{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T02:59:12Z","timestamp":1775617152022,"version":"3.50.1"},"reference-count":32,"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":"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":[{"name":"National Key Research and Development Program of China","award":["2022YFB2502901"],"award-info":[{"award-number":["2022YFB2502901"]}]},{"DOI":"10.13039\/501100001809","name":"NSF China","doi-asserted-by":"publisher","award":["52221005"],"award-info":[{"award-number":["52221005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004147","name":"Tsinghua University Initiative Scientific Research Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004147","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Tsinghua University-Toyota Joint Research Center for AI Technology of Automated Vehicle"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tits.2023.3329823","type":"journal-article","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T19:59:43Z","timestamp":1700596783000},"page":"4335-4345","source":"Crossref","is-referenced-by-count":10,"title":["A Reinforcement Learning Benchmark for Autonomous Driving in General Urban Scenarios"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4285-0495","authenticated-orcid":false,"given":"Yuxuan","family":"Jiang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1246-4860","authenticated-orcid":false,"given":"Guojian","family":"Zhan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4102-1919","authenticated-orcid":false,"given":"Zhiqian","family":"Lan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chang","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Advanced Manufacturing and Robotics, College of Engineering, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1753-2922","authenticated-orcid":false,"given":"Bo","family":"Cheng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Automotive Safety and Energy, 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":"State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3026111"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1007\/978-981-19-7784-8","volume-title":"Reinforcement Learning for Sequential Decision-Making and Control","author":"Li","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082568"},{"key":"ref4","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lillicrap"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2019.0317"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917306"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3163816"},{"issue":"6","key":"ref8","first-page":"2","volume-title":"Torcs, the open racing car simulator","volume":"4","author":"Wymann","year":"2000"},{"key":"ref9","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Dosovitskiy"},{"key":"ref10","first-page":"264","article-title":"Smarts: An open-source scalable multi-agent RL training school for autonomous driving","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Zhou"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3190471"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"ref13","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref14","first-page":"3053","article-title":"RLlib: Abstractions for distributed reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Liang"},{"issue":"267","key":"ref15","first-page":"1","article-title":"Tianshou: A highly modularized deep reinforcement learning library","volume":"23","author":"Weng","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.commtr.2023.100096"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67361-5_40"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197228"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207663"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1002\/int.22466"},{"issue":"42","key":"ref21","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":"ref22","first-page":"1","article-title":"Reward constrained policy optimization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Tessler"},{"key":"ref23","first-page":"1","article-title":"Risk-sensitive and robust decision-making: A CVaR optimization approach","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Chow"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029720"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2023.104161"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IVWorkshops54471.2021.9669260"},{"key":"ref27","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3136588"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3196167"},{"key":"ref30","article-title":"Benchmarking batch deep reinforcement learning algorithms","author":"Fujimoto","year":"2019","journal-title":"arXiv:1910.01708"},{"key":"ref31","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. (ICML)","author":"Haarnoja"},{"key":"ref32","first-page":"1110","article-title":"Learning to walk in the real world with minimal human effort","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Ha"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/10530501\/10324473.pdf?arnumber=10324473","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T02:43:59Z","timestamp":1733885039000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10324473\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":32,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tits.2023.3329823","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}