{"id":"https://openalex.org/W4205501012","doi":"https://doi.org/10.1109/tnnls.2021.3139138","title":"Distributed Actor\u2013Critic Algorithms for Multiagent Reinforcement Learning Over Directed Graphs","display_name":"Distributed Actor\u2013Critic Algorithms for Multiagent Reinforcement Learning Over Directed Graphs","publication_year":2022,"publication_date":"2022-01-11","ids":{"openalex":"https://openalex.org/W4205501012","doi":"https://doi.org/10.1109/tnnls.2021.3139138","pmid":"https://pubmed.ncbi.nlm.nih.gov/35015654"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3139138","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3139138","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.tudelft.nl/file/File_56a852c8-8378-4bd2-aff4-da69eb475275","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Pengcheng Dai","orcid":"https://orcid.org/0000-0003-1455-7216"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Dai","raw_affiliation_strings":["School of Mathematics, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-1455-7216","affiliations":[{"raw_affiliation_string":"School of Mathematics, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenwu Yu","orcid":"https://orcid.org/0000-0001-6406-2399"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwu Yu","raw_affiliation_strings":["School of Mathematics and the School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-6406-2399","affiliations":[{"raw_affiliation_string":"School of Mathematics and the School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":null,"display_name":"He Wang","orcid":"https://orcid.org/0000-0002-3065-393X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Wang","raw_affiliation_strings":["School of Mathematics, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-3065-393X","affiliations":[{"raw_affiliation_string":"School of Mathematics, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":null,"display_name":"Simone Baldi","orcid":"https://orcid.org/0000-0001-9752-8925"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Simone Baldi","raw_affiliation_strings":["School of Mathematics, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9752-8925","affiliations":[{"raw_affiliation_string":"School of Mathematics, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":2.6667,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.9084888,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"34","issue":"10","first_page":"7210","last_page":"7221"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4602000117301941,"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":0.4602000117301941,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.44769999384880066,"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"}},{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.01590000092983246,"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/directed-graph","display_name":"Directed graph","score":0.690500020980835},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6078000068664551},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5942000150680542},{"id":"https://openalex.org/keywords/distributed-algorithm","display_name":"Distributed algorithm","score":0.5189999938011169},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.48660001158714294},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4122999906539917},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.36730000376701355},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.3564000129699707},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.3465000092983246}],"concepts":[{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.690500020980835},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6078000068664551},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5942000150680542},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.57669997215271},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.5189999938011169},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.48660001158714294},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4415000081062317},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4122999906539917},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3605000078678131},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3402999937534332},{"id":"https://openalex.org/C38754835","wikidata":"https://www.wikidata.org/wiki/Q2003238","display_name":"Strongly connected component","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.30799999833106995},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C134466208","wikidata":"https://www.wikidata.org/wiki/Q1520657","display_name":"Weight function","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C54848796","wikidata":"https://www.wikidata.org/wiki/Q339011","display_name":"Symmetric matrix","level":3,"score":0.2883000075817108},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C189693848","wikidata":"https://www.wikidata.org/wiki/Q6031064","display_name":"Information exchange","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tnnls.2021.3139138","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3139138","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:35015654","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35015654","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null},{"id":"pmh:oai:tudelft.nl:uuid:14b1af75-bf0f-42d6-b2cb-33232afacd4b","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:14b1af75-bf0f-42d6-b2cb-33232afacd4b","pdf_url":"https://repository.tudelft.nl/file/File_56a852c8-8378-4bd2-aff4-da69eb475275","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"}],"best_oa_location":{"id":"pmh:oai:tudelft.nl:uuid:14b1af75-bf0f-42d6-b2cb-33232afacd4b","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:14b1af75-bf0f-42d6-b2cb-33232afacd4b","pdf_url":"https://repository.tudelft.nl/file/File_56a852c8-8378-4bd2-aff4-da69eb475275","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4949000581","display_name":null,"funder_award_id":"62073076","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4995428506","display_name":null,"funder_award_id":"62073074","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6315690620","display_name":null,"funder_award_id":"61673107","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4205501012.pdf","grobid_xml":"https://content.openalex.org/works/W4205501012.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1918371733","https://openalex.org/W2032704188","https://openalex.org/W2044212084","https://openalex.org/W2060605484","https://openalex.org/W2107396783","https://openalex.org/W2114791779","https://openalex.org/W2124829859","https://openalex.org/W2137435346","https://openalex.org/W2145339207","https://openalex.org/W2156629001","https://openalex.org/W2462102501","https://openalex.org/W2541582879","https://openalex.org/W2581108373","https://openalex.org/W2794842761","https://openalex.org/W2799693052","https://openalex.org/W2913173906","https://openalex.org/W2913326990","https://openalex.org/W2954968417","https://openalex.org/W2963058313","https://openalex.org/W2963304272","https://openalex.org/W2965489695","https://openalex.org/W2966633400","https://openalex.org/W3011272463","https://openalex.org/W3035289456","https://openalex.org/W3036397266","https://openalex.org/W3081103181","https://openalex.org/W3153787838","https://openalex.org/W4243772471","https://openalex.org/W4249154916","https://openalex.org/W6632901617","https://openalex.org/W6633472260","https://openalex.org/W6637967152","https://openalex.org/W6678168664","https://openalex.org/W6749032143","https://openalex.org/W6749304979","https://openalex.org/W6752380930","https://openalex.org/W6762491519","https://openalex.org/W6767327128","https://openalex.org/W6781750019","https://openalex.org/W6787177955"],"related_works":[],"abstract_inverted_index":{"Actor-critic":[0],"(AC)":[1],"cooperative":[2],"multiagent":[3],"reinforcement":[4],"learning":[5],"(MARL)":[6],"over":[7,91,113],"directed":[8,92,114],"graphs":[9,53,115],"is":[10,22,148],"studied":[11],"in":[12,20,29,47],"this":[13],"article.":[14],"The":[15],"goal":[16],"of":[17,144,154,166],"the":[18,25,48,51,58,67,100,111,130,136,145,155,164,167],"agents":[19],"MARL":[21,90,112],"to":[23,54,61,103,139,162],"maximize":[24],"globally":[26],"averaged":[27],"return":[28],"a":[30,85,123],"distributed":[31,86,125],"way,":[32],"i.e.,":[33],"each":[34],"agent":[35],"can":[36],"only":[37,98,134],"exchange":[38],"information":[39],"with":[40,94,119],"its":[41],"neighboring":[42],"agents.":[43],"AC":[44,87,126],"methods":[45],"proposed":[46,146,168],"literature":[49],"require":[50],"communication":[52],"be":[55,62,104,140],"undirected":[56],"and":[57,73],"weight":[59,68,101,137],"matrices":[60,69,138],"doubly":[63],"stochastic":[64,72],"(more":[65],"precisely,":[66],"are":[70,76,160],"row":[71,105],"their":[74],"expectation":[75],"column":[77,141],"stochastic).":[78],"Differently":[79],"from":[80],"these":[81],"methods,":[82],"we":[83,108],"propose":[84],"algorithm":[88,127],"for":[89,150],"graph":[93],"fixed":[95],"topology":[96],"that":[97,133],"requires":[99,135],"matrix":[102],"stochastic.":[106,142],"Then,":[107],"also":[109],"study":[110],"(possibly":[116],"not":[117],"connected)":[118],"changing":[120],"topologies,":[121],"proposing":[122],"different":[124],"based":[128],"on":[129],"push-sum":[131],"protocol":[132],"Convergence":[143],"algorithms":[147],"proven":[149],"linear":[151],"function":[152],"approximation":[153],"action":[156],"value":[157],"function.":[158],"Simulations":[159],"presented":[161],"demonstrate":[163],"effectiveness":[165],"algorithms.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2022-01-25T00:00:00"}