{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T20:15:44Z","timestamp":1780690544244,"version":"3.54.1"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Ministry of Education (MOE), Singapore, under the Tier 2","award":["MOE-T2EP50222-0002"],"award-info":[{"award-number":["MOE-T2EP50222-0002"]}]},{"name":"Nanyang Technological University, under NTUitive Gap Fund","award":["NGF-2025-18-033"],"award-info":[{"award-number":["NGF-2025-18-033"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tits.2026.3675752","type":"journal-article","created":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:51:43Z","timestamp":1774554703000},"page":"6289-6303","source":"Crossref","is-referenced-by-count":0,"title":["Predictive Risk-Aware MARL-Based Cooperative Driving Strategy for CAVs in Highly Interactive Driving Environments"],"prefix":"10.1109","volume":"27","author":[{"given":"Lin","family":"Li","sequence":"first","affiliation":[{"name":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangkun","family":"He","sequence":"additional","affiliation":[{"name":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6897-4512","authenticated-orcid":false,"given":"Chen","family":"Lv","sequence":"additional","affiliation":[{"name":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3023957"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3085297"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3008612"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.geits.2024.100159"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1186\/s10033-024-01158-7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8916924"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3286898"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3169907"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/iThings-GreenCom-CPSCom-SmartData-Cybermatics55523.2022.00048"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.geits.2024.100156"},{"key":"ref11","article-title":"Safe, multi-agent, reinforcement learning for autonomous driving","author":"Shalev-Shwartz","year":"2016","journal-title":"arXiv:1610.03295"},{"key":"ref12","article-title":"Multi-agent reinforcement learning: A comprehensive survey","author":"Huh","year":"2023","journal-title":"arXiv:2312.10256"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/SICE56594.2022.9905866"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2022.3173031"},{"key":"ref17","first-page":"13859","article-title":"Safe reinforcement learning by imagining the near future","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Garrett"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-27026-9"},{"key":"ref19","article-title":"On a formal model of safe and scalable self-driving cars","author":"Shalev-Shwartz","year":"2017","journal-title":"arXiv:1708.06374"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3164469"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2401837"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14435-6_7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812060"},{"key":"ref24","article-title":"Parameter sharing deep deterministic policy gradient for cooperative multi-agent reinforcement learning","author":"Chu","year":"2017","journal-title":"arXiv:1710.00336"},{"key":"ref25","volume-title":"An Environment for Autonomous Driving Decision-Making","author":"Leurent","year":"2018"},{"key":"ref26","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lowe"},{"key":"ref27","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref28","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver"},{"key":"ref29","article-title":"Reducing overestimation bias in multi-agent domains using double centralized critics","author":"Ackermann","year":"2019","journal-title":"arXiv:1910.01465"},{"key":"ref30","article-title":"Reinforcement learning through asynchronous advantage actor-critic on a GPU","author":"Babaeizadeh","year":"2016","journal-title":"arXiv:1611.06256"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1787"},{"key":"ref32","first-page":"1","article-title":"Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3322426"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3285442"},{"key":"ref35","article-title":"Multi-agent constrained policy optimisation","author":"Gu","year":"2021","journal-title":"arXiv:2110.02793"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3141\/1999-10"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/11551813\/11456431.pdf?arnumber=11456431","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T19:41:04Z","timestamp":1780688464000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11456431\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":37,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tits.2026.3675752","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}