{"id":"https://openalex.org/W4414432313","doi":"https://doi.org/10.1109/case58245.2025.11163947","title":"Group-Based QMIX for Multi-Agent Reinforcement Learning","display_name":"Group-Based QMIX for Multi-Agent Reinforcement Learning","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4414432313","doi":"https://doi.org/10.1109/case58245.2025.11163947"},"language":"en","primary_location":{"id":"doi:10.1109/case58245.2025.11163947","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case58245.2025.11163947","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"},"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":"https://openalex.org/A5007959538","display_name":"Weixin Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixin Hong","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101748794","display_name":"Huaiyu Wu","orcid":"https://orcid.org/0000-0002-8089-7588"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaiyu Wu","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016539926","display_name":"Fang He","orcid":"https://orcid.org/0000-0003-2576-9978"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Fang","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045934908","display_name":"Zhen Shen","orcid":"https://orcid.org/0000-0002-9634-4945"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Shen","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100912910","display_name":"Yunjun Han","orcid":"https://orcid.org/0000-0003-1161-4721"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunjun Han","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076992681","display_name":"Yisheng Lv","orcid":"https://orcid.org/0000-0002-7565-4979"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yisheng Lv","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115601598","display_name":"Gang Xiong","orcid":"https://orcid.org/0000-0002-3190-6521"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Xiong","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"650","last_page":"655"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.3758000135421753,"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":0.3758000135421753,"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":0.821399986743927},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.52920001745224},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4876999855041504},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4706999957561493},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.4375999867916107},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.36469998955726624},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.3546000123023987}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.821399986743927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6391000151634216},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.52920001745224},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5170000195503235},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4876999855041504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47510001063346863},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4706999957561493},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.4375999867916107},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.36469998955726624},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33169999718666077},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.2766999900341034},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.26429998874664307},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/case58245.2025.11163947","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case58245.2025.11163947","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"multi-agent":[1,21,61,188],"reinforcement":[2,189],"learning":[3,57,145,190],"environments,":[4],"value":[5,22,48,81,122,160],"decomposition":[6,23,49,123],"methods":[7,70,191],"are":[8,51],"popularly":[9],"applied":[10],"to":[11,38,54,73,104,119],"address":[12,90],"the":[13,25,64,76,79,91,133,144,147,155,159,177],"cooperation":[14],"issue":[15],"among":[16],"agents.":[17],"However,":[18],"in":[19,75,84,140,150,192],"some":[20],"methods,":[24],"global":[26,126],"action-value":[27],"is":[28,169],"usually":[29],"approximated":[30],"using":[31],"upper":[32],"and":[33,36,128,153,196],"lower":[34],"bounds,":[35],"leads":[37],"a":[39,97],"lack":[40],"of":[41,66,78,135,146,158,194],"fine-grained":[42],"cooperative":[43,56,87],"actions.":[44],"Furthermore,":[45],"current":[46],"state-of-the-art":[47],"approaches":[50],"predominantly":[52],"confined":[53],"addressing":[55],"problems":[58],"involving":[59],"small-scale":[60],"systems.":[62],"As":[63],"number":[65],"agents":[67,107,136],"increases,":[68],"these":[69],"may":[71],"lead":[72],"difficulties":[74],"convergence":[77,156,195],"Q":[80],"function":[82],"especially":[83],"more":[85],"complex":[86,151],"scenarios.":[88],"To":[89],"above":[92],"two":[93],"challenges,":[94],"we":[95],"propose":[96],"Group-based":[98],"QMIX":[99],"(GQMIX)":[100],"method":[101],"which":[102],"learns":[103],"dynamically":[105],"divide":[106],"into":[108,137],"multiple":[109],"groups":[110,139],"during":[111],"exploration":[112],"while":[113],"applying":[114],"Graph":[115],"Attention":[116],"Network":[117],"(GAT)":[118],"simultaneously":[120],"learn":[121],"under":[124],"both":[125],"observation":[127],"local":[129],"observation.":[130],"This":[131],"enables":[132],"subdivision":[134],"different":[138],"large-scale":[141],"settings,":[142],"allowing":[143],"common":[148],"subtasks":[149],"scenarios":[152],"improving":[154],"efficiency":[157],"function.":[161],"Experimental":[162],"results":[163],"demonstrate":[164],"that":[165],"our":[166],"proposed":[167],"algorithm":[168],"valid":[170],"by":[171],"providing":[172],"better":[173],"scheduling":[174,182],"solutions":[175],"for":[176],"extended":[178],"flexible":[179],"job":[180],"shop":[181],"problem.":[183],"And":[184],"it":[185],"outperforms":[186],"existing":[187],"terms":[193],"stability.":[197]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}