{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T19:28:10Z","timestamp":1780428490304,"version":"3.54.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Science Fund for Distinguished Young Scholars of China","award":["52325212"],"award-info":[{"award-number":["52325212"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52372394"],"award-info":[{"award-number":["52372394"]}],"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","award":["22120230311"],"award-info":[{"award-number":["22120230311"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/lra.2025.3623016","type":"journal-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:42:36Z","timestamp":1760722956000},"page":"12772-12779","source":"Crossref","is-referenced-by-count":3,"title":["Multi-Timescale Hierarchical Reinforcement Learning for Unified Behavior and Control of Autonomous Driving"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7781-2108","authenticated-orcid":false,"given":"Guizhe","family":"Jin","sequence":"first","affiliation":[{"name":"School of Automotive Studies, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6246-3404","authenticated-orcid":false,"given":"Zhuoren","family":"Li","sequence":"additional","affiliation":[{"name":"School of Automotive Studies, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3513-1708","authenticated-orcid":false,"given":"Bo","family":"Leng","sequence":"additional","affiliation":[{"name":"School of Automotive Studies, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0450-2189","authenticated-orcid":false,"given":"Ran","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Automotive Studies, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1673-2658","authenticated-orcid":false,"given":"Lu","family":"Xiong","sequence":"additional","affiliation":[{"name":"School of Automotive Studies, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8772-9627","authenticated-orcid":false,"given":"Chen","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Data and Systems Engineering, University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3577523"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s42154-023-00231-6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3151651"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564412"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3150793"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.102"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00340"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2023.104328"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2024.3349511"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3326548"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9922428"},{"key":"ref12","article-title":"Extensive exploration in complex traffic scenarios using hierarchical reinforcement learning","author":"Zhang","year":"2025"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC58415.2024.10920092"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3185255"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.005.2300020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3457776"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3266940"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.55092\/aias20240009"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s42154-022-00177-1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341449"},{"key":"ref21","first-page":"21847","article-title":"Accelerating robotic reinforcement learning via parameterized action primitives","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dalal","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3568308"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/machines12040213"},{"key":"ref24","article-title":"Hybrid action based reinforcement learning for multi-objective compatible autonomous driving","author":"Jin","year":"2025"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.4271\/2024-01-7035"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3458439"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.102980"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2024.104606"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160371"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3368231"},{"key":"ref31","first-page":"2012","article-title":"DAC: The double actor-critic architecture for learning options","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2019"},{"key":"ref32","article-title":"Parametrized deep Q-networks learning: Reinforcement learning with discrete-continuous hybrid action space","author":"Xiong","year":"2018"},{"key":"ref33","article-title":"An environment for autonomous driving decision-making","author":"Leurent","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995816"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569552"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11215960\/11206491.pdf?arnumber=11206491","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T19:02:14Z","timestamp":1764010934000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11206491\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":35,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3623016","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}