{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:36:56Z","timestamp":1767339416265,"version":"3.37.3"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science foundation of China","doi-asserted-by":"publisher","award":["62293541","62136008"],"award-info":[{"award-number":["62293541","62136008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4232056"],"award-info":[{"award-number":["4232056"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Strategic Priority Research Program of Chinese Academy of Sciences","award":["XDA27030100"],"award-info":[{"award-number":["XDA27030100"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tetci.2024.3383454","type":"journal-article","created":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T17:33:56Z","timestamp":1712943236000},"page":"4033-4045","source":"Crossref","is-referenced-by-count":6,"title":["FM3Q: Factorized Multi-Agent MiniMax Q-Learning for Two-Team Zero-Sum Markov Game"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8035-7410","authenticated-orcid":false,"given":"Guangzheng","family":"Hu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5384-423X","authenticated-orcid":false,"given":"Yuanheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2559-9585","authenticated-orcid":false,"given":"Haoran","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8218-9633","authenticated-orcid":false,"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2020.3042244"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6190"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2021.3082204"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2020.3022698"},{"key":"ref9","first-page":"1039","article-title":"Nash Q-learning for general-sum stochastic games","volume":"4","author":"Hu","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref11","first-page":"322","article-title":"Friend-or-foe Q-learning in general-sum games","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Littman","year":"2001"},{"key":"ref12","first-page":"3504","article-title":"Neural auto-curricula in two-player zero-sum games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Feng","year":"2021"},{"key":"ref13","first-page":"1","article-title":"MALib: A parallel framework for population-based multi-agent reinforcement learning","volume":"24","author":"Zhou","year":"2023","journal-title":"J. Mach. Learn. Res."},{"article-title":"Dota 2 with large scale deep reinforcement learning","year":"2019","author":"Berner","key":"ref14"},{"key":"ref15","first-page":"20238","article-title":"Pipeline PSRO: A scalable approach for finding approximate Nash equilibria in large games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"McAleer","year":"2020"},{"key":"ref16","first-page":"4193","article-title":"A unified game-theoretic approach to multiagent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lanctot","year":"2017"},{"key":"ref17","first-page":"434","article-title":"Open-ended learning in symmetric zero-sum games","volume-title":"Proc Int. Conf. Mach. Learn.","author":"Balduzzi","year":"2019"},{"key":"ref18","first-page":"23128","article-title":"XDO: A double oracle algorithm for extensive-form games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"McAleer","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2018.2823329"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"article-title":"Coordination in adversarial sequential team games via multi-agent deep reinforcement learning","year":"2019","author":"Celli","key":"ref21"},{"key":"ref22","first-page":"1","article-title":"Efficiently computing nash equilibria in adversarial team Markov games","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kalogiannis","year":"2023"},{"key":"ref23","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative, multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3209655"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121546"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3157026"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3041469"},{"key":"ref28","first-page":"1","article-title":"A generalized training approach for multiagent learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Muller","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3580507.3597776"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3025491"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3179775"},{"key":"ref32","first-page":"4295","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid","year":"2018"},{"key":"ref33","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst.","author":"Sunehag","year":"2018"},{"key":"ref34","first-page":"10199","article-title":"Weighted QMIX: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rashid","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105869"},{"key":"ref36","first-page":"317","article-title":"Neural fitted Q iterationfirst experiences with a data efficient neural reinforcement learning method","volume-title":"Proc. Eur. Conf. Mach. Learn.","author":"Riedmiller","year":"2005"},{"key":"ref37","first-page":"9","article-title":"Fitted Q-iteration in continuous action-space MDPs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Antos","year":"2007"},{"key":"ref38","first-page":"568","article-title":"Error propagation for approximate policy and value iteration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Farahmand","year":"2010"},{"key":"ref39","first-page":"29142","article-title":"Towards understanding cooperative multi-agent Q-learning with value factorization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2021"},{"key":"ref40","first-page":"941","article-title":"Towards unifying behavioral and response diversity for open-ended learning in zero-sum games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref42","first-page":"15032","article-title":"PettingZoo: Gym for multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Terry","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191291"},{"key":"ref44","first-page":"1","article-title":"MAESTRO: Open-ended environment design for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Samvelyan","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/484"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7433297\/10765927\/10496905.pdf?arnumber=10496905","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T18:20:46Z","timestamp":1732731646000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10496905\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":45,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2024.3383454","relation":{},"ISSN":["2471-285X"],"issn-type":[{"type":"electronic","value":"2471-285X"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}