{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T07:02:08Z","timestamp":1760598128958,"version":"3.37.3"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Ministry of Innovation and Technology NRDI Office within the framework of the Autonomous Systems National Laboratory Program"},{"name":"Ministry of Innovation and Technology of Hungary from the National Research, Development and Innovation Fund, under the TKP2021 Funding Scheme","award":["BME-NVA-02"],"award-info":[{"award-number":["BME-NVA-02"]}]},{"name":"J\u00e1nos Bolyai Research Scholarship of the Hungarian Academy of Sciences"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1109\/tits.2022.3150493","type":"journal-article","created":{"date-parts":[[2022,2,23]],"date-time":"2022-02-23T20:32:46Z","timestamp":1645648366000},"page":"18707-18718","source":"Crossref","is-referenced-by-count":7,"title":["Skills to Drive: Successor Features for Autonomous Highway Pilot"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9926-4054","authenticated-orcid":false,"given":"Laszlo","family":"Szoke","sequence":"first","affiliation":[{"name":"Department of Control for Transportation and Vehicle Systems, Budapest University of Technology and Economics, Budapest, Hungary"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6811-2584","authenticated-orcid":false,"given":"Szilard","family":"Aradi","sequence":"additional","affiliation":[{"name":"Department of Control for Transportation and Vehicle Systems, Budapest University of Technology and Economics, Budapest, Hungary"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1487-9672","authenticated-orcid":false,"given":"Tamas","family":"Becsi","sequence":"additional","affiliation":[{"name":"Department of Control for Transportation and Vehicle Systems, Budapest University of Technology and Economics, Budapest, Hungary"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3388-1724","authenticated-orcid":false,"given":"Peter","family":"Gaspar","sequence":"additional","affiliation":[{"name":"Systems and Control Laboratory, Institute for Computer Science and Control, Budapest, Hungary"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A general reinforcement learning algorithm that masters chess, Shogi and go through self-play","author":"Silver","year":"2017","journal-title":"arXiv:1712.01815"},{"volume-title":"AlphaStar: Mastering the Real-Time Strategy Game StarCraft II","year":"2019","author":"Vinyals","key":"ref2"},{"key":"ref3","article-title":"Dota 2 with large scale deep reinforcement learning","author":"OpenAI","year":"2019","journal-title":"arXiv:1912.06680"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref5","article-title":"Agent57: Outperforming the Atari human benchmark","author":"Badia","year":"2020","journal-title":"arXiv:2003.13350"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2022.103829"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1907370117"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1109\/TNN.1998.712192","volume-title":"Introduction to Reinforcement Learning","author":"Sutton","year":"1998"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3311\/PPtr.9464"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1016\/j.artint.2021.103535","article-title":"Reward is enough","volume":"299","author":"Silver","year":"2021","journal-title":"Artif. Intell."},{"key":"ref11","first-page":"1","article-title":"Model-predictive policy learning with uncertainty regularization for driving in dense traffic","volume-title":"Proc. 7th Int. Conf. Learn. Represent. (ICLR)","author":"Henaff"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00718"},{"key":"ref13","article-title":"Survey of deep reinforcement learning for motion planning of autonomous vehicles","author":"Aradi","year":"2020","journal-title":"arXiv:2001.11231"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917306"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8813903"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/INES49302.2020.9147185"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SISY50555.2020.9217076"},{"key":"ref18","article-title":"End-to-end deep reinforcement learning for lane keeping assist","author":"Sallab","year":"2016","journal-title":"arXiv:1612.04340"},{"key":"ref19","first-page":"3846","article-title":"Interpolated policy gradient: Merging on-policy and off-policy gradient estimation for deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Gu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2017.8317735"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2018.10.024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8916924"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/app10207171"},{"key":"ref24","article-title":"Successor features for transfer in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Barreto"},{"key":"ref25","first-page":"501","article-title":"Transfer in deep reinforcement learning using successor features and generalised policy improvement","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Barreto"},{"key":"ref26","article-title":"The option keyboard: Combining skills in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Barreto"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1993.5.4.613"},{"key":"ref28","article-title":"Deep successor reinforcement learning","author":"Kulkarni","year":"2016","journal-title":"arXiv:1606.02396"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206049"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/458"},{"key":"ref31","first-page":"6401","article-title":"Composing value functions in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Van Niekerk"},{"key":"ref32","article-title":"Universal successor features approximators","author":"Borsa","year":"2018","journal-title":"arXiv:1812.07626"},{"key":"ref33","article-title":"Fast task inference with variational intrinsic successor features","author":"Hansen","year":"2019","journal-title":"arXiv:1906.05030"},{"key":"ref34","article-title":"RL2: Fast reinforcement learning via slow reinforcement learning","author":"Duan","year":"2016","journal-title":"arXiv:1611.02779"},{"key":"ref35","first-page":"5409","article-title":"FeUdal networks for hierarchical reinforcement learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn., (ICML)","volume":"7","author":"Vezhnevets"},{"article-title":"Planning in hierarchical reinforcement learning: Guarantees for using local policies yishay mansour","year":"2020","author":"Zahavy","key":"ref36"},{"key":"ref37","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. 1st Annu. Conf. Robot Learn.","author":"Dosovitskiy"},{"volume-title":"PreScan | TASS International","year":"2021","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-30626-9_9"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"},{"volume-title":"SUMO (Simulation of Urban MObility","year":"2002","author":"Krajzewicz","key":"ref41"},{"volume-title":"SUMO","year":"2011","author":"Behrisch","key":"ref42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917192"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2019.8914621"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.23919\/ChiCC.2019.8866005"},{"key":"ref46","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/9916643\/09719995.pdf?arnumber=9719995","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T23:46:43Z","timestamp":1705535203000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9719995\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":47,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tits.2022.3150493","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"type":"print","value":"1524-9050"},{"type":"electronic","value":"1558-0016"}],"subject":[],"published":{"date-parts":[[2022,10]]}}}