{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T16:35:41Z","timestamp":1776875741818,"version":"3.51.2"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2023YFB4302003"],"award-info":[{"award-number":["2023YFB4302003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3443916","type":"journal-article","created":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T17:35:49Z","timestamp":1723743349000},"page":"10876-10890","source":"Crossref","is-referenced-by-count":13,"title":["Safe Reinforcement Learning With Dual Robustness"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2868-1153","authenticated-orcid":false,"given":"Zeyang","family":"Li","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3504-3065","authenticated-orcid":false,"given":"Chuxiong","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9812-7709","authenticated-orcid":false,"given":"Yunan","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7222-0019","authenticated-orcid":false,"given":"Yujie","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4923-3633","authenticated-orcid":false,"given":"Shengbo Eben","family":"Li","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility & College of AI, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223407"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05732-2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3163816"},{"issue":"1","key":"ref6","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garc\u0131a","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00573-6"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3266277"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-7784-8"},{"key":"ref10","first-page":"1110","article-title":"Learning to walk in the real world with minimal human effort","volume-title":"Proc. Conf. Robot Learn.","author":"Ha"},{"issue":"1","key":"ref11","first-page":"6070","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref12","article-title":"Reward constrained policy optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tessler"},{"key":"ref13","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achiam"},{"key":"ref14","article-title":"Projection-based constrained policy optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/130914565"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2638961"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1004353"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3238656"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029720"},{"key":"ref20","first-page":"97","article-title":"Joint synthesis of safety certificate and safe control policy using constrained reinforcement learning","volume-title":"Proc. Learn. Dyn. Control Conf.","author":"Ma"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2011.2105730"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794107"},{"key":"ref23","first-page":"25 636","article-title":"Reachability constrained reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/make4010013"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123186"},{"key":"ref26","first-page":"21 024","article-title":"Robust deep reinforcement learning against adversarial perturbations on state observations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3278715"},{"key":"ref28","first-page":"6215","article-title":"Action robust reinforcement learning and applications in continuous control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tessler"},{"key":"ref29","first-page":"839","article-title":"Robustness in Markov decision problems with uncertain transition matrices","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nilim"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6086"},{"key":"ref31","first-page":"1321","article-title":"Approximate dynamic programming for two-player zero-sum Markov games","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Perolat"},{"key":"ref32","first-page":"2817","article-title":"Robust adversarial reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pinto"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3041469"},{"key":"ref34","article-title":"On the robustness of safe reinforcement learning under observational perturbations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref35","first-page":"21 586","article-title":"Towards robust and safe reinforcement learning with benign off-policy data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3336263"},{"key":"ref37","first-page":"13 644","article-title":"Constrained variational policy optimization for safe reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3290-0"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2982585"},{"key":"ref40","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref41","first-page":"8693","article-title":"Approximate heavily-constrained learning with lagrange multiplier models","volume-title":"PRoc. Adv. Neural Inf. Process. Syst.","author":"Narasimhan"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref43","article-title":"Bullet-safety-gym: A framework for constrained reinforcement learning","author":"Gronauer","year":"2022"},{"key":"ref44","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10637743.pdf?arnumber=10637743","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T18:38:25Z","timestamp":1741372705000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10637743\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":45,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3443916","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}