{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T17:45:22Z","timestamp":1786211122242,"version":"3.56.0"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176259"],"award-info":[{"award-number":["62176259"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62373364"],"award-info":[{"award-number":["62373364"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013064","name":"Key Research and Development Program of Jiangsu Province","doi-asserted-by":"publisher","award":["BE2022095"],"award-info":[{"award-number":["BE2022095"]}],"id":[{"id":"10.13039\/501100013064","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tits.2025.3587341","type":"journal-article","created":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T17:46:58Z","timestamp":1752860818000},"page":"18854-18863","source":"Crossref","is-referenced-by-count":3,"title":["Uncertainty-Based Alternative Diffusion Policy for Safe Autonomous Driving"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7370-9289","authenticated-orcid":false,"given":"Xiaohan","family":"Huang","sequence":"first","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5327-1088","authenticated-orcid":false,"given":"Xuesong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2022-9999","authenticated-orcid":false,"given":"Yuhu","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3032227"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3292253"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1049\/itr2.70013"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref6","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.0164"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3368474"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250269"},{"key":"ref9","first-page":"11784","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref10","first-page":"28701","article-title":"Policy regularization with dataset constraint for offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ran"},{"key":"ref11","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kumar"},{"key":"ref12","first-page":"5774","article-title":"Offline reinforcement learning with Fisher divergence critic regularization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kostrikov"},{"key":"ref13","first-page":"1","article-title":"Pessimistic bootstrapping for uncertainty-driven offline reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bai"},{"key":"ref14","first-page":"7436","article-title":"Uncertainty-based offline reinforcement learning with diversified Q-ensemble","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"An"},{"key":"ref15","first-page":"18267","article-title":"Why so pessimistic? Estimating uncertainties for offline RL through ensembles, and why their independence matters","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ghasemipour"},{"key":"ref16","first-page":"1","article-title":"Deep exploration via bootstrapped DQN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Osband"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v18i1.21959"},{"key":"ref18","first-page":"20485","article-title":"Offline reinforcement learning with closed-form policy improvement operators","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref19","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref20","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv:2011.13456"},{"key":"ref21","first-page":"1","article-title":"Diffusion policies as an expressive policy class for offline reinforcement learning","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref22","article-title":"IDQL: Implicit Q-learning as an actor-critic method with diffusion policies","author":"Hansen-Estruch","year":"2023","journal-title":"arXiv:2304.10573"},{"key":"ref23","first-page":"1","article-title":"Planning with diffusion for flexible behavior synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"J\u00e4nner"},{"key":"ref24","first-page":"1","article-title":"Learning a diffusion model policy from rewards via Q-score matching","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Psenka"},{"key":"ref25","first-page":"78451","article-title":"Oasis: Conditional distribution shaping for offline safe reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yao"},{"key":"ref26","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref27","article-title":"Training diffusion models with reinforcement learning","author":"Black","year":"2023","journal-title":"arXiv:2305.13301"},{"key":"ref28","article-title":"Datasets and benchmarks for offline safe reinforcement learning","author":"Liu","year":"2023","journal-title":"arXiv:2306.09303"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3190471"},{"key":"ref30","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. 1st Annu. Conf. Robot Learn.","volume":"78","author":"Dosovitskiy"},{"key":"ref31","article-title":"Understanding diffusion models: A unified perspective","author":"Luo","year":"2022","journal-title":"arXiv:2208.11970"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20855"},{"key":"ref34","first-page":"21611","article-title":"Constrained decision transformer for offline safe reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref35","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3379805"},{"key":"ref37","first-page":"21127","article-title":"Safe offline reinforcement learning with real-time budget constraints","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lin"},{"key":"ref38","first-page":"1","article-title":"Safe offline reinforcement learning with feasibility-guided diffusion model","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zheng"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/11241045\/11083769.pdf?arnumber=11083769","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T18:44:25Z","timestamp":1762973065000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11083769\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":38,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tits.2025.3587341","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}