{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T16:11:02Z","timestamp":1776528662198,"version":"3.51.2"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100000038","name":"research grants from the Natural Sciences and Engineering Research Council (NSERC) of Canada","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 J. Select. Areas Commun."],"published-print":{"date-parts":[[2021,1]]},"DOI":"10.1109\/jsac.2020.3036962","type":"journal-article","created":{"date-parts":[[2020,11,10]],"date-time":"2020-11-10T21:14:37Z","timestamp":1605042877000},"page":"131-141","source":"Crossref","is-referenced-by-count":474,"title":["Multi-Agent Reinforcement Learning Based Resource Management in MEC- and UAV-Assisted Vehicular Networks"],"prefix":"10.1109","volume":"39","author":[{"ORCID":"https:\/\/linproxy.fan.workers.dev:443\/https\/orcid.org\/0000-0001-7206-4706","authenticated-orcid":false,"given":"Haixia","family":"Peng","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/linproxy.fan.workers.dev:443\/https\/orcid.org\/0000-0002-4140-287X","authenticated-orcid":false,"given":"Xuemin","family":"Shen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2859740"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2723430"},{"key":"ref33","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume":"99","author":"ng","year":"1999","journal-title":"Proc ICML"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/OJVT.2020.2965100"},{"key":"ref31","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","author":"puterman","year":"2014","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref37","year":"2020","journal-title":"PTV Vissim"},{"key":"ref36","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc ICLR"},{"key":"ref34","year":"2020","journal-title":"Deep Reinforcement Learning Models Tips & Tricks for Writing Reward Functions"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2928539"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/AiDAS47888.2019.8970890"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2019.1800222"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2872753"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2922656"},{"key":"ref14","year":"2020","journal-title":"Why Autonomous Vehicles Will Rely on Edge Computing and Not the Cloud?"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.2984261"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2935877"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2951169"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.2986615"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890685"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2935201"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2897134"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2878435"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2929741"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933962"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2864426"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2833427"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1109\/TNSE.2020.2978856","article-title":"Deep reinforcement learning based resource management for multi-access edge computing in vehicular networks","author":"peng","year":"2020","journal-title":"IEEE Transactions on Network Science and Engineering"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2878552"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2957798"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2878876"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2893067"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2927313"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2018.1701092"},{"key":"ref21","year":"2020","journal-title":"Building an Ecosystem for Responsible Drone Use and Development on Microsoft Azure"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3000416"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2993849"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933973"},{"key":"ref25","first-page":"1","article-title":"DDPG-based resource management for MEC\/UAV-assisted vehicular networks","author":"peng","year":"2020","journal-title":"Proc IEEE VTC Fall"}],"container-title":["IEEE Journal on Selected Areas in Communications"],"original-title":[],"link":[{"URL":"https:\/\/linproxy.fan.workers.dev:443\/http\/xplorestaging.ieee.org\/ielx7\/49\/9295467\/09254093.pdf?arnumber=9254093","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,25]],"date-time":"2022-01-25T22:43:58Z","timestamp":1643150638000},"score":1,"resource":{"primary":{"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/ieeexplore.ieee.org\/document\/9254093\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":40,"journal-issue":{"issue":"1"},"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.1109\/jsac.2020.3036962","relation":{},"ISSN":["0733-8716","1558-0008"],"issn-type":[{"value":"0733-8716","type":"print"},{"value":"1558-0008","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1]]}}}