{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:03:22Z","timestamp":1783530202766,"version":"3.55.0"},"reference-count":284,"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":[{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["52202495"],"award-info":[{"award-number":["52202495"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["52202494"],"award-info":[{"award-number":["52202494"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tits.2024.3452480","type":"journal-article","created":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T18:01:55Z","timestamp":1726682515000},"page":"19365-19398","source":"Crossref","is-referenced-by-count":72,"title":["A Survey on Recent Advancements in Autonomous Driving Using Deep Reinforcement Learning: Applications, Challenges, and Solutions"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1597-1961","authenticated-orcid":false,"given":"Rui","family":"Zhao","sequence":"first","affiliation":[{"name":"College of Automotive Engineering, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7824-7751","authenticated-orcid":false,"given":"Yun","family":"Li","sequence":"additional","affiliation":[{"name":"Graduate School of Information and Science Technology, The University of Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8309-7396","authenticated-orcid":false,"given":"Yuze","family":"Fan","sequence":"additional","affiliation":[{"name":"College of Automotive Engineering, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9020-6720","authenticated-orcid":false,"given":"Fei","family":"Gao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Automotive Simulation and Control, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8045-3939","authenticated-orcid":false,"given":"Manabu","family":"Tsukada","sequence":"additional","affiliation":[{"name":"Graduate School of Information and Science Technology, The University of Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4623-3956","authenticated-orcid":false,"given":"Zhenhai","family":"Gao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Automotive Simulation and Control, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2023.3317372"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2023.3320088"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.122719","article-title":"LaTAS-F: Locality-aware transformer architecture search with multi-source fusion for driver continuous braking intention inference","volume":"242","author":"Jiang","year":"2024","journal-title":"Exp. Syst. Appl."},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3357983"},{"issue":"6","key":"ref5","doi-asserted-by":"crossref","first-page":"4964","DOI":"10.1109\/TITS.2023.3335310","article-title":"Cooperative adaptive cruise control in the presence of communication and radar stochastic data loss","volume":"25","author":"Rezaee","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/itsc57777.2023.10422088"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-47990-8_39"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3485767"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121983","article-title":"Pedestrian and vehicle behaviour prediction in autonomous vehicle system\u2014A review","volume":"238","author":"Galv\u00e3o","year":"2024","journal-title":"Exp. Syst. Appl."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105106"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21918"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ivs.2019.8813994"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-022-01603-6"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3057446"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1561\/2200000071"},{"key":"ref16","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"issue":"1","key":"ref17","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1109\/TITS.2020.3012034","article-title":"Deep learning-based vehicle behaviour prediction for autonomous driving applications: A review","volume":"23","author":"Mozaffari","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2024.3377288"},{"key":"ref19","article-title":"Efficient and generalized end-to-end autonomous driving system with latent deep reinforcement learning and demonstrations","author":"Tang","year":"2024","journal-title":"arXiv:2401.11792"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05732-2"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121959","article-title":"Managing mixed traffic at signalized intersections: An adaptive signal control and CAV coordination system based on deep reinforcement learning","volume":"238","author":"Li","year":"2024","journal-title":"Exp. Syst. Appl."},{"key":"ref22","article-title":"A review of safe reinforcement learning: Methods, theory and applications","author":"Gu","year":"2022","journal-title":"arXiv:2205.10330"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2020.106685","article-title":"Explainability in deep reinforcement learning","volume":"214","author":"Heuillet","year":"2021","journal-title":"Knowl.-Based Syst."},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2020.115036","article-title":"Reinforcement learning for building controls: The opportunities and challenges","volume":"269","author":"Wang","year":"2020","journal-title":"Appl. Energy"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"issue":"9","key":"ref26","first-page":"8261","article-title":"Metrics and continuity in reinforcement learning","volume-title":"Proc. Conf. AAAI Artif. Intell.","volume":"35","author":"Le Lan"},{"issue":"6","key":"ref27","doi-asserted-by":"crossref","first-page":"3692","DOI":"10.1109\/TIV.2023.3274536","article-title":"Motion planning for autonomous driving: The state of the art and future perspectives","volume":"8","author":"Teng","year":"2023","journal-title":"IEEE Trans. Intell. Vehicles"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2019.2962338"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2023.3318070"},{"issue":"2","key":"ref30","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1109\/MITS.2023.3341952","article-title":"A survey on datasets for the decision making of autonomous vehicles","volume":"16","author":"Wang","year":"2024","journal-title":"IEEE Intell. Transp. Syst. Mag."},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/msp.2017.2743240"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2021.3054625"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2020.3024655"},{"issue":"9","key":"ref34","first-page":"7366","article-title":"A comprehensive survey on the application of deep and reinforcement learning approaches in autonomous driving","volume":"34","author":"Elallid","year":"2022","journal-title":"J. King Saud Univ.-Comput. Inf. Sci."},{"key":"ref35","article-title":"Path planning algorithms in the autonomous driving system: A comprehensive review","volume":"174","author":"Reda","year":"2024","journal-title":"Robot. Auto. Syst."},{"key":"ref36","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.108060","article-title":"Human-like mechanism deep learning model for longitudinal motion control of autonomous vehicles","volume":"133","author":"Gao","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref37","article-title":"ActiveAD: Planning-oriented active learning for end-to-end autonomous driving","author":"Lu","year":"2024","journal-title":"arXiv:2403.02877"},{"key":"ref38","article-title":"Guiding pretraining in reinforcement learning with large language models","author":"Du","year":"2023","journal-title":"arXiv:2302.06692"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-092451"},{"key":"ref40","first-page":"1","article-title":"ScenarioNet: Open-source platform for large-scale traffic scenario simulation and modeling","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2023.3259322"},{"key":"ref42","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv:1511.05952"},{"key":"ref43","first-page":"1","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"key":"ref44","first-page":"1","article-title":"Deep exploration via bootstrapped DQN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Osband"},{"issue":"1","key":"ref45","first-page":"1","article-title":"Deep reinforcement learning with double Q-learning","volume-title":"Proc. Conf. AAAI Artif. Intell.","volume":"30","author":"Van Hasselt"},{"key":"ref46","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/itsc.2019.8917306"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2021.3086397"},{"key":"ref49","first-page":"2829","article-title":"Continuous deep Q-learning with model-based acceleration","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"48","author":"Gu"},{"key":"ref50","first-page":"2469","article-title":"Policy optimization with demonstrations","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Kang"},{"key":"ref51","first-page":"1531","article-title":"A natural policy gradient","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kakade"},{"key":"ref52","first-page":"1","article-title":"Actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Konda"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2023.3268500"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2022.3168486"},{"key":"ref55","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Haarnoja"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2023.3285440"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3142822"},{"key":"ref58","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 31st Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref59","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv:1506.02438"},{"key":"ref60","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref61","first-page":"1","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref62","first-page":"27042","article-title":"Online decision transformer","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Zheng"},{"key":"ref63","first-page":"16509","article-title":"Multi-agent reinforcement learning is a sequence modeling problem","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wen"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2023.3331723"},{"key":"ref65","doi-asserted-by":"crossref","DOI":"10.1016\/j.artint.2021.103500","article-title":"A survey of inverse reinforcement learning: Challenges, methods and progress","volume":"297","author":"Arora","year":"2021","journal-title":"Artif. Intell."},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref67","first-page":"1","article-title":"Dual RL: Unification and new methods for reinforcement and imitation learning","volume-title":"Proc. The 12th Int. Conf. Learn. Represent.","author":"Sikchi"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2023.3254579"},{"key":"ref69","first-page":"1","article-title":"When demonstrations meet generative world models: A maximum likelihood framework for offline inverse reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zeng"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1080\/23249935.2024.2318621"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3610977.3634984"},{"key":"ref72","first-page":"146","article-title":"Maximum entropy inverse reinforcement learning-based trajectory planning for autonomous driving","volume-title":"Proc. 3rd Int. Conf. High Perform. Comput. Commun. Eng. (HPCCE)","author":"Zhang"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/tro.2022.3232300"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106208"},{"key":"ref75","first-page":"1","article-title":"Generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref76","first-page":"1","article-title":"Learning robust rewards with adversarial inverse reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Fu"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3453160"},{"key":"ref78","article-title":"Data-efficient hierarchical reinforcement learning","author":"Nachum","year":"2018","journal-title":"arXiv:1805.08296"},{"key":"ref79","article-title":"Learning multi-level hierarchies with hindsight","author":"Levy","year":"2017","journal-title":"arXiv:1712.00948"},{"key":"ref80","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.ins.2023.03.087","article-title":"Hierarchical graph multi-agent reinforcement learning for traffic signal control","volume":"634","author":"Yang","year":"2023","journal-title":"Inf. Sci."},{"key":"ref81","first-page":"157","article-title":"Markov games as a framework for multi-agent reinforcement learning","volume-title":"Proc. Mach. Learn.","author":"Littman"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09938-y"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/tsg.2023.3309528"},{"key":"ref84","first-page":"1801","article-title":"A new framework for multi-agent reinforcement learning? Centralized training and exploration with decentralized execution via policy distillation","volume-title":"Proc. 19th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Chen"},{"issue":"1","key":"ref85","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1109\/TIV.2023.3312777","article-title":"How simulation helps autonomous driving: A survey of sim2real, digital twins, and parallel intelligence","volume":"9","author":"Hu","year":"2024","journal-title":"IEEE Trans. Intell. Vehicles"},{"key":"ref86","first-page":"1","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. 30th Adv. Neural Inf. Process.","author":"Lowe"},{"key":"ref87","first-page":"1","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref88","first-page":"1","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid"},{"key":"ref89","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achiam"},{"issue":"1","key":"ref90","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/0167-6377(96)00003-X","article-title":"On constrained Markov decision processes","volume":"19","author":"Haviv","year":"1996","journal-title":"Oper. Res. Lett."},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/s001860400402"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/itsc45102.2020.9294262"},{"key":"ref93","article-title":"Multi-agent constrained policy optimisation","author":"Gu","year":"2021","journal-title":"arXiv:2110.02793"},{"key":"ref94","first-page":"8753","article-title":"Constraints penalized Q-learning for safe offline reinforcement learning","volume-title":"Proc. 37th AAAI Conf. Artif. Intell.","volume":"36","author":"Xu"},{"key":"ref95","article-title":"COptiDICE: Offline constrained reinforcement learning via stationary distribution correction estimation","author":"Lee","year":"2022","journal-title":"arXiv:2204.08957"},{"key":"ref96","first-page":"1","article-title":"SaFormer: A conditional sequence modeling approach to offline safe reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref97","article-title":"Reward constrained policy optimization","author":"Tessler","year":"2018","journal-title":"arXiv:1805.11074"},{"issue":"167","key":"ref98","first-page":"1","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"ref99","article-title":"Lyapunov-based safe policy optimization for continuous control","author":"Chow","year":"2019","journal-title":"arXiv:1901.10031"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3331304"},{"key":"ref101","first-page":"1","article-title":"Iterative reachability estimation for safe reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ganai"},{"key":"ref102","first-page":"1","article-title":"UNI-O4: Unifying online and offline deep reinforcement learning with multi-step on-policy optimization","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Kun"},{"key":"ref103","article-title":"Safe exploration in continuous action spaces","author":"Dalal","year":"2018","journal-title":"arXiv:1801.08757"},{"key":"ref104","first-page":"1","article-title":"Model-free safe control for zero-violation reinforcement learning","volume-title":"Proc. 5th Annu. Conf. Robot. Learn.","author":"Zhao"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2021.3070252"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982038"},{"key":"ref107","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2024.104572","article-title":"How do active road users act around autonomous vehicles? An inverse reinforcement learning approach","volume":"161","author":"Alozi","year":"2024","journal-title":"Transp. Res. C, Emerg. Technol."},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/icmla.2018.00026"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1049\/itr2.12172"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2023.3326276"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2021.3059628"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2023.3298150"},{"key":"ref113","first-page":"1179","article-title":"Neighbourhood context embeddings in deep inverse reinforcement learning for predicting pedestrian motion over long time horizons","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. Workshop (ICCVW)","author":"Fernando"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ivs.2017.7995721"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827292"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/IV55152.2023.10186547"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3227738"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3285891"},{"key":"ref119","first-page":"1","article-title":"Infogail: Interpretable imitation learning from visual demonstrations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Li"},{"key":"ref120","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2021.103091","article-title":"TrajGAIL: Generating urban vehicle trajectories using generative adversarial imitation learning","volume":"128","author":"Choi","year":"2021","journal-title":"Transp. Res. C, Emerg. Technol."},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917722396"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304721"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3156011"},{"key":"ref124","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume-title":"Proc. ICML","volume":"1","author":"Ng"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3088935"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2988287"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/IV55152.2023.10186668"},{"key":"ref128","article-title":"Maximum entropy deep inverse reinforcement learning","author":"Wulfmeier","year":"2015","journal-title":"arXiv:1507.04888"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3167103"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3323440"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/ASYU58738.2023.10296611"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564912"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3207872"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560907"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3061627"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636468"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294259"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3262132"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3216288"},{"issue":"1","key":"ref140","first-page":"1","article-title":"An analysis of Monte Carlo tree search","volume-title":"Proc. AAAI","volume":"31","author":"James"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10421993"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3069497"},{"key":"ref143","first-page":"1","article-title":"End-to-end deep reinforcement learning for lane keeping assist","volume-title":"Proc. 30th Conf. Neural Inf. Process. Syst.","author":"El Sallab"},{"key":"ref144","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2023.104019","article-title":"A deep reinforcement learning based distributed control strategy for connected automated vehicles in mixed traffic platoon","volume":"148","author":"Shi","year":"2023","journal-title":"Transp. Res. C, Emerg. Technol."},{"key":"ref145","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2021.103421","article-title":"Connected automated vehicle cooperative control with a deep reinforcement learning approach in a mixed traffic environment","volume":"133","author":"Shi","year":"2021","journal-title":"Transp. Res. C, Emerg. Technol."},{"key":"ref146","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.eng.2022.05.017","article-title":"Toward human-in-the-loop AI: Enhancing deep reinforcement learning via real-time human guidance for autonomous driving","volume":"21","author":"Wu","year":"2023","journal-title":"Engineering"},{"key":"ref147","doi-asserted-by":"crossref","first-page":"103452","DOI":"10.1016\/j.trc.2021.103452","article-title":"Decision making of autonomous vehicles in lane change scenarios: Deep reinforcement learning approaches with risk awareness","volume":"134","author":"Li","year":"2022","journal-title":"Transp. Res. C, Emerg. Technol."},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3229518"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3102432"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084685"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3150793"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.102"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/tsmc.2017.2712561"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/tcst.2013.2271276"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.23919\/ecc54610.2021.9655042"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2022.3233592"},{"key":"ref157","first-page":"1","article-title":"Reinforcement learning for safety-critical control under model uncertainty, using control Lyapunov functions and control barrier functions","volume-title":"Proc. Robot., Sci. Syst.","author":"Choi"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2021.3086033"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1177\/0954407020954591"},{"key":"ref160","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.oceaneng.2019.04.099","article-title":"Deep reinforcement learning-based controller for path following of an unmanned surface vehicle","volume":"183","author":"Woo","year":"2019","journal-title":"Ocean Eng."},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2018.2884797"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2020.3009214"},{"issue":"8","key":"ref163","first-page":"759","article-title":"Optimum settings for automatic controllers","volume":"64","author":"Ziegler","year":"1942","journal-title":"J. Fluids Eng."},{"issue":"7","key":"ref164","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1016\/S0967-0661(02)00186-7","article-title":"A survey of industrial model predictive control technology","volume":"11","author":"Qin","year":"2003","journal-title":"Control Eng. Pract."},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2022.3173448"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/tcst.2021.3056315"},{"issue":"1","key":"ref167","first-page":"35","article-title":"A review of some pure-pursuit based path tracking techniques for control of autonomous vehicle","volume":"135","author":"Samuel","year":"2016","journal-title":"Int. J. Comput. Appl."},{"key":"ref168","first-page":"36599","article-title":"When to trust your simulator: Dynamics-aware hybrid offline-and-online reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Niu"},{"key":"ref169","article-title":"(Re)2H2O: Autonomous driving scenario generation via reversely regularized hybrid offline-and-online reinforcement learning","author":"Niu","year":"2023","journal-title":"arXiv:2302.13726"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/3ict56508.2022.9990801"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2020.3025671"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2022.3217299"},{"issue":"2","key":"ref173","doi-asserted-by":"crossref","first-page":"1143","DOI":"10.1109\/LRA.2020.2966414","article-title":"Learning robust control policies for end-to-end autonomous driving from data-driven simulation","volume":"5","author":"Amini","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref174","first-page":"17853","article-title":"Planning-oriented autonomous driving","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Hu"},{"key":"ref175","first-page":"8248","article-title":"Learning to drive in a day","volume-title":"Proc. Int. Conf. Robot. Autom. (ICRA)","author":"Kendall"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2979493"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2022.3146307"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3109284"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1002\/wcs.1459"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.23919\/ecc57647.2023.10178245"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2021.3115235"},{"issue":"1","key":"ref182","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1109\/TITS.2020.3013234","article-title":"Multimodal end-to-end autonomous driving","volume":"23","author":"Xiao","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref183","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101834","article-title":"Multi-modal policy fusion for end-to-end autonomous driving","volume":"98","author":"Huang","year":"2023","journal-title":"Inf. Fusion"},{"key":"ref184","doi-asserted-by":"crossref","DOI":"10.1016\/j.conengprac.2020.104630","article-title":"Vision-based robust control framework based on deep reinforcement learning applied to autonomous ground vehicles","volume":"104","author":"de Morais","year":"2020","journal-title":"Control Eng. Pract."},{"issue":"1","key":"ref185","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1109\/TIV.2022.3225340","article-title":"Hierarchical interpretable imitation learning for end-to-end autonomous driving","volume":"8","author":"Teng","year":"2023","journal-title":"IEEE Trans. Intell. Vehicles"},{"issue":"12","key":"ref186","doi-asserted-by":"crossref","first-page":"24355","DOI":"10.1109\/TITS.2022.3197602","article-title":"PNNUAD: Perception neural networks uncertainty aware decision-making for autonomous vehicle","volume":"23","author":"Liu","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"3","key":"ref187","doi-asserted-by":"crossref","first-page":"2197","DOI":"10.1109\/TIV.2022.3227921","article-title":"Lane change strategies for autonomous vehicles: A deep reinforcement learning approach based on transformer","volume":"8","author":"Li","year":"2023","journal-title":"IEEE Trans. Intell. Vehicles"},{"key":"ref188","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2021.3097345"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1007\/s42154-021-00151-3"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2018.8460934"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3266940"},{"key":"ref193","article-title":"Learning to change: Choreographing mixed traffic through lateral control and hierarchical reinforcement learning","author":"Wang","year":"2024","journal-title":"arXiv:2403.14879"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3271642"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341496"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2019.0317"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500368"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564634"},{"key":"ref199","first-page":"3697","article-title":"Attention-based hierarchical deep reinforcement learning for lane change behaviors in autonomous driving","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR) Workshops","author":"Chen"},{"key":"ref200","first-page":"1","article-title":"Towards practical hierarchical reinforcement learning for multi-lane autonomous driving","volume-title":"Proc. NeurIPS","author":"Nosrati"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599839"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1109\/icra40945.2020.9197351"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2021.3091477"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/832"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/ictc49870.2020.9289269"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-21007-8"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66845-1_4"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-40648-0_14"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8813875"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564432"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304549"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827153"},{"key":"ref213","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.entcs.2004.01.029","article-title":"Monitoring algorithms for metric temporal logic specifications","volume":"113","author":"Thati","year":"2005","journal-title":"Electron. Notes Theor. Comput. Sci."},{"key":"ref214","first-page":"8536","article-title":"Liability, ethics, and culture-aware behavior specification using rulebooks","volume-title":"Proc. Int. Conf. Robot. Autom. (ICRA)","author":"Censi"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569434"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995951"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2020.3017385"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3319689"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1109\/ICSA-C57050.2023.00069"},{"key":"ref220","first-page":"1","article-title":"ISO 26262 safety cases: Compliance and assurance","volume-title":"Proc. 6th IET Int. Conf. Syst. Saf.","author":"Palin"},{"issue":"2","key":"ref221","first-page":"129","article-title":"On the integrated process of RSS model and ISO\/DIS 21448 (SOTIF) for securing autonomous vehicle safety","volume":"17","author":"Kim","year":"2021","journal-title":"J. Korean Soc. Syst. Eng."},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44694-5"},{"key":"ref223","article-title":"Responsibility-sensitive safety: An introduction with an eye to logical foundations and formalization","author":"Hasuo","year":"2022","journal-title":"arXiv:2206.03418"},{"key":"ref224","article-title":"The safety force field","author":"Nist\u00e9r","year":"2019"},{"key":"ref225","first-page":"21611","article-title":"Constrained decision transformer for offline safe reinforcement learning","volume-title":"Proc. ICML","author":"Liu"},{"key":"ref226","first-page":"9133","article-title":"Responsive safety in reinforcement learning by PID Lagrangian methods","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Stooke"},{"key":"ref227","article-title":"A primal-dual approach to constrained Markov decision processes","author":"Chen","year":"2021","journal-title":"arXiv:2101.10895"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33353-8_7"},{"key":"ref229","article-title":"Traffic rules encoding sing defeasible deontic logic","volume-title":"Proc. 4th Int. Workshop Mining Reasoning Legal Texts (MIREL)","volume":"2632","author":"Bhuiyan"},{"key":"ref230","first-page":"1","article-title":"A methodology for encoding regulatory rules","volume-title":"Proc. 4th Int. Workshop Mining Reasoning Legal Texts, Co-Located 32nd Int. Conf. Legal Knowl. Inf. Syst.","volume":"2632","author":"Bhuiyan"},{"key":"ref231","first-page":"50","article-title":"Formalising and monitoring traffic rules for autonomous vehicles in Isabelle\/HOL","volume-title":"Proc. Int. Conf. Integr. Form Method","author":"Rizaldi"},{"key":"ref232","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2021.102988","article-title":"Calibration and evaluation of the responsibility-sensitive safety model of autonomous car-following maneuvers using naturalistic driving study data","volume":"123","author":"Xu","year":"2021","journal-title":"Transp. Res. C, Emerg. Technol."},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564554"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564749"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564801"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3300423"},{"issue":"2","key":"ref237","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1109\/TIV.2020.3017342","article-title":"Using reachable sets for trajectory planning of automated vehicles","volume":"6","author":"Manzinger","year":"2021","journal-title":"IEEE Trans. Intell. Vehicles"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9922100"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10422308"},{"key":"ref240","first-page":"4576","article-title":"PixelNeRF: Neural radiance fields from one or few images","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Yu"},{"key":"ref241","article-title":"OASim: An open and adaptive simulator based on neural rendering for autonomous driving","author":"Yan","year":"2024","journal-title":"arXiv:2402.03830"},{"key":"ref242","article-title":"S-NeRF: Neural radiance fields for street views","author":"Xie","year":"2022","journal-title":"arXiv:2303.00749"},{"key":"ref243","article-title":"S-NeRF++: Autonomous driving simulation via neural reconstruction and generation","author":"Chen","year":"2024","journal-title":"arXiv:2402.02112"},{"key":"ref244","article-title":"EmerNeRF: Emergent spatial\u2013temporal scene decomposition via self-supervision","author":"Yang","year":"2023","journal-title":"arXiv:2311.02077"},{"issue":"2","key":"ref245","first-page":"1522","article-title":"READ: Large-scale neural scene rendering for autonomous driving","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"37","author":"Li"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref247","first-page":"5491","article-title":"Plenoxels: Radiance fields without neural networks","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Fridovich-Keil"},{"key":"ref248","article-title":"Differentiable rendering with reparameterized volume sampling","author":"Morozov","year":"2023","journal-title":"arXiv:2302.10970"},{"key":"ref249","first-page":"5428","article-title":"Point-NeRF: Point-based neural radiance fields","volume-title":"Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit.","author":"Xu"},{"key":"ref250","first-page":"1282","article-title":"Quantifying generalization in reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Cobbe"},{"key":"ref251","first-page":"1162","article-title":"Active domain randomization","volume-title":"Proc. Conf. Robot Learn.","volume":"100","author":"Mehta"},{"key":"ref252","article-title":"Gen2Sim: Scaling up robot learning in simulation with generative models","author":"Katara","year":"2023","journal-title":"arXiv:2310.18308"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1109\/jas.2017.7510493"},{"key":"ref254","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-98833-7"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.1109\/jas.2018.7511186"},{"key":"ref256","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8018-5_16"},{"key":"ref258","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3079209"},{"key":"ref259","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.107727","article-title":"Using meta-learning to establish a highly transferable driving speed prediction model from the visual road environment","volume":"130","author":"Yu","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"1","key":"ref260","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","article-title":"A comprehensive survey on transfer learning","volume":"109","author":"Zhuang","year":"2021","journal-title":"Proc. IEEE"},{"key":"ref261","first-page":"5986","article-title":"Enhanced transfer learning for autonomous driving with systematic accident simulation","volume-title":"Proc. IEEE\/RSJ Int. Conf. Intell. Robots Syst. (IROS)","author":"Akhauri"},{"key":"ref262","first-page":"1","article-title":"Investigating multi-task pretraining and generalization in reinforcement learning","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Taiga"},{"key":"ref263","article-title":"Model-based imitation learning for urban driving","author":"Hu","year":"2022","journal-title":"arXiv:2210.07729"},{"key":"ref264","first-page":"7541","article-title":"Generating behaviorally diverse policies with latent diffusion models","volume-title":"Proc. 37th Annu. Conf. Neural Inf. Process. Syst.","volume":"36","author":"Hegde"},{"key":"ref265","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.026"},{"key":"ref266","first-page":"1","article-title":"Goal-conditioned imitation learning using score-based diffusion policies","volume-title":"Proc. Robot., Sci. Syst.","author":"Reuss"},{"key":"ref267","article-title":"A survey of large language models","author":"Xin Zhao","year":"2023","journal-title":"arXiv:2303.18223"},{"key":"ref268","article-title":"PERL: Parameter efficient reinforcement learning from human feedback","author":"Sidahmed","year":"2024","journal-title":"arXiv:2403.10704"},{"key":"ref269","article-title":"DriveLM: Driving with graph visual question answering","author":"Sima","year":"2023","journal-title":"arXiv:2312.14150"},{"key":"ref270","article-title":"A survey on multimodal large language models for autonomous driving","author":"Cui","year":"2023","journal-title":"arXiv:2311.12320"},{"key":"ref271","first-page":"6325","article-title":"Recent advances in imitation learning from observation","volume-title":"Proc. Twenty-Eighth Int. Joint Conf. Artif. Intell.","author":"Torabi"},{"key":"ref272","doi-asserted-by":"publisher","DOI":"10.1109\/icra46639.2022.9812316"},{"key":"ref273","first-page":"1","article-title":"Domain adaptive imitation learning with visual observation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Choi"},{"key":"ref274","first-page":"1","article-title":"Action inference by maximising evidence: Zero-shot imitation from observation with world models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref275","first-page":"19360","article-title":"MAHALO: Unifying offline reinforcement learning and imitation learning from observations","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"202","author":"Li"},{"key":"ref276","first-page":"5286","article-title":"Domain adaptive imitation learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Kim"},{"key":"ref277","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2021.3122865"},{"key":"ref278","article-title":"DriveMLM: Aligning multi-modal large language models with behavioral planning states for autonomous driving","author":"Wang","year":"2023","journal-title":"arXiv:2312.09245"},{"key":"ref279","article-title":"LanguageMPC: Large language models as decision makers for autonomous driving","author":"Sha","year":"2023","journal-title":"arXiv:2310.03026"},{"key":"ref280","article-title":"Holistic autonomous driving understanding by bird\u2019s-eye-view injected multi-modal large models","author":"Ding","year":"2024","journal-title":"arXiv:2401.00988"},{"key":"ref281","first-page":"441","article-title":"Reactive exploration to cope with non-stationarity in lifelong reinforcement learning","volume-title":"Proc. 1st Conf. Lifelong Learn. Agents","volume":"199","author":"Steinparz"},{"key":"ref282","article-title":"Reinforcement twinning: From digital twins to model-based reinforcement learning","author":"Schena","year":"2023","journal-title":"arXiv:2311.03628"},{"key":"ref283","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2021.3088407"},{"key":"ref284","doi-asserted-by":"publisher","DOI":"10.1109\/mspec.2022.9915627"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/10769775\/10682977.pdf?arnumber=10682977","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T02:50:23Z","timestamp":1733885423000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10682977\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":284,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tits.2024.3452480","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}