{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T00:31:29Z","timestamp":1768437089465,"version":"3.49.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"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":[[2021,12,14]]},"DOI":"10.1109\/cdc45484.2021.9683721","type":"proceedings-article","created":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T20:50:18Z","timestamp":1643748618000},"page":"2258-2263","source":"Crossref","is-referenced-by-count":7,"title":["Reinforcement Learning Policies With Local LQR Guarantees For Nonlinear Discrete-Time Systems"],"prefix":"10.1109","author":[{"given":"Samuele","family":"Zoboli","sequence":"first","affiliation":[{"name":"Université Claude Bernard Lyon 1, CNRS, LAGEPP UMR 5007,Villeurbanne,France,F-69100"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vincent","family":"Andrieu","sequence":"additional","affiliation":[{"name":"Université Claude Bernard Lyon 1, CNRS, LAGEPP UMR 5007,Villeurbanne,France,F-69100"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniele","family":"Astolfi","sequence":"additional","affiliation":[{"name":"Université Claude Bernard Lyon 1, CNRS, LAGEPP UMR 5007,Villeurbanne,France,F-69100"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giacomo","family":"Casadei","sequence":"additional","affiliation":[{"name":"Université de Lyon,Laboratoire Ampere Dpt. EEA of the \u00c9cole Centrale de Lyon,Ecully,France,69134"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jilles S.","family":"Dibangoye","sequence":"additional","affiliation":[{"name":"INRIA Chroma Team,CITI Lab. INSA Lyon,Villeubanne,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Madiha","family":"Nadri","sequence":"additional","affiliation":[{"name":"Université Claude Bernard Lyon 1, CNRS, LAGEPP UMR 5007,Villeurbanne,France,F-69100"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","author":"kirk","year":"1970","journal-title":"Optimal Control Theory An Introduction"},{"key":"ref11","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463209"},{"key":"ref13","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref14","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref15","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":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2616644"},{"key":"ref17","author":"raffin","year":"2019","journal-title":"Stable baselines3"},{"key":"ref18","first-page":"775","article-title":"Combining reinforcement learning with a local control algorithm","author":"randl\u00f8v","year":"2000","journal-title":"Proc Seventh Int Conf Machine Learning"},{"key":"ref19","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref4","author":"bertsekas","year":"2018","journal-title":"REINFORCEMENT LEARNING AND OPTIMAL CONTROL"},{"key":"ref3","article-title":"Dynamic Programming and Optimal Control 4th Edition, Volume II Chapter 4 Noncontractive Total Cost Problems","author":"bertsekas","year":"2018"},{"key":"ref6","article-title":"Lyapunov-based safe policy optimization for continuous control","author":"chow","year":"2019"},{"key":"ref5","first-page":"295","article-title":"Reinforcement learning applied to linear quadratic regulation","author":"bradtke","year":"1993","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3011351"},{"key":"ref7","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref2","article-title":"Safe model-based reinforcement learning with stability guarantees","author":"berkenkamp","year":"2017"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798979"},{"key":"ref9","author":"khalil","year":"2002","journal-title":"Nonlinear System"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref22","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref21","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683721"}],"event":{"name":"2021 60th IEEE Conference on Decision and Control (CDC)","location":"Austin, TX, USA","start":{"date-parts":[[2021,12,14]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 60th IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9682670\/9682776\/09683721.pdf?arnumber=9683721","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,6]],"date-time":"2022-06-06T20:23:50Z","timestamp":1654547030000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9683721\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/cdc45484.2021.9683721","relation":{},"subject":[],"published":{"date-parts":[[2021,12,14]]}}}