{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T16:46:02Z","timestamp":1779900362894,"version":"3.53.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF Beijing","award":["JQ18010"],"award-info":[{"award-number":["JQ18010"]}]},{"DOI":"10.13039\/501100001809","name":"NSF China","doi-asserted-by":"publisher","award":["51575293"],"award-info":[{"award-number":["51575293"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSF China","doi-asserted-by":"publisher","award":["U20A20334"],"award-info":[{"award-number":["U20A20334"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004147","name":"Tsinghua University\u2013Toyota Joint Research Center for AI Technology of Automated Vehicle","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004147","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2022,11]]},"DOI":"10.1109\/tnnls.2021.3082568","type":"journal-article","created":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T14:12:14Z","timestamp":1623247934000},"page":"6584-6598","source":"Crossref","is-referenced-by-count":239,"title":["Distributional Soft Actor-Critic: Off-Policy Reinforcement Learning for Addressing Value Estimation Errors"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3697-1576","authenticated-orcid":false,"given":"Jingliang","family":"Duan","sequence":"first","affiliation":[{"name":"State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0689-0510","authenticated-orcid":false,"given":"Yang","family":"Guan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4923-3633","authenticated-orcid":false,"given":"Shengbo Eben","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1173-7230","authenticated-orcid":false,"given":"Yangang","family":"Ren","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Sun","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Cheng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref3","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn. (ICML)","author":"Mnih"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2019.0317"},{"key":"ref6","article-title":"Learning from delayed rewards","author":"Watkins","year":"1989"},{"key":"ref7","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref9","first-page":"255","article-title":"Issues in using function approximation for reinforcement learning","volume-title":"Proc. Connectionist Models Summer School","author":"Thrun"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2013.6614994"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2912443"},{"key":"ref12","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","author":"Fujimoto"},{"key":"ref13","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. 31st Int. Conf. Mach. Learn. (ICML)","author":"Silver"},{"key":"ref14","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. 4th Int. Conf. Learn. Represent. (ICLR)","author":"Lillicrap"},{"key":"ref15","first-page":"2613","article-title":"Double Q-learning","volume-title":"Proc. 23rd Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"van Hasselt"},{"key":"ref16","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. (ICML)","author":"Haarnoja"},{"key":"ref17","article-title":"Soft actor-critic algorithms and applications","volume-title":"arXiv:1812.05905","author":"Haarnoja","year":"2018"},{"key":"ref18","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn. (ICML)","author":"Bellemare"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref20","first-page":"1096","article-title":"Implicit quantile networks for distributional reinforcement learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","author":"Dabney"},{"key":"ref21","first-page":"29","article-title":"An analysis of categorical distributional reinforcement learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist. (AISTATS)","author":"Rowland"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014504"},{"key":"ref23","article-title":"Distributed distributional deterministic policy gradients","volume-title":"Proc. 6th Int. Conf. Learn. Represent. (ICLR)","author":"Barth-Maron"},{"key":"ref24","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn. (ICML)","author":"Schulman"},{"key":"ref25","article-title":"Proximal policy optimization algorithms","volume-title":"arXiv:1707.06347","author":"Schulman","year":"2017"},{"key":"ref26","article-title":"Emergence of locomotion behaviours in rich environments","volume-title":"arXiv:1707.02286","author":"Heess","year":"2017"},{"key":"ref27","article-title":"Combining policy gradient and Q-learning","volume-title":"Proc. 4th Int. Conf. Learn. Represent. (ICLR)","author":"O\u2019Donoghue"},{"key":"ref28","article-title":"Equivalence between policy gradients and soft Q-learning","volume-title":"arXiv:1704.06440","author":"Schulman","year":"2017"},{"key":"ref29","first-page":"2775","article-title":"Bridging the gap between value and policy based reinforcement learning","volume-title":"Proc. 30th Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Nachum"},{"issue":"8","key":"ref30","first-page":"1063","article-title":"Reinforcement learning with factored states and actions","volume":"5","author":"Sallans","year":"2004","journal-title":"J. Mach. Learn. Res."},{"key":"ref31","first-page":"202","article-title":"Taming the noise in reinforcement learning via soft updates","volume-title":"Proc. 32nd Conf. Uncertainty Artif. Intell. (UAI)","author":"Fox"},{"key":"ref32","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. 34th Int. Conf. Mach. Learn. (ICML)","author":"Haarnoja"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1924-6"},{"key":"ref34","article-title":"Auto-encoding variational bayes","volume-title":"arXiv:1312.6114","author":"Kingma","year":"2013"},{"key":"ref35","first-page":"1407","article-title":"IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","author":"Espeholt"},{"key":"ref36","article-title":"Distributed prioritized experience replay","volume-title":"arXiv:1803.00933","author":"Horgan","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref38","article-title":"OpenAI gym","volume-title":"arXiv:1606.01540","author":"Brockman","year":"2016"},{"key":"ref39","article-title":"Gaussian error linear units (GELUs)","volume-title":"arXiv:1606.08415","author":"Hendrycks","year":"2016"},{"key":"ref40","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/5962385\/9931397\/9448360-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9931397\/09448360.pdf?arnumber=9448360","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:13:03Z","timestamp":1705018383000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9448360\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11]]},"references-count":40,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3082568","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11]]}}}