{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T16:32:38Z","timestamp":1772641958375,"version":"3.50.1"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,17]],"date-time":"2022-10-17T00:00:00Z","timestamp":1665964800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,17]],"date-time":"2022-10-17T00:00:00Z","timestamp":1665964800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,17]]},"DOI":"10.23919\/wmnc56391.2022.9954301","type":"proceedings-article","created":{"date-parts":[[2022,11,25]],"date-time":"2022-11-25T22:41:50Z","timestamp":1669416110000},"page":"93-100","source":"Crossref","is-referenced-by-count":4,"title":["Multi-Agent Actor-Critic for Cooperative Resource Allocation in Vehicular Networks"],"prefix":"10.23919","author":[{"given":"Nessrine","family":"Hammami","sequence":"first","affiliation":[{"name":"Ecole de Technologie Supérieure (ÉTS), University of Quebec,Canada"}]},{"given":"Kim Khoa","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Ecole de Technologie Supérieure (ÉTS), University of Quebec,Canada"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2014.6884222"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2016.2622180"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933962"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/WIOPT.2017.7959912"},{"key":"ref14","article-title":"Working Group 2 AI\/ML workflow description and requirements","year":"2019","journal-title":"Technical Report"},{"key":"ref15","article-title":"Multi-agent reinforcement learning for edge information sharing in vehicular networks","author":"wang","year":"2021","journal-title":"Digital Communications and Networks"},{"key":"ref16","article-title":"Interpolated policy gradient: Merging on-policy and off-policy gradient estimation for deep reinforcement learning","author":"gu","year":"2017","journal-title":"ArXiv abs\/1706 00387"},{"key":"ref17","article-title":"Deep multi-agent reinforcement learning for highway on-ramp merging in mixed traffic","author":"chen","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref18","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref19","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"ArXiv Preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2015.2479248"},{"key":"ref3","article-title":"3rd Generation Partnership Project; Technical Specification Group Radio Access Network. Study on enhancement of 3GPP Support for 5G V2X Services; (Release 15)","year":"2017","journal-title":"3GPP TR 22 886 V1 1 0"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2909923"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2991723"},{"key":"ref8","article-title":"OpenAI Pieter Abbeel, and Igor Mordatch. Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2018.2811185"},{"key":"ref2","article-title":"3rd Generation Partnership Project; Technical Specification Group Radio Access Network. Study on LTE-based V2X Services; (Release 14)","year":"2016","journal-title":"3GPP TR 36 885 v14 0 0"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3028621"},{"key":"ref9","article-title":"Parameter sharing deep deterministic policy gradient for cooperative multi-agent reinforcement learning","author":"chu","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref20","first-page":"151","article-title":"Understanding the impact of entropy on policy optimization","author":"ahmed","year":"0","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2022 14th IFIP Wireless and Mobile Networking Conference (WMNC)","location":"Sousse, Tunisia","start":{"date-parts":[[2022,10,17]]},"end":{"date-parts":[[2022,10,19]]}},"container-title":["2022 14th IFIP Wireless and Mobile Networking Conference (WMNC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9954222\/9954223\/09954301.pdf?arnumber=9954301","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,6]],"date-time":"2023-02-06T19:28:04Z","timestamp":1675711684000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9954301\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,17]]},"references-count":20,"URL":"https:\/\/doi.org\/10.23919\/wmnc56391.2022.9954301","relation":{},"subject":[],"published":{"date-parts":[[2022,10,17]]}}}