{"id":"https://openalex.org/W4315471814","doi":"https://doi.org/10.1109/cdc51059.2022.9993175","title":"Independent Natural Policy Gradient Methods for Potential Games: Finite-time Global Convergence with Entropy Regularization","display_name":"Independent Natural Policy Gradient Methods for Potential Games: Finite-time Global Convergence with Entropy Regularization","publication_year":2022,"publication_date":"2022-12-06","ids":{"openalex":"https://openalex.org/W4315471814","doi":"https://doi.org/10.1109/cdc51059.2022.9993175"},"language":"en","primary_location":{"id":"doi:10.1109/cdc51059.2022.9993175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc51059.2022.9993175","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","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":"2022 IEEE 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5091389636","display_name":"Shicong Cen","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shicong Cen","raw_affiliation_strings":["Carnegie Mellon University,Department of Electrical and Computer Engineering","Department of Electrical and Computer Engineering, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100322066","display_name":"Fan Chen","orcid":"https://orcid.org/0000-0001-7928-8331"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Chen","raw_affiliation_strings":["Peking University,Department of Mathematics","Department of Mathematics, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Department of Mathematics","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Department of Mathematics, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053809095","display_name":"Yuejie Chi","orcid":"https://orcid.org/0000-0002-6766-5459"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuejie Chi","raw_affiliation_strings":["Carnegie Mellon University,Department of Electrical and Computer Engineering","Department of Electrical and Computer Engineering, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2833","last_page":"2838"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9980999827384949,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/nash-equilibrium","display_name":"Nash equilibrium","score":0.6431920528411865},{"id":"https://openalex.org/keywords/sublinear-function","display_name":"Sublinear function","score":0.6320586204528809},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6043295860290527},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5527738332748413},{"id":"https://openalex.org/keywords/multiplicative-function","display_name":"Multiplicative function","score":0.5286339521408081},{"id":"https://openalex.org/keywords/potential-game","display_name":"Potential game","score":0.5247162580490112},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5181295275688171},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.5029205679893494},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5027318000793457},{"id":"https://openalex.org/keywords/stochastic-game","display_name":"Stochastic game","score":0.4447154998779297},{"id":"https://openalex.org/keywords/best-response","display_name":"Best response","score":0.41214099526405334},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.4120088517665863},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3982686400413513},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3509664535522461},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.1499226689338684},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11106029152870178}],"concepts":[{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.6431920528411865},{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.6320586204528809},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6043295860290527},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5527738332748413},{"id":"https://openalex.org/C42747912","wikidata":"https://www.wikidata.org/wiki/Q1048447","display_name":"Multiplicative function","level":2,"score":0.5286339521408081},{"id":"https://openalex.org/C2778079155","wikidata":"https://www.wikidata.org/wiki/Q288500","display_name":"Potential game","level":3,"score":0.5247162580490112},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5181295275688171},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.5029205679893494},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5027318000793457},{"id":"https://openalex.org/C22171661","wikidata":"https://www.wikidata.org/wiki/Q1074380","display_name":"Stochastic game","level":2,"score":0.4447154998779297},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.41214099526405334},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.4120088517665863},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3982686400413513},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3509664535522461},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.1499226689338684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11106029152870178},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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:10.1109/cdc51059.2022.9993175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc51059.2022.9993175","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","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":"2022 IEEE 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W1990873282","https://openalex.org/W2016663842","https://openalex.org/W2064790943","https://openalex.org/W2093825590","https://openalex.org/W2106887613","https://openalex.org/W2118247617","https://openalex.org/W2126211987","https://openalex.org/W2130801532","https://openalex.org/W2138627397","https://openalex.org/W2150865801","https://openalex.org/W2155007355","https://openalex.org/W2176451521","https://openalex.org/W2254533881","https://openalex.org/W2257979135","https://openalex.org/W2264897026","https://openalex.org/W2752505153","https://openalex.org/W2781726626","https://openalex.org/W2948432982","https://openalex.org/W2962990479","https://openalex.org/W2971587637","https://openalex.org/W3022321359","https://openalex.org/W3098410977","https://openalex.org/W3103047293","https://openalex.org/W3127686539","https://openalex.org/W3127950324","https://openalex.org/W3131948096","https://openalex.org/W3148958427","https://openalex.org/W3169011731","https://openalex.org/W3169452765","https://openalex.org/W3171752851","https://openalex.org/W3173515307","https://openalex.org/W3205079722","https://openalex.org/W3205487934","https://openalex.org/W3209461740","https://openalex.org/W3211621594","https://openalex.org/W3217314940","https://openalex.org/W4221157223","https://openalex.org/W4226138304","https://openalex.org/W4234761190","https://openalex.org/W4250356017","https://openalex.org/W4286898817","https://openalex.org/W4287391791","https://openalex.org/W4297741778","https://openalex.org/W4299802797","https://openalex.org/W4312406920","https://openalex.org/W4315471814","https://openalex.org/W4318224770","https://openalex.org/W4381739798","https://openalex.org/W4388317804","https://openalex.org/W6679257226","https://openalex.org/W6682849425","https://openalex.org/W6736607274","https://openalex.org/W6738796088","https://openalex.org/W6747473740","https://openalex.org/W6754297394","https://openalex.org/W6766497270","https://openalex.org/W6767941141","https://openalex.org/W6776824048","https://openalex.org/W6784698908","https://openalex.org/W6785161469","https://openalex.org/W6786084949","https://openalex.org/W6790279749","https://openalex.org/W6790858184","https://openalex.org/W6796527454","https://openalex.org/W6796554599","https://openalex.org/W6800321118","https://openalex.org/W6802197776","https://openalex.org/W6802528643","https://openalex.org/W6802970913","https://openalex.org/W6809872370","https://openalex.org/W6810414227","https://openalex.org/W6840107105"],"related_works":["https://openalex.org/W2236801283","https://openalex.org/W2728657731","https://openalex.org/W1853631319","https://openalex.org/W2092374696","https://openalex.org/W2481143976","https://openalex.org/W2803932348","https://openalex.org/W4214835929","https://openalex.org/W1598931193","https://openalex.org/W2030545874","https://openalex.org/W2623069875"],"abstract_inverted_index":{"A":[0],"major":[1],"challenge":[2],"in":[3,30,46,98],"multi-agent":[4],"systems":[5],"is":[6,28,44,61,158],"that":[7,109,137,202,230],"the":[8,14,21,56,69,81,96,138,143,148,151,161,164,173,178,185,190,199,225],"system":[9],"complexity":[10],"grows":[11,168],"dramatically":[12],"with":[13,172,184],"number":[15,174,186],"of":[16,23,58,71,84,110,160,163,175,187,194,224],"agents":[17,188],"as":[18,20,35,213],"well":[19],"size":[22,162],"their":[24,65],"action":[25,165],"spaces,":[26],"which":[27,157],"typical":[29],"real":[31],"world":[32],"scenarios":[33],"such":[34],"autonomous":[36],"vehicles,":[37],"robotic":[38],"teams,":[39],"network":[40],"routing,":[41],"etc.":[42],"It":[43],"hence":[45],"imminent":[47],"need":[48,70],"to":[49,104,123,131,142,150,198,217],"design":[50],"decentralized":[51],"or":[52],"independent":[53,85,159,183],"algorithms":[54],"where":[55,95],"update":[57],"each":[59,121],"agent":[60,122],"only":[62],"based":[63],"on":[64],"local":[66],"observations":[67],"without":[68,228],"introducing":[72],"complex":[73],"communication/coordination":[74],"mechanisms.":[75],"In":[76],"this":[77],"work,":[78],"we":[79],"study":[80],"finite-time":[82],"convergence":[83,179],"entropy-regularized":[86,117,152],"natural":[87],"policy":[88],"gradient":[89],"(NPG)":[90],"methods":[91],"for":[92,189],"potential":[93,113],"games,":[94,196],"difference":[97],"an":[99,219],"agent\u2019s":[100],"utility":[101],"function":[102],"due":[103],"unilateral":[105],"deviation":[106],"matches":[107],"exactly":[108],"a":[111,154,205,214],"common":[112],"function.":[114],"The":[115],"proposed":[116,139],"NPG":[118],"method":[119,140,201],"enables":[120],"deploy":[124],"symmetric,":[125],"decentralized,":[126],"and":[127,167],"multiplicative":[128],"updates":[129],"according":[130],"its":[132],"own":[133],"payoff.":[134],"We":[135],"show":[136],"converges":[141,203],"quantal":[144],"response":[145],"equilibrium":[146,149,222],"(QRE)\u2014":[147],"game\u2014at":[153],"sublinear":[155],"rate,":[156],"space":[166],"at":[169,204],"most":[170],"sublinearly":[171],"agents.":[176],"Appealingly,":[177],"rate":[180],"further":[181],"becomes":[182],"important":[191],"special":[192],"case":[193],"identical-interest":[195],"leading":[197],"first":[200],"dimension-free":[206],"rate.":[207],"Our":[208],"approach":[209],"can":[210],"be":[211],"used":[212],"smoothing":[215],"technique":[216],"find":[218],"approximate":[220],"Nash":[221],"(NE)":[223],"unregularized":[226],"problem":[227],"assuming":[229],"stationary":[231],"policies":[232],"are":[233],"isolated.":[234]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}