{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T22:18:47Z","timestamp":1776118727684,"version":"3.50.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62036002"],"award-info":[{"award-number":["62036002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["201906010075"],"award-info":[{"award-number":["201906010075"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["ERC-CoG-771687"],"award-info":[{"award-number":["ERC-CoG-771687"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tac.2024.3510596","type":"journal-article","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T13:44:47Z","timestamp":1733147087000},"page":"3587-3602","source":"Crossref","is-referenced-by-count":3,"title":["Approximate Policy Iteration for Robust Stochastic Control of Multiagent Markov Decision Processes"],"prefix":"10.1109","volume":"70","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6725-8263","authenticated-orcid":false,"given":"Feng","family":"Huang","sequence":"first","affiliation":[{"name":"Center for Systems and Control, College of Engineering, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5472-562X","authenticated-orcid":false,"given":"Ming","family":"Cao","sequence":"additional","affiliation":[{"name":"ENTEG, Faculty of Science and Engineering, University of Groningen, Groningen, The Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5600-8157","authenticated-orcid":false,"given":"Long","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Systems and Control, College of Engineering, Peking University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1973.1100265"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.39.10.1953"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref5","volume-title":"Reinforcement Learning and Optimal Control","author":"Bertsekas","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref7","first-page":"195","article-title":"Planning, learning and coordination in multiagent decision processes","volume-title":"Proc. 6th Conf. Theor. Aspects Rationality Knowl.","volume":"96","author":"Boutilier","year":"1996"},{"key":"ref8","first-page":"1603","article-title":"Reinforcement learning to play an optimal Nash equilibrium in team Markov games","volume-title":"Proc. 15th Int. Conf. Neural Inf. Process. Syst.","author":"Wang","year":"2002"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000057"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-005-2631-2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04105-y"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tac.1972.1099850"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-060117-105102"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3121228"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2006.02.006"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.06.004"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3002592"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1287\/educ.2019.0205"},{"key":"ref20","article-title":"Concrete problems in AI safety","author":"Amodei","year":"2016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2020.100270"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2876389"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v36i4.2577"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1287\/opre.21.3.728"},{"issue":"13","key":"ref25","first-page":"239","article-title":"On worst case design strategies","volume":"13","author":"Baar","year":"1987","journal-title":"Comput. Math. Appl."},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1050.0216"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1040.0129"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.1120.0509"},{"key":"ref29","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"Puterman","year":"2014"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3010490"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.007"},{"key":"ref32","first-page":"2817","article-title":"Robust adversarial reinforcement learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Pinto","year":"2017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17348"},{"key":"ref34","first-page":"1","article-title":"Robust reinforcement learning for continuous control with model misspecification","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Mankowitz","year":"2020"},{"key":"ref35","first-page":"1","article-title":"Online robust reinforcement learning with model uncertainty","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Wang","year":"2021"},{"key":"ref36","first-page":"511","article-title":"Robust reinforcement learning using least squares policy iteration with provable performance guarantees","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Badrinath","year":"2021"},{"key":"ref37","first-page":"10571","article-title":"Robust multi-agent reinforcement learning with model uncertainty","volume":"33","author":"Zhang","year":"2020","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1110.0931"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2241057"},{"key":"ref40","volume-title":"Neuro-Dynamic Programming","author":"Bertsekas","year":"1996"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1971.8488"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1003814"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-05156-2"},{"issue":"49","key":"ref44","first-page":"1629","article-title":"Approximate modified policy iteration and its application to the game of Tetris","volume":"16","author":"Scherrer","year":"2015","journal-title":"J. Mach. Learn. Res."},{"issue":"5","key":"ref45","first-page":"815","article-title":"Finite-time bounds for fitted value iteration","volume":"9","author":"Munos","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1098\/rsif.2020.0639"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-005-0686-0"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3032086"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3052485"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-25953-1"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9\/11018158\/10772632.pdf?arnumber=10772632","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T21:01:56Z","timestamp":1769634116000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10772632\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":50,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tac.2024.3510596","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":[[2025,6]]}}}