{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T06:10:10Z","timestamp":1755843010648,"version":"3.44.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T00:00:00Z","timestamp":1751932800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T00:00:00Z","timestamp":1751932800000},"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":[[2025,7,8]]},"DOI":"10.23919\/acc63710.2025.11107899","type":"proceedings-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:17:51Z","timestamp":1755800271000},"page":"194-199","source":"Crossref","is-referenced-by-count":0,"title":["When to Localize? A Risk-Constrained Reinforcement Learning Approach"],"prefix":"10.23919","author":[{"given":"Chak Lam","family":"Shek","sequence":"first","affiliation":[{"name":"University of Maryland,College Park,MD,USA,20742"}]},{"given":"Kasra","family":"Torshizi","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,MD,USA,20742"}]},{"given":"Troi","family":"Williams","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,MD,USA,20742"}]},{"given":"Pratap","family":"Tokekar","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,MD,USA,20742"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21472"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SSRR62954.2024.10770054"},{"key":"ref3","article-title":"Monte-Carlo Tree Search for Constrained POMDPs","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Lee","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3152724"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/34.3905"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-017-9615-3"},{"key":"ref7","first-page":"1346","article-title":"Active mobile robot localization","volume-title":"Proceedings of the Fifteenth International Joint Conference on Artifical Intelligence - Volume 2, ser. IJCAI\u201997","author":"Burgard"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/70.736774"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3248510"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2970650"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341650"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907417"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2777526"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2932575"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21925"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3013906"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MRS60187.2023.10416783"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref18"},{"article-title":"Asynchronous methods for deep reinforcement learning","year":"2016","author":"Mnih","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636140"},{"article-title":"Recurrent model-free rl can be a strong baseline for many pomdps","year":"2022","author":"Ni","key":"ref21"},{"key":"ref22","first-page":"243","article-title":"Safe reinforcement learning with linear function approximation","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"139","author":"Amani"},{"article-title":"Accelerated primal-dual policy optimization for safe reinforcement learning","year":"2018","author":"Liang","key":"ref23"},{"article-title":"Convergent policy optimization for safe reinforcement learning","year":"2019","author":"Yu","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11768-011-0177-1"},{"key":"ref26","first-page":"153","article-title":"Toward a brain-inspired system: Deep recurrent reinforcement learning for a simulated self-driving agent","volume":"11","author":"Ho","year":"2017","journal-title":"Frontiers in Neuroscience"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"article-title":"Evolving rewards to automate reinforcement learning","volume-title":"6th ICML Workshop on Automated Machine Learning","author":"Faust","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRAE56463.2022.10056178"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/AUV50043.2020.9267899"}],"event":{"name":"2025 American Control Conference (ACC)","start":{"date-parts":[[2025,7,8]]},"location":"Denver, CO, USA","end":{"date-parts":[[2025,7,10]]}},"container-title":["2025 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11107441\/11107442\/11107899.pdf?arnumber=11107899","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:34:31Z","timestamp":1755840871000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11107899\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,8]]},"references-count":30,"URL":"https:\/\/doi.org\/10.23919\/acc63710.2025.11107899","relation":{},"subject":[],"published":{"date-parts":[[2025,7,8]]}}}