955320052","https://openalex.org/W4248623114"],"abstract_inverted_index":{"In":[0],"this":[1,75],"paper,":[2],"we":[3,77,111],"investigate":[4],"the":[5,13,22,25,42,48,51,54,72,79,90,100,106,118,124],"impact":[6],"of":[7,17,27,44,50,82,92,97,120],"introducing":[8],"relative":[9],"entropy":[10,45,93,107],"regularization":[11,108],"on":[12],"Nash":[14],"Equilibria":[15],"(NE)":[16],"General-Sum":[18],"N-agent":[19],"games,":[20],"revealing":[21],"fact":[23],"that":[24],"NE":[26,52],"such":[28],"games":[29],"conform":[30],"to":[31,89],"linear":[32,80],"Gaussian":[33],"policies.":[34],"Moreover,":[35],"it":[36],"delineates":[37],"sufficient":[38],"conditions,":[39],"contingent":[40],"upon":[41],"adequacy":[43,91],"regularization,":[46],"for":[47,64],"uniqueness":[49],"within":[53,123],"game.":[55,125],"As":[56],"Policy":[57],"Optimization":[58],"serves":[59],"as":[60],"a":[61,83,113],"foundational":[62],"approach":[63],"Reinforcement":[65],"Learning":[66],"(RL)":[67],"techniques":[68],"aimed":[69],"at":[70],"finding":[71],"NE,":[73],"in":[74,103],"work":[76],"prove":[78],"convergence":[81],"policy":[84],"optimization":[85],"algorithm":[86],"which":[87,116],"(subject":[88],"regularization)":[94],"is":[95],"capable":[96],"provably":[98],"attaining":[99],"NE.":[101],"Furthermore,":[102],"scenarios":[104],"where":[105],"proves":[109],"insufficient,":[110],"present":[112],"\u03b4-augmentation":[114],"technique,":[115],"facilitates":[117],"achievement":[119],"an":[121],"\u03f5-NE":[122]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}
