{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T17:03:09Z","timestamp":1770483789452,"version":"3.49.0"},"reference-count":52,"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":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFB2504704-02"],"award-info":[{"award-number":["2023YFB2504704-02"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52402522"],"award-info":[{"award-number":["52402522"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012401","name":"Beijing Science and Technology Planning Project","doi-asserted-by":"publisher","award":["Z241100003524011"],"award-info":[{"award-number":["Z241100003524011"]}],"id":[{"id":"10.13039\/501100012401","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tits.2025.3611296","type":"journal-article","created":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T17:42:19Z","timestamp":1760377339000},"page":"22246-22261","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Option Hierarchical Reinforcement Learning Framework With State Segmentation for Mixed On-Ramp Merging"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7233-9817","authenticated-orcid":false,"given":"Zoutao","family":"Wen","sequence":"first","affiliation":[{"name":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5968-103X","authenticated-orcid":false,"given":"Huachun","family":"Tan","sequence":"additional","affiliation":[{"name":"School of Interdisciplinary Science, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5549-5798","authenticated-orcid":false,"given":"Yanan","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1764-0392","authenticated-orcid":false,"given":"Hailong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, North University of China, Taiyuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4969-4334","authenticated-orcid":false,"given":"Peifeng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinguo","family":"Chen","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Institute of Software, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5582-7289","authenticated-orcid":false,"given":"Bolin","family":"Gao","sequence":"additional","affiliation":[{"name":"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\/TITS.2020.3046643"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2974291"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2024.10.021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtte.2021.07.003"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3024655"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3015748"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.trip.2021.100425"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2024.3349511"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IV55156.2024.10588704"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103008"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref14","article-title":"Trust region policy optimization","author":"Schulman","year":"2015","journal-title":"arXiv:1502.05477"},{"key":"ref15","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3008612"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304647"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103650"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TTE.2021.3138140"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3221450"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461233"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3276416"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121242"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3087314"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3453160"},{"key":"ref26","first-page":"271","article-title":"Feudal reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"5","author":"Dayan"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref29","first-page":"13031","article-title":"The option keyboard: Combining skills in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Barreto"},{"key":"ref30","first-page":"2012","article-title":"DAC: The double actor-critic architecture for learning options","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref31","article-title":"Hierarchical reinforcement learning by discovering intrinsic options","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341496"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3096666"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.005.2300020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304841"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561195"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3285440"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3457776"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/9.905687"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10422296"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2021.09.004"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123543"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3069908"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1049\/itr2.12494"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52825\/scp.v1i.95"},{"key":"ref47","first-page":"399","article-title":"Benchmarks for reinforcement learning in mixed-autonomy traffic","volume-title":"Proc. 2nd Conf. Robot Learn.","author":"Vinitsky"},{"key":"ref48","volume-title":"Next Generation Simulation (NGSIM) Vehicle Trajectories and Supporting Data","year":"2017"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3390\/s21020464"},{"key":"ref50","first-page":"2","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. 4th Int. Conf. Learn. Represent.","author":"Lillicrap"},{"key":"ref51","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref52","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Deep Reinforcement Learn. Symp.","author":"Haarnoja"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/11278554\/11202663.pdf?arnumber=11202663","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T20:52:07Z","timestamp":1770411127000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11202663\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":52,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tits.2025.3611296","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}