{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T20:52:31Z","timestamp":1775163151460,"version":"3.50.1"},"reference-count":11,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62273077"],"award-info":[{"award-number":["62273077"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan Province","doi-asserted-by":"publisher","award":["2024NSFJQ0013"],"award-info":[{"award-number":["2024NSFJQ0013"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/CAA J. Autom. Sinica"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/jas.2025.125666","type":"journal-article","created":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:13:58Z","timestamp":1775074438000},"page":"728-730","source":"Crossref","is-referenced-by-count":0,"title":["QuadQ: Quadratic-Based Value Decomposition for Cooperative Policy Optimization in Multi-Agent Reinforcement Learning"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3180-0815","authenticated-orcid":false,"given":"Siying","family":"Wang","sequence":"first","affiliation":[{"name":"School of Automation Engineering, University of Electronic Science and Technology of China,Chengdu,China,611731"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5442-6148","authenticated-orcid":false,"given":"Ruoning","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering (School of Cyber Security), University of Electronic Science and Technology of China,Chengdu,China,611731"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6141-2133","authenticated-orcid":false,"given":"Yang","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering (School of Cyber Security), University of Electronic Science and Technology of China,Chengdu,China,611731"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2508-7451","authenticated-orcid":false,"given":"Jinliang","family":"Shao","sequence":"additional","affiliation":[{"name":"School of Automation Engineering, University of Electronic Science and Technology of China,Chengdu,611731"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9756-4387","authenticated-orcid":false,"given":"Yuhua","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Automation Engineering, University of Electronic Science and Technology of China,Chengdu,China,611731"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s43684-022-00023-5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1004359"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123381"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.65109\/jsrc7365"},{"key":"ref6","first-page":"178","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Machine Learning Research"},{"key":"ref7","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Machine Learning","author":"Son","year":"2019"},{"key":"ref8","first-page":"1","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. Int. Conf Learning Representations","author":"Wang","year":"2021"},{"key":"ref9","first-page":"10199","article-title":"Weighted QMIX: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"33","author":"Rashid","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29695"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.65109\/LVZZ5205"}],"container-title":["IEEE\/CAA Journal of Automatica Sinica"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570654\/11459966\/11460149.pdf?arnumber=11460149","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:51:50Z","timestamp":1775159510000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11460149\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":11,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/jas.2025.125666","relation":{},"ISSN":["2329-9266","2329-9274"],"issn-type":[{"value":"2329-9266","type":"print"},{"value":"2329-9274","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}