{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T12:10:55Z","timestamp":1768738255260,"version":"3.49.0"},"reference-count":47,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62273256"],"award-info":[{"award-number":["62273256"]}],"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":["62373289"],"award-info":[{"award-number":["62373289"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Veh."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tiv.2024.3406679","type":"journal-article","created":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T13:33:43Z","timestamp":1716989623000},"page":"8089-8103","source":"Crossref","is-referenced-by-count":5,"title":["HGRL: Human-Driving-Data Guided Reinforcement Learning for Autonomous Driving"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2534-5528","authenticated-orcid":false,"given":"Hejian","family":"Zhuang","sequence":"first","affiliation":[{"name":"School of Automotive Studies, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8015-9788","authenticated-orcid":false,"given":"Hongqing","family":"Chu","sequence":"additional","affiliation":[{"name":"School of Automotive Studies, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4880-5054","authenticated-orcid":false,"given":"Yafei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Shanghai Jiaotong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5155-7835","authenticated-orcid":false,"given":"Bingzhao","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Automotive Studies, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1724-8649","authenticated-orcid":false,"given":"Hong","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Tongji University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3223131"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3276218"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3188662"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3036984"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2023.10.005"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04357-7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3322426"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3372522"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3348134"},{"key":"ref11","first-page":"6152","article-title":"Pebble: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee","year":"2021"},{"key":"ref12","article-title":"Preference transformer: Modeling human preferences using transformers for RL","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Kim","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3323138"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10108-x"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3142822"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3336768"},{"key":"ref17","article-title":"Deep reinforcement learning from human preferences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Christiano","year":"2017"},{"key":"ref18","article-title":"Open problems and fundamental limitations of reinforcement learning from human feedback","author":"Casper","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_36"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827073"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2022.05.017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3144867"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968205"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3088935"},{"key":"ref27","article-title":"Generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Ho","year":"2016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560907"},{"key":"ref29","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3253281"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980101"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3254579"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/robot.2010.5509799"},{"key":"ref35","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen","year":"2021"},{"key":"ref36","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Janner","year":"2021"},{"key":"ref37","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref39","article-title":"Training a helpful and harmless assistant with reinforcement learning from human feedback","author":"Bai","year":"2022"},{"key":"ref40","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015"},{"key":"ref41","article-title":"Implementation matters in deep policy gradients: A case study on PPO and TRPO","author":"Engstrom","year":"2020"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2913998"},{"key":"ref43","article-title":"An environment for autonomous driving decision-making","author":"Leurent","year":"2018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569552"},{"key":"ref45","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3274536"},{"key":"ref47","first-page":"80","article-title":"Augmenting gail with BC for sample efficient imitation learning","volume-title":"Proc. Conf. Robot Learn.","author":"Jena","year":"2021"}],"container-title":["IEEE Transactions on Intelligent Vehicles"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274857\/11077821\/10541090.pdf?arnumber=10541090","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T17:47:18Z","timestamp":1752860838000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10541090\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":47,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tiv.2024.3406679","relation":{},"ISSN":["2379-8904","2379-8858"],"issn-type":[{"value":"2379-8904","type":"electronic"},{"value":"2379-8858","type":"print"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}