{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:32:50Z","timestamp":1773246770701,"version":"3.50.1"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3659797","type":"journal-article","created":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T21:04:29Z","timestamp":1769807069000},"page":"17506-17524","source":"Crossref","is-referenced-by-count":1,"title":["Stackelberg Game-Theoretic Safe MARL With Bilevel Control for Autonomous Driving"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9063-3953","authenticated-orcid":false,"given":"Haoming","family":"Qu","sequence":"first","affiliation":[{"name":"School of Automation, Shenyang Institute of Engineering, Shenyang, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2233-1241","authenticated-orcid":false,"given":"Xin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Automation, Shenyang Institute of Engineering, Shenyang, China"}]},{"given":"Charles Z.","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5698-6043","authenticated-orcid":false,"given":"Jingyan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1488-3743","authenticated-orcid":false,"given":"Siyuan","family":"Zhuang","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7265-5059","authenticated-orcid":false,"given":"Ming","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3268500"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TTE.2023.3290069"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2691346"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.trf.2024.07.021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1057\/s41599-022-01286-2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.techsoc.2021.101631"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s00146-022-01442-x"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3207759"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2578706"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICMI60790.2024.10585649"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1080\/01441647.2014.983210"},{"key":"ref12","article-title":"Bionic decision-making analysis during urban expressway ramp merging for autonomous vehicle","author":"Chen","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.geits.2024.100156"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3266941"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12586-7"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s43684-022-00045-z"},{"key":"ref17","article-title":"Multi-agent reinforcement learning for autonomous driving: A survey","author":"Zhang","year":"2024","journal-title":"arXiv:2408.09675"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3040085"},{"key":"ref19","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IV48863.2021.9575880"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48130\/dts-0025-0013"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.109655"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852110"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2020.103568"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/s23020990"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1177\/03611981231161355"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10080894"},{"key":"ref29","article-title":"Stackelberg driver model for continual policy improvement in scenario-based closed-loop autonomous driving","author":"Niu","year":"2023","journal-title":"arXiv:2309.14235"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13163180"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3584787"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3497919"},{"key":"ref33","article-title":"Multi-agent chance-constrained reinforcement learning for autonomous vehicles","author":"Araia","year":"2023"},{"key":"ref34","first-page":"315","article-title":"Provably efficient generalized Lagrangian policy optimization for safe multi-agent reinforcement learning","volume-title":"Proc. Learn. Dyn. Control Conf.","author":"Ding"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1186\/s10033-024-01160-z"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/14207.001.0001"},{"key":"ref37","first-page":"19235","article-title":"Conservative offline distributional reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ma"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.17526"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3390\/a16070325"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1177\/09544070231186841"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3329785"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3390\/app12146831"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3390\/app112210659"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3311\/PPtr.18581"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1017\/9781009160865"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11368873.pdf?arnumber=11368873","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:08:56Z","timestamp":1770671336000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11368873\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3659797","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}