{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T11:21:59Z","timestamp":1773228119716,"version":"3.50.1"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,24]],"date-time":"2023-09-24T00:00:00Z","timestamp":1695513600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,24]],"date-time":"2023-09-24T00:00:00Z","timestamp":1695513600000},"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":[[2023,9,24]]},"DOI":"10.1109\/itsc57777.2023.10422159","type":"proceedings-article","created":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T23:32:39Z","timestamp":1707867159000},"page":"6165-6170","source":"Crossref","is-referenced-by-count":2,"title":["Comprehensive Training and Evaluation on Deep Reinforcement Learning for Automated Driving in Various Simulated Driving Maneuvers"],"prefix":"10.1109","author":[{"given":"Yongqi","family":"Dong","sequence":"first","affiliation":[{"name":"Delft University of Technology,Department of Transport and Planning,Delft,CN,the Netherlands,2628"}]},{"given":"Tobias","family":"Datema","sequence":"additional","affiliation":[{"name":"Delft University of Technology,Faculty of Electrical Engineering, Mathematics & Computer Science,Delft,CN,the Netherlands,2628"}]},{"given":"Vincent","family":"Wassenaar","sequence":"additional","affiliation":[{"name":"Delft University of Technology,Faculty of Electrical Engineering, Mathematics & Computer Science,Delft,CN,the Netherlands,2628"}]},{"given":"Joris","family":"Van de Weg","sequence":"additional","affiliation":[{"name":"Delft University of Technology,Faculty of Electrical Engineering, Mathematics & Computer Science,Delft,CN,the Netherlands,2628"}]},{"given":"Cahit Tolga","family":"Kopar","sequence":"additional","affiliation":[{"name":"Delft University of Technology,Faculty of Electrical Engineering, Mathematics & Computer Science,Delft,CN,the Netherlands,2628"}]},{"given":"Harim","family":"Suleman","sequence":"additional","affiliation":[{"name":"Delft University of Technology,Faculty of Electrical Engineering, Mathematics & Computer Science,Delft,CN,the Netherlands,2628"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113816"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1145\/3194085.3194087","article-title":"Deep learning for self-driving cars: Chances and challenges","volume-title":"Proceedings of the 1 st international workshop on software engineering for AI in autonomous systems","author":"Rao","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref4","author":"Shao","year":"2019","journal-title":"A survey of deep reinforcement learning in video games"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3134702"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2022.3217299"},{"key":"ref8","author":"Sallab","year":"2016","journal-title":"End-to-end deep reinforcement learning for lane keeping assist"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.2352\/issn.2470-1173.2017.19.avm-023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500556"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3216288"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500718"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/itsc.2017.8317735"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461233"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103416"},{"key":"ref16","volume-title":"Markov decision processes with their applications","volume":"14","author":"Hu","year":"2007"},{"key":"ref17","volume-title":"An environment for autonomous driving decision-making","author":"Leurent","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917192"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9921741"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995816"},{"key":"ref21","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"In-ternational conference on machine learning","author":"Schulman","year":"2015"},{"key":"ref22","first-page":"486","article-title":"A theoretical analysis of deep q-learning","author":"Fan","year":"2020","journal-title":"Learning for Dynamics and Control"},{"key":"ref23","volume-title":"D. H. P. C. C. (DHPC)","year":"2022"}],"event":{"name":"2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)","location":"Bilbao, Spain","start":{"date-parts":[[2023,9,24]]},"end":{"date-parts":[[2023,9,28]]}},"container-title":["2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10420842\/10420843\/10422159.pdf?arnumber=10422159","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T07:58:45Z","timestamp":1710403125000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10422159\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,24]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/itsc57777.2023.10422159","relation":{},"subject":[],"published":{"date-parts":[[2023,9,24]]}}}