{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T22:35:31Z","timestamp":1792794931472,"version":"4.5.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icra.2019.8793742","type":"proceedings-article","created":{"date-parts":[[2019,8,12]],"date-time":"2019-08-12T21:26:12Z","timestamp":1565645172000},"page":"8248-8254","source":"Crossref","is-referenced-by-count":529,"title":["Learning to Drive in a Day"],"prefix":"10.1109","author":[{"given":"Alex","family":"Kendall","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeffrey","family":"Hawke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Janz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Przemyslaw","family":"Mazur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniele","family":"Reda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John-Mark","family":"Allen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vinh-Dieu","family":"Lam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Bewley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amar","family":"Shah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Deep recurrent q-learning for partially observable MDPs","volume":"abs 1507 6527","author":"hausknecht","year":"2015","journal-title":"CoRR"},{"key":"ref38","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref33","article-title":"Concrete problems in ai safety","author":"amodei","year":"2016","journal-title":"arXiv preprint arXiv 1606 06565"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.36.823"},{"key":"ref31","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref30","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.18"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref35","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","author":"kendall","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.2307\/796133"},{"key":"ref10","first-page":"1089","article-title":"First results in robot road-following","author":"wallace","year":"1985","journal-title":"IJCAI Citeseer"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20258"},{"key":"ref40","article-title":"Deep variational reinforcement learning for POMDPs","author":"igl","year":"2018","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2011.5940562"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/5254.736001"},{"key":"ref14","author":"thrun","year":"2005","journal-title":"Probabilistic Robotics"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487208"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916679498"},{"key":"ref18","first-page":"305","article-title":"Alvinn: An autonomous land vehicle in a neural network","author":"pomerleau","year":"1989","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"End to end learning for self-driving cars","author":"bojarski","year":"2016","journal-title":"arXiv preprint arXiv 1604 07316"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref28","article-title":"Stochastic backprop-agation and approximate inference in deep generative models","author":"rezende","year":"2014","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref27","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref5","article-title":"Mastering chess and shogi by selfplay with a general reinforcement learning algorithm","volume":"abs 1712 1815","author":"silver","year":"2017","journal-title":"CoRR"},{"key":"ref29","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460519"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/324634.325197"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2015.2509024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206247"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2795643"},{"key":"ref42","article-title":"World models","volume":"abs 1803 10122","author":"ha","year":"2018","journal-title":"CoRR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989202"},{"key":"ref23","first-page":"465","article-title":"Pilco: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML)"},{"key":"ref41","article-title":"TreeQN and ATreeC: Differentiable tree planning for deep reinforcement learning","author":"farquhar","year":"2018","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/FBIT.2007.37"}],"event":{"name":"2019 International Conference on Robotics and Automation (ICRA)","location":"Montreal, QC, Canada","start":{"date-parts":[[2019,5,20]]},"end":{"date-parts":[[2019,5,24]]}},"container-title":["2019 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8780387\/8793254\/08793742.pdf?arnumber=8793742","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,14]],"date-time":"2022-07-14T23:08:11Z","timestamp":1657840091000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8793742\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icra.2019.8793742","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}