{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:27:52Z","timestamp":1784737672622,"version":"3.55.0"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100023581","name":"National Science Foundation Graduate Research Fellowship Program","doi-asserted-by":"publisher","award":["DGE1745016"],"award-info":[{"award-number":["DGE1745016"]}],"id":[{"id":"10.13039\/100023581","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hsu Chang Memorial Fellowship in ECE"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Control Netw. Syst."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tcns.2024.3469031","type":"journal-article","created":{"date-parts":[[2024,9,25]],"date-time":"2024-09-25T19:29:51Z","timestamp":1727292591000},"page":"361-373","source":"Crossref","is-referenced-by-count":3,"title":["Model-Free Learning and Optimal Policy Design in Multiagent MDPs Under Probabilistic Agent Dropout"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3053-0833","authenticated-orcid":false,"given":"Carmel","family":"Fiscko","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8060-5581","authenticated-orcid":false,"given":"Soummya","family":"Kar","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5778-4879","authenticated-orcid":false,"given":"Bruno","family":"Sinopoli","sequence":"additional","affiliation":[{"name":"Department of Electrical and Systems Engineering, Washington University in St. Louis, St. Louis, MO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512215"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.scs.2021.103163"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1111\/mice.12702"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3238336"},{"key":"ref5","first-page":"21024","article-title":"Robust deep reinforcement learning against adversarial perturbations on state observations","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Zhang","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1214\/23-AAP1949"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.39.10.1953"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8796274"},{"key":"ref10","first-page":"604","article-title":"Near-optimal reinforcement learning in factored MDPs","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Osband","year":"2014"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/860575.860583"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tcns.2023.3330925"},{"issue":"35","key":"ref13","first-page":"1","article-title":"Learning and planning for time-varying MDPs using maximum likelihood estimation","volume-title":"J. Mach. Learn. Res.","volume":"22","author":"Ornik","year":"2021"},{"key":"ref14","first-page":"7216","article-title":"Non-stationary Markov decision processes, a worst-case approach using model-based reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Lecarpentier","year":"2019"},{"key":"ref15","first-page":"1843","article-title":"Reinforcement learning for non-stationary Markov decision processes: The blessing of (more) optimism","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cheung","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.1400"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2664883"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2241057"},{"key":"ref19","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2018"},{"key":"ref20","first-page":"2380","article-title":"High confidence policy improvement","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Thomas","year":"2015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9993252"},{"key":"ref22","first-page":"652","article-title":"Doubly robust off-policy value evaluation for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jiang","year":"2016"},{"key":"ref23","volume-title":"A Course in Game Theory","author":"Osborne","year":"1994"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1000"},{"key":"ref25","volume-title":"Dynamic Programming and Optimal Control","author":"Bertsekas","year":"1995"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tcns.2024.3469031"},{"key":"ref27","first-page":"890","article-title":"Mixing time estimation in ergodic Markov chains from a single trajectory with contraction methods","volume-title":"Proc. Algorithmic Learn. Theory","author":"Wolfer","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1214\/EJP.v20-4039"},{"key":"ref29","first-page":"2139","article-title":"Data-efficient off-policy policy evaluation for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Thomas","year":"2016"}],"container-title":["IEEE Transactions on Control of Network Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6509490\/10935358\/10694782-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6509490\/10935358\/10694782.pdf?arnumber=10694782","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T18:53:57Z","timestamp":1742842437000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10694782\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":29,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcns.2024.3469031","relation":{},"ISSN":["2325-5870","2372-2533"],"issn-type":[{"value":"2325-5870","type":"electronic"},{"value":"2372-2533","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}