{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T17:21:54Z","timestamp":1768411314879,"version":"3.49.0"},"reference-count":27,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","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":"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\/501100000038","name":"Natural Sciences and Engineering Research Council (NSERC) of Canada under Discovery Grant","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2024,5,1]]},"DOI":"10.1109\/jiot.2023.3348594","type":"journal-article","created":{"date-parts":[[2023,12,29]],"date-time":"2023-12-29T15:04:17Z","timestamp":1703862257000},"page":"15475-15489","source":"Crossref","is-referenced-by-count":11,"title":["Multitimescale Control and Communications With Deep Reinforcement Learning\u2014Part II: Control-Aware Radio Resource Allocation"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7828-0415","authenticated-orcid":false,"given":"Lei","family":"Lei","sequence":"first","affiliation":[{"name":"School of Engineering, University of Guelph, Guelph, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7537-7070","authenticated-orcid":false,"given":"Tong","family":"Liu","sequence":"additional","affiliation":[{"name":"Intelligent Computing and Communication Lab, Key Laboratory of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8531-6762","authenticated-orcid":false,"given":"Kan","family":"Zheng","sequence":"additional","affiliation":[{"name":"College of Electrical Engineering and Computer Sciences, Ningbo University, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4140-287X","authenticated-orcid":false,"given":"Xuemin","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2017.2709781"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3161585"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2988367"},{"key":"ref4","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Omidshafiei"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2897134"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890686"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2890210"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3087833"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933962"},{"key":"ref10","article-title":"Multi-agent reinforcement learning for joint channel assignment and power allocation in platoon-based C-V2X systems","author":"Vu","year":"2020","journal-title":"arXiv:2011.04555"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3103058"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3214525"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3259688"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3240425"},{"key":"ref15","volume-title":"Reward Backpropagation Prioritized Experience Replay","author":"Zhong","year":"2017"},{"key":"ref16","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3222128"},{"key":"ref18","article-title":"Deep reinforcement learning for distributed dynamic power allocation in wireless networks","author":"Nasir","year":"2018","journal-title":"arXiv:1808.00490"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2012.6195689"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2017.8006543"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322451"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2022.3167545"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3302509.3311050"},{"key":"ref24","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Foerster"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref27","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lowe"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/10508620\/10376461.pdf?arnumber=10376461","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T18:08:00Z","timestamp":1754417280000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10376461\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,1]]},"references-count":27,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2023.3348594","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,1]]}}}