{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T12:30:06Z","timestamp":1730205006216,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CPS-2311084"],"award-info":[{"award-number":["CPS-2311084"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,13]]},"DOI":"10.1109\/cdc49753.2023.10383560","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:36Z","timestamp":1705689516000},"page":"8306-8311","source":"Crossref","is-referenced-by-count":0,"title":["Physics-Model-Regulated Deep Reinforcement Learning Towards Safety & Stability Guarantees"],"prefix":"10.1109","author":[{"given":"Hongpeng","family":"Cao","sequence":"first","affiliation":[{"name":"Hongpeng Cao is with School of Engineering and Design, Technical University of Munich,Munich,Germany,85748"}]},{"given":"Yanbing","family":"Mao","sequence":"additional","affiliation":[{"name":"Wayne State University,Yanbing Mao is with Engineering Technology Division,Detroit,MI,USA,48201"}]},{"given":"Lui","family":"Sha","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign,Department of Computer Science,Urbana,IL,USA,61801"}]},{"given":"Marco","family":"Caccamo","sequence":"additional","affiliation":[{"name":"School of Engineering and Design and Institute of Robotics and Machine Intelligence, Technical University of Munich,Munich,Germany"}]}],"member":"263","reference":[{"issue":"1","key":"ref1","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"ref3","article-title":"Adversarial attacks on neural network policies","volume-title":"5th International Conference on Learning Representations, ICLR 2017, Workshop Track Proceedings","author":"Huang","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63387-9_5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/02783649231167210"},{"article-title":"Equipping black-box policies with model-based advice for stable nonlinear control","volume-title":"arXiv preprint","author":"Li","key":"ref7"},{"key":"ref8","first-page":"1141","article-title":"Control regularization for reduced variance reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Cheng","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794127"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139172455"},{"key":"ref11","first-page":"9797","article-title":"Safe reinforcement learning in constrained markov decision processes","volume-title":"International Conference on Machine Learning","author":"Wachi","year":"2020"},{"issue":"Dec","key":"ref12","first-page":"803","article-title":"Lyapunov design for safe reinforcement learning","volume":"3","author":"Perkins","year":"2002","journal-title":"Journal of Machine Learning Research"},{"key":"ref13","article-title":"Safe model-based reinforcement learning with stability guarantees","volume":"30","author":"Berkenkamp","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982058"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2876389"},{"article-title":"A barrier-lyapunov actor-critic reinforcement learning approach for safe and stable control","volume-title":"arXiv preprint","author":"Zhao","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560886"},{"key":"ref18","first-page":"2125","article-title":"Lyapunov design for robust and efficient robotic reinforcement learning","author":"Westenbroek","year":"2022","journal-title":"Conference on Robot Learning, CoRL 2022, vol. 205 of Proceedings of Machine Learning Research"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3564273"},{"key":"ref20","article-title":"Continuous control with deep reinforcement learning","volume-title":"4th International Conference on Learning Representations, ICLR","author":"Lillicrap","year":"2016"},{"article-title":"Proximal policy optimization algorithms","volume-title":"arXiv preprint","author":"Schulman","key":"ref21"},{"key":"ref22","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Haarnoja","year":"10\u201315 Jul 2018"},{"journal-title":"arXiv preprint","article-title":"Physical deep reinforcement learning: Safety and unknown unknowns","author":"Cao","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970777"},{"key":"ref25","article-title":"Correct equations for the dynamics of the cart-pole system","author":"Florian","year":"2007","journal-title":"Center for Cognitive and Neural Studies, Romania"}],"event":{"name":"2023 62nd IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2023,12,13]]},"location":"Singapore, Singapore","end":{"date-parts":[[2023,12,15]]}},"container-title":["2023 62nd IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10383192\/10383193\/10383560.pdf?arnumber=10383560","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:41:56Z","timestamp":1706028116000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10383560\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,13]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/cdc49753.2023.10383560","relation":{},"subject":[],"published":{"date-parts":[[2023,12,13]]}}}