{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T16:23:31Z","timestamp":1759335811756,"version":"3.41.0"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Space Optoelectronic Measurement and Perception Lab, Beijing Institute of Control Engineering","award":["LabSOMP-2023-03"],"award-info":[{"award-number":["LabSOMP-2023-03"]}]},{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"publisher","award":["62172299","62032019"],"award-info":[{"award-number":["62172299","62032019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Science and Technology Innovation Action Plan","award":["23511100800"],"award-info":[{"award-number":["23511100800"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tsmc.2025.3561276","type":"journal-article","created":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T17:41:15Z","timestamp":1745602875000},"page":"4957-4968","source":"Crossref","is-referenced-by-count":1,"title":["Robust Training in Multiagent Deep Reinforcement Learning Against Optimal Adversary"],"prefix":"10.1109","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1626-8745","authenticated-orcid":false,"given":"Weiran","family":"Guo","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7523-4827","authenticated-orcid":false,"given":"Guanjun","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2649-8666","authenticated-orcid":false,"given":"Ziyuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6601-3515","authenticated-orcid":false,"given":"Jiacun","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Software Engineering, Monmouth University, West Long Branch, NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6064-1908","authenticated-orcid":false,"given":"Ying","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Rowan University, Glassboro, NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miaomiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Space Optoelectronic Measurement and Perception Lab, Beijing Institute of Control Engineering, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/drones7070476"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2023.3307134"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2023.3324687"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jii.2021.100257"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3408257"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tsmc.2022.3227919"},{"issue":"1","key":"ref7","first-page":"7234","article-title":"Monotonic value function factorization for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref8","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. 17th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Sunehag"},{"key":"ref9","first-page":"10707","article-title":"Shared experience actor\u2013critic for multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Christianos"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/spw50608.2020.00027"},{"key":"ref12","article-title":"Whatever does not kill deep reinforcement learning, makes it stronger","author":"Behzadan","year":"2017","journal-title":"arXiv:1712.09344"},{"key":"ref13","first-page":"2629","article-title":"Robust deep reinforcement learning against adversarial perturbations on state observations","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref14","first-page":"6","article-title":"Robust reinforcement learning on state observations with learned optimal adversary","volume-title":"Proc. Int. Conf. Learn. Rep. (ICLR)","author":"Zhang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2024.124818"},{"key":"ref16","first-page":"1","article-title":"Who is the strongest enemy? Towards optimal and efficient evasion attacks in deep RL","volume-title":"Proc. 10th Int. Conf. Learn. Rep. (ICLR)","author":"Sun"},{"key":"ref17","first-page":"1","article-title":"Delving into adversarial attacks on deep policies","volume-title":"Proc. 5th Int. Conf. Learn. Rep. (ICLR)","author":"Kos"},{"key":"ref18","first-page":"1","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. 3rd Int. Conf. Learn. Rep. (ICLR)","author":"Goodfellow"},{"key":"ref19","first-page":"1","article-title":"Sequential attacks on agents for long-term adversarial goals","volume-title":"Proc. ACM Comput. Sci. Cars Symp.","author":"Tretschk"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11672"},{"key":"ref21","first-page":"13","article-title":"Deep reinforcement learning with robust and smooth policy","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Shen"},{"key":"ref22","first-page":"23","article-title":"Towards robust and safe reinforcement learning with benign off-policy data","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2024.104632"},{"key":"ref24","article-title":"Sparse adversarial attack in multi-agent reinforcement learning","author":"Hu","year":"2022","journal-title":"arXiv:2205.09362"},{"volume-title":"Evaluating robustness of cooperative MARL: A model-based approach","year":"2023","author":"Pham","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3233\/faia230632"},{"volume-title":"What is the solution for state-adversarial multi-agent reinforcement learning?","year":"2023","author":"Han","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tsmc.2022.3229213"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3278715"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127191"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29708"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref34","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yu"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3285442"},{"key":"ref37","first-page":"1","article-title":"Benchmarking multi-agent deep reinforcement learning algorithms in cooperative tasks","volume-title":"Proc. Neural Inf. Process. Syst. Datasets Benchmarks (NeurIPS)","author":"Papoudakis"},{"key":"ref38","article-title":"The StarCraft multi-agent challenge","author":"Samvelyan","year":"2019","journal-title":"arxiv.abs\/1902.04043"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221021\/11039116\/10977657.pdf?arnumber=10977657","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T17:40:05Z","timestamp":1750268405000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10977657\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":38,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2025.3561276","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"type":"print","value":"2168-2216"},{"type":"electronic","value":"2168-2232"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}