{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T21:09:02Z","timestamp":1768338542638,"version":"3.49.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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\/cdc45484.2021.9683748","type":"proceedings-article","created":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T15:50:18Z","timestamp":1643730618000},"page":"4694-4700","source":"Crossref","is-referenced-by-count":11,"title":["Model-Based Actor-Critic with Chance Constraint for Stochastic System"],"prefix":"10.1109","author":[{"given":"Baiyu","family":"Peng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Mu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Guan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengbo Eben","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuming","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Reward constrained policy optimization","author":"tessler","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref11","article-title":"Projection-based constrained policy optimization","author":"yang","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1666"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1016\/S0005-1098(99)00214-9","article-title":"Constrained model predictive control: Stability and optimality","volume":"36","author":"mayne","year":"2000","journal-title":"Automatica"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2019.0317"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/080734510"},{"key":"ref16","article-title":"Hierarchical reinforcement learning for self-driving decision-making without reliance on labeled driving data","volume":"abs 2001 9816","author":"duan","year":"2020","journal-title":"ArXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3026111"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9467-7"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029423"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-004-0559-y"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2014.0002"},{"key":"ref27","article-title":"Safe exploration in continuous action spaces","author":"dalal","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref6","article-title":"Challenges of realworld reinforcement learning","volume":"abs 1904 12901","author":"dulac-arnold","year":"2019","journal-title":"ArXiv"},{"key":"ref5","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garc?a","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","first-page":"6070","article-title":"Riskconstrained reinforcement learning with percentile risk criteria","volume":"18","author":"chow","year":"2017","journal-title":"The Journal of Machine Learning Research"},{"key":"ref7","article-title":"Variance adjusted actor critic algorithms","volume":"abs 1310 3697","author":"tamar","year":"2013","journal-title":"ArXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref9","first-page":"22","article-title":"Constrained policy optimization","author":"achiam","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref1","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":"ref20","article-title":"Safe policies for reinforcement learning via primal-dual methods","volume":"abs 1911 9101","author":"paternain","year":"2019","journal-title":"ArXiv"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"1859","DOI":"10.1109\/TAC.2006.884922","article-title":"Convex optimization","volume":"51","author":"boyd","year":"2006","journal-title":"IEEE Transactions on Automatic Control"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1109\/MCS.2016.2602087","article-title":"Stochastic model predictive control: An overview and perspectives for future research","volume":"36","author":"mesbah","year":"2016","journal-title":"IEEE Control Systems"},{"key":"ref24","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)"},{"key":"ref23","article-title":"Reinforcement Learning and Control","author":"li","year":"2020","journal-title":"Lecture Note Tsinghua University"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2017.10.026"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50815-3"}],"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\/09683748.pdf?arnumber=9683748","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T12:58:15Z","timestamp":1652187495000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9683748\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,14]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/cdc45484.2021.9683748","relation":{},"subject":[],"published":{"date-parts":[[2021,12,14]]}}}