{"id":"https://openalex.org/W7147548045","doi":"https://doi.org/10.1109/jas.2025.125666","title":"QuadQ: Quadratic-Based Value Decomposition for Cooperative Policy Optimization in Multi-Agent Reinforcement Learning","display_name":"QuadQ: Quadratic-Based Value Decomposition for Cooperative Policy Optimization in Multi-Agent Reinforcement Learning","publication_year":2026,"publication_date":"2026-03-01","ids":{"openalex":"https://openalex.org/W7147548045","doi":"https://doi.org/10.1109/jas.2025.125666"},"language":null,"primary_location":{"id":"doi:10.1109/jas.2025.125666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jas.2025.125666","pdf_url":null,"source":{"id":"https://openalex.org/S2484288132","display_name":"IEEE/CAA Journal of Automatica Sinica","issn_l":"2329-9266","issn":["2329-9266","2329-9274"],"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/CAA Journal of Automatica Sinica","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/A5132650748","display_name":"Siying Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siying Wang","raw_affiliation_strings":["School of Automation Engineering, University of Electronic Science and Technology of China,Chengdu,China,611731"],"raw_orcid":"https://orcid.org/0000-0002-3180-0815","affiliations":[{"raw_affiliation_string":"School of Automation Engineering, University of Electronic Science and Technology of China,Chengdu,China,611731","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132652777","display_name":"Ruoning Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruoning Zhang","raw_affiliation_strings":["School of Computer Science and Engineering (School of Cyber Security), University of Electronic Science and Technology of China,Chengdu,China,611731"],"raw_orcid":"https://orcid.org/0009-0006-5442-6148","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering (School of Cyber Security), University of Electronic Science and Technology of China,Chengdu,China,611731","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Zhou","orcid":"https://orcid.org/0009-0009-6141-2133"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zhou","raw_affiliation_strings":["School of Computer Science and Engineering (School of Cyber Security), University of Electronic Science and Technology of China,Chengdu,China,611731"],"raw_orcid":"https://orcid.org/0009-0009-6141-2133","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering (School of Cyber Security), University of Electronic Science and Technology of China,Chengdu,China,611731","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132572434","display_name":"Jinliang Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinliang Shao","raw_affiliation_strings":["School of Automation Engineering, University of Electronic Science and Technology of China,Chengdu,611731"],"raw_orcid":"https://orcid.org/0000-0002-2508-7451","affiliations":[{"raw_affiliation_string":"School of Automation Engineering, University of Electronic Science and Technology of China,Chengdu,611731","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yuhua Cheng","orcid":"https://orcid.org/0000-0001-9756-4387"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhua Cheng","raw_affiliation_strings":["School of Automation Engineering, University of Electronic Science and Technology of China,Chengdu,China,611731"],"raw_orcid":"https://orcid.org/0000-0001-9756-4387","affiliations":[{"raw_affiliation_string":"School of Automation Engineering, University of Electronic Science and Technology of China,Chengdu,China,611731","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36476779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":"3","first_page":"728","last_page":"730"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7912999987602234,"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":0.7912999987602234,"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":0.10350000113248825,"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/T11413","display_name":"Risk and Portfolio Optimization","score":0.006599999964237213,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7475000023841858},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.6291999816894531},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5684999823570251},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.5608000159263611},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5167999863624573},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.46230000257492065},{"id":"https://openalex.org/keywords/decomposition-method","display_name":"Decomposition method (queueing theory)","score":0.3659000098705292}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7475000023841858},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6628000140190125},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.6291999816894531},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5810999870300293},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5684999823570251},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.5608000159263611},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5167999863624573},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.46230000257492065},{"id":"https://openalex.org/C2778258933","wikidata":"https://www.wikidata.org/wiki/Q16918986","display_name":"Decomposition method (queueing theory)","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.3653999865055084},{"id":"https://openalex.org/C81845259","wikidata":"https://www.wikidata.org/wiki/Q290117","display_name":"Quadratic programming","level":2,"score":0.36039999127388},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C166437778","wikidata":"https://www.wikidata.org/wiki/Q50695","display_name":"Quadratic function","level":3,"score":0.3522999882698059},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.3264000117778778},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30550000071525574},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2808000147342682},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jas.2025.125666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jas.2025.125666","pdf_url":null,"source":{"id":"https://openalex.org/S2484288132","display_name":"IEEE/CAA Journal of Automatica Sinica","issn_l":"2329-9266","issn":["2329-9266","2329-9274"],"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/CAA Journal of Automatica Sinica","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5426960617","display_name":null,"funder_award_id":"62273077","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7487646668","display_name":null,"funder_award_id":"2024NSFJQ0013","funder_id":"https://openalex.org/F4320329861","funder_display_name":"Natural Science Foundation of Sichuan Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329861","display_name":"Natural Science Foundation of Sichuan Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2807741983","https://openalex.org/W2913662073","https://openalex.org/W3212907084","https://openalex.org/W4205294007","https://openalex.org/W4313642983","https://openalex.org/W4388579570","https://openalex.org/W4393156820"],"related_works":[],"abstract_inverted_index":{"Dear":[0],"Editor,":[1],"This":[2],"letter":[3],"introduces":[4],"a":[5,11,32,45,63,86],"value":[6,65],"decomposition":[7,66],"method":[8,110],"based":[9],"on":[10,58],"quadratic":[12,33,61],"function":[13,34,43],"for":[14],"multi-agent":[15],"reinforcement":[16],"learning,":[17],"aiming":[18],"to":[19,70,91],"derive":[20],"cooperative":[21,73],"policies":[22],"among":[23],"agents":[24],"modeled":[25],"by":[26],"artificial":[27],"neural":[28],"networks.":[29],"By":[30],"constructing":[31],"with":[35,80],"specific":[36],"parameter":[37],"constraints,":[38],"it":[39],"ensures":[40],"that":[41],"the":[42,49,77,93,96,105,108],"achieves":[44],"global":[46],"maximum":[47],"when":[48],"local":[50],"optimal":[51,72],"actions":[52],"are":[53],"used":[54],"as":[55],"inputs.":[56],"Based":[57],"this":[59],"structured":[60],"function,":[62],"novel":[64],"algorithm":[67],"is":[68,89],"proposed":[69,109],"facilitate":[71],"policy":[74],"training":[75,79],"within":[76],"centralized":[78],"decentralized":[81],"execution":[82],"(CTDE)":[83],"framework.":[84],"Furthermore,":[85],"theoretical":[87],"analysis":[88],"provided":[90],"guarantee":[92],"satisfaction":[94],"of":[95,107],"individual-global":[97],"max":[98],"(IGM)":[99],"condition.":[100],"Finally,":[101],"simulation":[102],"results":[103],"validate":[104],"effectiveness":[106],"in":[111],"solving":[112],"relative":[113],"overgeneralization":[114],"problems.":[115]},"counts_by_year":[],"updated_date":"2026-04-02T13:53:19.096889","created_date":"2026-04-02T00:00:00"}