{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T15:27:58Z","timestamp":1775143678408,"version":"3.50.1"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Strategic Priority Research Program of Chinese Academy of Sciences","award":["XDA27030204"],"award-info":[{"award-number":["XDA27030204"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322316"],"award-info":[{"award-number":["62322316"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62073323"],"award-info":[{"award-number":["62073323"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20220484077"],"award-info":[{"award-number":["20220484077"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2018AAA0102404"],"award-info":[{"award-number":["2018AAA0102404"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Fuzzy Syst."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tfuzz.2024.3363053","type":"journal-article","created":{"date-parts":[[2024,2,7]],"date-time":"2024-02-07T19:05:20Z","timestamp":1707332720000},"page":"2811-2824","source":"Crossref","is-referenced-by-count":3,"title":["Fuzzy Feedback Multiagent Reinforcement Learning for Adversarial Dynamic Multiteam Competitions"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5120-2046","authenticated-orcid":false,"given":"Qingxu","family":"Fu","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4841-4048","authenticated-orcid":false,"given":"Zhiqiang","family":"Pu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5417-6013","authenticated-orcid":false,"given":"Yi","family":"Pan","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0312-5728","authenticated-orcid":false,"given":"Tenghai","family":"Qiu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3268-9482","authenticated-orcid":false,"given":"Jianqiang","family":"Yi","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2186","article-title":"The starcraft multi-agent challenge","volume-title":"Proc. 18th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Samvelyan","year":"2019"},{"key":"ref2","article-title":"SMACv2: An improved benchmark for cooperative multi-agent reinforcement learning","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Ellis","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26028"},{"key":"ref4","first-page":"5527","article-title":"Independent policy gradient methods for competitive reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Daskalakis","year":"2020"},{"key":"ref5","first-page":"1","article-title":"Emergent tool use from multi-agent autocurricula","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Baker","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WCSP49889.2020.9299760"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3188833"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121870"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/S0165-1889(02)00122-7"},{"key":"ref11","first-page":"13870","article-title":"Welfare maximization in competitive equilibrium: Reinforcement learning for Markov exchange economy","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2022"},{"key":"ref12","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. 17th Int. Conf. Autonom. Agents Multi-Agent Syst.","author":"Sunehag","year":"2018"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636636"},{"key":"ref15","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang","year":"2018"},{"key":"ref16","first-page":"1804","article-title":"Opponent modeling in deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"He","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1002\/int.22594"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1196\/annals.1296.001"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2002.805890"},{"key":"ref20","first-page":"2960","article-title":"Practical Bayesian optimization of machine learning algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Snoek","year":"2012"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/artl.1995.2.4.355"},{"key":"ref22","first-page":"92","article-title":"Coevolution of a backgammon player","volume-title":"Proc. Artif. Life V: 5th Int. Workshop Synth. Simul. Living Syst.","author":"Pollack","year":"1997"},{"key":"ref23","first-page":"373","article-title":"Methods for competitive co-evolution: Finding opponents worth beating","volume-title":"Proc. ICGA","author":"Rosin","year":"1995"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1338"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref28","first-page":"1","article-title":"Emergent complexity via multi-agent competition","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Bansal","year":"2018"},{"key":"ref29","first-page":"575","article-title":"Learning latent representations to influence multi-agent interaction","volume-title":"Proc. Conf. Robot learn.","author":"Xie","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109916"},{"key":"ref31","first-page":"24611","article-title":"The surprising effectiveness of MAPPO in cooperative, multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17353"},{"key":"ref33","first-page":"10199","article-title":"Weighted QMIX: Expanding monotonic value function factorisation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rashid","year":"2020"},{"key":"ref34","first-page":"1","article-title":"Rethinking the implementation tricks and monotonicity constraint in cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2023"},{"key":"ref35","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Son","year":"2019"},{"key":"ref36","first-page":"1","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Wang","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau6249"},{"key":"ref38","first-page":"1","article-title":"Emergent coordination through competition","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Liu","year":"2019"},{"key":"ref39","first-page":"1","article-title":"MARLLiB: A scalable and efficient multi-agent reinforcement learning library","volume":"24","author":"Hu","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn54540.2023.10191422"},{"key":"ref41","article-title":"HMP: A hybrid reinforcement learning research platform for large-scale multiagent tasks","author":"Fu","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13596"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2003.1250664"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IRC.2019.00121"},{"key":"ref45","article-title":"Meta-gradient reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu","year":"2018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-38527-2_55"},{"key":"ref47","first-page":"10663","article-title":"Think global and act local: Bayesian optimisation over high-dimensional categorical and mixed search spaces","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Wan","year":"2021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2015.11.030"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2017.2787561"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2022.3170646"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s40815-020-01035-0"},{"key":"ref52","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"Lowe","year":"2017"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_15"},{"key":"ref54","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2017.2672732"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2012.2201338"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/91.493904"},{"key":"ref58","volume-title":"Adaptive Fuzzy Systems and Control: Design and Stability Analysis","author":"Wang","year":"1994"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1049\/piee.1974.0328"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/91.277960"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1142\/9789814261302_0010"},{"key":"ref62","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ng","year":"1999"},{"key":"ref63","article-title":"IS curiosity all you need? On the utility of emergent behaviours from curious exploration","author":"Groth","year":"2021"},{"key":"ref64","first-page":"4405","article-title":"LIIR: Learning individual intrinsic reward in multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Du","year":"2019"},{"key":"ref65","first-page":"9041","article-title":"Policy diagnosis via measuring role diversity in cooperative multi-agent RL","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Hu","year":"2022"}],"container-title":["IEEE Transactions on Fuzzy Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/91\/10517720\/10424698.pdf?arnumber=10424698","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T04:02:01Z","timestamp":1733889721000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10424698\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":65,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tfuzz.2024.3363053","relation":{},"ISSN":["1063-6706","1941-0034"],"issn-type":[{"value":"1063-6706","type":"print"},{"value":"1941-0034","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}