{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:33:02Z","timestamp":1730255582672,"version":"3.28.0"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"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":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561450","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"13186-13193","source":"Crossref","is-referenced-by-count":1,"title":["Learning robust driving policies without online exploration"],"prefix":"10.1109","author":[{"given":"Daniel","family":"Graves","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nhat M.","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kimia","family":"Hassanzadeh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-014-0171-1"},{"key":"ref38","first-page":"2139","article-title":"Data-efficient off-policy policy evaluation for reinforcement learning","volume":"48","author":"thomas","year":"2016","journal-title":"International Conference on International Conference on Machine Learning"},{"key":"ref33","first-page":"1555","article-title":"Predictive representations of state","author":"littman","year":"2002","journal-title":"Advances in Neural Information Processing Systems 14"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2012.2200826"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1080\/00423114.2015.1055279"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1068\/p5343"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.312"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.031"},{"key":"ref35","first-page":"1656","article-title":"Better generalization with forecasts","author":"schaul","year":"2013","journal-title":"International Joint Conference on Artificial Intelligence"},{"key":"ref34","first-page":"835","article-title":"Using predictive representations to improve generalization in reinforcement learning","author":"rafols","year":"2005","journal-title":"International Joint Conference on Artificial Intelligence"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X12000477"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33093-3_30"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1005768"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2949603"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-33410-6_34"},{"key":"ref20","article-title":"Investigating generalisation in continuous deep reinforcement learning","volume":"abs 1902 7015","author":"zhao","year":"2019","journal-title":"CoRR"},{"key":"ref22","article-title":"Generalization and regularization in DQN","volume":"abs 1810 123","author":"farebrother","year":"2018","journal-title":"CoRR"},{"key":"ref21","article-title":"Deep reinforcement learning that matters","volume":"abs 1709 6560","author":"henderson","year":"2017","journal-title":"CoRR"},{"key":"ref24","article-title":"Benchmarking batch deep reinforcement learning algorithms","volume":"abs 1910 1708","author":"fujimoto","year":"2019","journal-title":"CoRR"},{"key":"ref23","article-title":"Off-policy deep reinforcement learning without exploration","volume":"abs 1812 2900","author":"fujimoto","year":"2018","journal-title":"CoRR"},{"key":"ref26","first-page":"761","article-title":"Horde: A scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction","volume":"2","author":"sutton","year":"2011","journal-title":"International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref25","article-title":"Offline reinforcement learning: tutorial, review and perspectives on open problems","volume":"abs 2005 1643","author":"levine","year":"2020","journal-title":"CoRR"},{"key":"ref50","first-page":"i-387?i","article-title":"Deterministic policy gradient algorithms","volume":"32","author":"silver","year":"2014","journal-title":"International Conference on International Conference on Machine Learning"},{"key":"ref51","first-page":"10","article-title":"Density ratio estimation: A comprehensive review","author":"sugiyama","year":"2010","journal-title":"RIMS Kokyuroku"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2578706"},{"key":"ref53","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995975"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechatronics.2015.09.004"},{"key":"ref12","article-title":"Deep steering: Learning end-to-end driving model from spatial and temporal visual cues","volume":"abs 1708 3798","author":"chi","year":"2018","journal-title":"CoRR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919880273"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref15","article-title":"Deep reinforcement learning for autonomous driving: A survey","volume":"abs 2002 444","author":"kiran","year":"2020","journal-title":"CoRR"},{"key":"ref16","article-title":"Challenges of real-world reinforcement learning","volume":"abs 1904 12901","author":"dulac-arnold","year":"0"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref18","article-title":"Solving rubik’s cube with a robot hands","volume":"abs 1910 7113","author":"akkaya","year":"2019","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2011.5967363"},{"key":"ref4","first-page":"3294","article-title":"Gps navigation based autonomous driving system design for intelligent vehicles","author":"wu","year":"2007","journal-title":"IEEE International Conference on Systems Man and Cybernetics"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460519"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1017\/S0373463319000638"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206084"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968225"},{"key":"ref7","first-page":"276","article-title":"Map-based localization method for autonomous vehicles using 3d-lidar","volume":"50","author":"wang","year":"2017","journal-title":"IFAC"},{"key":"ref49","article-title":"Perception as prediction using general value functions in autonomous driving applications","author":"graves","year":"2019","journal-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems"},{"key":"ref9","article-title":"End to end learning for self-driving cars","volume":"abs 1604 7316","author":"bojarski","year":"2016","journal-title":"CoRR"},{"key":"ref46","article-title":"Playing atari with deep reinforcement learning","volume":"abs 1312 5602","author":"mnih","year":"2013","journal-title":"CoRR"},{"key":"ref45","first-page":"5392","article-title":"Hybrid reward architecture for reinforcement learning","author":"van seijen","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref48","article-title":"Online off-policy prediction","volume":"abs 1811 2597","author":"ghiassian","year":"2018","journal-title":"CoRR"},{"key":"ref47","article-title":"Importance resampling off-policy prediction","author":"schlegel","year":"2019","journal-title":"Neural Information Processing Systems"},{"key":"ref42","article-title":"Developing a predictive approach to knowledge","author":"white","year":"2015","journal-title":"Ph D Dissertation"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1177\/0309364615605373"},{"key":"ref44","first-page":"4055","article-title":"Successor features for transfer in reinforcement learning","author":"barreto","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref43","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"jaderberg","year":"2017","journal-title":"International Conference on Learning Representations"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2021,5,30]]},"location":"Xi'an, China","end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561450.pdf?arnumber=9561450","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:47:04Z","timestamp":1652197624000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561450\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561450","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}