{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T16:02:27Z","timestamp":1772121747205,"version":"3.50.1"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/spawc48557.2020.9154250","type":"proceedings-article","created":{"date-parts":[[2020,8,3]],"date-time":"2020-08-03T18:12:25Z","timestamp":1596478345000},"page":"1-5","source":"Crossref","is-referenced-by-count":22,"title":["Resource Management in Wireless Networks via Multi-Agent Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Navid","family":"Naderializadeh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaroslaw","family":"Sydir","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meryem","family":"Simsek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hosein","family":"Nikopour","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933962"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7997440"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761431"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933973"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2016.7588290"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2015.2413412"},{"key":"ref16","article-title":"The simulation of independent Rayleigh faders","volume":"50","author":"li","year":"2002","journal-title":"IEEE Transactions on Communications"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10295","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"THIRTIETH AAAI Conference on Artificial Intelligence"},{"key":"ref18","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","author":"omidshafiei","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"},{"key":"ref19","article-title":"Quantifying generalization in reinforcement learning","author":"cobbe","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2014.2328102"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2014.6845058"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2017.8006944"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref7","article-title":"Move evaluation in Go using deep convolutional neural networks","author":"maddison","year":"2014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2011.2147784"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2008.070227"},{"key":"ref9","article-title":"Deep reinforcement learning for distributed uncoordinated cognitive radios resource allocation","author":"tondwalkar","year":"2019"},{"key":"ref20","article-title":"Learning to reinforcement learn","author":"wang","year":"2016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/VTCFall.2017.8288417"}],"event":{"name":"2020 IEEE 21st International Workshop on Signal Processing Advances in Wireless Communications (SPAWC)","location":"Atlanta, GA, USA","start":{"date-parts":[[2020,5,26]]},"end":{"date-parts":[[2020,5,29]]}},"container-title":["2020 IEEE 21st International Workshop on Signal Processing Advances in Wireless Communications (SPAWC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9144330\/9153881\/09154250.pdf?arnumber=9154250","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T12:32:00Z","timestamp":1667651520000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9154250\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/spawc48557.2020.9154250","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}