{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T18:21:04Z","timestamp":1761848464124,"version":"build-2065373602"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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","52202494","52394261"],"award-info":[{"award-number":["52202495","52202494","52394261"]}],"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":[[2025,10]]},"DOI":"10.1109\/tits.2025.3595526","type":"journal-article","created":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T18:48:53Z","timestamp":1755197333000},"page":"15728-15745","source":"Crossref","is-referenced-by-count":0,"title":["Autonomous Intersection Management via Prior-Enhanced Multi-Agent Constrained Decision Transformer"],"prefix":"10.1109","volume":"26","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":[{"role":"author","vocabulary":"crossref"}]},{"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":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7824-7751","authenticated-orcid":false,"given":"Yun","family":"Li","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0821-1660","authenticated-orcid":false,"given":"Kui","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengyuan","family":"Zheng","sequence":"additional","affiliation":[{"name":"College of Automotive Engineering, Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9020-6720","authenticated-orcid":false,"given":"Fei","family":"Gao","sequence":"additional","affiliation":[{"name":"College of Automotive Engineering and the National Key Laboratory of Automotive Chassis Integration and Bionics, Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4623-3956","authenticated-orcid":false,"given":"Zhenhai","family":"Gao","sequence":"additional","affiliation":[{"name":"College of Automotive Engineering and the National Key Laboratory of Automotive Chassis Integration and Bionics, Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2023.103923"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2019.03.002"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2514271"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102773"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2019.04.012"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2411619"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2018.2804164"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3162038"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3182403"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2018.5100"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3230682"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2014.2354380"},{"key":"ref13","first-page":"530","article-title":"Multiagent traffic management: A reservation-based intersection control mechanism","volume-title":"Proc. Joint Conf. Auton. Agents Multiagent Syst.","volume":"3","author":"Dresner"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3250957"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2019.01.004"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1080\/15472450.2018.1519706"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2016.0043"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3169907"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.tra.2016.05.013"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2850335"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/VTCFall.2018.8690681"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2021.10.012"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1177\/1550147719895956"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1061\/JTEPBS.0000243"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2940641"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3026111"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1061\/(asce)0733-947x(2003)129:3(278)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3069921"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2942014"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3243940"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3285440"},{"key":"ref32","article-title":"A review of safe reinforcement learning: Methods, theory and applications","author":"Gu","year":"2022","journal-title":"arXiv:2205.10330"},{"key":"ref33","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Achiam"},{"key":"ref34","first-page":"1","article-title":"Projection-based constrained policy optimization","volume-title":"Proc. 8th Int. Conf. Learn. Represent. (ICLR)","author":"Yang"},{"key":"ref35","first-page":"1","article-title":"Benchmarking safe exploration in deep reinforcement learning","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Ray"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3331723"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17062"},{"key":"ref38","first-page":"1","article-title":"Improving language understanding by generative pre-training","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Radford"},{"key":"ref39","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref40","first-page":"1","article-title":"Deep reinforcement learning with relational inductive biases","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zambaldi"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref42","first-page":"1","article-title":"Emergent tool use from multi-agent autocurricula","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Baker"},{"key":"ref43","first-page":"7487","article-title":"Stabilizing transformers for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Parisotto"},{"key":"ref44","article-title":"Efficient transformers in reinforcement learning using actor-learner distillation","author":"Parisotto","year":"2021","journal-title":"arXiv:2104.01655"},{"key":"ref45","article-title":"Decision transformer: Reinforcement learning via sequence modeling","author":"Chen","year":"2021","journal-title":"arXiv:2106.01345"},{"key":"ref46","article-title":"Offline reinforcement learning as one big sequence modeling problem","author":"Janner","year":"2021","journal-title":"arXiv:2106.02039"},{"key":"ref47","article-title":"Constrained decision transformer for offline safe reinforcement learning","author":"Liu","year":"2023","journal-title":"arXiv:2302.07351"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.131.118301"},{"key":"ref49","article-title":"Hybrid RL: Using both offline and online data can make RL efficient","author":"Song","year":"2022","journal-title":"arXiv:2210.06718"},{"key":"ref50","first-page":"1577","article-title":"Efficient online reinforcement learning with offline data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ball"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794102"},{"key":"ref52","article-title":"OPAL: Offline primitive discovery for accelerating offline reinforcement learning","author":"Ajay","year":"2020","journal-title":"arXiv:2010.13611"},{"key":"ref53","first-page":"31278","article-title":"Supported policy optimization for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref54","first-page":"1702","article-title":"Offline-to-Online reinforcement learning via balanced replay and pessimistic Q-ensemble","volume-title":"Proc. Conf. Robot Learn.","author":"Lee"},{"key":"ref55","first-page":"1","article-title":"Fine-tuning offline policies with optimistic action selection","volume-title":"Proc. Deep Reinforcement Learn. Workshop NeurIPS","author":"Mark"},{"key":"ref56","article-title":"Online decision transformer","author":"Zheng","year":"2022","journal-title":"arXiv:2202.05607"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29633"},{"key":"ref58","first-page":"3682","article-title":"EMaQ: Expected-max Q-learning operator for simple yet effective offline and online RL","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ghasemipour"},{"key":"ref59","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kumar"},{"key":"ref60","article-title":"Policy expansion for bridging offline-to-online reinforcement learning","author":"Zhang","year":"2023","journal-title":"arXiv:2302.00935"},{"key":"ref61","article-title":"PROTO: Iterative policy regularized offline-to-online reinforcement learning","author":"Li","year":"2023","journal-title":"arXiv:2305.15669"},{"key":"ref62","article-title":"AWAC: Accelerating online reinforcement learning with offline datasets","author":"Nair","year":"2020","journal-title":"arXiv:2006.09359"},{"key":"ref63","article-title":"Offline reinforcement learning with implicit Q-learning","author":"Kostrikov","year":"2021","journal-title":"arXiv:2110.06169"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/11220917\/11125839.pdf?arnumber=11125839","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T18:04:34Z","timestamp":1761847474000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11125839\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":63,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tits.2025.3595526","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"type":"print","value":"1524-9050"},{"type":"electronic","value":"1558-0016"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}