{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T14:09:49Z","timestamp":1779199789447,"version":"3.51.4"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"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":["62272357"],"award-info":[{"award-number":["62272357"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302326"],"award-info":[{"award-number":["62302326"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176194"],"award-info":[{"award-number":["62176194"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Hubei","award":["2022BAA052"],"award-info":[{"award-number":["2022BAA052"]}]},{"name":"Key Research and Development Program of Hainan","award":["ZDYF2021GXJS014"],"award-info":[{"award-number":["ZDYF2021GXJS014"]}]},{"name":"Hong Kong Research Grant Council","award":["NSFC\/RGC N_CityU 140\/20"],"award-info":[{"award-number":["NSFC\/RGC N_CityU 140\/20"]}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2120369"],"award-info":[{"award-number":["CNS-2120369"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science Foundation of Chongqing of China","award":["cstc2021jcyj-msxm4262"],"award-info":[{"award-number":["cstc2021jcyj-msxm4262"]}]},{"name":"Chongqing Research Institute of Wuhan University of Technology","award":["ZD2021-04"],"award-info":[{"award-number":["ZD2021-04"]}]},{"name":"Chongqing Research Institute of Wuhan University of Technology","award":["ZL2021-05"],"award-info":[{"award-number":["ZL2021-05"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tmc.2023.3312220","type":"journal-article","created":{"date-parts":[[2023,9,5]],"date-time":"2023-09-05T18:04:47Z","timestamp":1693937087000},"page":"5527-5542","source":"Crossref","is-referenced-by-count":22,"title":["An Efficient Message Dissemination Scheme for Cooperative Drivings via Cooperative Hierarchical Attention Reinforcement Learning"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8403-1776","authenticated-orcid":false,"given":"Bingyi","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2992-2650","authenticated-orcid":false,"given":"Weizhen","family":"Han","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7253-4763","authenticated-orcid":false,"given":"Enshu","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Future Science and Engineering, Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4006-7029","authenticated-orcid":false,"given":"Shengwu","family":"Xiong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4679-6572","authenticated-orcid":false,"given":"Chunming","family":"Qiao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, State University of New York at Buffalo, Buffalo, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9318-1482","authenticated-orcid":false,"given":"Jianping","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2886883"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2702650"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2012.2227070"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3218152"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3182386"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3133480"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3080523"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2966586"},{"key":"ref9","first-page":"7651","article-title":"Sparse attentive backtracking: Temporal credit assignment through reminding","volume-title":"Proc. 31st Adv. Neural Inf. Process. Syst.","author":"Ke"},{"key":"ref10","first-page":"13 566","article-title":"RUDDER: Return decomposition for delayed rewards","volume-title":"Proc. 32nd Adv. Neural Inf. Process. Syst.","author":"Arjona-Medina"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2866496"},{"key":"ref12","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","volume-title":"Proc. 34th ACM Int. Conf. Mach. Learn.","author":"Vezhnevets"},{"key":"ref13","first-page":"1","article-title":"Graph attention networks","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Veli\u010dkovi\u0107"},{"key":"ref14","first-page":"4403","article-title":"LIIR: Learning individual intrinsic reward in multi-agent reinforcement learning","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Du"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/VNC.2014.7013309"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2015.2410831"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LCN.2010.5735764"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2013.2258361"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WiMOB.2016.7763224"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/EUROCON.2017.8011240"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2016.2571696"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2989524"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/ett.3730"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322567"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2844826"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1109\/TNN.1998.712192","volume-title":"Introduction to Reinforcement Learning","author":"Sutton","year":"1998"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2928811"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.2991326"},{"key":"ref29","first-page":"3303","article-title":"Data-efficient hierarchical reinforcement learning","volume-title":"Proc. 31st ACM Adv. Neural Inf. Process. Syst.","author":"Nachum"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref31","first-page":"2012","article-title":"DAC: The double actor-critic architecture for learning options","volume-title":"Proc. 32nd Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref33","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. 30th Adv. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref34","first-page":"5567","article-title":"Mean field multi-agent reinforcement learning","volume-title":"Proc. 35th ACM Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313433"},{"key":"ref36","first-page":"1","article-title":"Graph convolutional reinforcement learning","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Jiang"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref38","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"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00039"},{"key":"ref40","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. 33rd ACM Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref43","first-page":"3794","article-title":"Sample and communication-efficient decentralized actor-critic algorithms with finite-time analysis","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref44","first-page":"1","article-title":"Finite-time convergence and sample complexity of multi-agent actor-critic reinforcement learning with average reward","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hairi"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17136"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2010.133"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2015.2489459"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7755\/10491282\/10239451-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7755\/10491282\/10239451.pdf?arnumber=10239451","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T19:56:03Z","timestamp":1712692563000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10239451\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":47,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2023.3312220","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}