{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:42:51Z","timestamp":1792791771841,"version":"4.5.0"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Sony R&D Center Europe Stuttgart Laboratory 1"},{"DOI":"10.13039\/501100011021","name":"National Centre of Competence in Research Robotics","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011021","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"name":"SNSF-ERC"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1109\/lra.2021.3064284","type":"journal-article","created":{"date-parts":[[2021,3,8]],"date-time":"2021-03-08T16:13:42Z","timestamp":1615220022000},"page":"4257-4264","source":"Crossref","is-referenced-by-count":109,"title":["Super-Human Performance in Gran Turismo Sport Using Deep Reinforcement Learning"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1072-3718","authenticated-orcid":false,"given":"Florian","family":"Fuchs","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6352-3744","authenticated-orcid":false,"given":"Yunlong","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6094-5901","authenticated-orcid":false,"given":"Elia","family":"Kaufmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3831-6778","authenticated-orcid":false,"given":"Davide","family":"Scaramuzza","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3840-5009","authenticated-orcid":false,"given":"Peter","family":"Durr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1101","article-title":"Deep dynamics models for learning dexterous manipulation","author":"nagabandi","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1080\/00423114.2019.1605081"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2019.2948135"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21977"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916645661"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7039771"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2926677"},{"key":"ref17","first-page":"305","article-title":"Alvinn: An autonomous land vehicle in a neural network","author":"pomerleau","year":"1989","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref18","article-title":"End to end learning for self-driving cars","volume":"abs 1604 7316","author":"bojarski","year":"2016","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.056"},{"key":"ref28","article-title":"At human speed: Deep reinforcement learning with action delay","volume":"abs 1810 7286","author":"firoiu","year":"2018","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989202"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grandmaster level in starcraft ii using multi-agent reinforcement learning","volume":"575","author":"vinyals","year":"2019","journal-title":"Nat"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2514\/2.4856"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aaw1975"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1111\/j.2044-8317.1969.tb00423.x"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2865891"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/oca.2123"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2720851"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487277"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460934"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/FBIT.2007.37"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2967299"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21918"},{"key":"ref26","article-title":"Uncertainty-aware reinforcement learning for collision avoidance","volume":"abs 1702 1182","author":"kahn","year":"2017","journal-title":"CoRR"},{"key":"ref25","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7083369\/9399748\/9372847-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9399748\/09372847.pdf?arnumber=9372847","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T10:54:04Z","timestamp":1652180044000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9372847\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7]]},"references-count":29,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2021.3064284","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7]]}}}