{"id":"https://openalex.org/W4402039386","doi":"https://doi.org/10.1109/tai.2024.3452678","title":"Policy Consensus-Based Distributed Deterministic Multi-Agent Reinforcement Learning Over Directed Graphs","display_name":"Policy Consensus-Based Distributed Deterministic Multi-Agent Reinforcement Learning Over Directed Graphs","publication_year":2024,"publication_date":"2024-08-30","ids":{"openalex":"https://openalex.org/W4402039386","doi":"https://doi.org/10.1109/tai.2024.3452678"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2024.3452678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2024.3452678","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Artificial Intelligence","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/A5077045940","display_name":"Yifan Hu","orcid":"https://orcid.org/0000-0003-0756-6157"},"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":"Yifan Hu","raw_affiliation_strings":["School of Mathematics, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-0756-6157","affiliations":[{"raw_affiliation_string":"School of Mathematics, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030933117","display_name":"Junjie Fu","orcid":"https://orcid.org/0000-0002-1528-8727"},"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":"Junjie Fu","raw_affiliation_strings":["School of Mathematics, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-1528-8727","affiliations":[{"raw_affiliation_string":"School of Mathematics, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040088510","display_name":"Guanghui Wen","orcid":"https://orcid.org/0000-0003-0070-8597"},"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":"Guanghui Wen","raw_affiliation_strings":["School of Mathematics, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-0070-8597","affiliations":[{"raw_affiliation_string":"School of Mathematics, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019248683","display_name":"Changyin Sun","orcid":"https://orcid.org/0000-0001-9269-334X"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changyin Sun","raw_affiliation_strings":["School of Artificial Intelligence, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-9269-334X","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5557,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71433129,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"6","issue":"1","first_page":"118","last_page":"131"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4404999911785126,"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":0.4404999911785126,"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/T14420","display_name":"Advanced Research in Systems and Signal Processing","score":0.43479999899864197,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.43470001220703125,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7738646864891052},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5836254358291626},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5188823342323303},{"id":"https://openalex.org/keywords/consensus","display_name":"Consensus","score":0.5091504454612732},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.37776482105255127},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3484164774417877}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7738646864891052},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5836254358291626},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5188823342323303},{"id":"https://openalex.org/C107107730","wikidata":"https://www.wikidata.org/wiki/Q2994424","display_name":"Consensus","level":3,"score":0.5091504454612732},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37776482105255127},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3484164774417877}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2024.3452678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2024.3452678","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2575069074","display_name":null,"funder_award_id":"62088101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2710225095","display_name":null,"funder_award_id":"62173085","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2843151570","display_name":null,"funder_award_id":"62325304","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5060958647","display_name":null,"funder_award_id":"62073079","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8967878662","display_name":null,"funder_award_id":"U22B2046","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1938894423","https://openalex.org/W2094387729","https://openalex.org/W2107396783","https://openalex.org/W2114791779","https://openalex.org/W2746553466","https://openalex.org/W2768629321","https://openalex.org/W2913326990","https://openalex.org/W2963304272","https://openalex.org/W2963755123","https://openalex.org/W3010758700","https://openalex.org/W3093571944","https://openalex.org/W3183210514","https://openalex.org/W4205501012","https://openalex.org/W4243772471","https://openalex.org/W4312741895","https://openalex.org/W4313478129","https://openalex.org/W4361801650","https://openalex.org/W4388579659","https://openalex.org/W4390730760","https://openalex.org/W4399558212","https://openalex.org/W6677984395","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6738796088","https://openalex.org/W6748839928","https://openalex.org/W6749032143","https://openalex.org/W6751139674","https://openalex.org/W6752380930","https://openalex.org/W6767151588","https://openalex.org/W6768731700","https://openalex.org/W6770566355","https://openalex.org/W6795908048","https://openalex.org/W6800131325","https://openalex.org/W6810201281","https://openalex.org/W6840380725","https://openalex.org/W7039202139"],"related_works":["https://openalex.org/W3046732854","https://openalex.org/W2784026553","https://openalex.org/W3127518712","https://openalex.org/W2511063373","https://openalex.org/W3088852461","https://openalex.org/W2113824758","https://openalex.org/W2118264468","https://openalex.org/W2335243741","https://openalex.org/W2063140052","https://openalex.org/W2467364348"],"abstract_inverted_index":{"Learning":[0],"efficient":[1],"coordination":[2],"policies":[3],"over":[4],"continuous":[5,42,143],"state":[6],"and":[7,77,84,131],"action":[8,144],"spaces":[9],"remains":[10],"a":[11,48,55,69,105],"huge":[12],"challenge":[13],"for":[14,47,81],"existing":[15],"distributed":[16,36,61,107,153],"multi-agent":[17],"reinforcement":[18,121],"learning":[19,45,122,157],"(MARL)":[20],"algorithms.":[21],"In":[22],"this":[23],"article,":[24],"the":[25,35,41,82,99,115,119,147,151],"classic":[26],"deterministic":[27,108],"policy":[28,44],"gradient":[29],"(DPG)":[30],"method":[31],"is":[32,64,90,111],"extended":[33],"to":[34,39,93,159],"MARL":[37,140],"domain":[38],"handle":[40],"control":[43],"issue":[46],"team":[49],"of":[50,98],"homogeneous":[51],"agents":[52],"connected":[53],"through":[54],"directed":[56],"graph.":[57],"A":[58],"theoretical":[59,116],"on-policy":[60],"actor\u2013critic":[62,109],"algorithm":[63,100,110,117,154],"first":[65],"proposed":[66,112,152],"based":[67],"on":[68],"local":[70],"DPG":[71],"theorem,":[72],"which":[73,125],"considers":[74],"observation-based":[75],"policies,":[76],"incorporates":[78],"consensus":[79],"updates":[80],"critic":[83],"actor":[85],"parameters.":[86],"Stochastic":[87],"approximation":[88],"theory":[89],"then":[91],"used":[92],"obtain":[94],"asymptotic":[95],"convergence":[96],"results":[97,148],"under":[101],"standard":[102,139],"assumptions.":[103],"Thereafter,":[104],"practical":[106],"by":[113],"integrating":[114],"with":[118,142],"deep":[120],"training":[123],"architecture,":[124],"achieves":[126,155],"better":[127],"scalability,":[128],"exploration":[129],"ability,":[130],"data":[132],"efficiency.":[133],"Simulations":[134],"are":[135],"carried":[136],"out":[137],"in":[138],"environments":[141],"spaces,":[145],"where":[146],"demonstrate":[149],"that":[150],"comparable":[156],"performance":[158],"solid":[160],"centralized":[161],"trained":[162],"baselines":[163],"while":[164],"demanding":[165],"much":[166],"less":[167],"communication":[168],"resources.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}