{"id":"https://openalex.org/W4399451091","doi":"https://doi.org/10.1109/lcsys.2024.3410149","title":"Linear Convergence of Independent Natural Policy Gradient in Games With Entropy Regularization","display_name":"Linear Convergence of Independent Natural Policy Gradient in Games With Entropy Regularization","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4399451091","doi":"https://doi.org/10.1109/lcsys.2024.3410149"},"language":"en","primary_location":{"id":"doi:10.1109/lcsys.2024.3410149","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2024.3410149","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Control Systems Letters","raw_type":"journal-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/A5076743577","display_name":"Youbang Sun","orcid":"https://orcid.org/0000-0003-2494-8552"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Youbang Sun","raw_affiliation_strings":["Department of Mechanical and Industrial Engineering, Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Industrial Engineering, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009740610","display_name":"Tao Liu","orcid":"https://orcid.org/0000-0001-7879-5315"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Liu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107699893","display_name":"P. R. Kumar","orcid":"https://orcid.org/0000-0003-0389-5367"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. R. Kumar","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040922600","display_name":"Shahin Shahrampour","orcid":"https://orcid.org/0000-0003-3093-8510"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shahin Shahrampour","raw_affiliation_strings":["Department of Mechanical and Industrial Engineering, Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Industrial Engineering, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5076743577"],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":1.032,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.77507682,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"8","issue":null,"first_page":"1217","last_page":"1222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9961000084877014,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9961000084877014,"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/T12879","display_name":"Distributed Sensor Networks and Detection Algorithms","score":0.9819999933242798,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T13553","display_name":"Age of Information Optimization","score":0.9787999987602234,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6361308097839355},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.507145881652832},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.46906137466430664},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4426918029785156},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4418882131576538},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4305289089679718},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.4170101583003998},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3526553809642792},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.24182164669036865},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.15802201628684998},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14764851331710815},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.08198100328445435},{"id":"https://openalex.org/keywords/macroeconomics","display_name":"Macroeconomics","score":0.06103694438934326}],"concepts":[{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6361308097839355},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.507145881652832},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.46906137466430664},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4426918029785156},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4418882131576538},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4305289089679718},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.4170101583003998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3526553809642792},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.24182164669036865},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15802201628684998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14764851331710815},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.08198100328445435},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.06103694438934326}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lcsys.2024.3410149","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2024.3410149","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Control Systems Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G271639475","display_name":null,"funder_award_id":"CMMI-2038625","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3716715531","display_name":null,"funder_award_id":"N00014-21-1-2385","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4020837731","display_name":null,"funder_award_id":"CNS-2328395","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1491494309","https://openalex.org/W2067050450","https://openalex.org/W2264897026","https://openalex.org/W2913845934","https://openalex.org/W2948432982","https://openalex.org/W2949531204","https://openalex.org/W3127686539","https://openalex.org/W3171210634","https://openalex.org/W3196741622","https://openalex.org/W3217314940","https://openalex.org/W4254429271","https://openalex.org/W4301501993","https://openalex.org/W4315471814","https://openalex.org/W4379185386","https://openalex.org/W4381739798","https://openalex.org/W4394674309","https://openalex.org/W4399451091","https://openalex.org/W6728155968","https://openalex.org/W6747473740","https://openalex.org/W6760161302","https://openalex.org/W6776824048","https://openalex.org/W6780486084","https://openalex.org/W6785161469","https://openalex.org/W6786084949","https://openalex.org/W6790279749","https://openalex.org/W6796554599","https://openalex.org/W6809591387","https://openalex.org/W6838589368","https://openalex.org/W6845733484","https://openalex.org/W6854900933","https://openalex.org/W6857463059","https://openalex.org/W6863068607"],"related_works":["https://openalex.org/W1517908938","https://openalex.org/W4254199101","https://openalex.org/W4300427796","https://openalex.org/W2281834912","https://openalex.org/W1670153145","https://openalex.org/W1489941249","https://openalex.org/W3123492739","https://openalex.org/W2051864124","https://openalex.org/W4320486059","https://openalex.org/W2494168571"],"abstract_inverted_index":{"This":[0],"letter":[1],"focuses":[2],"on":[3,47,172],"the":[4,48,54,77,100,122,133,142],"entropy-regularized":[5],"independent":[6,38],"natural":[7],"policy":[8,30,69],"gradient":[9],"(NPG)":[10],"algorithm":[11],"in":[12,53],"multi-agent":[13,55],"reinforcement":[14],"learning.":[15],"In":[16,82],"this":[17,125],"letter,":[18],"agents":[19,52,64,89,106],"are":[20,90],"assumed":[21,44],"to":[22,25,34,45,58,96,108,132,153],"have":[23],"access":[24],"an":[26],"oracle":[27],"with":[28,70,103],"exact":[29],"evaluation":[31],"and":[32,93,162],"seek":[33],"maximize":[35],"their":[36],"respective":[37],"rewards.":[39],"Each":[40],"individual\u2019s":[41],"reward":[42],"is":[43,74],"depend":[46],"actions":[49],"of":[50,79,124,157,181],"all":[51],"system,":[56],"leading":[57],"a":[59,68,84,129,146,154,179],"game":[60],"between":[61],"agents.":[62],"All":[63],"make":[65],"decisions":[66],"under":[67,118],"bounded":[71],"rationality,":[72],"which":[73,111],"enforced":[75],"by":[76],"introduction":[78],"entropy":[80,120],"regularization.":[81],"practice,":[83],"smaller":[85],"regularization":[86,105,139],"implies":[87],"that":[88],"more":[91,113],"rational":[92],"behave":[94],"closer":[95],"Nash":[97,147],"policies.":[98],"On":[99],"other":[101],"hand,":[102],"larger":[104],"tend":[107],"act":[109],"randomly,":[110],"ensures":[112],"exploration.":[114],"We":[115,166],"show":[116],"that,":[117],"sufficient":[119],"regularization,":[121],"dynamics":[123],"system":[126],"converge":[127],"at":[128],"linear":[130],"rate":[131],"quantal":[134],"response":[135],"equilibrium":[136,148],"(QRE).":[137],"Although":[138],"assumptions":[140],"prevent":[141],"QRE":[143],"from":[144],"approximating":[145],"(NE),":[149],"our":[150,182],"findings":[151],"apply":[152],"wide":[155],"range":[156],"games,":[158],"including":[159],"cooperative,":[160],"potential,":[161],"two-player":[163],"matrix":[164],"games.":[165],"also":[167],"provide":[168],"extensive":[169],"empirical":[170],"results":[171],"multiple":[173],"games":[174],"(including":[175],"Markov":[176],"games)":[177],"as":[178],"verification":[180],"theoretical":[183],"analysis.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}