{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:27:19Z","timestamp":1780586839965,"version":"3.54.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB2502901"],"award-info":[{"award-number":["2022YFB2502901"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004147","name":"Tsinghua University Initiative Scientific Research Program;","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004147","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSF, China","doi-asserted-by":"publisher","award":["U20A20334"],"award-info":[{"award-number":["U20A20334"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSF, China","doi-asserted-by":"publisher","award":["52072213"],"award-info":[{"award-number":["52072213"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSF, China","doi-asserted-by":"publisher","award":["52202487"],"award-info":[{"award-number":["52202487"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002855","name":"Ministry of Science and Technology of the People's Republic of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]},{"name":"2030 Innovation Megaprojects \"Program on New Generation Artificial Intelligence\"","award":["2021AAA0150000"],"award-info":[{"award-number":["2021AAA0150000"]}]},{"name":"Tsinghua University\u2013Toyota Joint Research Center for AI Technology of Automated Vehicle"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/tase.2023.3292388","type":"journal-article","created":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T20:18:35Z","timestamp":1701116315000},"page":"4129-4142","source":"Crossref","is-referenced-by-count":18,"title":["Safe Model-Based Reinforcement Learning With an Uncertainty-Aware Reachability Certificate"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3616-5400","authenticated-orcid":false,"given":"Dongjie","family":"Yu","sequence":"first","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5331-0938","authenticated-orcid":false,"given":"Wenjun","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7222-0019","authenticated-orcid":false,"given":"Yujie","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9943-0638","authenticated-orcid":false,"given":"Haitong","family":"Ma","sequence":"additional","affiliation":[{"name":"John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4923-3633","authenticated-orcid":false,"given":"Shengbo Eben","family":"Li","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2854-921X","authenticated-orcid":false,"given":"Yuming","family":"Yin","sequence":"additional","affiliation":[{"name":"College of Mechanical Engineering, Zhejiang University of Technology, Zhejiang, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0282-8621","authenticated-orcid":false,"given":"Jianyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3697-1576","authenticated-orcid":false,"given":"Jingliang","family":"Duan","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Dream to control: Learning behaviors by latent imagination","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hafner"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3114327"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3151607"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3168621"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3163816"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.134"},{"key":"ref8","article-title":"Reward constrained policy optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tessler"},{"key":"ref9","volume-title":"Benchmarking safe exploration in deep reinforcement learning","author":"Ray","year":"2019"},{"key":"ref10","article-title":"Projection-based constrained policy optimization","author":"Yang","year":"2020","journal-title":"arXiv:2010.03152"},{"key":"ref11","first-page":"97","article-title":"Joint synthesis of safety certificate and safe control policy using constrained reinforcement learning","volume-title":"Proc. 4th Annu. Learn. Dyn. Control Conf.","author":"Ma"},{"key":"ref12","first-page":"25636","article-title":"Reachability constrained reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu"},{"key":"ref13","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume":"31","author":"Chua","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","article-title":"When to trust your model: Model-based policy optimization","volume":"32","author":"Janner","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","first-page":"13859","article-title":"Safe reinforcement learning by imagining the near future","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Thomas"},{"key":"ref16","volume-title":"Constrained Policy Optimization via Bayesian World Models","author":"As","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635984"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-022-06187-8"},{"key":"ref19","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Hafner"},{"key":"ref20","first-page":"1031","article-title":"Model-based reinforcement learning with nearly tight exploration complexity bounds","volume-title":"Proc. ICML","author":"Szita"},{"key":"ref21","article-title":"Constrained model-based reinforcement learning with robust cross-entropy method","author":"Liu","year":"2021","journal-title":"arXiv:2010.07968"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683085"},{"key":"ref23","first-page":"8550","article-title":"Bridging Hamilton\u2013Jacobi safety analysis and reinforcement learning","volume-title":"Proc. Int. Conf. Robot. Automat. (ICRA)","author":"Fisac"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2728606.2728612"},{"key":"ref25","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. 34th Int. Conf. Mach. Learn. (ICML)","author":"Achiam"},{"key":"ref26","article-title":"Feasible actor-critic: Constrained reinforcement learning for ensuring statewise safety","author":"Ma","year":"2021","journal-title":"arXiv:2105.10682"},{"key":"ref27","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. ICML","author":"Bellemare"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082568"},{"key":"ref29","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-7784-8"},{"key":"ref31","first-page":"10708","article-title":"Lyapunov density models: Constraining distribution shift in learning-based control","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"162","author":"Kang"},{"key":"ref32","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref33","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.commtr.2023.100096"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref36","first-page":"25621","article-title":"Learning barrier certificates: Towards safe reinforcement learning with zero training-time violations","volume":"34","author":"Luo","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","article-title":"Safe-control-gym: A unified benchmark suite for safe learning-based control and reinforcement learning in robotics","author":"Yuan","year":"2021","journal-title":"arXiv:2109.06325"},{"key":"ref38","article-title":"Conservative safety critics for exploration","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bharadhwaj"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070252"},{"key":"ref40","first-page":"784","article-title":"Model-free safe control for zero-violation reinforcement learning","volume-title":"Proc. 5th Annu. Conf. Robot Learn.","volume":"164","author":"Zhao"},{"key":"ref41","volume-title":"Safe exploration in reinforcement learning: Theory and applications in robotics,","author":"Berkenkamp","year":"2019"},{"key":"ref42","article-title":"Mastering diverse domains through world models","author":"Hafner","year":"2023","journal-title":"arXiv:2301.04104"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8856\/10631742\/10329343.pdf?arnumber=10329343","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T06:37:51Z","timestamp":1723271871000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10329343\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":42,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tase.2023.3292388","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}