{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T14:03:11Z","timestamp":1769004191461,"version":"3.49.0"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Korea National Police Agency through the Project \u201cDevelopment of Autonomous Driving Patrol Service for Active Prevention and Response to Traffic Accidents\u201d","award":["RS-2024-00403630"],"award-info":[{"award-number":["RS-2024-00403630"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tits.2024.3457776","type":"journal-article","created":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T17:30:12Z","timestamp":1727112612000},"page":"19522-19535","source":"Crossref","is-referenced-by-count":4,"title":["Imagination-Augmented Hierarchical Reinforcement Learning for Safe and Interactive Autonomous Driving in Urban Environments"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3360-4758","authenticated-orcid":false,"given":"Sang-Hyun","family":"Lee","sequence":"first","affiliation":[{"name":"Department of Mobility Engineering, Ajou University, Gyeonggi-do, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0963-2381","authenticated-orcid":false,"given":"Yoonjae","family":"Jung","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4890-8563","authenticated-orcid":false,"given":"Seung-Woo","family":"Seo","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1043","article-title":"Reinforcement learning with hierarchies of machines","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"10","author":"Parr"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.639"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45622-8_16"},{"key":"ref4","first-page":"15246","article-title":"Search on the replay buffer: Bridging planning and reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Eysenbach"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3071062"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561151"},{"key":"ref7","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Vezhnevets"},{"key":"ref8","article-title":"Skill-critic: Refining learned skills for hierarchical reinforcement learning","author":"Hao","year":"2023","journal-title":"arXiv:2306.08388"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3134702"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref12","first-page":"5360","article-title":"Thinking fast and slow with deep learning and tree search","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Anthony"},{"key":"ref13","first-page":"5690","article-title":"Imagination-augmented agents for deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Racani\u00e8re"},{"key":"ref14","article-title":"Dream to control: Learning behaviors by latent imagination","author":"Hafner","year":"2019","journal-title":"arXiv:1912.01603"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341496"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561095"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561195"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.1997.660524"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.1998.707332"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84628-638-4"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20255"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20262"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2014.2306552"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2477556"},{"key":"ref25","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. 1st Annu. Conf. Robot Learn.","volume":"78","author":"Dosovitskiy"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1068\/p050437"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/100.580977"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-03991-1","volume":"56","author":"Buehler","year":"2009","journal-title":"The DARPA Urban Challenge: Autonomous Vehicles in City Traffic"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20258"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2008.4651211"},{"key":"ref31","first-page":"305","article-title":"ALVINN: An autonomous land vehicle in a neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"1","author":"Pomerleau"},{"key":"ref32","article-title":"End to end learning for self-driving cars","author":"Bojarski","year":"2016","journal-title":"arXiv:1604.07316"},{"key":"ref33","article-title":"ChauffeurNet: Learning to drive by imitating the best and synthesizing the worst","author":"Bansal","year":"2018","journal-title":"arXiv:1812.03079"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160992"},{"key":"ref35","first-page":"661","article-title":"Efficient reductions for imitation learning","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Ross"},{"key":"ref36","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist.","author":"Ross"},{"key":"ref37","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref39","author":"Wymann","journal-title":"Torcs, the Open Racing Car Simulator"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref41","article-title":"Safe, multi-agent, reinforcement learning for autonomous driving","author":"Shalev-Shwartz","year":"2016","journal-title":"arXiv:1610.03295"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982041"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.102"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3271642"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3316285"},{"key":"ref46","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"issue":"8","key":"ref47","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref48","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref50","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"ref52","first-page":"3744","article-title":"Set Transformer: A framework for attention-based permutation-invariant neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Lee"},{"key":"ref53","first-page":"22574","article-title":"The sensory neuron as a transformer: Permutation-invariant neural networks for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Tang"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/robot.2010.5509799"},{"key":"ref55","first-page":"3391","article-title":"Deep sets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Zaheer"},{"key":"ref56","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461233"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3160673"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3153848"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3184990"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/10769775\/10689466.pdf?arnumber=10689466","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T05:29:20Z","timestamp":1732771760000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10689466\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":61,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tits.2024.3457776","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}