{"id":"https://openalex.org/W4400590075","doi":"https://doi.org/10.1007/s40747-024-01529-6","title":"A distributed adaptive policy gradient method based on momentum for multi-agent reinforcement learning","display_name":"A distributed adaptive policy gradient method based on momentum for multi-agent reinforcement learning","publication_year":2024,"publication_date":"2024-07-12","ids":{"openalex":"https://openalex.org/W4400590075","doi":"https://doi.org/10.1007/s40747-024-01529-6"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-024-01529-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-024-01529-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01529-6.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex &amp; Intelligent 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/s40747-024-01529-6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011981862","display_name":"Junru Shi","orcid":"https://orcid.org/0000-0002-6449-1588"},"institutions":[{"id":"https://openalex.org/I167383011","display_name":"Henan University of Science and Technology","ror":"https://ror.org/05d80kz58","country_code":"CN","type":"education","lineage":["https://openalex.org/I167383011"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junru Shi","raw_affiliation_strings":["The School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China","institution_ids":["https://openalex.org/I167383011"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001636340","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0002-7552-455X"},"institutions":[{"id":"https://openalex.org/I11406153","display_name":"Shanghai International Studies University","ror":"https://ror.org/01bn89z48","country_code":"CN","type":"education","lineage":["https://openalex.org/I11406153"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xin Wang","raw_affiliation_strings":["The School of Business and Management, Shanghai International Studies University, Shanghai, 200083, China"],"raw_orcid":"https://orcid.org/0000-0002-7552-455X","affiliations":[{"raw_affiliation_string":"The School of Business and Management, Shanghai International Studies University, Shanghai, 200083, China","institution_ids":["https://openalex.org/I11406153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087014857","display_name":"Mingchuan Zhang","orcid":"https://orcid.org/0000-0002-2523-1089"},"institutions":[{"id":"https://openalex.org/I167383011","display_name":"Henan University of Science and Technology","ror":"https://ror.org/05d80kz58","country_code":"CN","type":"education","lineage":["https://openalex.org/I167383011"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingchuan Zhang","raw_affiliation_strings":["The School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China","institution_ids":["https://openalex.org/I167383011"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040868833","display_name":"Muhua Liu","orcid":"https://orcid.org/0000-0002-4707-1354"},"institutions":[{"id":"https://openalex.org/I167383011","display_name":"Henan University of Science and Technology","ror":"https://ror.org/05d80kz58","country_code":"CN","type":"education","lineage":["https://openalex.org/I167383011"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Muhua Liu","raw_affiliation_strings":["The School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China","institution_ids":["https://openalex.org/I167383011"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050705532","display_name":"Junlong Zhu","orcid":"https://orcid.org/0000-0002-6411-7035"},"institutions":[{"id":"https://openalex.org/I167383011","display_name":"Henan University of Science and Technology","ror":"https://ror.org/05d80kz58","country_code":"CN","type":"education","lineage":["https://openalex.org/I167383011"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junlong Zhu","raw_affiliation_strings":["The School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China","institution_ids":["https://openalex.org/I167383011"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080439384","display_name":"Qingtao Wu","orcid":"https://orcid.org/0000-0003-1572-5293"},"institutions":[{"id":"https://openalex.org/I167383011","display_name":"Henan University of Science and Technology","ror":"https://ror.org/05d80kz58","country_code":"CN","type":"education","lineage":["https://openalex.org/I167383011"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingtao Wu","raw_affiliation_strings":["The School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China","institution_ids":["https://openalex.org/I167383011"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001636340"],"corresponding_institution_ids":["https://openalex.org/I11406153"],"apc_list":{"value":1320,"currency":"GBP","value_usd":1619},"apc_paid":{"value":1320,"currency":"GBP","value_usd":1619},"fwci":1.3245,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.83327582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"10","issue":"5","first_page":"7297","last_page":"7310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9958999752998352,"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/T12676","display_name":"Machine Learning and ELM","score":0.9937999844551086,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7537041306495667},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6299275755882263},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6194062829017639},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5661780834197998},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.47795653343200684},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4632687568664551},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4569379389286041},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.07129913568496704}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7537041306495667},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6299275755882263},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6194062829017639},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5661780834197998},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.47795653343200684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4632687568664551},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4569379389286041},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.07129913568496704},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s40747-024-01529-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-024-01529-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01529-6.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex &amp; Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:6396ec8713a04f02822c1906e004b340","is_oa":true,"landing_page_url":"https://doaj.org/article/6396ec8713a04f02822c1906e004b340","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complex & Intelligent Systems, Vol 10, Iss 5, Pp 7297-7310 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40747-024-01529-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-024-01529-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01529-6.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex &amp; Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1413938862","display_name":null,"funder_award_id":"61976243","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G214799685","display_name":null,"funder_award_id":"72371164","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":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4400590075.pdf"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W178169250","https://openalex.org/W1583837637","https://openalex.org/W2047152541","https://openalex.org/W2119717200","https://openalex.org/W2144446635","https://openalex.org/W2602856279","https://openalex.org/W2766447205","https://openalex.org/W2768629321","https://openalex.org/W2788125442","https://openalex.org/W2883364792","https://openalex.org/W2905810301","https://openalex.org/W2913326990","https://openalex.org/W2963470657","https://openalex.org/W3103752844","https://openalex.org/W3163894240","https://openalex.org/W3173294282","https://openalex.org/W3173589300","https://openalex.org/W4200635498","https://openalex.org/W4210623715","https://openalex.org/W4296335812","https://openalex.org/W4308889875","https://openalex.org/W4312720137","https://openalex.org/W4363649062","https://openalex.org/W4387441922","https://openalex.org/W4387441942","https://openalex.org/W4387452262"],"related_works":["https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"Abstract":[0],"Policy":[1],"Gradient":[2],"(PG)":[3],"method":[4],"is":[5,104,134],"one":[6],"of":[7,20,56,78,86,110,126,132],"the":[8,52,76,83,87,108,124,130,138],"most":[9],"popular":[10],"algorithms":[11],"in":[12,25,99],"Reinforcement":[13],"Learning":[14],"(RL).":[15],"However,":[16],"distributed":[17,34,119],"adaptive":[18,35],"variants":[19],"PG":[21,120],"are":[22,97],"rarely":[23],"studied":[24],"multi-agent.":[26],"For":[27],"this":[28,30],"reason,":[29],"paper":[31],"proposes":[32],"a":[33,100,105],"policy":[36,90],"gradient":[37,91],"algorithm":[38],"(IS-DAPGM)":[39],"incorporated":[40],"with":[41,116],"Adam-type":[42],"updates":[43],"and":[44,122],"importance":[45],"sampling":[46],"technique.":[47],"Furthermore,":[48],"we":[49,128],"also":[50],"establish":[51],"theoretical":[53],"convergence":[54,84],"rate":[55,85],"$$\\mathcal":[57],"{O}(1/\\sqrt{T})$$":[58],"<mml:math":[59],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\">":[60],"<mml:mrow>":[61],"<mml:mi>O</mml:mi>":[62],"<mml:mo>(</mml:mo>":[63],"<mml:mn>1</mml:mn>":[64],"<mml:mo>/</mml:mo>":[65],"<mml:msqrt>":[66],"<mml:mi>T</mml:mi>":[67],"</mml:msqrt>":[68],"<mml:mo>)</mml:mo>":[69],"</mml:mrow>":[70],"</mml:math>":[71],",":[72],"where":[73],"T":[74],"represents":[75],"number":[77,125],"iterations,":[79],"it":[80],"can":[81],"match":[82],"state-of-the-art":[88],"centralized":[89],"methods.":[92,140],"In":[93],"addition,":[94],"many":[95],"experiments":[96],"conducted":[98],"multi-agent":[101],"environment,":[102],"which":[103],"modification":[106],"on":[107],"basis":[109],"Particle":[111],"world":[112],"environment.":[113],"By":[114],"comparing":[115],"some":[117],"other":[118],"methods":[121],"changing":[123],"agents,":[127],"verify":[129],"performance":[131],"IS-DAPGM":[133],"more":[135],"efficient":[136],"than":[137],"existing":[139]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
