{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:24:33Z","timestamp":1760711073286,"version":"3.37.3"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100020430","name":"LG Chem Ltd.","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020430","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation Graduate Research Fellowship","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Contr. Syst. Technol."],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1109\/tcst.2022.3216988","type":"journal-article","created":{"date-parts":[[2022,11,7]],"date-time":"2022-11-07T17:27:48Z","timestamp":1667842068000},"page":"1196-1207","source":"Crossref","is-referenced-by-count":3,"title":["Distributionally Robust Surrogate Optimal Control for High-Dimensional Systems"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6973-7308","authenticated-orcid":false,"given":"Aaron","family":"Kandel","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, University of California at Berkeley, Berkeley, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0547-6345","authenticated-orcid":false,"given":"Saehong","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, University of California at Berkeley, Berkeley, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6393-4375","authenticated-orcid":false,"given":"Scott J.","family":"Moura","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, University of California at Berkeley, Berkeley, CA, USA"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Benchmarking safe exploration in deep reinforcement learning","author":"ray","year":"2020","journal-title":"arXiv 1910 01708"},{"key":"ref35","article-title":"Simple random search provides a competitive approach to reinforcement learning","author":"mania","year":"2018","journal-title":"arXiv 1803 07055"},{"key":"ref12","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garc\u00eda","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107279667"},{"key":"ref15","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume":"33","author":"kumar","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.orl.2018.01.011"},{"key":"ref14","article-title":"AWAC: Accelerating online reinforcement learning with offline datasets","author":"nair","year":"2020","journal-title":"arXiv 2006 09359"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1050.0216"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1149\/1.3519059"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2015.7402829"},{"key":"ref11","volume":"5","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref33","first-page":"146","article-title":"Input convex neural networks","author":"amos","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref10","volume":"1","author":"bertsekas","year":"2017","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147350"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-55508-4_1"},{"journal-title":"Optimal Control Theory","year":"1970","author":"kirk","key":"ref1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.paerosci.2005.02.001"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2016.2523440"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-49774-5_14"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2018.2807623"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3182\/20120711-3-BE-2027.00136"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008306431147"},{"key":"ref24","article-title":"Model-based reinforcement learning: A survey","author":"moerland","year":"2020","journal-title":"arXiv 2006 16712"},{"key":"ref23","article-title":"A model-based approach for sample-efficient multi-task reinforcement learning","author":"landolfi","year":"2019","journal-title":"arXiv 1907 04964"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-017-1172-1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-015-0929-7"},{"key":"ref20","first-page":"1","article-title":"Optimal control via neural networks: A convex approach","author":"chen","year":"2019","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TTE.2022.3140316"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/B978-0-444-53859-8.00003-5","article-title":"The cross-entropy method for optimization","volume":"31","author":"botev","year":"2013","journal-title":"Handbook of Statistics"},{"key":"ref22","article-title":"Model-based reinforcement learning for atari","author":"kaiser","year":"2019","journal-title":"arXiv 1903 00374"},{"key":"ref44","article-title":"MOPO: Model-based offline policy optimization","author":"yu","year":"2020","journal-title":"arXiv 2005 13239"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref43","first-page":"3506","article-title":"Optimal control of battery fast charging based-on Pontryagin’s minimum principle","author":"park","year":"2020","journal-title":"Proc 59th IEEE Conf Decis Control (CDC)"},{"key":"ref28","article-title":"Safe Wasserstein constrained deep Q-learning","author":"kandel","year":"2020","journal-title":"arXiv 2002 03016"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2014.2379695"},{"journal-title":"Battery Systems Engineering","year":"2012","author":"rahn","key":"ref29"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.est.2015.10.004"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1149\/1.3414012"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2005.02.036"},{"journal-title":"Linear Systems Theory","year":"2009","author":"hespanha","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11071-005-2803-2"},{"journal-title":"Theory of Optimal Control and Mathematical Programming","year":"1970","author":"canon","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2013.6580670"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/0-306-47508-1_13"}],"container-title":["IEEE Transactions on Control Systems Technology"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/87\/10108397\/9940561-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/87\/10108397\/09940561.pdf?arnumber=9940561","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T15:00:40Z","timestamp":1684162840000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9940561\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5]]},"references-count":44,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcst.2022.3216988","relation":{},"ISSN":["1063-6536","1558-0865","2374-0159"],"issn-type":[{"type":"print","value":"1063-6536"},{"type":"electronic","value":"1558-0865"},{"type":"electronic","value":"2374-0159"}],"subject":[],"published":{"date-parts":[[2023,5]]}}}