{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T04:17:26Z","timestamp":1768364246915,"version":"3.49.0"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF China","award":["52202487"],"award-info":[{"award-number":["52202487"]}]},{"name":"NSF China","award":["62273256"],"award-info":[{"award-number":["62273256"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["FRF-OT-23-02"],"award-info":[{"award-number":["FRF-OT-23-02"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Young Elite Scientists Sponsorship Program by CAST","award":["2023QNRC001"],"award-info":[{"award-number":["2023QNRC001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Veh."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tiv.2024.3432891","type":"journal-article","created":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T14:44:54Z","timestamp":1721832294000},"page":"1759-1770","source":"Crossref","is-referenced-by-count":2,"title":["Multi-Style Distributional Soft Actor-Critic: Learning a Unified Policy for Diverse Control Behaviors"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4566-1103","authenticated-orcid":false,"given":"Liming","family":"Xiao","sequence":"first","affiliation":[{"name":"School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1539-472X","authenticated-orcid":false,"given":"Yao","family":"Lyu","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7455-9694","authenticated-orcid":false,"given":"Fawang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8442-3205","authenticated-orcid":false,"given":"Liangfa","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangyuan","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, University of Science and Technology Beijing, 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":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3697-1576","authenticated-orcid":false,"given":"Jingliang","family":"Duan","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3236239"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3372522"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3165178"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3275732"},{"key":"ref5","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018"},{"key":"ref6","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. 35th Int. Conf. Mach. Learn. 2018","author":"Fujimoto","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460756"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3348134"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2608003"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2024.3364428"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2023.104585"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3150493"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3157049"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139555"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3088935"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160751"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2019.1911825"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342038"},{"key":"ref22","first-page":"6948","article-title":"Reinforcement learning can be more efficient with multiple rewards","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Dann","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294300"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3255264"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.386"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i19.30170"},{"key":"ref27","first-page":"28954","article-title":"Conservative offline model-based policy optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yu","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103770"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2022.3144586"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00687-5"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-7784-8_10"},{"key":"ref32","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. 34th Int. Conf. Mach. Learn. 2017","author":"Haarnoja"},{"key":"ref33","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn. 2018","author":"Haarnoja","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082568"},{"key":"ref35","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Bellemare","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref37","first-page":"1096","article-title":"Implicit quantile networks for distributional reinforcement learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Dabney","year":"2018"},{"key":"ref38","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn. 2017","author":"Bellemare"},{"key":"ref39","article-title":"Distributed distributional deterministic policy gradients","volume-title":"Proc. 6th Int. Conf. Learn. Representations 2018","author":"Barth-Maron","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3537087"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref42","article-title":"OpenAI gym","author":"Brockman","year":"2016"},{"key":"ref43","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. 4th Int. Conf. Learn. Representations 2016","author":"Lillicrap","year":"2016"},{"key":"ref44","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn. 2015","author":"Schulman"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.commtr.2023.100096"}],"container-title":["IEEE Transactions on Intelligent Vehicles"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7274857\/11125674\/10608151.pdf?arnumber=10608151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T21:00:27Z","timestamp":1768338027000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10608151\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":45,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tiv.2024.3432891","relation":{},"ISSN":["2379-8904","2379-8858"],"issn-type":[{"value":"2379-8904","type":"electronic"},{"value":"2379-8858","type":"print"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}