{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T00:14:10Z","timestamp":1778285650444,"version":"3.51.4"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","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":"am","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\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2230101"],"award-info":[{"award-number":["2230101"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2300355"],"award-info":[{"award-number":["2300355"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62203179"],"award-info":[{"award-number":["62203179"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ARO","award":["W911NF2310111"],"award-info":[{"award-number":["W911NF2310111"]}]},{"name":"ARO","award":["W911NF-23-1-0316"],"award-info":[{"award-number":["W911NF-23-1-0316"]}]},{"name":"ARO","award":["W911NF2310266"],"award-info":[{"award-number":["W911NF2310266"]}]},{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["FA9550-21-1-0231"],"award-info":[{"award-number":["FA9550-21-1-0231"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","award":["13001364"],"award-info":[{"award-number":["13001364"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","award":["F.10052139.02.012"],"award-info":[{"award-number":["F.10052139.02.012"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tac.2024.3409676","type":"journal-article","created":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T18:15:24Z","timestamp":1717611324000},"page":"8497-8512","source":"Crossref","is-referenced-by-count":9,"title":["Resilient Multiagent Reinforcement Learning With Function Approximation"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8608-5815","authenticated-orcid":false,"given":"Lintao","family":"Ye","sequence":"first","affiliation":[{"name":"Key Laboratory of Image Processing and Intelligent Control, Ministry of Education and the School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3141-4762","authenticated-orcid":false,"given":"Martin","family":"Figura","sequence":"additional","affiliation":[{"name":"Fortna, Denver, CO, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2251-9474","authenticated-orcid":false,"given":"Yixuan","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics and Statistics, Stony Brook University, Centereach, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0206-2112","authenticated-orcid":false,"given":"Mainak","family":"Pal","sequence":"additional","affiliation":[{"name":"Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2175-3402","authenticated-orcid":false,"given":"Pranoy","family":"Das","sequence":"additional","affiliation":[{"name":"Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2871-9888","authenticated-orcid":false,"given":"Ji","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Stony Brook University, Centereach, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7060-3956","authenticated-orcid":false,"given":"Vijay","family":"Gupta","sequence":"additional","affiliation":[{"name":"Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3081626"},{"key":"ref2","article-title":"Multiagent reinforcement learning for multi-robot systems: A survey","author":"Yang","year":"2004"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87479-9_61"},{"issue":"54","key":"ref4","first-page":"1","article-title":"Deep reinforcement learning for swarm systems","volume":"20","author":"Httenrauch","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref5","first-page":"1","article-title":"Reinforcement learning in economics and finance","volume":"62","author":"Charpentier","year":"2021","journal-title":"Comput. Econ."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref7","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lowe","year":"2017"},{"key":"ref8","first-page":"178","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":"ref9","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"80","author":"Zhang","year":"2018"},{"key":"ref10","first-page":"256","article-title":"Scalable reinforcement learning of localized policies for multi-agent networked systems","volume-title":"Proc. Mach. Learn. Res.","volume":"1","author":"Qu","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029257"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2021"},{"key":"ref13","article-title":"Communication-efficient actor-critic methods for homogeneous Markov games","author":"Chen","year":"2022"},{"key":"ref14","first-page":"1184","article-title":"Value propagation for decentralized networked deep multi-agent reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Qu","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2241057"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2013.130413"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483080"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-45249-9_2"},{"key":"ref19","article-title":"Generalized Byzantine-tolerant SGD","author":"Xie","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3154503"},{"issue":"84","key":"ref21","first-page":"1","article-title":"Variance reduced median-of-means estimator for Byzantine-robust distributed inference","volume":"22","author":"Tu","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref22","first-page":"4613","article-title":"Byzantine stochastic gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Alistarh","year":"2018"},{"key":"ref23","first-page":"118","article-title":"Machine learning with adversaries: Byzantine tolerant gradient descent","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Blanchard","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17348"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683145"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147381"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413992"},{"key":"ref28","first-page":"278","article-title":"Learning to coordinate in multi-agent systems: A coordinated actor-critic algorithm and finite-time guarantees","volume-title":"Proc. Learn. Dyn. Control Conf.","author":"Zeng","year":"2022"},{"key":"ref29","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref30","volume-title":"Stochastic Approximation and Recursive Algorithms and Applications","volume":"35","author":"Kushner","year":"2003"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-93-86279-38-5"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2015.2413551"},{"issue":"1","key":"ref33","first-page":"261","article-title":"On the strength of connectedness of a random graph","volume":"12","author":"Erds","year":"1961","journal-title":"Acta Mathematica Hungarica"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2836919"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2016.0821"},{"key":"ref36","volume-title":"Stochastic Approximation Methods for Constrained and Unconstrained Systems","volume":"26","author":"Kushner","year":"2012"},{"key":"ref37","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781139020411","volume-title":"Matrix Analysis 2nd Edition","author":"Horn","year":"2012"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2332432.2332505"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/9\/10778053\/10549785-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9\/10778053\/10549785.pdf?arnumber=10549785","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T18:56:31Z","timestamp":1733511391000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10549785\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":38,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tac.2024.3409676","relation":{},"ISSN":["0018-9286","1558-2523","2334-3303"],"issn-type":[{"value":"0018-9286","type":"print"},{"value":"1558-2523","type":"electronic"},{"value":"2334-3303","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}