{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T05:19:34Z","timestamp":1775711974278,"version":"3.50.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/lra.2024.3512374","type":"journal-article","created":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T19:18:20Z","timestamp":1733426300000},"page":"788-795","source":"Crossref","is-referenced-by-count":8,"title":["Safety Filtering While Training: Improving the Performance and Sample Efficiency of Reinforcement Learning Agents"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4566-6466","authenticated-orcid":false,"given":"Federico Pizarro","family":"Bejarano","sequence":"first","affiliation":[{"name":"Learning Systems and Robotics Lab, University of Toronto, Toronto, ON, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9893-9889","authenticated-orcid":false,"given":"Lukas","family":"Brunke","sequence":"additional","affiliation":[{"name":"Learning Systems and Robotics Lab, University of Toronto, Toronto, ON, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4012-4668","authenticated-orcid":false,"given":"Angela P.","family":"Schoellig","sequence":"additional","affiliation":[{"name":"Learning Systems and Robotics Lab, University of Toronto, Toronto, ON, Canada"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21958"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2018.00100"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-071723-102940"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2023.3291885"},{"key":"ref7","article-title":"Provably safe reinforcement learning: Conceptual analysis, survey, and benchmarking","author":"Krasowski","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196132"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10383734"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8796030"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2021.109597"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref13","article-title":"Safe exploration in continuous action spaces","author":"Dalal","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460547"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref16","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Achiam","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8430770"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/OJCSYS.2023.3256305"},{"key":"ref20","article-title":"Learn with imagination: Safe set guided state-wise constrained policy optimization","author":"Zhao","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3216996"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3152313"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1177\/09596518231153445"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.2514\/1.I011126"},{"key":"ref25","first-page":"1","article-title":"Safe reinforcement learning with chance-constrained model predictive control","volume-title":"Proc. Learn. Dyn. Control Conf.","author":"Pfrommer","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3249564"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2022.3233322"},{"key":"ref28","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Int. Conf. Mach. Learn.","volume":"99","author":"Ng","year":"1999"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2982585"},{"key":"ref30","volume-title":"Model Predictive Control: Theory, Computation, and Design","author":"Rawlings","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2023.3344226"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(99)00113-2"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s12532-021-00208-8"},{"key":"ref34","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref35","article-title":"Design of a trajectory tracking controller for a nanoquadcopter","author":"Luis","year":"2016"},{"key":"ref36","article-title":"A remote sim2real aerial competition: Fostering reproducibility and solutions\u2019 diversity in robotics challenges","author":"Teetaert","year":"2023"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10768868\/10778608.pdf?arnumber=10778608","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,17]],"date-time":"2024-12-17T05:45:52Z","timestamp":1734414352000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10778608\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":36,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3512374","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}