{"id":"https://openalex.org/W4226401293","doi":"https://doi.org/10.1007/s11424-025-4426-7","title":"Distributed Policy Gradient with Variance Reduction in Multi-Agent Reinforcement Learning","display_name":"Distributed Policy Gradient with Variance Reduction in Multi-Agent Reinforcement Learning","publication_year":2025,"publication_date":"2025-08-06","ids":{"openalex":"https://openalex.org/W4226401293","doi":"https://doi.org/10.1007/s11424-025-4426-7"},"language":"en","primary_location":{"id":"doi:10.1007/s11424-025-4426-7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11424-025-4426-7","pdf_url":null,"source":{"id":"https://openalex.org/S45848134","display_name":"Journal of Systems Science and Complexity","issn_l":"1009-6124","issn":["1009-6124","1559-7067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Systems Science and Complexity","raw_type":"journal-article"},"type":"preprint","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/A5114752761","display_name":"Xiaoxiao Zhao","orcid":"https://orcid.org/0000-0002-9125-465X"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoxiao Zhao","raw_affiliation_strings":["Department of Control Science and Engineering, Tongji University, Shanghai, 201804, China","Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, 201210, China"],"affiliations":[{"raw_affiliation_string":"Department of Control Science and Engineering, Tongji University, Shanghai, 201804, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, 201210, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102966230","display_name":"Jinlong Lei","orcid":"https://orcid.org/0000-0003-1581-8932"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinlong Lei","raw_affiliation_strings":["Department of Control Science and Engineering, Tongji University, Shanghai, 201804, China","Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, 201210, China"],"affiliations":[{"raw_affiliation_string":"Department of Control Science and Engineering, Tongji University, Shanghai, 201804, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, 201210, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361244","display_name":"Li Li","orcid":"https://orcid.org/0000-0002-7654-7374"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":["Department of Control Science and Engineering, Tongji University, Shanghai, 201804, China","Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, 201210, China"],"affiliations":[{"raw_affiliation_string":"Department of Control Science and Engineering, Tongji University, Shanghai, 201804, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, 201210, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lucian Busoniu","orcid":null},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Lucian Busoniu","raw_affiliation_strings":["Department of Automation, Technical University of Cluj-Napoca, Memorandumului 28, 400114, Cluj-Napoca, Romania"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Technical University of Cluj-Napoca, Memorandumului 28, 400114, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jia Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Xu","raw_affiliation_strings":["Department of Control Science and Engineering, Tongji University, Shanghai, 201804, China","Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, 201210, China"],"affiliations":[{"raw_affiliation_string":"Department of Control Science and Engineering, Tongji University, Shanghai, 201804, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, 201210, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5114752761"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00071301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":"5","first_page":"1853","last_page":"1886"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9187999963760376,"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"}},"topics":[{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9187999963760376,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8033277988433838},{"id":"https://openalex.org/keywords/variance-reduction","display_name":"Variance reduction","score":0.6878708600997925},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6245243549346924},{"id":"https://openalex.org/keywords/stationary-point","display_name":"Stationary point","score":0.5813065767288208},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.5546252131462097},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5496375560760498},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5344791412353516},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35230082273483276},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.32588624954223633},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.15415015816688538},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14851605892181396},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10974982380867004},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.086710125207901}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8033277988433838},{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.6878708600997925},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6245243549346924},{"id":"https://openalex.org/C189237950","wikidata":"https://www.wikidata.org/wiki/Q2500758","display_name":"Stationary point","level":2,"score":0.5813065767288208},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.5546252131462097},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5496375560760498},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5344791412353516},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35230082273483276},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.32588624954223633},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.15415015816688538},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14851605892181396},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10974982380867004},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.086710125207901},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11424-025-4426-7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11424-025-4426-7","pdf_url":null,"source":{"id":"https://openalex.org/S45848134","display_name":"Journal of Systems Science and Complexity","issn_l":"1009-6124","issn":["1009-6124","1559-7067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Systems Science and Complexity","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1571416372","https://openalex.org/W1973183176","https://openalex.org/W2094387729","https://openalex.org/W2099618002","https://openalex.org/W2144446635","https://openalex.org/W2144672231","https://openalex.org/W2763533254","https://openalex.org/W2806414180","https://openalex.org/W2908261578","https://openalex.org/W2941971445","https://openalex.org/W2962764167","https://openalex.org/W2963156201","https://openalex.org/W2981038142","https://openalex.org/W2982316857","https://openalex.org/W2991046523","https://openalex.org/W2991772480","https://openalex.org/W3011252985","https://openalex.org/W3023368031","https://openalex.org/W3023944502","https://openalex.org/W3027121709","https://openalex.org/W3047780503","https://openalex.org/W3209874641","https://openalex.org/W4241811150","https://openalex.org/W4360584446","https://openalex.org/W4389579959","https://openalex.org/W4399535836","https://openalex.org/W6600120041"],"related_works":["https://openalex.org/W1279312","https://openalex.org/W1356373","https://openalex.org/W1290750","https://openalex.org/W3412817","https://openalex.org/W15494768","https://openalex.org/W156643","https://openalex.org/W1938335","https://openalex.org/W9323111","https://openalex.org/W8245103","https://openalex.org/W13926841"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2022-05-05T00:00:00"}
