{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:38:41Z","timestamp":1757608721921,"version":"3.44.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128069","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"1170-1176","source":"Crossref","is-referenced-by-count":0,"title":["Neural Lyapunov Function Approximation with Self-Supervised Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Luc","family":"McCutcheon","sequence":"first","affiliation":[{"name":"University of Surrey,CAV-Lab,Department of Mechanical Engineering Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bahman","family":"Gharesifard","sequence":"additional","affiliation":[{"name":"University of California,Department of Electrical and Computer Engineering,Los Angeles"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saber","family":"Fallah","sequence":"additional","affiliation":[{"name":"University of Surrey,CAV-Lab,Department of Mechanical Engineering Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3302789"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3934\/dcdsb.2015.20.2361"},{"key":"ref3","article-title":"Neural lyapunov control","volume":"32","author":"Chang","year":"2019","journal-title":"Advances in neural information processing systems"},{"journal-title":"Lyapunov-stable neural control for state and output feedback: A novel formulation for efficient synthesis and verification","year":"2024","author":"Yang","key":"ref4"},{"key":"ref5","first-page":"2939","article-title":"Neural lyapunov control for discrete-time systems","volume":"36","author":"Wu","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-31365-3_23"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2019.108758"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1994.374324"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9682880"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3011351"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref12","article-title":"A Lyapunov-based approach to safe Reinforcement Learning","volume":"31","author":"Chow","year":"2018","journal-title":"Advances in neural information processing systems"},{"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":"10.1016\/j.ifacol.2020.12.2276"},{"journal-title":"Mind the uncertainty: Risk-aware and actively exploring model-based reinforcement learning","year":"2023","author":"Vlastelica","key":"ref15"},{"key":"ref16","first-page":"1724","article-title":"Safe nonlinear control using robust neural lyapunov-barrier functions","volume-title":"Conference on Robot Learning","author":"Dawson","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8796030"},{"key":"ref18","first-page":"36593","article-title":"Enforcing hard constraints with soft barriers: Safe reinforcement learning in unknown stochastic environments","volume-title":"International Conference on Machine Learning","author":"Wang","year":"2023"},{"key":"ref19","first-page":"29113","article-title":"Neural lyapunov control of unknown nonlinear systems with stability guarantees","volume":"35","author":"Zhou","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10383718"},{"key":"ref21","first-page":"52","article-title":"Learning to stabilize highdimensional unknown systems using lyapunov-guided exploration","volume-title":"6th Annual Learning for Dynamics & Control Conference","author":"Zhang","year":"2024"},{"key":"ref22","article-title":"Learning stable deep dynamics models","volume":"32","author":"Kolter","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/770"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9993006"},{"key":"ref25","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"},{"journal-title":"Soft actor-critic algorithms and applications","year":"2018","author":"Haarnoja","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"journal-title":"Multigoal reinforcement learning: Challenging robotics environments and request for research","year":"2018","author":"Plappert","key":"ref28"},{"key":"ref29","article-title":"Hindsight experience replay","volume":"30","author":"Andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128069.pdf?arnumber=11128069","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:13:20Z","timestamp":1756880000000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128069\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128069","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}