{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T20:31:33Z","timestamp":1793478693726,"version":"4.5.0"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2047454"],"award-info":[{"award-number":["CNS-2047454"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100002427","name":"Ford Motor Company","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002427","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/lra.2024.3379805","type":"journal-article","created":{"date-parts":[[2024,3,20]],"date-time":"2024-03-20T14:35:28Z","timestamp":1710945328000},"page":"4639-4646","source":"Crossref","is-referenced-by-count":24,"title":["Safety-Aware Causal Representation for Trustworthy Offline Reinforcement Learning in Autonomous Driving"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3786-3557","authenticated-orcid":false,"given":"Haohong","family":"Lin","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3218-8792","authenticated-orcid":false,"given":"Wenhao","family":"Ding","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7412-5074","authenticated-orcid":false,"given":"Zuxin","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0782-6385","authenticated-orcid":false,"given":"Yaru","family":"Niu","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9707-7503","authenticated-orcid":false,"given":"Jiacheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5280-7174","authenticated-orcid":false,"given":"Yuming","family":"Niu","sequence":"additional","affiliation":[{"name":"Ford Motor Company, Dearborn, MI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9400-8446","authenticated-orcid":false,"given":"Ding","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917306"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919880273"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3046646"},{"key":"ref4","first-page":"1154","article-title":"Offline reinforcement learning from images with latent space models","volume-title":"Proc. Learn. Dyn. Control","author":"Rafailov","year":"2021"},{"key":"ref5","first-page":"812","article-title":"CausalAF: Causal autoregressive flow for safety-critical driving scenario generation","volume-title":"Proc. Conf. Robot Learn.","author":"Ding","year":"2023"},{"key":"ref6","first-page":"459","article-title":"Plant: Explainable planning transformers via object-level representations","volume-title":"Proc. Conf. Robot Learn.","author":"Renz","year":"2023"},{"key":"ref7","first-page":"726","article-title":"Safety-enhanced autonomous driving using interpretable sensor fusion transformer","volume-title":"Proc. Conf. Robot Learn.","author":"Shao","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3259322"},{"key":"ref9","article-title":"Trustworthy reinforcement learning against intrinsic vulnerabilities: Robustness, safety, and generalizability","author":"Xu","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3064284"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04357-7"},{"key":"ref12","article-title":"Fastrlap: A system for learning high-speed driving via deep RL and autonomous practicing","volume-title":"Proc. ICRA Workshop Pretraining Robot.","author":"Shah","year":"2023"},{"key":"ref13","article-title":"Structure in reinforcement learning: A survey and open problems","author":"Mohan","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02105"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2019.00145"},{"key":"ref16","first-page":"3952","article-title":"Invariant causal imitation learning for generalizable policies","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Bica","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594201"},{"key":"ref18","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Kumar","year":"2019"},{"key":"ref19","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20855"},{"key":"ref21","first-page":"21611","article-title":"Constrained decision transformer for offline safe reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9922100"},{"key":"ref23","article-title":"Datasets and benchmarks for offline safe reinforcement learning","author":"Liu","year":"2023"},{"key":"ref24","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achiam","year":"2017"},{"key":"ref25","first-page":"13644","article-title":"Constrained variational policy optimization for safe reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968287"},{"key":"ref27","first-page":"3703","article-title":"Batch policy learning under constraints","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Le","year":"2019"},{"key":"ref28","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Chen","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3372625"},{"key":"ref30","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Janner","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974682"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref33","article-title":"Learning invariant representations for reinforcement learning without reconstruction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2020"},{"key":"ref34","first-page":"2307","article-title":"Offline reinforcement learning with pseudometric learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dadashi","year":"2021"},{"key":"ref35","first-page":"26532","article-title":"Generalizing goal-conditioned reinforcement learning with variational causal reasoning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Ding","year":"2022"},{"key":"ref36","article-title":"Seeing is not believing: Robust reinforcement learning against spurious correlation","volume-title":"proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Ding","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561593"},{"key":"ref38","volume-title":"Elements of Causal Inference: Foundations and Learning Algorithms","author":"Peters","year":"2017"},{"key":"ref39","volume-title":"Towards a Unified Theory of State Abstraction for MDPs","author":"Li","year":"2006"},{"key":"ref40","first-page":"162","article-title":"Metrics for finite Markov decision processes","volume-title":"Proc. 20th Conf. Uncertainty Artif. Intell.","author":"Ferns","year":"2004"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3190471"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3141\/1999-10"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7083369\/10474437\/10476686-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10474437\/10476686.pdf?arnumber=10476686","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,10]],"date-time":"2024-04-10T02:26:57Z","timestamp":1712716017000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10476686\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":42,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3379805","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}