{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T10:17:50Z","timestamp":1779358670666,"version":"3.51.4"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSFC China","award":["52202487"],"award-info":[{"award-number":["52202487"]}]},{"name":"National Key Research and Development Program of China","award":["2022YFB2502901"],"award-info":[{"award-number":["2022YFB2502901"]}]},{"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. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tpami.2025.3537087","type":"journal-article","created":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T14:17:19Z","timestamp":1738246639000},"page":"3935-3946","source":"Crossref","is-referenced-by-count":56,"title":["Distributional Soft Actor-Critic With Three Refinements"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3697-1576","authenticated-orcid":false,"given":"Jingliang","family":"Duan","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\/0000-0002-0193-816X","authenticated-orcid":false,"given":"Wenxuan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4566-1103","authenticated-orcid":false,"given":"Liming","family":"Xiao","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\/0000-0001-5455-0620","authenticated-orcid":false,"given":"Jiaxin","family":"Gao","sequence":"additional","affiliation":[{"name":"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":"School of Vehicle and Mobility and College of AI, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7686-2510","authenticated-orcid":false,"given":"Chang","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Engineering, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4515-6212","authenticated-orcid":false,"given":"Ya-Qin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute for AI Industry Research, Tsinghua 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":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9333-7416","authenticated-orcid":false,"given":"Keqiang","family":"Li","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":"10.13140\/RG.2.2.18893.74727"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2024.3364428"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103452"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3322426"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3275732"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref8","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. 4th Int. Conf. Learn. Representations","author":"Lillicrap"},{"key":"ref9","first-page":"2613","article-title":"Double Q-learning","volume-title":"Proc. 23rd Adv. Neural Inf. Process. Syst.","author":"van Hasselt"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref11","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref12","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.","author":"Haarnoja"},{"key":"ref13","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2022.1081242"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10383277"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.120255"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2023.10.005"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082568"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.commtr.2023.100096"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-7784-8"},{"key":"ref21","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref22","article-title":"OpenAI gym","author":"Brockman","year":"2016"},{"key":"ref23","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref25","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Bellemare"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref27","first-page":"1096","article-title":"Implicit quantile networks for distributional reinforcement learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Dabney"},{"key":"ref28","article-title":"Fully parameterized quantile function for distributional reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref29","first-page":"5528","article-title":"Statistics and samples in distributional reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Rowland"},{"key":"ref30","first-page":"4424","article-title":"Distributional reinforcement learning for efficient exploration","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Mavrin"},{"key":"ref31","first-page":"1","article-title":"Distributed distributional deterministic policy gradients","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Barth-Maron"},{"key":"ref32","article-title":"Distributional policy optimization: An alternative approach for continuous control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tessler"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1924-6"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/14207.001.0001"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294300"},{"key":"ref36","article-title":"Universal off-policy evaluation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chandak"},{"key":"ref37","first-page":"2479","article-title":"Bayesian robust optimization for imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref38","article-title":"Estimating risk and uncertainty in deep reinforcement learning","author":"Clements","year":"2019"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3432891"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10958761\/10858686.pdf?arnumber=10858686","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T06:02:38Z","timestamp":1762927358000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10858686\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":39,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3537087","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}