{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T08:11:07Z","timestamp":1770538267279,"version":"3.49.0"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tai.2024.3497919","type":"journal-article","created":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T14:04:52Z","timestamp":1731506692000},"page":"829-842","source":"Crossref","is-referenced-by-count":7,"title":["Safe Multiagent Reinforcement Learning With Bilevel Optimization in Autonomous Driving"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3817-7632","authenticated-orcid":false,"given":"Zhi","family":"Zheng","sequence":"first","affiliation":[{"name":"Department of Informatics, Technical University of Munich, Munich, Germany"}]},{"given":"Shangding","family":"Gu","sequence":"additional","affiliation":[{"name":"Department of Informatics, Technical University of Munich, Munich, Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3457538"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2023.1280341"},{"issue":"42","key":"ref4","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garc\u00eda","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/robotics11040081"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2023.103905"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17062"},{"key":"ref8","first-page":"483","article-title":"Safe multi-agent reinforcement learning via shielding","volume-title":"Proc. 20th Int. Conf. Auton. Agents MultiAgent Syst.","author":"ElSayed-Aly","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86486-6_10"},{"key":"ref10","article-title":"Safe multi-agent reinforcement learning through decentralized multiple control barrier functions","author":"Cai","year":"2021"},{"key":"ref11","first-page":"13458","article-title":"Settling the variance of multi-agent policy gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Kuba","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1287\/opre.32.2.390"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20908"},{"issue":"05","key":"ref14","first-page":"7325","article-title":"Bi-level actor-critic for multi-agent coordination","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"34","author":"Zhang","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/430"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892747"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1007\/978-3-030-31489-7_9","article-title":"Gradient methods for solving Stackelberg games","volume-title":"Proc. 6th Int. Conf. Algorithmic Decis. Theory (ADT)","author":"Naveiro","year":"2019"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1613\/jair.2502","article-title":"A multiagent approach to autonomous intersection management","volume":"31","author":"Dresner","year":"2008","journal-title":"J. Artif. Intell. Res."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3141\/2259-21"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS.2012.17"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2010.5625245"},{"key":"ref22","first-page":"161","article-title":"Definition of a merging assistant strategy using intelligent vehicles","volume-title":"Transp. Res. Part C: Emerg. Technol.","volume":"82","author":"Scarinci","year":"2017"},{"key":"ref23","first-page":"1263","article-title":"Sharing the road: Autonomous vehicles meet human drivers","volume-title":"Proc. 20th Int. Joint Conf. Artifical Intell.","author":"Dresner","year":"2007"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2017.7969448"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3285442"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_28"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.1201\/9781315140223","volume-title":"Constrained Markov Decision Processes","author":"Altman","year":"2021"},{"key":"ref28","volume-title":"Markov Decision Processes","author":"Uther","year":"2010"},{"key":"ref29","article-title":"Reward constrained policy optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tessler","year":"2019"},{"key":"ref30","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achiam","year":"2017"},{"key":"ref31","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref32","first-page":"13367","article-title":"Shield decentralization for safe multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Melcer","year":"2022"},{"key":"ref33","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","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161216"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3139138"},{"issue":"1","key":"ref36","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref37","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. 17th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Sunehag","year":"2018"},{"key":"ref38","first-page":"330","article-title":"Multi-agent reinforcement learning: Independent vs","volume-title":"cooperative agents,\u201d in Proc. 10th Int. Conf. Mach. Learn.","author":"Tan","year":"1993"},{"key":"ref39","first-page":"1046","article-title":"Trust region policy optimisation in multi-agent reinforcement learning","volume-title":"Proc. 10th Int. Conf. Learn. Represent. (ICLR)","author":"Kuba","year":"2022"},{"key":"ref40","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yu","year":"2022"},{"key":"ref41","volume-title":"Market Structure and Equilibrium","author":"Stackelberg","year":"2010"},{"key":"ref42","first-page":"1039","article-title":"Nash Q-learning for general-sum stochastic games","volume":"4","author":"Hu","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref43","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lowe","year":"2017"},{"key":"ref44","article-title":"An environment for autonomous driving decision-making","author":"Leurent","year":"2018"},{"key":"ref45","article-title":"Openai gym","author":"Brockman","year":"2016"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995816"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1103\/physreve.62.1805"},{"key":"ref48","first-page":"133","article-title":"Autonomous intersection driving with neuro-evolution","volume-title":"Proc. Genetic Evol. Comput. Conf. Companion (GECCO)","author":"Parker","year":"2017"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1162\/089976699300016070"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/10946214\/10752922.pdf?arnumber=10752922","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T19:01:07Z","timestamp":1764270067000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10752922\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":49,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tai.2024.3497919","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}