{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T16:51:31Z","timestamp":1778345491197,"version":"3.51.4"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100002427","name":"Ford Motor Company\u2013Michigan State University Alliance","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002427","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Contr. Syst. Technol."],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1109\/tcst.2023.3245824","type":"journal-article","created":{"date-parts":[[2023,2,28]],"date-time":"2023-02-28T18:56:17Z","timestamp":1677610577000},"page":"1803-1818","source":"Crossref","is-referenced-by-count":5,"title":["A Risk-Averse Preview-Based Q-Learning Algorithm: Application to Highway Driving of Autonomous Vehicles"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2069-8760","authenticated-orcid":false,"given":"Majid","family":"Mazouchi","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, Michigan State University, East Lansing, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Subramanya P.","family":"Nageshrao","sequence":"additional","affiliation":[{"name":"Ford Research and Innovation Center, Ford Motor Company, Palo Alto, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0800-5140","authenticated-orcid":false,"given":"Hamidreza","family":"Modares","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Michigan State University, East Lansing, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8264535"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9030133"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2926674"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2014.2357038"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2019.1044"},{"key":"ref59","author":"althoff","year":"2010","journal-title":"Reachability Analysis and Its Application to the Safety Assessment of Autonomous Cars"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718751"},{"key":"ref58","first-page":"1557","article-title":"Safety control with preview automaton","author":"liu","year":"2019","journal-title":"Proc IEEE 58th Conf Decis Control (CDC)"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1997.609450"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.5121\/mlaij.2017.4401"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7040014"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2016.7795922"},{"key":"ref10","article-title":"Risk-sensitive safety specifications for stochastic systems using conditional value-at-risk","author":"chapman","year":"2019","journal-title":"arXiv 1909 09703"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2017.8317943"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1137\/19M1305355"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s00186-011-0367-0"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1080.0684"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012997320614"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-060117-105157"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3012034"},{"key":"ref46","author":"lavalle","year":"1998","journal-title":"Rapidly-Exploring Random Trees A New Tool for Path Planning"},{"key":"ref45","article-title":"Rapidly-exploring random trees: Progress and prospects","author":"lavalle","year":"2000","journal-title":"Algorithmic and Computational Robotics New Directions the Fourth Workshop on the Algorithmic Foundations of Robotics"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911406761"},{"key":"ref47","first-page":"895","article-title":"An obstacle-based rapidly-exploring random tree","author":"tang","year":"2006","journal-title":"Proc IEEE Int Conf Robot Autom (ICRA)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1666"},{"key":"ref41","article-title":"Optimizing the CVaR via sampling","author":"tamar","year":"2014","journal-title":"arXiv 1404 3862"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7040014"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8264535"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IV48863.2021.9575880"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2002.808484"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/9.286253"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/9.989082"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1994.411203"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/9.633830"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.07.028"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2013.2253556"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11662-4_12"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1137\/120874679"},{"key":"ref79","article-title":"Transferred Q-learning","author":"chen","year":"2022","journal-title":"arXiv 2202 04709"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1137\/140969221"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2009.2018966"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1137\/120899005"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-010-0393-3"},{"key":"ref31","author":"agarwal","year":"2020","journal-title":"Reinforcement learning Theory and algorithms"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2017.08.1431"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029405"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.11.022"},{"key":"ref33","first-page":"6070","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"chow","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2037"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/9.633830"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2014.6859437"},{"key":"ref2","first-page":"1025","article-title":"Risk-sensitive optimal feedback control for haptic assistance","author":"medina","year":"2012","journal-title":"Proc IEEE Int Conf Robot Autom"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2929980"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.2.294.324"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1023\/A:1017940631555","article-title":"Risk-sensitive reinforcement learning","volume":"49","author":"mihatsch","year":"2014","journal-title":"Mach Learn"},{"key":"ref71","article-title":"A taxonomy of similarity metrics for Markov decision processes","author":"garc\u00eda","year":"2021","journal-title":"arXiv 2103 04706"},{"key":"ref70","first-page":"1","article-title":"An automated measure of MDP similarity for transfer in reinforcement learning","author":"ammar","year":"2014","journal-title":"Proc Workshops 28th AAAI Conf Artif Intell"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.109402"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CASE48305.2020.9216872"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1002\/9780470182963","volume":"703","author":"powell","year":"2007","journal-title":"Approximate Dynamic Programming Solving the Curses of Dimensionality"},{"key":"ref68","volume":"96","author":"conway","year":"2019","journal-title":"A Course in Functional Analysis"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636834"},{"key":"ref67","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref26","author":"bertsekas","year":"2019","journal-title":"Reinforcement and Optimal Control"},{"key":"ref25","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref69","first-page":"1746","article-title":"Transfer from multiple MDPs","volume":"24","author":"lazaric","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","article-title":"Risk-sensitive safety analysis using conditional value-at-risk","author":"chapman","year":"2021","journal-title":"arXiv 2101 12086"},{"key":"ref64","first-page":"5","author":"bertsekas","year":"2012","journal-title":"Weighted sup-norm contractions in dynamic programming A review and some new applications"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2014.00102"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147792"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2906423"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/INDIANCC.2019.8715578"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1287\/opre.51.6.850.24925"},{"key":"ref28","volume":"17","author":"lewis","year":"2013","journal-title":"Reinforcement Learning and Approximate Dynamic Programming for Feedback Control"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-78384-0"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1109\/MCS.2012.2214134","article-title":"Reinforcement learning and feedback control: Using natural decision methods to design optimal adaptive controllers","volume":"32","author":"lewis","year":"2012","journal-title":"IEEE Control Syst"},{"key":"ref60","article-title":"Safe value functions","author":"massiani","year":"2021","journal-title":"arXiv 2105 12204"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.jet.2017.11.005"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2019.1044"}],"container-title":["IEEE Transactions on Control Systems Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/87\/10159463\/10056416.pdf?arnumber=10056416","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T18:00:36Z","timestamp":1689616836000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10056416\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7]]},"references-count":79,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcst.2023.3245824","relation":{},"ISSN":["1063-6536","1558-0865","2374-0159"],"issn-type":[{"value":"1063-6536","type":"print"},{"value":"1558-0865","type":"electronic"},{"value":"2374-0159","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7]]}}}