{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T00:31:28Z","timestamp":1778200288900,"version":"3.51.4"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF Real-Time Machine Learning","award":["CCF-1937403"],"award-info":[{"award-number":["CCF-1937403"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tits.2025.3560227","type":"journal-article","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T13:42:45Z","timestamp":1745329365000},"page":"12148-12161","source":"Crossref","is-referenced-by-count":32,"title":["Toward Adaptive and Coordinated Transportation Systems: A Multi-Personality Multi-Agent Meta-Reinforcement Learning Framework"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9900-0530","authenticated-orcid":false,"given":"Songjun","family":"Huang","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Rutgers University-New Brunswick, Piscataway, NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7524-9044","authenticated-orcid":false,"given":"Chuanneng","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Rutgers University-New Brunswick, Piscataway, NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2052-8948","authenticated-orcid":false,"given":"Ruo-Qian","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, Rutgers University-New Brunswick, Piscataway, NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5365-509X","authenticated-orcid":false,"given":"Dario","family":"Pompili","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Rutgers University-New Brunswick, Piscataway, NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/DCOSS-IoT61029.2024.00014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/DCOSS-IoT61029.2024.00060"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3109011"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3117290"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2025.3529088"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3205596"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TTE.2022.3167647"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MASS50613.2020.00030"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref11","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Rakelly"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3262663"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2942593"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103624"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3400312"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3162850"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3232242"},{"key":"ref18","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"Jaderberg","year":"2016","journal-title":"arXiv:1611.05397"},{"key":"ref19","article-title":"Learning to navigate in complex environments","author":"Mirowski","year":"2016","journal-title":"arXiv:1611.03673"},{"key":"ref20","article-title":"Evolutionary principles in self-referential learning, or on learning how to learn: The meta-meta-. hook","author":"Schmidhuber","year":"1987"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref22","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Finn"},{"key":"ref23","first-page":"2402","article-title":"Meta-gradient reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Xu"},{"key":"ref24","article-title":"Learning to learn: Meta-critic networks for sample efficient learning","author":"Sung","year":"2017","journal-title":"arXiv:1706.09529"},{"key":"ref25","first-page":"1","article-title":"Meta-reinforcement learning of structured exploration strategies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gupta"},{"key":"ref26","article-title":"Rl2: Fast reinforcement learning via slow reinforcement learning","author":"Duan","year":"2016","journal-title":"arXiv:1611.02779"},{"key":"ref27","article-title":"Learning to reinforcement learn","author":"Wang","year":"2016","journal-title":"arXiv:1611.05763"},{"key":"ref28","article-title":"A simple neural attentive meta-learner","author":"Mishra","year":"2017","journal-title":"arXiv:1707.03141"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.12.086"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IV48863.2021.9575379"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3348034"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3229527"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/4"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref36","volume-title":"Modeling Purposeful Adaptive Behavior With the Principle of Maximum Causal Entropy","author":"Ziebart","year":"2010"},{"key":"ref37","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lillicrap"},{"key":"ref38","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Sutton"},{"key":"ref39","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref40","volume-title":"Probablistic Embeddings for Actor-critic Reinforcement Learning (pearl)","author":"Rakelly","year":"2019"},{"key":"ref41","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref42","volume-title":"Minimalistic gridworld environment for gymnasium","author":"Chevalier-Boisvert","year":"2018"},{"key":"ref43","volume-title":"Planet Dump Retrieved From Https:\/\/planet.osm.org","year":"2017"},{"key":"ref44","volume-title":"NVIDIA Jetson Nano","year":"2019"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6979\/11121550\/10974402-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/11121550\/10974402.pdf?arnumber=10974402","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,11]],"date-time":"2025-08-11T17:45:20Z","timestamp":1754934320000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10974402\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":44,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tits.2025.3560227","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}