{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T13:49:52Z","timestamp":1778248192912,"version":"3.51.4"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Advanced Research Projects Agency-Energy (ARPA-E) NEXTCAR","award":["DE-AR0000794"],"award-info":[{"award-number":["DE-AR0000794"]}]},{"DOI":"10.13039\/100017186","name":"Ohio Supercomputer Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017186","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Veh."],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1109\/tiv.2022.3150668","type":"journal-article","created":{"date-parts":[[2022,2,15]],"date-time":"2022-02-15T02:15:13Z","timestamp":1644891313000},"page":"387-398","source":"Crossref","is-referenced-by-count":59,"title":["Safe Model-Based Off-Policy Reinforcement Learning for Eco-Driving in Connected and Automated Hybrid Electric Vehicles"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3654-7318","authenticated-orcid":false,"given":"Zhaoxuan","family":"Zhu","sequence":"first","affiliation":[{"name":"Center for Automotive Research, The Ohio State University, Columbus, OH, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicola","family":"Pivaro","sequence":"additional","affiliation":[{"name":"Center for Automotive Research, The Ohio State University, Columbus, OH, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5169-3263","authenticated-orcid":false,"given":"Shobhit","family":"Gupta","sequence":"additional","affiliation":[{"name":"Center for Automotive Research, The Ohio State University, Columbus, OH, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1117-325X","authenticated-orcid":false,"given":"Abhishek","family":"Gupta","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, The Ohio State University, Columbus, OH, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1846-8894","authenticated-orcid":false,"given":"Marcello","family":"Canova","sequence":"additional","affiliation":[{"name":"Center for Automotive Research, The Ohio State University, Columbus, OH, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2018.09.001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2015.2449688"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2535439"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2014.2319812"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2019.02.031"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2968120"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/VPPC.2012.6422774"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2634019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.4271\/2019-01-1213"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2017.10.011"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2010.2047860"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3070445"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/0361198118796939"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2947756"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2021.104758"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9304005"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3318552"},{"key":"ref18","article-title":"Plan online, learn offline: Efficient learning and exploration via model-based control","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lowrey","year":"2019"},{"key":"ref19","first-page":"211","article-title":"Practical reinforcement learning for MPC: Learning from sparse objectives in under an hour on a real robot","volume-title":"Proc. Learn. Dyn. Control","author":"Karnchanachari","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2976272"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66723-8_1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_179268"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref24","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2018"},{"key":"ref25","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"ref26","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9030270"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"ref29","article-title":"Planet dump retrieved from https:\/\/planet.osm.org","year":"2017"},{"key":"ref30","article-title":"Emergence of locomotion behaviours in rich environments","author":"Heess","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1115\/1.4053292"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.23919\/ECC54610.2021.9655197"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1017\/9781139061759"},{"key":"ref34","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Chua","year":"2018"},{"key":"ref35","article-title":"Learning from delayed rewards","author":"Watkins","year":"1989"},{"key":"ref36","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lillicrap","year":"2016"},{"key":"ref37","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2016"},{"key":"ref38","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref39","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver","year":"2014"},{"key":"ref40","article-title":"Visualizing and understanding recurrent networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Karpathy","year":"2016"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CCA.2009.5281131"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref43","article-title":"Wavenet: A generative model for raw audio","author":"van den Oord","year":"2016"},{"key":"ref44","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018"},{"key":"ref45","article-title":"Ohio Supercomputer Center","author":"Center","year":"1987"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2019.09.091"}],"container-title":["IEEE Transactions on Intelligent Vehicles"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7274857\/9826527\/9712376-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274857\/9826527\/09712376.pdf?arnumber=9712376","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T22:55:36Z","timestamp":1705532136000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9712376\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":46,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tiv.2022.3150668","relation":{},"ISSN":["2379-8904","2379-8858"],"issn-type":[{"value":"2379-8904","type":"electronic"},{"value":"2379-8858","type":"print"}],"subject":[],"published":{"date-parts":[[2022,6]]}}}