{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T14:29:46Z","timestamp":1773930586073,"version":"3.50.1"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,11]]},"DOI":"10.1109\/iros40897.2019.8967820","type":"proceedings-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T23:53:51Z","timestamp":1580428431000},"page":"6878-6884","source":"Crossref","is-referenced-by-count":45,"title":["Episodic Learning with Control Lyapunov Functions for Uncertain Robotic Systems"],"prefix":"10.1109","author":[{"given":"Andrew J.","family":"Taylor","sequence":"first","affiliation":[{"name":"California Institute of Technology,Department of Computing and Mathematical Sciences,Pasadena,USA,CA 91125"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Victor D.","family":"Dorobantu","sequence":"additional","affiliation":[{"name":"California Institute of Technology,Department of Computing and Mathematical Sciences,Pasadena,USA,CA 91125"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hoang M.","family":"Le","sequence":"additional","affiliation":[{"name":"California Institute of Technology,Department of Computing and Mathematical Sciences,Pasadena,USA,CA 91125"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yisong","family":"Yue","sequence":"additional","affiliation":[{"name":"California Institute of Technology,Department of Computing and Mathematical Sciences,Pasadena,USA,CA 91125"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aaron D.","family":"Ames","sequence":"additional","affiliation":[{"name":"California Institute of Technology,Department of Computing and Mathematical Sciences,Pasadena,USA,CA 91125"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77653-6_3"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6911(89)90028-5"},{"key":"ref33","article-title":"No-regret reductions for imitation learning and structured prediction","volume":"abs 1011 686","author":"ross","year":"2010","journal-title":"CoRR"},{"key":"ref32","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref31","article-title":"The lyapunov neural network: Adaptive stability certification for safe learning of dynamic systems","author":"richards","year":"2018","journal-title":"arXiv preprint arXiv 1808 02194"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.049"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794351"},{"key":"ref36","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2010.936957"},{"key":"ref34","author":"sastry","year":"1999","journal-title":"Nonlinear Systems Analysis Stability and Control"},{"key":"ref10","article-title":"Accelerating imitation learning with predictive models","author":"cheng","year":"2019","journal-title":"International Conference on Artificial Intelligence and Statistics (AISTATS)"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6911(94)00050-6"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref12","first-page":"8092","article-title":"A lyapunov-based approach to safe reinforcement learning","author":"chow","year":"2018","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5106-x"},{"key":"ref14","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref15","first-page":"503","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"ernst","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"ref16","article-title":"A general safety framework for learning-based control in uncertain robotic systems","author":"fisac","year":"2018","journal-title":"IEEE Transactions on Automatic Control"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2015.2419630"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS.2018.00018"},{"key":"ref19","author":"gy\u00f6rfi","year":"2006","journal-title":"A Distribution-Free Theory of Nonparametric Regression"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1080\/00207178708933715"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/0362-546X(83)90049-4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2013.6760327"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2638961"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798979"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2015.XI.048"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2019.01.023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487170"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ECC.2015.7330913"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-01159-2_12"},{"key":"ref9","first-page":"908","article-title":"Safe model-based reinforcement learning with stability guarantees","author":"berkenkamp","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2299335"},{"key":"ref20","article-title":"Adaptive control by regulation-triggered batch least-squares estimation of non-observable parameters","author":"karafyllis","year":"2018","journal-title":"arXiv preprint arXiv 1811 10833"},{"key":"ref45","author":"westervelt","year":"2007","journal-title":"Feedback Control of Dynamic Bipedal Robot Locomotion"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref21","author":"khalil","year":"2002","journal-title":"Nonlinear Systems 3rd ed"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref24","first-page":"680","article-title":"Smooth imitation learning for online sequence prediction","author":"le","year":"2016","journal-title":"Proceedings of the 33rd International Conference on International Conference on Machine Learning-Volume 48"},{"key":"ref41","first-page":"3309","article-title":"Deeply aggrevated: Differentiable imitation learning for sequential prediction","author":"sun","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6911(94)00107-7"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460471"},{"key":"ref26","first-page":"265","article-title":"Bipedal robotic running with durus-2d: Bridging the gap between theory and experiment","author":"ma","year":"2017","journal-title":"Proceedings of the 20th International Conference on Hybrid Systems Computation and Control"},{"key":"ref43","article-title":"A control lyapunov perspective on episodic learning via projection to state stability","author":"taylor","year":"2019","journal-title":"58th Conference on Decision and Control (CDC)"},{"key":"ref25","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"}],"event":{"name":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Macau, China","start":{"date-parts":[[2019,11,3]]},"end":{"date-parts":[[2019,11,8]]}},"container-title":["2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8957008\/8967518\/08967820.pdf?arnumber=8967820","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,20]],"date-time":"2023-01-20T14:09:03Z","timestamp":1674223743000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8967820\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/iros40897.2019.8967820","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}