{"id":"https://openalex.org/W4302013128","doi":"https://doi.org/10.48550/arxiv.2210.01050","title":"Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games","display_name":"Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games","publication_year":2022,"publication_date":"2022-10-03","ids":{"openalex":"https://openalex.org/W4302013128","doi":"https://doi.org/10.48550/arxiv.2210.01050"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2210.01050","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.01050","pdf_url":"https://arxiv.org/pdf/2210.01050","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2210.01050","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091389636","display_name":"Shicong Cen","orcid":null,"observed_orcids":[]},"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":"Cen, Shicong","raw_affiliation_strings":["Carnegie Mellon University","Department of Electrical and Computer Engineering , Carnegie Mellon University ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","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/A5053809095","display_name":"Yuejie Chi","orcid":"https://orcid.org/0000-0002-6766-5459","observed_orcids":["https://orcid.org/0000-0002-6766-5459"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chi, Yuejie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033061754","display_name":"Simon S. Du","orcid":"https://orcid.org/0000-0003-0056-8299","observed_orcids":["https://orcid.org/0000-0003-0056-8299"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Simon S.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005130812","display_name":"Lin Xiao","orcid":"https://orcid.org/0000-0003-3172-3490","observed_orcids":["https://orcid.org/0000-0003-3172-3490"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Lin","raw_affiliation_strings":["Meta AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9970999956130981,"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":0.9970999956130981,"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":0.0007999999797903001,"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/T11031","display_name":"Game Theory and Applications","score":0.0007999999797903001,"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/zero-sum-markov-games","display_name":"zero-sum Markov games","score":0.9100000262260437},{"id":"https://openalex.org/keywords/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.9150000214576721},{"id":"https://openalex.org/keywords/policy-optimization","display_name":"policy optimization","score":0.781000018119812},{"id":"https://openalex.org/keywords/last-iterate-convergence","display_name":"last-iterate convergence","score":0.9229999780654907},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.9700000286102295},{"id":"https://openalex.org/keywords/quantal-response-equilibrium","display_name":"quantal response equilibrium","score":0.9660000205039978},{"id":"https://openalex.org/keywords/entropy-regularization","display_name":"entropy regularization","score":0.9599999785423279}],"concepts":[{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6979996562004089},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6845097541809082},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6841700077056885},{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.6688673496246338},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5723918080329895},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.5624163746833801},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5419297218322754},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5368021130561829},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.42095616459846497},{"id":"https://openalex.org/C199510392","wikidata":"https://www.wikidata.org/wiki/Q1184602","display_name":"Stackelberg competition","level":2,"score":0.4182650148868561},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3707205057144165},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3698045611381531},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.368973970413208},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.09786069393157959},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2210.01050","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.01050","pdf_url":"https://arxiv.org/pdf/2210.01050","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2210.01050","doi":"https://doi.org/10.48550/arxiv.2210.01050","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.01050","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2210.01050","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.01050","pdf_url":"https://arxiv.org/pdf/2210.01050","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1469985387","display_name":null,"funder_award_id":"N00014-19-1-2404","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G1640465657","display_name":"RINGS: Learning-Enabled Ground and Air Integrated Networks (GAINs)","funder_award_id":"2148212","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1970041747","display_name":"CIF: Medium: Collaborative Research: Theory of Optimization Geometry and Algorithms for Neural Networks","funder_award_id":"1901199","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2241881954","display_name":"IIS:RI Theoretical Foundations of Reinforcement Learning: From Tabula Rasa to Function Approximation","funder_award_id":"2110170","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4353487559","display_name":null,"funder_award_id":"ONR-N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G5174315691","display_name":"Collaborative Research: CIF: Medium: Statistical and Algorithmic Foundations of Efficient Reinforcement Learning","funder_award_id":"2106778","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5522209294","display_name":"CAREER: Toward a Foundation of Over-Parameterization","funder_award_id":"2143493","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5972442391","display_name":null,"funder_award_id":"N00014-19","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6151270557","display_name":"Collaborative Research: SCALE MoDL: Adaptivity of Deep Neural Networks","funder_award_id":"2134106","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6920479218","display_name":"Collaborative Research: CIF: Medium: MoDL:Toward a Mathematical Foundation of Deep Reinforcement Learning","funder_award_id":"2212261","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8429103732","display_name":"AI Institute: Institute for Foundations of Machine Learning","funder_award_id":"2019844","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310207","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7133243806","https://openalex.org/W7212012687","https://openalex.org/W4385965393","https://openalex.org/W7134807297","https://openalex.org/W4391416565","https://openalex.org/W4327990324","https://openalex.org/W4393156376","https://openalex.org/W7129179798","https://openalex.org/W2145067550","https://openalex.org/W2105643086"],"abstract_inverted_index":{"Multi-Agent":[0],"Reinforcement":[1],"Learning":[2],"(MARL)":[3],"--":[4,16],"where":[5,115],"multiple":[6],"agents":[7],"learn":[8],"to":[9,155,166,171,193],"interact":[10],"in":[11,40,51,91,141,200],"a":[12,19,104,135,150,167,194],"shared":[13],"dynamic":[14],"environment":[15],"permeates":[17],"across":[18],"wide":[20],"range":[21],"of":[22,36,46,77,160,179,197],"critical":[23],"applications.":[24],"While":[25],"there":[26],"has":[27],"been":[28],"substantial":[29],"progress":[30],"on":[31,72,134],"understanding":[32,196],"the":[33,52,73,93,98,116,121,130,142,146,156,161,172,177,186],"global":[34],"convergence":[35,154,170,182],"policy":[37,48,106,117,198],"optimization":[38,49,107,199],"methods":[39],"single-agent":[41],"RL,":[42,80],"designing":[43],"and":[44,86,97,129,191],"analysis":[45],"efficient":[47],"algorithms":[50,90],"MARL":[53],"setting":[54,76,96],"present":[55],"significant":[56],"challenges,":[57],"which":[58,164],"unfortunately,":[59],"remain":[60],"highly":[61],"inadequately":[62],"addressed":[63],"by":[64,175],"existing":[65],"theory.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70],"focus":[71],"most":[74],"basic":[75],"competitive":[78,201],"multi-agent":[79],"namely":[81],"two-player":[82],"zero-sum":[83],"Markov":[84,202],"games,":[85],"study":[87],"equilibrium":[88,159,174],"finding":[89],"both":[92,113],"infinite-horizon":[94],"discounted":[95],"finite-horizon":[99],"episodic":[100],"setting.":[101],"We":[102,138],"propose":[103],"single-loop":[105],"method":[108,128,148],"with":[109],"symmetric":[110],"updates":[111],"from":[112],"agents,":[114],"is":[118,132],"updated":[119,133],"via":[120],"entropy-regularized":[122],"optimistic":[123],"multiplicative":[124],"weights":[125],"update":[126],"(OMWU)":[127],"value":[131],"slower":[136],"timescale.":[137],"show":[139],"that,":[140],"full-information":[143],"tabular":[144],"setting,":[145],"proposed":[147],"achieves":[149],"finite-time":[151],"last-iterate":[152,169],"linear":[153],"quantal":[157],"response":[158],"regularized":[162],"problem,":[163],"translates":[165],"sublinear":[168],"Nash":[173],"controlling":[176],"amount":[178],"regularization.":[180],"Our":[181],"results":[183],"improve":[184],"upon":[185],"best":[187],"known":[188],"iteration":[189],"complexities,":[190],"lead":[192],"better":[195],"games.":[203]},"counts_by_year":[{"year":2024,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2022-10-06T00:00:00"}