{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:35:44Z","timestamp":1767339344312},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"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":[[2020,8]]},"DOI":"10.1109\/pimrc48278.2020.9217276","type":"proceedings-article","created":{"date-parts":[[2020,10,8]],"date-time":"2020-10-08T19:58:06Z","timestamp":1602187086000},"page":"1-6","source":"Crossref","is-referenced-by-count":10,"title":["Optimization of Resource Allocation in Multi-Cell OFDM Systems: A Distributed Reinforcement Learning Approach"],"prefix":"10.1109","author":[{"given":"Yuntao","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaohui","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingzhe","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangyu","family":"Jia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Multi-agent reinforcement learning based resource allocation for UAV networks","author":"cui","year":"2019","journal-title":"IEEE Transactions on Wireless Communications"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2255286"},{"key":"ref12","article-title":"When multiple agents learn to schedule: A distributed radio resource management framework","author":"naderializadeh","year":"2019","journal-title":"arXiv preprint arXiv 1906 03008"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/AISP.2017.8324111"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00121-2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-005-2631-2"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref17","article-title":"Optimal power allocation in multiuser ofdm systems","author":"shen","year":"2003","journal-title":"Proc of IEEE Global Telecommunications Conference"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2016.2516999"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2005.858010"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2926625"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2015.2413950"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2900624"},{"key":"ref5","article-title":"A joint learning and communications framework for federated learning over wireless networks","author":"chen","year":"2019","journal-title":"arXiv preprint arXiv 1909 01771"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2930115"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2891629"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2016.2611847"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.001.1900287"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933973"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/VTCFall.2012.6399230"},{"key":"ref22","first-page":"1","article-title":"Convergence of Q-learning: A simple proof","author":"melo","year":"2001","journal-title":"Institute Of Systems and Robotics Tech"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2014.6952410"}],"event":{"name":"2020 IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications","start":{"date-parts":[[2020,8,31]]},"location":"London, United Kingdom","end":{"date-parts":[[2020,9,3]]}},"container-title":["2020 IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9210501\/9217048\/09217276.pdf?arnumber=9217276","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:58:42Z","timestamp":1656453522000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9217276\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/pimrc48278.2020.9217276","relation":{},"subject":[],"published":{"date-parts":[[2020,8]]}}}