{"id":"https://openalex.org/W4224990480","doi":"https://doi.org/10.1142/s0218001422520140","title":"Actor-Critic for Multi-Agent Reinforcement Learning with Self-Attention","display_name":"Actor-Critic for Multi-Agent Reinforcement Learning with Self-Attention","publication_year":2022,"publication_date":"2022-04-28","ids":{"openalex":"https://openalex.org/W4224990480","doi":"https://doi.org/10.1142/s0218001422520140"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001422520140","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001422520140","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and 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/A5101933531","display_name":"Juan Zhao","orcid":"https://orcid.org/0000-0002-5005-0036"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juan Zhao","raw_affiliation_strings":["Department of Mechanical and Electrical Engineering, Henan Industrial and Trade Vocational College, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Electrical Engineering, Henan Industrial and Trade Vocational College, Zhengzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075171995","display_name":"Tong Zhu","orcid":"https://orcid.org/0000-0003-0066-0108"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tong Zhu","raw_affiliation_strings":["Zhengzhou Coal Industry (Group) Co., Ltd, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhengzhou Coal Industry (Group) Co., Ltd, Zhengzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001891274","display_name":"Shuo Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuo Xiao","raw_affiliation_strings":["School of Computer Sciences and Technology, China University of Mining & Technology, Xuzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Sciences and Technology, China University of Mining & Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043968140","display_name":"Zongqian Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongqian Gao","raw_affiliation_strings":["School of Computer Sciences and Technology, China University of Mining & Technology, Xuzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Sciences and Technology, China University of Mining & Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100359490","display_name":"Hao Sun","orcid":"https://orcid.org/0000-0002-6315-4838"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Sun","raw_affiliation_strings":["School of Computer Sciences and Technology, China University of Mining & Technology, Xuzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Sciences and Technology, China University of Mining & Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5001891274"],"corresponding_institution_ids":["https://openalex.org/I25757504"],"apc_list":null,"apc_paid":null,"fwci":1.1104,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.81017061,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"36","issue":"09","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9377999901771545,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9104999899864197,"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":0.9153423309326172},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8093757629394531},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6497079730033875},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.567660927772522},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4609085023403168},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4181345999240875},{"id":"https://openalex.org/keywords/intelligent-agent","display_name":"Intelligent agent","score":0.41117969155311584},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39813539385795593}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9153423309326172},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8093757629394531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6497079730033875},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.567660927772522},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4609085023403168},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4181345999240875},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.41117969155311584},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39813539385795593},{"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:10.1142/s0218001422520140","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001422520140","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/1","display_name":"No poverty"}],"awards":[{"id":"https://openalex.org/G2102075816","display_name":null,"funder_award_id":"KC20167","funder_id":"https://openalex.org/F4320336657","funder_display_name":"Xuzhou Science and Technology Program"},{"id":"https://openalex.org/G3813728118","display_name":null,"funder_award_id":"62071470","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G633339172","display_name":null,"funder_award_id":"61971421","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/F4320336657","display_name":"Xuzhou Science and Technology Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1561533740","https://openalex.org/W1994923984","https://openalex.org/W2054339854","https://openalex.org/W2107112577","https://openalex.org/W2145339207","https://openalex.org/W2751604774","https://openalex.org/W2768629321","https://openalex.org/W2802832243","https://openalex.org/W2913674227","https://openalex.org/W2933871090","https://openalex.org/W2958727589","https://openalex.org/W2959675909","https://openalex.org/W4206759694"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2024136090","https://openalex.org/W2108086216","https://openalex.org/W1515650145"],"abstract_inverted_index":{"The":[0],"rapid":[1],"development":[2],"of":[3,25,50,91,100,103,118,125,130,149,186,212],"deep":[4,34,61,72,195],"reinforcement":[5,35,62,73,196],"learning":[6,36,63,74,197],"makes":[7],"it":[8,94,133,205],"widely":[9],"used":[10],"in":[11,152,214],"multi-agent":[12,17,26,71,194],"environments":[13],"to":[14,22,38,56,106,136,141,160],"solve":[15,97],"the":[16,23,28,48,58,70,79,87,92,98,110,116,123,126,138,142,147,157,162,166,187,192,210,215],"cooperation":[18],"problem.":[19],"However,":[20],"due":[21,105],"instability":[24],"environments,":[27],"performance":[29],"is":[30,134],"insufficient":[31],"when":[32,209],"using":[33,121],"algorithms":[37,104],"train":[39],"each":[40],"agent":[41,170],"independently.":[42],"In":[43],"this":[44],"work,":[45],"we":[46,113,155],"use":[47,156],"framework":[49],"centralized":[51,119],"training":[52],"with":[53,175,191],"decentralized":[54],"execution":[55],"extend":[57],"maximum":[59,80],"entropy":[60,81],"algorithm":[64,75],"Soft":[65],"Actor-Critic":[66],"(SAC)":[67],"and":[68,132,164,181],"proposes":[69],"MASAC":[76],"based":[77],"on":[78],"framework.":[82],"Proposed":[83],"model":[84],"treats":[85],"all":[86,122],"agents":[88,127,177,213],"as":[89,128,184],"part":[90,185],"environment,":[93],"can":[95,171],"effectively":[96],"problem":[99],"poor":[101],"convergence":[102,202],"environmental":[107],"instability.":[108],"At":[109],"same":[111],"time,":[112],"have":[114],"noticed":[115],"shortcoming":[117],"training,":[120],"information":[124,139],"input":[129],"critics,":[131],"easy":[135],"lose":[137],"related":[140],"current":[143],"agent.":[144],"Inspired":[145],"by":[146],"application":[148],"self-attention":[150,158],"mechanism":[151,159],"machine":[153],"translation,":[154],"improve":[161],"critic":[163,188],"propose":[165],"ATT-MASAC":[167,199],"algorithm.":[168],"Each":[169],"discover":[172],"their":[173],"relationship":[174],"other":[176],"through":[178],"encoder":[179],"operation":[180],"attention":[182],"calculation":[183],"networks.":[189],"Compared":[190],"recent":[193],"algorithms,":[198],"has":[200,206],"better":[201,207],"effect.":[203],"Also,":[204],"stability":[208],"number":[211],"environment":[216],"increases.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
