{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T05:57:04Z","timestamp":1761631024010,"version":"3.37.3"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,6]]},"DOI":"10.1109\/cdc51059.2022.9992470","type":"proceedings-article","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T19:26:56Z","timestamp":1673378816000},"page":"3409-3415","source":"Crossref","is-referenced-by-count":4,"title":["Safe Reinforcement Learning via Confidence-Based Filters"],"prefix":"10.1109","author":[{"given":"Sebastian","family":"Curi","sequence":"first","affiliation":[{"name":"ETH Zurich,LAS Group,Department of Computer Science,Switzerland"}]},{"given":"Armin","family":"Lederer","sequence":"additional","affiliation":[{"name":"Technical University of Munich,Chair of Information-Oriented Control,Department of Electrical and Computer Engineering,Germany"}]},{"given":"Sandra","family":"Hirche","sequence":"additional","affiliation":[{"name":"Technical University of Munich,Chair of Information-Oriented Control,Department of Electrical and Computer Engineering,Germany"}]},{"given":"Andreas","family":"Krause","sequence":"additional","affiliation":[{"name":"ETH Zurich,LAS Group,Department of Computer Science,Switzerland"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"article-title":"Continuous control with deep reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Lillicrap","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"key":"ref4","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Gar\u0107\u0131a","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref7","first-page":"30","article-title":"Constrained policy optimization","volume-title":"International Conference on Machine Learning","author":"Achiam"},{"key":"ref8","first-page":"7555","article-title":"Constrained reinforcement learning has zero duality gap","author":"Paternain","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","first-page":"3304","article-title":"Provably\u00b4 efficient safe exploration via primal-dual policy optimization","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Ding"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814865"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2753460"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619572"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3006279"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2876389"},{"key":"ref15","first-page":"708","article-title":"Learning for safety-critical control with control barrier functions","author":"Taylor","year":"2019","journal-title":"Learning for Dynamics & Control"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483182"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3049335"},{"key":"ref18","article-title":"Efficient model-based reinforcement learning through optimistic policy search and planning","author":"Curi","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2016.2602087"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.2013.801082"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1155\/2013\/356746"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-3267-7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.03.076"},{"key":"ref24","first-page":"2254","article-title":"Combining pessimism with optimism for robust and efficient model-based deep reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Curi"},{"key":"ref25","first-page":"4310","article-title":"Robust adversarial reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Pinto"},{"key":"ref26","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International Conference on Machine Learning","author":"Haarnoja"},{"article-title":"Constrained model-based reinforcement learning with robust cross-entropy method","year":"2020","author":"Liu","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-011-5235-x"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-444-53859-8.00003-5"}],"event":{"name":"2022 IEEE 61st Conference on Decision and Control (CDC)","start":{"date-parts":[[2022,12,6]]},"location":"Cancun, Mexico","end":{"date-parts":[[2022,12,9]]}},"container-title":["2022 IEEE 61st Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9992315\/9992317\/09992470.pdf?arnumber=9992470","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T02:28:43Z","timestamp":1710383323000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9992470\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/cdc51059.2022.9992470","relation":{},"subject":[],"published":{"date-parts":[[2022,12,6]]}}}