{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T16:09:34Z","timestamp":1780589374602,"version":"3.54.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100018146","name":"DENSO International at America","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018146","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1109\/tits.2020.3046646","type":"journal-article","created":{"date-parts":[[2021,2,3]],"date-time":"2021-02-03T22:03:09Z","timestamp":1612389789000},"page":"5068-5078","source":"Crossref","is-referenced-by-count":259,"title":["Interpretable End-to-End Urban Autonomous Driving With Latent Deep Reinforcement Learning"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0282-8621","authenticated-orcid":false,"given":"Jianyu","family":"Chen","sequence":"first","affiliation":[{"name":"University of California at Berkeley, Berkeley, CA, USA"}],"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 Lab of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0206-6639","authenticated-orcid":false,"given":"Masayoshi","family":"Tomizuka","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, University of California at Berkeley, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20147"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20255"},{"key":"ref3","article-title":"End to end learning for self-driving cars","volume-title":"arXiv:1604.07316","author":"Bojarski","year":"2016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.376"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.031"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968225"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995727"},{"key":"ref9","article-title":"Continuous control with deep reinforcement learning","volume-title":"arXiv:1509.02971","author":"Lillicrap","year":"2015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref11","article-title":"Playing atari with deep reinforcement learning","volume-title":"arXiv:1312.5602","author":"Mnih","year":"2013"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"issue":"1","key":"ref15","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref16","article-title":"QT-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"arXiv:1806.10293","author":"Kalashnikov","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref18","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref19","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"arXiv:1802.09477","author":"Fujimoto","year":"2018"},{"key":"ref20","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref21","article-title":"Proximal policy optimization algorithms","volume-title":"arXiv:1707.06347","author":"Schulman","year":"2017"},{"key":"ref22","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"arXiv:1801.01290","author":"Haarnoja","year":"2018"},{"key":"ref23","article-title":"Soft actor-critic algorithms and applications","volume-title":"arXiv:1812.05905","author":"Haarnoja","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500368"},{"key":"ref25","article-title":"Explaining how a deep neural network trained with end-to-end learning steers a car","volume-title":"arXiv:1704.07911","author":"Bojarski","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.320"},{"key":"ref27","article-title":"Conditional affordance learning for driving in urban environments","volume-title":"arXiv:1806.06498","author":"Sauer","year":"2018"},{"key":"ref28","volume-title":"Machine Learning: A Probabilistic Perspective","author":"Murphy","year":"2012"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995935"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2017.8317887"},{"key":"ref31","article-title":"Deep Kalman filters","volume-title":"arXiv:1511.05121","author":"Krishnan","year":"2015"},{"key":"ref32","article-title":"Deep variational Bayes filters: Unsupervised learning of state space models from raw data","volume-title":"arXiv:1605.06432","author":"Karl","year":"2016"},{"key":"ref33","first-page":"3601","article-title":"A disentangled recognition and nonlinear dynamics model for unsupervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fraccaro"},{"key":"ref34","article-title":"Learning latent dynamics for planning from pixels","volume-title":"arXiv:1811.04551","author":"Hafner","year":"2018"},{"key":"ref35","article-title":"Stochastic latent actor-critic: Deep reinforcement learning with a latent variable model","volume-title":"arXiv:1907.00953","author":"Lee","year":"2019"},{"key":"ref36","article-title":"Reinforcement learning and control as probabilistic inference: Tutorial and review","volume-title":"arXiv:1805.00909","author":"Levine","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9816.003.0050"},{"key":"ref38","article-title":"Modeling purposeful adaptive behavior with the principle of maximum causal entropy","author":"Ziebart","year":"2018"},{"key":"ref39","article-title":"World models","volume-title":"arXiv:1803.10122","author":"Ha","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340873"},{"key":"ref41","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref42","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Haarnoja"},{"key":"ref43","article-title":"If MaxEnt RL is the answer, what is the question?","volume-title":"arXiv:1910.01913","author":"Eysenbach","year":"2019"},{"key":"ref44","article-title":"Auto-encoding variational Bayes","volume-title":"arXiv:1312.6114","author":"Kingma","year":"2013"},{"key":"ref45","article-title":"CARLA: An open urban driving simulator","volume-title":"arXiv:1711.03938","author":"Dosovitskiy","year":"2017"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917306"},{"key":"ref47","article-title":"A survey of autonomous driving: Common practices and emerging technologies","volume-title":"arXiv:1906.05113","author":"Yurtsever","year":"2019"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/9784950\/09346000.pdf?arnumber=9346000","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T00:21:59Z","timestamp":1704846119000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9346000\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":47,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tits.2020.3046646","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6]]}}}