{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T15:10:20Z","timestamp":1785856220913,"version":"3.56.0"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62071425"],"award-info":[{"award-number":["62071425"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Key Research and Development Plan","award":["2022C01093"],"award-info":[{"award-number":["2022C01093"]}]},{"name":"Huawei Cooperation Project"},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LR23F010005"],"award-info":[{"award-number":["LR23F010005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Veh. Technol."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tvt.2023.3312574","type":"journal-article","created":{"date-parts":[[2023,9,6]],"date-time":"2023-09-06T17:28:57Z","timestamp":1694021337000},"page":"1582-1596","source":"Crossref","is-referenced-by-count":13,"title":["Stochastic Graph Neural Network-Based Value Decomposition for MARL in Internet of Vehicles"],"prefix":"10.1109","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5913-1109","authenticated-orcid":false,"given":"Baidi","family":"Xiao","sequence":"first","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4297-5060","authenticated-orcid":false,"given":"Rongpeng","family":"Li","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Wang","sequence":"additional","affiliation":[{"name":"Huawei Technologies, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenghui","family":"Peng","sequence":"additional","affiliation":[{"name":"Huawei Technologies, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianjun","family":"Wu","sequence":"additional","affiliation":[{"name":"Huawei Technologies, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5479-7890","authenticated-orcid":false,"given":"Zhifeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang Lab, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1492-1364","authenticated-orcid":false,"given":"Honggang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang Lab, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2023-Spring57618.2023.10199985"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2498841"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2010.0032"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/s21062140"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2578706"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364909340445"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2008.2012116"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3141732"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2016.7508798"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/robotics7040067"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2930115"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3023788"},{"key":"ref14","first-page":"330","article-title":"Multi-agent reinforcement learning: Independent versus cooperative agents","volume-title":"Proc. 10th Int. Conf. Mach. Learn.","author":"Tan","year":"1993"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref16","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Lowe","year":"2017"},{"key":"ref17","first-page":"6846","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Rashid","year":"2018"},{"key":"ref18","first-page":"1","article-title":"DOP: Off-policy multi-agent decomposed policy gradients","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17353"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-92238-2_5"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6212"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref23","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2706186"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3092336"},{"key":"ref26","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45855.2022.9838936"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2010.5625133"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2019.06.005"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103008"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2017.8292737"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3052542"},{"key":"ref34","first-page":"2145","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Foerster","year":"2016"},{"key":"ref35","first-page":"7265","article-title":"Learning attentional communication for multi-agent cooperation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jiang","year":"2018"},{"key":"ref36","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Yang","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-47358-7_7"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207663"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1111\/mice.12702"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3169907"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3219428"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref43","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Wang","year":"2016"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/0024-3795(94)90486-3"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3087314"},{"key":"ref46","first-page":"399","article-title":"Benchmarks for reinforcement learning in mixed-autonomy traffic","volume-title":"Proc. 2nd Conf. Robot Learn.","author":"Vinitsky","year":"2018"}],"container-title":["IEEE Transactions on Vehicular Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/25\/10433392\/10242021.pdf?arnumber=10242021","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T00:16:11Z","timestamp":1709338571000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10242021\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":46,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tvt.2023.3312574","relation":{},"ISSN":["0018-9545","1939-9359"],"issn-type":[{"value":"0018-9545","type":"print"},{"value":"1939-9359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}