{"id":"https://openalex.org/W4404914276","doi":"https://doi.org/10.1109/lcsys.2024.3510193","title":"Convergence of Decentralized Actor-Critic Algorithm in General\u2013Sum Markov Games","display_name":"Convergence of Decentralized Actor-Critic Algorithm in General\u2013Sum Markov Games","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404914276","doi":"https://doi.org/10.1109/lcsys.2024.3510193"},"language":"en","primary_location":{"id":"doi:10.1109/lcsys.2024.3510193","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2024.3510193","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/A5031376831","display_name":"Chinmay Maheshwari","orcid":"https://orcid.org/0000-0003-3596-2851"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chinmay Maheshwari","raw_affiliation_strings":["Department of EECS, University of California at Berkeley, Berkeley, CA, USA","EECS at UC Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3596-2851","affiliations":[{"raw_affiliation_string":"Department of EECS, University of California at Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"EECS at UC Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103061454","display_name":"Manxi Wu","orcid":"https://orcid.org/0000-0001-5334-4163"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manxi Wu","raw_affiliation_strings":["Department of Civil and Environmental Engineering, University of California at Berkeley, Berkeley, CA, USA","Department of Civil and Environmental Engineering, University of California, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5334-4163","affiliations":[{"raw_affiliation_string":"Department of Civil and Environmental Engineering, University of California at Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Department of Civil and Environmental Engineering, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103101043","display_name":"S. Shankar Sastry","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shankar Sastry","raw_affiliation_strings":["Department of EECS, University of California at Berkeley, Berkeley, CA, USA","EECS at UC Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1300-1574","affiliations":[{"raw_affiliation_string":"Department of EECS, University of California at Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"EECS at UC Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.7951,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76878858,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"8","issue":null,"first_page":"2643","last_page":"2648"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.9151999950408936,"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":0.9151999950408936,"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/T12288","display_name":"Optimization and Search Problems","score":0.9120000004768372,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.909500002861023,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7889740467071533},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.653114378452301},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5176456570625305},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5031313300132751},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4495759904384613},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.42919549345970154},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3510935604572296},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.33954036235809326},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.09892863035202026},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08141177892684937}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7889740467071533},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.653114378452301},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5176456570625305},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5031313300132751},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4495759904384613},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.42919549345970154},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3510935604572296},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.33954036235809326},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.09892863035202026},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08141177892684937},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lcsys.2024.3510193","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2024.3510193","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":"Reduced inequalities","score":0.5,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1981609310","https://openalex.org/W2135608404","https://openalex.org/W2949597507","https://openalex.org/W2962990479","https://openalex.org/W3121224226","https://openalex.org/W3205079722","https://openalex.org/W3209754935","https://openalex.org/W4396982303","https://openalex.org/W6785161469","https://openalex.org/W6796569726","https://openalex.org/W6802197776","https://openalex.org/W6802970913","https://openalex.org/W6810414227","https://openalex.org/W6838604868","https://openalex.org/W6855340604","https://openalex.org/W6874200831","https://openalex.org/W6879552555"],"related_works":["https://openalex.org/W1660242800","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W2315999538","https://openalex.org/W2367222340","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"Markov":[0,33,62,106],"games":[1],"provide":[2],"a":[3,69,105],"powerful":[4],"framework":[5],"for":[6,28,120],"modeling":[7],"strategic":[8],"multi-agent":[9],"interactions":[10],"in":[11,21,60,124],"dynamic":[12,79],"environments.":[13],"Traditionally,":[14],"convergence":[15],"properties":[16,56],"of":[17,57,95,104,137],"decentralized":[18,70,85,126],"learning":[19,58,78,127],"algorithms":[20,59],"these":[22],"settings":[23],"have":[24],"been":[25],"established":[26],"only":[27],"special":[29],"cases,":[30],"such":[31],"as":[32,115],"zero-sum":[34],"and":[35,110,148],"potential":[36],"games,":[37],"which":[38,129],"do":[39],"not":[40],"fully":[41],"capture":[42],"real-world":[43],"interactions.":[44],"In":[45,64],"this":[46,50],"letter,":[47],"we":[48,66],"address":[49],"gap":[51],"by":[52],"studying":[53],"the":[54,102,121,125,134],"asymptotic":[55],"general-sum":[61],"games.":[63],"particular,":[65],"focus":[67],"on":[68],"algorithm":[71],"where":[72],"each":[73],"agent":[74],"adopts":[75],"an":[76,116],"actor-critic":[77],"with":[80,149],"asynchronous":[81],"step":[82],"sizes.":[83],"This":[84],"approach":[86],"enables":[87],"agents":[88],"to":[89,132],"operate":[90],"independently,":[91],"without":[92],"requiring":[93],"knowledge":[94],"others\u2019":[96],"strategies":[97],"or":[98],"payoffs.":[99],"We":[100,139],"introduce":[101],"concept":[103],"Near-Potential":[107],"Function":[108],"(MNPF)":[109],"demonstrate":[111],"that":[112],"it":[113],"serves":[114],"approximate":[117],"Lyapunov":[118],"function":[119],"policy":[122],"updates":[123],"dynamics,":[128],"allows":[130],"us":[131],"characterize":[133],"convergent":[135],"set":[136],"strategies.":[138],"further":[140],"strengthen":[141],"our":[142],"result":[143],"under":[144],"specific":[145],"regularity":[146],"conditions":[147],"finite":[150],"Nash":[151],"equilibria.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}