{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T01:00:44Z","timestamp":1755219644624,"version":"3.43.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,22]]},"DOI":"10.1109\/iv64158.2025.11097380","type":"proceedings-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T17:54:55Z","timestamp":1754502895000},"page":"648-655","source":"Crossref","is-referenced-by-count":0,"title":["Enhanced DACER Algorithm with Multimodal Q-value Distribution for Risk-Sensitive Stochastic Vehicle Environments"],"prefix":"10.1109","author":[{"given":"Tong","family":"Liu","sequence":"first","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xujie","family":"Song","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinuo","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjun","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Shuai","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyu","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weixian","family":"He","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingliang","family":"Duan","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, University of Science and Technology Beijing,Beijing,China,100083"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengbo Eben","family":"Li","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Recent Progress in Energy Management of Connected Hybrid Electric Vehicles Using Reinforcement Learning","year":"2023","author":"Hua","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1080\/00423114.2023.2186249"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsr.2024.10.004"},{"journal-title":"Soft actor-critic algorithms and applications","year":"2018","author":"Haarnoja","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3537087"},{"journal-title":"Diffusion Actor-Critic with Entropy Regulator","year":"2024","author":"Wang","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176342415"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2307\/3213832"},{"journal-title":"Parametric return density estimation for reinforcement learning","year":"2012","author":"Morimura","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7758091"},{"key":"ref11","first-page":"449","article-title":"A distributional per-spective on reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Bellemare","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref14","first-page":"29","article-title":"An analysis of categorical distributional reinforcement learning","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Rowland","year":"2018"},{"key":"ref15","first-page":"1096","article-title":"Implicit quantile networks for distributional reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Dabney","year":"2018"},{"key":"ref16","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103452"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s13385-012-0058-0"},{"key":"ref19","first-page":"3509","article-title":"Algorithms for CVaR optimization in MDPs","author":"Chow","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref21","first-page":"1352","article-title":"Deep reinforcement learning with deep energy-based policies","volume-title":"International conference on machine learning (ICML)","author":"Levine","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.commtr.2023.100096"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2023.3329823"},{"volume-title":"Diffusion Actor-Critic with Entropy Regulator","year":"2024","author":"Wang","key":"ref24"},{"key":"ref25","article-title":"Continuous control with deep reinforcement learning","volume-title":"The Eleventh International Conference on Learning Representations","author":"Lillicrap","year":"2016"},{"key":"ref26","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"International Conference on Machine Learning","author":"Silver","year":"2014"},{"key":"ref27","first-page":"1587","article-title":"Addressing function approxi-mation error in actor-critic methods","volume-title":"International Conference on Machine Learning","author":"Fujimoto","year":"2018"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref28"},{"key":"ref29","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"International Conference on Machine Learning","author":"Schulman","year":"2015"},{"journal-title":"Gaussian error linear units (GELUs)","year":"2016","author":"Hendrycks","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5244\/c.34.191"},{"journal-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref32"}],"event":{"name":"2025 IEEE Intelligent Vehicles Symposium (IV)","start":{"date-parts":[[2025,6,22]]},"location":"Cluj-Napoca, Romania","end":{"date-parts":[[2025,6,25]]}},"container-title":["2025 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11097351\/11097337\/11097380.pdf?arnumber=11097380","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T04:58:29Z","timestamp":1754542709000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11097380\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/iv64158.2025.11097380","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}