{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:15:10Z","timestamp":1787012110986,"version":"3.56.0"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"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":[[2024,12,16]]},"DOI":"10.1109\/cdc56724.2024.10886034","type":"proceedings-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T13:43:32Z","timestamp":1740577412000},"page":"2517-2524","source":"Crossref","is-referenced-by-count":4,"title":["Critic as Lyapunov function (CALF): a model-free, stability-ensuring agent"],"prefix":"10.1109","author":[{"given":"Pavel","family":"Osinenko","sequence":"first","affiliation":[{"name":"Skolkovo Institute of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Grigory","family":"Yaremenko","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roman","family":"Zashchitin","sequence":"additional","affiliation":[{"name":"Deggendorf Institute of Technology, Technology Campus Cham"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anton","family":"Bolychev","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sinan","family":"Ibrahim","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dmitrii","family":"Dobriborsci","sequence":"additional","affiliation":[{"name":"Deggendorf Institute of Technology, Technology Campus Cham"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref2","article-title":"A natural policy gradient","volume":"14","author":"Kakade","year":"2001","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1613\/jair.806"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282564"},{"key":"ref5","article-title":"Reinforcement learning and optimal control","author":"Bertsekas","year":"2019","journal-title":"Athena Scientific Belmont"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3096935"},{"key":"ref8","article-title":"Trial without error: Towards safe reinforcement learning via human intervention","author":"Saunders","year":"2017","journal-title":"arXiv preprint arXiv:1707.05173"},{"key":"ref9","article-title":"Deductive stability proofs for ordinary differential equations","author":"Tan","year":"2020","journal-title":"arXiv:2010.13096"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-71070-7_15"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-10373-5_13"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12107"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-61362-4_16"},{"key":"ref14","article-title":"Safe reinforcement learning using probabilistic shields","volume-title":"International Conference on Concurrency Theory: 31st CONCUR 2020: Vienna, Austria (Virtual Conference)","author":"K\u00f6nighofer"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593420"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070252"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3024161"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8795816"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619572"},{"key":"ref20","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":"ref21","volume-title":"Safe exploration in reinforcement learning: Theory and applications in robotics","author":"Berkenkamp","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2023.10.1369"},{"key":"ref23","first-page":"211","article-title":"Practical reinforcement learning for mpc: Learning from sparse objectives in under an hour on a real robot","volume-title":"Proceedings of the 2nd Conference on Learning for Dynamics and Control, ser. Proceedings of Machine Learning Research","volume":"120","author":"Karnchanachari"},{"key":"ref24","article-title":"Plan online, learn offline: Efficient learning and exploration via model-based control","author":"Lowrey","year":"2018","journal-title":"arXiv preprint arXiv:1811.01848"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105793"},{"key":"ref26","first-page":"8289","article-title":"Differentiable MPC for end-to-end planning and control","volume":"31","author":"Amos","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","first-page":"990","article-title":"Deep value model predictive control","volume-title":"Proceedings of the Conference on Robot Learning, ser. Proceedings of Machine Learning Research","volume":"100","author":"Hoeller"},{"key":"ref28","article-title":"Infinitehorizon differentiable model predictive control","volume-title":"International Conference on Learning Representations","author":"East"},{"key":"ref29","article-title":"Learning human objectives by evaluating hypothetical behavior","volume-title":"International Conference on Machine Learning","author":"Reddy"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989324"},{"issue":"04","key":"ref31","first-page":"3741","article-title":"Fixed-horizon temporal difference methods for stable reinforcement learning","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"34","author":"Asis"},{"key":"ref32","article-title":"Dream to control: Learning behaviors by latent imagination","volume-title":"International Conference on Learning Representations","author":"Hafner"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1176\/appi.books.9781585622665.33114"},{"key":"ref34","first-page":"23","article-title":"Lyapunov design for safe reinforcement learning control","volume-title":"Safe Learning Agents: Papers from the 2002 AAAI Symposium","author":"Perkins"},{"key":"ref35","first-page":"409","article-title":"Lyapunov-constrained action sets for reinforcement learning","volume":"1","author":"Perkins","year":"2001","journal-title":"ICML"},{"key":"ref36","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":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2023.3238700"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3011351"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560886"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2011.2168538"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2487972"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-78384-0"},{"issue":"15","key":"ref43","first-page":"123","article-title":"Reinforcement learning with guarantees: a review","volume-title":"IFAC Conference on Intelligent Control and Automation Sciences","volume":"55","author":"Osinenko"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.088"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref46","article-title":"Stochastic Stability of Differential Equations, ser. Stochastic Modelling and Applied Probability","author":"Khasminskii","year":"2011"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.09.019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2016.12.003"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1049\/PBCE081E"},{"key":"ref50","article-title":"Transferring multiple policies to hotstart reinforcement learning in an air compressor management problem","author":"Plisnier","year":"2023","journal-title":"arXiv preprint arXiv:2301.12820"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6911(01)00164-5"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6911(98)00003-6"},{"key":"ref53","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2023.3306070","article-title":"An actor-critic framework for online control with environment stability guarantee","author":"Osinenko","year":"2023","journal-title":"IEEE Access"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-6670(17)46904-7"}],"event":{"name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","location":"Milan, Italy","start":{"date-parts":[[2024,12,16]]},"end":{"date-parts":[[2024,12,19]]}},"container-title":["2024 IEEE 63rd Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10885784\/10885785\/10886034.pdf?arnumber=10886034","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T02:24:05Z","timestamp":1740623045000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10886034\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,16]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/cdc56724.2024.10886034","relation":{},"subject":[],"published":{"date-parts":[[2024,12,16]]}}}