{"id":"https://openalex.org/W4393241368","doi":"https://doi.org/10.1109/tsmc.2024.3370186","title":"SQIX: QMIX Algorithm Activated by General Softmax Operator for Cooperative Multiagent Reinforcement Learning","display_name":"SQIX: QMIX Algorithm Activated by General Softmax Operator for Cooperative Multiagent Reinforcement Learning","publication_year":2024,"publication_date":"2024-03-27","ids":{"openalex":"https://openalex.org/W4393241368","doi":"https://doi.org/10.1109/tsmc.2024.3370186"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2024.3370186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2024.3370186","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","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/A5100357898","display_name":"Miaomiao Zhang","orcid":"https://orcid.org/0000-0001-9921-6511"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Miaomiao Zhang","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070954480","display_name":"Wei Tong","orcid":"https://orcid.org/0000-0002-8558-1822"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Tong","raw_affiliation_strings":["College of Automation &#x0026; Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, China","College of Automation and Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Automation &#x0026; Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"College of Automation and Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072445822","display_name":"Guangyu Zhu","orcid":"https://orcid.org/0009-0008-1467-1776"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyu Zhu","raw_affiliation_strings":["Beijing Research Center of Urban Traffic Information Sensing and Service Technologies, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Research Center of Urban Traffic Information Sensing and Service Technologies, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053112608","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-3238-745X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xu","raw_affiliation_strings":["School of Intelligent Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Intelligent Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110956301","display_name":"Edmond Q. Wu","orcid":"https://orcid.org/0000-0003-1301-9870"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Edmond Q. Wu","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100357898"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":4.7811,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.95378978,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"54","issue":"11","first_page":"6550","last_page":"6560"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9702000021934509,"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":0.9702000021934509,"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/softmax-function","display_name":"Softmax function","score":0.9441359043121338},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8149404525756836},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5989198684692383},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.570824146270752},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5633035898208618},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44912979006767273},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4462170898914337},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12628036737442017},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.07309415936470032},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.06905627250671387},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.05419278144836426}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.9441359043121338},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8149404525756836},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5989198684692383},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.570824146270752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5633035898208618},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44912979006767273},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4462170898914337},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12628036737442017},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07309415936470032},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.06905627250671387},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.05419278144836426},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmc.2024.3370186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2024.3370186","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G241012663","display_name":null,"funder_award_id":"62171274","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5886903507","display_name":null,"funder_award_id":"T2325018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8335343387","display_name":null,"funder_award_id":"U2241228","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8880411100","display_name":null,"funder_award_id":"62272036","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W206679605","https://openalex.org/W2107726111","https://openalex.org/W2522489477","https://openalex.org/W2617547828","https://openalex.org/W2746553466","https://openalex.org/W2897007254","https://openalex.org/W3100789280","https://openalex.org/W3166816823","https://openalex.org/W3173211893","https://openalex.org/W3206103164","https://openalex.org/W4220726597","https://openalex.org/W4283647312","https://openalex.org/W4285132031","https://openalex.org/W4287310023","https://openalex.org/W4292973120","https://openalex.org/W4293183440","https://openalex.org/W4311409157","https://openalex.org/W4312495133","https://openalex.org/W4312550876","https://openalex.org/W4312616886","https://openalex.org/W4312790244","https://openalex.org/W4324291189","https://openalex.org/W4327809167","https://openalex.org/W4361861314","https://openalex.org/W4375929017","https://openalex.org/W4376166839","https://openalex.org/W4379382600","https://openalex.org/W4383504005","https://openalex.org/W4386065468","https://openalex.org/W4386824832","https://openalex.org/W6637967152","https://openalex.org/W6684921986","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6743367460","https://openalex.org/W6748839928","https://openalex.org/W6755069753","https://openalex.org/W6758846586","https://openalex.org/W6762358693","https://openalex.org/W6762491519","https://openalex.org/W6766805167","https://openalex.org/W6768731700","https://openalex.org/W6784938585","https://openalex.org/W6787397593","https://openalex.org/W6791040878","https://openalex.org/W6795826604","https://openalex.org/W6796991022","https://openalex.org/W6847213728"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W4226420367","https://openalex.org/W2980176872","https://openalex.org/W2962876041","https://openalex.org/W3090555870","https://openalex.org/W3108503355","https://openalex.org/W2249953602","https://openalex.org/W2801655600","https://openalex.org/W2912971006"],"abstract_inverted_index":{"Multiagent":[0],"cooperative":[1,154],"systems":[2],"can":[3],"be":[4],"used":[5],"to":[6,55,70,77,109,159,175],"conceptualize":[7],"many":[8],"real-world":[9],"problems.":[10],"Reinforcement":[11],"learning":[12,35,75],"is":[13],"a":[14,38,86,105],"particularly":[15],"effective":[16],"tool.":[17],"The":[18,61],"issue":[19],"of":[20,40,58,63,94,139,170],"bias":[21,126],"in":[22,32,49,67,127],"<inline-formula":[23],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[24],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[25],"<tex-math":[26],"notation=\"LaTeX\">$Q$</tex-math>":[27],"</inline-formula>":[28],"-function":[29],"value":[30,96,113],"estimation":[31],"single-agent":[33,73],"reinforcement":[34,51,74],"has":[36],"garnered":[37],"lot":[39],"interest":[41],"and":[42,89],"substantial":[43],"study.":[44],"Indeed,":[45],"this":[46,82,119],"challenge":[47],"endures":[48],"multiagent":[50,79,153],"learning,":[52],"primarily":[53],"owing":[54],"the":[56,64,68,92,101,123,128,135,140,145,171],"inclusion":[57],"maximization":[59,102],"operations.":[60],"crux":[62],"matter":[65],"lies":[66],"inability":[69],"seamlessly":[71],"extrapolate":[72],"algorithms":[76],"their":[78],"counterparts.":[80],"In":[81],"article,":[83],"we":[84],"introduce":[85],"more":[87,111],"encompassing":[88],"straightforward":[90],"principle:":[91],"notion":[93],"appropriate":[95],"correction.":[97],"We":[98,115],"suggest":[99],"replacing":[100],"operation":[103,120],"with":[104],"monotonically":[106],"nondecreasing":[107],"function":[108],"obtain":[110],"accurate":[112],"estimates.":[114],"theoretically":[116],"demonstrate":[117],"that":[118],"effectively":[121],"reduces":[122],"potential":[124],"overestimation":[125],"QMIX":[129,141],"algorithm.":[130],"Ultimately,":[131],"our":[132],"methodology,":[133],"dubbed":[134],"SMIX":[136],"algorithm\u2014a":[137],"fusion":[138],"algorithm":[142],"empowered":[143],"by":[144],"Softmax":[146],"operator,":[147],"attains":[148],"state-of-the-art":[149],"outcomes":[150],"across":[151],"diverse":[152],"tasks.":[155],"This":[156],"success":[157],"extends":[158],"challenging":[160],"domains":[161],"such":[162],"as":[163,168],"StarCraft":[164],"II,":[165],"marking":[166],"it":[167],"one":[169],"most":[172],"formidable":[173],"games":[174],"date.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":4}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}