{"id":"https://openalex.org/W4399968983","doi":"https://doi.org/10.1007/s44196-024-00560-2","title":"Multi-agent Gradient-Based Off-Policy Actor-Critic Algorithm for Distributed Reinforcement Learning","display_name":"Multi-agent Gradient-Based Off-Policy Actor-Critic Algorithm for Distributed Reinforcement Learning","publication_year":2024,"publication_date":"2024-06-24","ids":{"openalex":"https://openalex.org/W4399968983","doi":"https://doi.org/10.1007/s44196-024-00560-2"},"language":"en","primary_location":{"id":"doi:10.1007/s44196-024-00560-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44196-024-00560-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44196-024-00560-2.pdf","source":{"id":"https://openalex.org/S190680769","display_name":"International Journal of Computational Intelligence Systems","issn_l":"1875-6883","issn":["1875-6883","1875-6891"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computational Intelligence Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s44196-024-00560-2.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101405882","display_name":"Jineng Ren","orcid":"https://orcid.org/0000-0003-0174-9366"},"institutions":[{"id":"https://openalex.org/I146620803","display_name":"Wenzhou University","ror":"https://ror.org/020hxh324","country_code":"CN","type":"education","lineage":["https://openalex.org/I146620803"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jineng Ren","raw_affiliation_strings":["School of Computer Sciences and Artificial Intelligence & Artificial Intelligence and Advanced Manufacturing Institute (Yongjia), Wenzhou University, Chashan University Town, Wenzhou City, 325035, Zhejiang Province, China"],"raw_orcid":"https://orcid.org/0000-0003-0174-9366","affiliations":[{"raw_affiliation_string":"School of Computer Sciences and Artificial Intelligence & Artificial Intelligence and Advanced Manufacturing Institute (Yongjia), Wenzhou University, Chashan University Town, Wenzhou City, 325035, Zhejiang Province, China","institution_ids":["https://openalex.org/I146620803"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101405882"],"corresponding_institution_ids":["https://openalex.org/I146620803"],"apc_list":{"value":2090,"currency":"USD","value_usd":2090},"apc_paid":{"value":2090,"currency":"USD","value_usd":2090},"fwci":1.0255,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77709183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"17","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9997000098228455,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9977999925613403,"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":0.9144508838653564},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.7952703833580017},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7123257517814636},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6669331192970276},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6040221452713013},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6007715463638306},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5674216747283936},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.515868067741394},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.504463791847229},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4607992470264435},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3608208894729614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29947200417518616},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2009846270084381},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.1527768075466156}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9144508838653564},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.7952703833580017},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7123257517814636},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6669331192970276},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6040221452713013},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6007715463638306},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5674216747283936},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.515868067741394},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.504463791847229},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4607992470264435},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3608208894729614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29947200417518616},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2009846270084381},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.1527768075466156},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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":2,"locations":[{"id":"doi:10.1007/s44196-024-00560-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44196-024-00560-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44196-024-00560-2.pdf","source":{"id":"https://openalex.org/S190680769","display_name":"International Journal of Computational Intelligence Systems","issn_l":"1875-6883","issn":["1875-6883","1875-6891"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computational Intelligence Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:3fd1277c9b234751b5bfbbae5d5a0742","is_oa":true,"landing_page_url":"https://doaj.org/article/3fd1277c9b234751b5bfbbae5d5a0742","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal of Computational Intelligence Systems, Vol 17, Iss 1, Pp 1-18 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44196-024-00560-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44196-024-00560-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44196-024-00560-2.pdf","source":{"id":"https://openalex.org/S190680769","display_name":"International Journal of Computational Intelligence Systems","issn_l":"1875-6883","issn":["1875-6883","1875-6891"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computational Intelligence Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310638","display_name":"McGill University","ror":"https://ror.org/01pxwe438"},{"id":"https://openalex.org/F4320324806","display_name":"Wenzhou University","ror":"https://ror.org/020hxh324"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399968983.pdf"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1646707810","https://openalex.org/W2005525403","https://openalex.org/W2011393317","https://openalex.org/W2044212084","https://openalex.org/W2073460177","https://openalex.org/W2075268401","https://openalex.org/W2094387729","https://openalex.org/W2117905067","https://openalex.org/W2132351269","https://openalex.org/W2139418546","https://openalex.org/W2161305486","https://openalex.org/W2504148212","https://openalex.org/W2583993537","https://openalex.org/W2592641032","https://openalex.org/W2766447205","https://openalex.org/W2768629321","https://openalex.org/W2796829218","https://openalex.org/W2913326990","https://openalex.org/W3010758700","https://openalex.org/W3011272463","https://openalex.org/W3037849017","https://openalex.org/W3042045548","https://openalex.org/W3045760389","https://openalex.org/W3100944043","https://openalex.org/W3104243370","https://openalex.org/W3116610253","https://openalex.org/W3154784371","https://openalex.org/W4214881442","https://openalex.org/W4312277898","https://openalex.org/W4388948923","https://openalex.org/W6600339963","https://openalex.org/W6601883942"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W2768629321","https://openalex.org/W4384574988","https://openalex.org/W2130711276","https://openalex.org/W4321463377","https://openalex.org/W3088331655","https://openalex.org/W4308828368"],"abstract_inverted_index":{"Abstract":[0],"This":[1],"paper":[2],"proposes":[3],"a":[4,70],"gradient-based":[5],"multi-agent":[6,37,110],"actor-critic":[7,38],"algorithm":[8,17,82],"for":[9],"off-policy":[10,47,63],"reinforcement":[11],"learning":[12,52,67],"using":[13],"importance":[14],"sampling.":[15],"Our":[16],"is":[18],"incremental":[19],"with":[20,30,134],"full":[21],"gradients,":[22],"and":[23,53,93,129],"its":[24],"complexity":[25],"per":[26],"iteration":[27],"scales":[28],"linearly":[29],"the":[31,43,60,76,80,85,89,94,99,109,113,119,135],"size":[32],"of":[33,59,79,88,101,112,127],"approximation":[34],"features.":[35],"Previous":[36],"algorithms":[39],"are":[40],"limited":[41],"to":[42,84,98],"on-policy":[44],"setting":[45],"or":[46],"emphatic":[48],"temporal":[49,65],"difference":[50,66],"(TD)":[51],"they":[54],"do":[55],"not":[56],"take":[57],"advantage":[58],"advances":[61],"in":[62,125],"gradient":[64],"(GTD).":[68],"As":[69],"theoretical":[71],"contribution,":[72],"we":[73],"establish":[74],"that":[75,118],"critic":[77],"step":[78,96],"proposed":[81,120],"converges":[83,97],"TD":[86],"solution":[87],"projected":[90],"Bellman":[91],"equation":[92],"actor":[95],"set":[100],"asymptotically":[102],"stable":[103],"fixed":[104],"points.":[105],"Numerical":[106],"experiments":[107],"on":[108],"generalization":[111],"Boyan\u2019s":[114],"chain":[115],"problem":[116],"show":[117],"approach":[121],"provides":[122],"improved":[123],"performances":[124],"terms":[126],"stability":[128],"convergence":[130],"rate":[131],"as":[132],"compared":[133],"state-of-the-art":[136],"baseline":[137],"algorithm.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}