{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:14:06Z","timestamp":1775578446128,"version":"3.50.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010098","name":"Shanghai Science and Technology Committee","doi-asserted-by":"publisher","award":["22511105500"],"award-info":[{"award-number":["22511105500"]}],"id":[{"id":"10.13039\/100010098","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"publisher","award":["62172299"],"award-info":[{"award-number":["62172299"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"publisher","award":["62032019"],"award-info":[{"award-number":["62032019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tnnls.2023.3278715","type":"journal-article","created":{"date-parts":[[2023,6,5]],"date-time":"2023-06-05T17:54:50Z","timestamp":1685987690000},"page":"14370-14381","source":"Crossref","is-referenced-by-count":26,"title":["A Robust Mean-Field Actor-Critic Reinforcement Learning Against Adversarial Perturbations on Agent States"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2649-8666","authenticated-orcid":false,"given":"Ziyuan","family":"Zhou","sequence":"first","affiliation":[{"name":"Department of Computer Science, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7523-4827","authenticated-orcid":false,"given":"Guanjun","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5408-8752","authenticated-orcid":false,"given":"Mengchu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark, NJ, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2943898"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2020.1003453"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3137605"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105901"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3195171"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2022.3181675"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MSMC.2022.3198027"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.3048056"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2022.3148276"},{"key":"ref10","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014","journal-title":"arXiv:1412.6572"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2981377"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2808203"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3231299"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3111139"},{"key":"ref17","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst","author":"Lowe"},{"key":"ref18","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn","volume":"97","author":"Iqbal"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"ref20","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. 17th Int. Conf. Auto. Agents MultiAgent Syst","author":"Sunehag"},{"key":"ref21","first-page":"1","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. 9th Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref22","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","volume-title":"Proc. 35th ICML","volume":"80","author":"Yang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014213"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SPW50608.2020.00027"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11371"},{"key":"ref26","article-title":"Adversarial attacks on neural network policies","author":"Huang","year":"2017","journal-title":"arXiv:1702.02284"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6047"},{"key":"ref28","first-page":"1","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":"ref29","first-page":"1","article-title":"Robust reinforcement learning on state observations with learned optimal adversary","volume-title":"Proc. 9th Int. Conf. Learn. Represent. (ICLR)","author":"Zhang"},{"key":"ref30","first-page":"26156","article-title":"Robust deep reinforcement learning through adversarial loss","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst","author":"Oikarinen"},{"key":"ref31","article-title":"Multi-agent reinforcement learning: Methods, applications, visionary prospects, and challenges","author":"Zhou","year":"2023","journal-title":"arXiv:2305.10091"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tdsc.2022.3207429"},{"key":"ref33","first-page":"1","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3114024"},{"key":"ref35","article-title":"Backdoor detection and mitigation in competitive reinforcement learning","author":"Guo","year":"2022","journal-title":"arXiv:2202.03609"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3183586"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3127346"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref39","article-title":"Sim-to-real transfer of accurate grasping with eye-in-hand observations and continuous control","author":"Yan","year":"2017","journal-title":"arXiv:1712.03303"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981319"},{"key":"ref41","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Yu","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3229213"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.39.10.1953"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.32917\/hmj\/1206139508"},{"key":"ref45","first-page":"1008","article-title":"Actor-critic agorithms","volume-title":"Proc. 12th Int. Conf. Neural Inf. Process. Syst","author":"Konda"},{"key":"ref46","article-title":"Sparse adversarial attack in multi-agent reinforcement learning","author":"Hu","year":"2022","journal-title":"arXiv:2205.09362"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812321"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1038\/sj.jors.2600425"},{"key":"ref49","article-title":"On the effectiveness of interval bound propagation for training verifiably robust models","author":"Gowal","year":"2018","journal-title":"arXiv:1810.12715"},{"key":"ref50","first-page":"6808","article-title":"Wasserstein adversarial examples via projected Sinkhorn iterations","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Wong"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10707065\/10143665.pdf?arnumber=10143665","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T05:25:17Z","timestamp":1728365117000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10143665\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":50,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3278715","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}