{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T00:33:47Z","timestamp":1781224427141,"version":"3.54.1"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Federal Ministry for Economic Affairs and Climate Action"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,2]]},"DOI":"10.1109\/lra.2023.3236579","type":"journal-article","created":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T21:18:49Z","timestamp":1673558329000},"page":"1167-1174","source":"Crossref","is-referenced-by-count":39,"title":["Uncertainty-Aware Model-Based Offline Reinforcement Learning for Automated Driving"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5326-534X","authenticated-orcid":false,"given":"Christopher","family":"Diehl","sequence":"first","affiliation":[{"name":"Institute of Control Theory and Systems Engineering, TU Dortmund University, Dortmund, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Timo Sebastian","family":"Sievernich","sequence":"additional","affiliation":[{"name":"Institute of Control Theory and Systems Engineering, TU Dortmund University, Dortmund, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0544-0331","authenticated-orcid":false,"given":"Martin","family":"Kruger","sequence":"additional","affiliation":[{"name":"Institute of Control Theory and Systems Engineering, TU Dortmund University, Dortmund, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8394-4047","authenticated-orcid":false,"given":"Frank","family":"Hoffmann","sequence":"additional","affiliation":[{"name":"Institute of Control Theory and Systems Engineering, TU Dortmund University, Dortmund, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6096-8190","authenticated-orcid":false,"given":"Torsten","family":"Bertram","sequence":"additional","affiliation":[{"name":"Institute of Control Theory and Systems Engineering, TU Dortmund University, Dortmund, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref2","first-page":"2020","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine"},{"key":"ref3","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist.","author":"Ross","year":"2011"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00942"},{"key":"ref5","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Kumar","year":"2020"},{"key":"ref6","first-page":"21810","article-title":"Morel: Model-based offline reinforcement learning","volume-title":"Proc. Adv. Conf. Neural Inf, Process. Syst.","volume":"33","author":"Kidambi","year":"2020"},{"key":"ref7","first-page":"14129","article-title":"Mopo: Model-based offline policy optimization","volume-title":"Proc. Adv. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Yu","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01657-x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-0225-y"},{"key":"ref10","article-title":"Model-based offline planning","volume-title":"Proc. Int. Conf. Learn. Represention","author":"Argenson","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.strusafe.2008.06.020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3057023"},{"key":"ref13","article-title":"UMBRELLA: Uncertainty-aware model-based offline reinforcement learning leveraging planning","volume-title":"Neural Inf. Process. Syst. Mach. Learn. Auton. Driv. Work.","author":"Diehl","year":"2021"},{"key":"ref14","first-page":"28954","article-title":"Combo: Conservative offline model-based policy optimization","volume-title":"Proc. Adv. Conf. Neural Inf. Process. Syst,","author":"Yu","year":"2021"},{"key":"ref15","first-page":"6402","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume-title":"Proc. Adv. Conf. Neural Inf. Process. Syst.","volume":"30","author":"Lakshminarayanan","year":"2017"},{"key":"ref16","article-title":"Model-predictive policy learning with uncertainty regularization for driving in dense traffic","volume-title":"Proc. Int. Conf. Learn. Represention","author":"Henaff","year":"2019"},{"key":"ref17","article-title":"Auto-encoding variational bayes","volume-title":"Proc. Int. Conf. Learn. Represention.","author":"Kingma","year":"2014"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2898093"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-021-10024-7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561123"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(78)90001-8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2514\/1.G001921"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1561\/9781638280576"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/516"},{"key":"ref25","first-page":"1101","article-title":"Deep dynamics models for learning dexterous manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Nagabandi","year":"2020"},{"key":"ref26","article-title":"NGSIM interstate 80 freeway dataset","author":"Halkias","year":"2006"},{"key":"ref27","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. Conf. Robot Learn.","author":"Dosovitskiy","year":"2017"},{"key":"ref28","first-page":"5320","article-title":"Robust imitation of diverse behaviors","volume-title":"Proc. Adv. Conf. Neural Inf. Process. Syst.","volume":"30","author":"Wang","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00886"},{"key":"ref30","article-title":"Feedback in imitation learning: The three regimes of covariate shift","author":"Spencer","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146635"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2022.103829"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01154"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9990971\/10015868.pdf?arnumber=10015868","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T07:14:13Z","timestamp":1707808453000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10015868\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2]]},"references-count":33,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2023.3236579","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2]]}}}