{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T20:24:28Z","timestamp":1773779068400,"version":"3.50.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"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":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1109\/lra.2022.3192770","type":"journal-article","created":{"date-parts":[[2022,7,20]],"date-time":"2022-07-20T19:32:11Z","timestamp":1658345531000},"page":"11625-11632","source":"Crossref","is-referenced-by-count":38,"title":["Residual Policy Learning Facilitates Efficient Model-Free Autonomous Racing"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8789-5609","authenticated-orcid":false,"given":"Ruiqi","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Automotive Studies, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4778-137X","authenticated-orcid":false,"given":"Jing","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Automotive Studies, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7416-592X","authenticated-orcid":false,"given":"Guang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Automotive Studies, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3909-488X","authenticated-orcid":false,"given":"Zhijun","family":"Li","sequence":"additional","affiliation":[{"name":"Wearable Robotics and Autonomous Systems Lab, University of Science and Technology of China, Hefei, China"}]},{"given":"Jianxiao","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Automotive Studies, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4840-076X","authenticated-orcid":false,"given":"Alois","family":"Knoll","sequence":"additional","affiliation":[{"name":"Department of Informatics, Technical University of Munich, Munich, Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487277"},{"key":"ref2","article-title":"Local NMPC on global optimised path for autonomous racing","author":"Kalaria","year":"2021"},{"key":"ref3","article-title":"End to end learning for self-driving cars","author":"Bojarski","year":"2016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.056"},{"key":"ref5","article-title":"Benchmarking TPU, GPU, and CPU platforms for deep learning","author":"Wang","year":"2019","journal-title":"arXiv:1907.10701"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2720851"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3301273"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2019.01.003"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abb2174"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.64"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460934"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811650"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3064284"},{"key":"ref16","article-title":"Residual policy learning","author":"Silver","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794127"},{"issue":"1","key":"ref18","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2985815"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2926677"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3073020"},{"key":"ref22","first-page":"1918","article-title":"BayesRace: Learning to race autonomously using prior experience","volume-title":"Proc. Conf. Robot Learn","author":"Jain","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2019.2948135"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989202"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2865891"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3293353.3293364"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.23919\/date48585.2020.9116486"},{"key":"ref29","article-title":"Dream to control: Learning behaviors by latent imagination","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hafner","year":"2019"},{"key":"ref30","article-title":"Model-based deep reinforcement learning for high-dimensional problems, a survey","author":"Plaat","year":"2020","journal-title":"arXiv:2008.05598"},{"key":"ref31","article-title":"Racecar gym","author":"Brunnbauer","year":"2020"},{"key":"ref32","article-title":"Pybullet, a python module for physics simulation in robotics, games and machine learning","author":"Coumans","year":"2016","journal-title":"Github Repository"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSSC.1968.300136"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/OJITS.2022.3181510"},{"issue":"11","key":"ref35","article-title":"Rapidly-exploring random trees: A new tool for path planning","volume":"98","author":"Lavalle","year":"1998","journal-title":"Comput. Sci. Dept. Oct"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911406761"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/AIM.2015.7222539"},{"key":"ref38","first-page":"27209","article-title":"Is bang-bang control all you need? Solving continuous control with bernoulli policies","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","author":"Seyde","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2746752"},{"key":"ref40","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref41","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref42","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"key":"ref43","first-page":"5015","article-title":"The mirage of action-dependent baselines in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tucker","year":"2018"},{"key":"ref44","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-6670(17)70095-X"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2012.05.021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s12532-020-00179-2"},{"key":"ref48","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2016"},{"key":"ref49","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2018"},{"key":"ref50","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Machin. Learn.","author":"Haarnoja","year":"2018"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9831196\/09834085.pdf?arnumber=9834085","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T06:42:52Z","timestamp":1706769772000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9834085\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":50,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2022.3192770","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10]]}}}