{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T03:30:11Z","timestamp":1780371011108,"version":"3.54.1"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004412","name":"Turkish Academy of Sciences of Turkey (T\u00daBA) through T\u00daBA Outstanding Young Scientist Award Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004412","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1109\/tits.2023.3292981","type":"journal-article","created":{"date-parts":[[2023,7,25]],"date-time":"2023-07-25T17:42:19Z","timestamp":1690306939000},"page":"11773-11784","source":"Crossref","is-referenced-by-count":14,"title":["A Real-World Reinforcement Learning Framework for Safe and Human-Like Tactical Decision-Making"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6192-4472","authenticated-orcid":false,"given":"Muharrem Ugur","family":"Yavas","sequence":"first","affiliation":[{"name":"Department of Mechatronics Engineering, Istanbul Technical University, Istanbul, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9366-0240","authenticated-orcid":false,"given":"Tufan","family":"Kumbasar","sequence":"additional","affiliation":[{"name":"Department of Control and Automation Engineering, Istanbul Technical University, Istanbul, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2660-2141","authenticated-orcid":false,"given":"Nazim Kemal","family":"Ure","sequence":"additional","affiliation":[{"name":"Artificial Intelligence and Data Science Research Center, Istanbul Technical University, Istanbul, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2015.165"},{"key":"ref2","first-page":"1","article-title":"Tactical decision making for lane changing with deep reinforcement learning","volume-title":"Proc. NIPS Workshop Mach. Learn. Intell. Transp. Syst.","author":"Mukadam"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569568"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/0191-2615(86)90012-3"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2016.2565718"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995936"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294679"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917192"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304594"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2019.2955905"},{"key":"ref13","article-title":"Amortized Q-learning with model-based action proposals for autonomous driving on highways","author":"Mirchevska","year":"2020","journal-title":"arXiv:2012.03234"},{"key":"ref14","article-title":"Automated lane changing using deep reinforcement learning: A user-acceptance case study","author":"Haak","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3008612"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569448"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ROSE.2003.1218700"},{"key":"ref19","article-title":"End to end learning for self-driving cars","author":"Bojarski","year":"2016","journal-title":"arXiv:1604.07316"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1201\/9781439821091"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref25","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv:1511.05952"},{"key":"ref26","article-title":"Distributed prioritized experience replay","author":"Horgan","year":"2018","journal-title":"arXiv:1803.00933"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-31895-0_19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2015.7225830"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1068\/p5343"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3141\/1999-10"},{"key":"ref32","volume-title":"Simstar\u2014Latest Features","year":"2019"},{"key":"ref33","volume-title":"Nvidia Physx SDK 3.4.0 Documentation","year":"2017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2010.2049203"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref36","article-title":"Evaluating agents without rewards","author":"Matusch","year":"2020","journal-title":"arXiv:2012.11538"},{"key":"ref37","article-title":"RLlib: Abstractions for distributed reinforcement learning","author":"Liang","year":"2017","journal-title":"arXiv:1712.09381"},{"key":"ref38","article-title":"Tune: A research platform for distributed model selection and training","author":"Liaw","year":"2018","journal-title":"arXiv:1807.05118"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/10304348\/10194473.pdf?arnumber=10194473","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T02:23:02Z","timestamp":1710382982000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10194473\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11]]},"references-count":38,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tits.2023.3292981","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11]]}}}