{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:52:56Z","timestamp":1777488776824,"version":"3.51.4"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"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":[[2025,12,9]]},"DOI":"10.1109\/cdc57313.2025.11312866","type":"proceedings-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T18:19:56Z","timestamp":1768241996000},"page":"6057-6062","source":"Crossref","is-referenced-by-count":1,"title":["Stochastic Reinforcement Learning with Stability Guarantees for Control of Unknown Nonlinear Systems"],"prefix":"10.1109","author":[{"given":"Thanin","family":"Quartz","sequence":"first","affiliation":[{"name":"University of Waterloo,Department of Applied Mathematics,Waterloo,Canada,N2L 3G1"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruikun","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Waterloo,Department of Applied Mathematics,Waterloo,Canada,N2L 3G1"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hans","family":"De Sterck","sequence":"additional","affiliation":[{"name":"University of Waterloo,Department of Applied Mathematics,Waterloo,Canada,N2L 3G1"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Waterloo,Department of Applied Mathematics,Waterloo,Canada,N2L 3G1"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref4","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref5","author":"Saunders","year":"2017","journal-title":"Trial without error: Towards safe reinforcement learning via human intervention"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-13823-7_31"},{"key":"ref8","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garc\u00eda","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.mcm.2010.04.001"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/9781119132677"},{"key":"ref11","article-title":"Neural Lyapunov control of unknown nonlinear systems with stability guarantees","author":"Zhou","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3024161"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9030185"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2022.07.619"},{"key":"ref15","first-page":"803","article-title":"Lyapunov design for safe reinforcement learning","volume":"3","author":"Perkins","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798979"},{"key":"ref17","first-page":"908","article-title":"Safe model-based reinforcement learning with stability guarantees","author":"Berkenkamp","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683721"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3011351"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2237"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2303"},{"key":"ref22","article-title":"Stochastic reinforcement learning with stability guarantees for control of unknown nonlinear systems","author":"Quartz","year":"2024"},{"key":"ref23","volume-title":"Dynamic Programming and Optimal Control: Volume II; Approximate Dynamic Programming.","author":"Bertsekas","year":"2012"},{"key":"ref24","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"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1985.1104084"},{"key":"ref26","article-title":"Physics-informed neural network policy iteration: Algorithms, convergence, and verification","volume-title":"International Conference on Machine Learning","author":"Meng"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3641513.3650134"}],"event":{"name":"2025 IEEE 64th Conference on Decision and Control (CDC)","location":"Rio de Janeiro, Brazil","start":{"date-parts":[[2025,12,9]]},"end":{"date-parts":[[2025,12,12]]}},"container-title":["2025 IEEE 64th Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11311984\/11311968\/11312866.pdf?arnumber=11312866","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T08:17:25Z","timestamp":1768292245000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11312866\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,9]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/cdc57313.2025.11312866","relation":{},"subject":[],"published":{"date-parts":[[2025,12,9]]}}}