{"id":"https://openalex.org/W4407466533","doi":"https://doi.org/10.1109/cac63892.2024.10864946","title":"An Improved WQMIX with Dual-Network and Dynamic Weights for Cooperative Multi-Agent Reinforcement Learning","display_name":"An Improved WQMIX with Dual-Network and Dynamic Weights for Cooperative Multi-Agent Reinforcement Learning","publication_year":2024,"publication_date":"2024-11-01","ids":{"openalex":"https://openalex.org/W4407466533","doi":"https://doi.org/10.1109/cac63892.2024.10864946"},"language":"en","primary_location":{"id":"doi:10.1109/cac63892.2024.10864946","doi":"https://doi.org/10.1109/cac63892.2024.10864946","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cac63892.2024.10864946","pdf_url":null,"source":{"id":"https://openalex.org/S4363604230","display_name":"China Automation Congress (CAC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 China Automation Congress (CAC)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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":null,"display_name":"Zhehan Xing","orcid":null,"observed_orcids":[]},"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"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhehan Xing","raw_affiliation_strings":["College of Auto. & AI Nanjing Univ. of Post. & Tele.,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Auto. & AI Nanjing Univ. of Post. & Tele.,Nanjing,China","institution_ids":["https://openalex.org/I41198531","https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107300921","display_name":"Jie Luo","orcid":"https://orcid.org/0009-0005-2948-9262","observed_orcids":["https://orcid.org/0009-0005-2948-9262"]},"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"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Luo","raw_affiliation_strings":["College of Auto. & AI Nanjing Univ. of Post. & Tele.,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Auto. & AI Nanjing Univ. of Post. & Tele.,Nanjing,China","institution_ids":["https://openalex.org/I41198531","https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103245915","display_name":"Hao Zhao","orcid":"https://orcid.org/0000-0002-6143-334X","observed_orcids":["https://orcid.org/0000-0002-6143-334X"]},"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"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zhao","raw_affiliation_strings":["College of Auto. & AI Nanjing Univ. of Post. & Tele.,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Auto. & AI Nanjing Univ. of Post. & Tele.,Nanjing,China","institution_ids":["https://openalex.org/I41198531","https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3171,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57782682,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3709","last_page":"3714"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.00019999999494757503,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/qmix","display_name":"QMIX","score":0.9620000123977661},{"id":"https://openalex.org/keywords/cooperative-multi-agent-reinforcement-learning","display_name":"cooperative multi-agent reinforcement learning","score":0.9459999799728394},{"id":"https://openalex.org/keywords/monotonicity-constraints","display_name":"monotonicity constraints","score":0.7979999780654907},{"id":"https://openalex.org/keywords/dynamic-weights","display_name":"dynamic weights","score":0.7929999828338623},{"id":"https://openalex.org/keywords/starcraft-multi-agent-challenge","display_name":"StarCraft Multi-Agent Challenge","score":0.7950000166893005}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8370075821876526},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.7041565179824829},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6948139071464539},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5002562999725342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3607960343360901},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1123228669166565},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cac63892.2024.10864946","doi":"https://doi.org/10.1109/cac63892.2024.10864946","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cac63892.2024.10864946","pdf_url":null,"source":{"id":"https://openalex.org/S4363604230","display_name":"China Automation Congress (CAC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 China Automation Congress (CAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2166533447","https://openalex.org/W2617547828","https://openalex.org/W2747213132","https://openalex.org/W2968526727","https://openalex.org/W3100789280"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"In":[0],"the":[1,26,36,63,115,119,132,137,161],"domain":[2],"of":[3,32,47,93,147],"cooperative":[4,178],"multi-agent":[5,71,163,177],"reinforcement":[6],"learning":[7,120],"(MARL),":[8],"QMIX":[9,100,173],"is":[10,77],"a":[11,57,104,125,143],"key":[12],"algorithm":[13],"that":[14,152,168],"facilitates":[15],"effective":[16],"collaboration":[17],"among":[18],"multiple":[19],"agents":[20],"by":[21,55,136],"enforcing":[22],"monotonicity":[23,33],"constraints":[24,54],"on":[25,131],"joint":[27,148],"Q-values.":[28],"However,":[29],"this":[30],"assumption":[31],"may":[34],"limit":[35],"algorithm's":[37,64],"capacity":[38],"to":[39,51,82,108,112],"explore":[40],"more":[41,109,144,182],"complex":[42,70,183],"strategies.":[43],"As":[44],"an":[45,90],"extension":[46],"QMIX,":[48],"WQMIX":[49,175],"attempts":[50],"relax":[52],"these":[53],"incorporating":[56],"weight":[58,75],"scheme,":[59],"aimed":[60],"at":[61],"enhancing":[62],"flexibility":[65],"and":[66,80,97,117,150,174],"efficiency":[67],"when":[68],"handling":[69],"interactions.":[72],"Nevertheless,":[73],"its":[74],"design":[76],"overly":[78],"simplistic":[79],"fails":[81],"fully":[83],"leverage":[84],"potential":[85],"performance.":[86],"This":[87],"paper":[88],"introduces":[89],"improved":[91],"version":[92],"WQMIX,":[94],"termed":[95],"Dual-Network":[96],"Dynamic":[98],"Weights":[99],"(DDWQMIX),":[101],"which":[102],"employs":[103],"dynamic":[105],"weights":[106],"strategy":[107],"flexibly":[110],"adapt":[111],"changes":[113],"in":[114,160,176,181],"environment":[116,166],"optimize":[118],"process.":[121],"Additionally,":[122],"DDWQMIX":[123,169],"integrates":[124],"dual-network":[126],"structure,":[127],"updating":[128],"targets":[129],"based":[130],"smaller":[133],"Q-values":[134,149],"produced":[135],"two":[138],"networks,":[139],"thus":[140],"allowing":[141],"for":[142],"accurate":[145],"estimation":[146],"ensuring":[151],"optimal":[153],"actions":[154],"are":[155],"not":[156],"missed.":[157],"Experiments":[158],"conducted":[159],"starcraft":[162],"challenge":[164],"(SMAC)":[165],"demonstrate":[167],"outperforms":[170],"traditional":[171],"VDN,":[172],"tasks,":[179],"particularly":[180],"scenarios.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-05T09:50:58.205359","created_date":"2025-10-10T00:00:00"}