{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T06:12:01Z","timestamp":1760508721317,"version":"build-2065373602"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T00:00:00Z","timestamp":1750723200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T00:00:00Z","timestamp":1750723200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"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":[[2025,6,24]]},"DOI":"10.23919\/ecc65951.2025.11187149","type":"proceedings-article","created":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T17:38:09Z","timestamp":1760463489000},"page":"892-897","source":"Crossref","is-referenced-by-count":0,"title":["On the Design of Safe Continual RL Methods for Control of Nonlinear Systems"],"prefix":"10.23919","author":[{"given":"Austin","family":"Coursey","sequence":"first","affiliation":[{"name":"Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcos","family":"Quinones-Grueiro","sequence":"additional","affiliation":[{"name":"Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gautam","family":"Biswas","sequence":"additional","affiliation":[{"name":"Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3301273"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04357-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2021.103569"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3457538"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3024161"},{"key":"ref7","article-title":"Safe model-based reinforcement learning with stability guarantees","volume":"30","author":"Berkenkamp","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.5132"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"ref10","first-page":"22","article-title":"Constrained policy optimization","volume-title":"International conference on machine learning","author":"Achiam"},{"issue":"1","key":"ref11","first-page":"2","article-title":"Benchmarking safe exploration in deep reinforcement learning","volume":"7","author":"Ray","year":"2019"},{"key":"ref12","article-title":"Safety gymnasium: A unified safe reinforcement learning benchmark","volume":"36","author":"Ji","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13673"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3280085"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref16","article-title":"Experience replay for continual learning","volume":"32","author":"Rolnick","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"2361","article-title":"Safe policy search for lifelong reinforcement learning with sublinear regret","volume-title":"International Conference on Machine Learning","author":"Ammar"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561593"},{"key":"ref19","first-page":"936","article-title":"Sharing lifelong reinforcement learning knowledge via modulating masks","volume-title":"Conference on Lifelong Learning Agents","author":"Nath"},{"volume-title":"Constrained Markov Decision Processes","year":"1999","author":"Altman","key":"ref20"}],"event":{"name":"2025 European Control Conference (ECC)","start":{"date-parts":[[2025,6,24]]},"location":"Thessaloniki, Greece","end":{"date-parts":[[2025,6,27]]}},"container-title":["2025 European Control Conference (ECC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11186289\/11186290\/11187149.pdf?arnumber=11187149","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T05:40:46Z","timestamp":1760506846000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11187149\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,24]]},"references-count":20,"URL":"https:\/\/doi.org\/10.23919\/ecc65951.2025.11187149","relation":{},"subject":[],"published":{"date-parts":[[2025,6,24]]}}}