{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T10:46:20Z","timestamp":1775126780884,"version":"3.50.1"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Institute of Electrical Engineering Chinese Academy of Sciences","award":["E1553301"],"award-info":[{"award-number":["E1553301"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Veh. Technol."],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1109\/tvt.2022.3219428","type":"journal-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T21:25:36Z","timestamp":1667597136000},"page":"3025-3034","source":"Crossref","is-referenced-by-count":32,"title":["Coordination for Connected and Automated Vehicles at Non-Signalized Intersections: A Value Decomposition-Based Multiagent Deep Reinforcement Learning Approach"],"prefix":"10.1109","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1403-0502","authenticated-orcid":false,"given":"Zihan","family":"Guo","sequence":"first","affiliation":[{"name":"Key Laboratory of Power Electronics and Electric Drives, Institute of Electrical Engineering Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5185-9948","authenticated-orcid":false,"given":"Yan","family":"Wu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Power Electronics and Electric Drives, Institute of Electrical Engineering Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6835-8285","authenticated-orcid":false,"given":"Lifang","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Power Electronics and Electric Drives, Institute of Electrical Engineering Chinese Academy of Sciences, Beijing, China"}]},{"given":"Junzhi","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Automotive Safety and Energy and Department of Automotive Engineering, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2600504"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2471812"},{"key":"ref3","article-title":"Traffic signal timing manual","author":"Koonce","year":"2008"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-6243-9_2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3026111"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220096"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461233"},{"key":"ref8","first-page":"399","article-title":"Benchmarks for reinforcement learning in mixed-autonomy traffic","volume-title":"Proc. Conf. Robot Learn.","author":"Vinitsky","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.commtr.2021.100017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1108\/JICV-03-2021-0004"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2725912"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09421-1"},{"key":"ref13","article-title":"An overview of multi-agent reinforcement learning from game theoretical perspective","author":"Yang","year":"2020"},{"key":"ref14","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":"ref15","first-page":"4295","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid","year":"2018"},{"key":"ref16","first-page":"5887","article-title":"QTRAN, Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.,","author":"Son","year":"2019"},{"key":"ref17","first-page":"10757","article-title":"Multi-agent determinantal Q-learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang","year":"2020"},{"key":"ref18","article-title":"RIIT: Rethinking the importance of implementation tricks in multi-agent reinforcement learning","author":"Hu","year":"2021"},{"key":"ref19","first-page":"2186","article-title":"The starcraft multi-agent challenge","volume-title":"Proc. 18th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Samvelyan","year":"2019"},{"key":"ref20","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","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2013.6760239"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/app10165722"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref27","first-page":"834","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lillicrap","year":"2016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref29","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50035-0"},{"key":"ref31","first-page":"1051","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638963"},{"key":"ref33","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist. Workshop Conf. Proc.","author":"Glorot","year":"2010"}],"container-title":["IEEE Transactions on Vehicular Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/25\/10070114\/09939107.pdf?arnumber=9939107","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T23:05:06Z","timestamp":1705964706000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9939107\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3]]},"references-count":33,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tvt.2022.3219428","relation":{},"ISSN":["0018-9545","1939-9359"],"issn-type":[{"value":"0018-9545","type":"print"},{"value":"1939-9359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3]]}}}