{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:09:39Z","timestamp":1778026179851,"version":"3.51.4"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"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":[[2023,12,13]]},"DOI":"10.1109\/cdc49753.2023.10383742","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:36Z","timestamp":1705689516000},"page":"1320-1325","source":"Crossref","is-referenced-by-count":15,"title":["Stable and Safe Reinforcement Learning via a Barrier-Lyapunov Actor-Critic Approach"],"prefix":"10.1109","author":[{"given":"Liqun","family":"Zhao","sequence":"first","affiliation":[{"name":"University of Oxford,Department of Engineering Science,Oxford,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Konstantinos","family":"Gatsis","sequence":"additional","affiliation":[{"name":"University of Oxford,Department of Engineering Science,Oxford,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonis","family":"Papachristodoulou","sequence":"additional","affiliation":[{"name":"University of Oxford,Department of Engineering Science,Oxford,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Zhao","year":"2023","journal-title":"Stable and safe reinforcement learning via a barrier-lyapunov actor-critic approach"},{"key":"ref2","author":"Wang","year":"2023","journal-title":"Trustworthy reinforcement learning for quadrotor uav tracking control systems"},{"key":"ref3","first-page":"2306","article-title":"Quadue-ccm: Interpretable distributional reinforcement learning using uncertain contraction metrics for precise quadrotor trajectory tracking","volume-title":"Conference on Robot Learning","author":"Wang","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3011351"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3348422"},{"key":"ref6","first-page":"97","article-title":"Joint synthesis of safety certificate and safe control policy using constrained reinforcement learning","volume-title":"Learning for Dynamics and Control Conference","author":"Ma","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2022.3216996"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2023.10.1876"},{"key":"ref10","author":"do Nascimento","year":"2023","journal-title":"A game theoretic approach for safe and distributed control of unmanned aerial vehicles"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2023.111359"},{"key":"ref12","author":"Cao","year":"2023","journal-title":"Physical deep reinforcement learning towards safety guarantee"},{"key":"ref13","author":"Haarnoja","year":"2018","journal-title":"Soft actor-critic algorithms and applications"},{"key":"ref14","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":"ref15","doi-asserted-by":"publisher","DOI":"10.1017\/9781009051873"},{"key":"ref16","author":"Wang","year":"2023","journal-title":"A rl-based policy optimization method guided by adaptive stability certification"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683088"},{"key":"ref18","first-page":"22","article-title":"Constrained policy optimization","volume-title":"International conference on machine learning","author":"Achiam","year":"2017"},{"key":"ref19","author":"Ray","year":"2019","journal-title":"Benchmarking Safe Exploration in Deep Reinforcement Learning"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MED51440.2021.9480331"}],"event":{"name":"2023 62nd IEEE Conference on Decision and Control (CDC)","location":"Singapore, Singapore","start":{"date-parts":[[2023,12,13]]},"end":{"date-parts":[[2023,12,15]]}},"container-title":["2023 62nd IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10383192\/10383193\/10383742.pdf?arnumber=10383742","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:25:20Z","timestamp":1706027120000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10383742\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,13]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/cdc49753.2023.10383742","relation":{},"subject":[],"published":{"date-parts":[[2023,12,13]]}}}