{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T05:57:33Z","timestamp":1761631053343},"reference-count":21,"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"}],"funder":[{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","award":["N00014-17-1-2622"],"award-info":[{"award-number":["N00014-17-1-2622"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010663","name":"European Research Council","doi-asserted-by":"publisher","award":["864686"],"award-info":[{"award-number":["864686"]}],"id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,13]]},"DOI":"10.1109\/cdc49753.2023.10383524","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T13:38:36Z","timestamp":1705671516000},"page":"1040-1045","source":"Crossref","is-referenced-by-count":2,"title":["Risk-Sensitive Inhibitory Control for Safe Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Armin","family":"Lederer","sequence":"first","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich,Chair of Information-oriented Control (ITR),Munich,Germany,80333"}]},{"given":"Erfaun","family":"Noorani","sequence":"additional","affiliation":[{"name":"Institute for Systems Research (ISR) at the University of Maryland,Department of Electrical and Computer Engineering,College Park,MD,USA"}]},{"given":"John S.","family":"Baras","sequence":"additional","affiliation":[{"name":"Institute for Systems Research (ISR) at the University of Maryland,Department of Electrical and Computer Engineering,College Park,MD,USA"}]},{"given":"Sandra","family":"Hirche","sequence":"additional","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich,Chair of Information-oriented Control (ITR),Munich,Germany,80333"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.126.2.220"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"ref6","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":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483182"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3049335"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.077"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9992470"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcn.2017.05.007"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2021.3086854"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3206.001.0001"},{"key":"ref14","first-page":"6405","article-title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","author":"Lakshminarayanan","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/9.286253"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.03.076"},{"key":"ref17","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","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.4310\/CIS.2006.v6.n3.a1"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref20","first-page":"4768","article-title":"RLlib: Abstractions for Distributed Reinforcement Learning","volume-title":"International Conference on Machine Learning","author":"Liang","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-444-53859-8.00003-5"}],"event":{"name":"2023 62nd IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2023,12,13]]},"location":"Singapore, Singapore","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\/10383524.pdf?arnumber=10383524","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T11:25:02Z","timestamp":1706009102000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10383524\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,13]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/cdc49753.2023.10383524","relation":{},"subject":[],"published":{"date-parts":[[2023,12,13]]}}}