{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T14:46:56Z","timestamp":1776955616077,"version":"3.51.4"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,23]],"date-time":"2022-08-23T00:00:00Z","timestamp":1661212800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,23]],"date-time":"2022-08-23T00:00:00Z","timestamp":1661212800000},"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":[[2022,8,23]]},"DOI":"10.1109\/ccta49430.2022.9966192","type":"proceedings-article","created":{"date-parts":[[2022,12,8]],"date-time":"2022-12-08T18:41:14Z","timestamp":1670524874000},"page":"1190-1195","source":"Crossref","is-referenced-by-count":2,"title":["Barrier Certified Safety Learning Control: When Sum-of-Square Programming Meets Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Hejun","family":"Huang","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenglong","family":"Li","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,Department of Electrical and Electronic Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongkun","family":"Han","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1993.42.42045"},{"key":"ref32","article-title":"Approximation Theory and Approximation Practice","author":"trefethen","year":"2019","journal-title":"SIAM"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.23919\/ASCC56756.2022.9828315"},{"key":"ref30","article-title":"On Estimating the Probabilistic Region of Attraction for Partially Unknown Nonlinear Systems: An Sum-of-Squares Approach","author":"huang","year":"2022","journal-title":"Proc Chinese Control and Decision Conf"},{"key":"ref35","article-title":"Mosek optimization toolbox for Matlab","author":"aps","year":"2019","journal-title":"User's Guide And Reference Manual Ver 4"},{"key":"ref34","author":"seiler","year":"2013","journal-title":"SOSOPT A Toolbox for Polynomial Optimization"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/robotics2030122"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2011.5940562"},{"key":"ref13","article-title":"Deep reinforcement learning for autonomous driving: A survey","author":"kiran","year":"2021","journal-title":"IEEE Trans on Intelligent Transportation Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8431617"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2894587"},{"key":"ref16","article-title":"Domain of attraction: analysis and control via SOS pro-gramming","volume":"415","author":"chesi","year":"2011","journal-title":"Springer Science & Business Media"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2012.2217971"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2014.2321197"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798586"},{"key":"ref28","author":"martin","year":"2014","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460471"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560769"},{"key":"ref29","first-page":"659","article-title":"Uniform error bounds for Gaussian process regression with application to safe control","author":"lederer","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref5","author":"lillicrap","year":"2015","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref8","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.02.003"},{"key":"ref2","first-page":"1329","article-title":"Bench-marking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"Proc 7th Int Conf Machine Learning"},{"key":"ref9","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc 7th Int Conf Machine Learning"},{"key":"ref1","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","first-page":"909","article-title":"A Safe model-based reinforcement learning with stability guarantees","author":"felix","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref22","author":"steven","year":"2022","journal-title":"Safe reinforcement learning via shielding"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"ref24","first-page":"1141","article-title":"Control Regularization for Reduced Variance Reinforcement Learning","author":"cheng","year":"2019","journal-title":"Proc 7th Int Conf Machine Learning"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref26","article-title":"Safety-Critical Control and Plan-ning for Obstacle Avoidance between Polytopes with Control Barrier Functions","author":"akshay","year":"2022","journal-title":"Proc Int Conf on Robotics and Automation"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2015.7172044"}],"event":{"name":"2022 IEEE Conference on Control Technology and Applications (CCTA)","location":"Trieste, Italy","start":{"date-parts":[[2022,8,23]]},"end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 IEEE Conference on Control Technology and Applications (CCTA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9965973\/9965785\/09966192.pdf?arnumber=9966192","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:40:07Z","timestamp":1672083607000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9966192\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,23]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/ccta49430.2022.9966192","relation":{},"subject":[],"published":{"date-parts":[[2022,8,23]]}}}