{"id":"https://openalex.org/W4410358454","doi":"https://doi.org/10.1109/tac.2025.3570065","title":"Distributed Neural Policy Gradient Algorithm for Global Convergence of Networked Multiagent Reinforcement Learning","display_name":"Distributed Neural Policy Gradient Algorithm for Global Convergence of Networked Multiagent Reinforcement Learning","publication_year":2025,"publication_date":"2025-05-14","ids":{"openalex":"https://openalex.org/W4410358454","doi":"https://doi.org/10.1109/tac.2025.3570065"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2025.3570065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2025.3570065","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","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/A5100705693","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":"https://openalex.org/A5016761365","display_name":"Yuanqiu Mo","orcid":"https://orcid.org/0000-0002-0500-5201"},"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":"Yuanqiu Mo","raw_affiliation_strings":["School of Mathematics, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-0500-5201","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/0000-0003-0301-9180"},"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, Frontiers Science Center for Mobile Information Communication and Security, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-0301-9180","affiliations":[{"raw_affiliation_string":"School of Mathematics, Frontiers Science Center for Mobile Information Communication and Security, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100339137","display_name":"Wei Ren","orcid":"https://orcid.org/0000-0002-2818-9752"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Ren","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, Riverside, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2818-9752","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1874,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.94689439,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"70","issue":"11","first_page":"7109","last_page":"7124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14225","display_name":"Advanced Sensor and Control Systems","score":0.9059000015258789,"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"}},"topics":[{"id":"https://openalex.org/T14225","display_name":"Advanced Sensor and Control Systems","score":0.9059000015258789,"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":0.8451180458068848},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7484713792800903},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6762393712997437},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5594258904457092},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4140439033508301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38613349199295044}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8451180458068848},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7484713792800903},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6762393712997437},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5594258904457092},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4140439033508301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38613349199295044},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2025.3570065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2025.3570065","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5}],"awards":[{"id":"https://openalex.org/G1326105430","display_name":null,"funder_award_id":"BK20230826","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G711384164","display_name":null,"funder_award_id":"62303112","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7846504898","display_name":null,"funder_award_id":"62233004","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"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1641379095","https://openalex.org/W2114791779","https://openalex.org/W2172968643","https://openalex.org/W2581108373","https://openalex.org/W2617547828","https://openalex.org/W2809148419","https://openalex.org/W2901838001","https://openalex.org/W2915117209","https://openalex.org/W2962771678","https://openalex.org/W2966633400","https://openalex.org/W2967474307","https://openalex.org/W2968782695","https://openalex.org/W2969195240","https://openalex.org/W3011272463","https://openalex.org/W3081103181","https://openalex.org/W3153787838","https://openalex.org/W3174056649","https://openalex.org/W4205501012","https://openalex.org/W4214717370","https://openalex.org/W4367298527","https://openalex.org/W4410358454"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{"This":[0,67],"paper":[1],"studies":[2],"the":[3,11,19,26,56,78,83,88,94,113,119,141,147,153,158,166,170,180,184,187,202],"networked":[4],"multi-agent":[5],"reinforcement":[6],"learning":[7],"(NMARL)":[8],"problem,":[9],"where":[10],"objective":[12,181],"of":[13,65,74,150,169,186],"agents":[14,92,104,151],"is":[15,190],"to":[16,35,110,179],"collaboratively":[17,111],"maximize":[18],"discounted":[20],"average":[21],"cumulative":[22],"rewards.":[23],"Different":[24],"from":[25,31,101],"existing":[27],"methods":[28],"that":[29,47],"suffer":[30],"poor":[32],"expression":[33],"due":[34],"linear":[36],"function":[37],"approximation,":[38],"we":[39,144,163],"propose":[40],"a":[41,106,196],"distributed":[42,68,79,89,159,172],"neural":[43,52,69,173],"policy":[44,63,70,128,155,174],"gradient":[45,71,175],"algorithm":[46,72,176,189,198],"features":[48],"two":[49,75],"innovatively":[50],"designed":[51],"networks,":[53],"specifically":[54],"for":[55,152],"approximate":[57,95,135],"<inline-formula":[58,96,136],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[59,97,137],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[60,98,138],"notation=\"LaTeX\">$Q$</tex-math></inline-formula>-functions":[61],"and":[62,82],"functions":[64],"agents.":[66],"consists":[73],"key":[76],"components:":[77],"critic":[80,90,160],"step":[81],"decentralized":[84,120],"actor":[85,121],"step.":[86,161],"In":[87,116,140],"step,":[91,122],"receive":[93],"notation=\"LaTeX\">$Q$</tex-math></inline-formula>-function":[99],"parameters":[100],"their":[102],"neighboring":[103],"via":[105],"time-varying":[107],"communication":[108],"networks":[109],"evaluate":[112],"joint":[114,154],"policy.":[115],"contrast,":[117],"in":[118,157,201],"each":[123],"agent":[124],"updates":[125],"its":[126,133],"local":[127],"parameter":[129],"solely":[130],"based":[131],"on":[132],"own":[134],"notation=\"LaTeX\">$Q$</tex-math></inline-formula>-function.":[139],"convergence":[142,149,168],"analysis,":[143],"first":[145],"establish":[146],"global":[148,167],"evaluation":[156],"Subsequently,":[162],"rigorously":[164],"demonstrate":[165],"overall":[171],"with":[177,195],"respect":[178],"function.":[182],"Finally,":[183],"effectiveness":[185],"proposed":[188],"demonstrated":[191],"by":[192],"comparing":[193],"it":[194],"centralized":[197],"through":[199],"simulation":[200],"robot":[203],"path":[204],"planning":[205],"environment.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}