{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T18:41:43Z","timestamp":1775673703599,"version":"3.50.1"},"reference-count":27,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003802","name":"University Research Committee, University of Hong Kong","doi-asserted-by":"publisher","award":["14200417"],"award-info":[{"award-number":["14200417"]}],"id":[{"id":"10.13039\/501100003802","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Select. Areas Commun."],"published-print":{"date-parts":[[2019,6]]},"DOI":"10.1109\/jsac.2019.2904329","type":"journal-article","created":{"date-parts":[[2019,3,12]],"date-time":"2019-03-12T22:19:42Z","timestamp":1552429182000},"page":"1277-1290","source":"Crossref","is-referenced-by-count":278,"title":["Deep-Reinforcement Learning Multiple Access for Heterogeneous Wireless Networks"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3538-576X","authenticated-orcid":false,"given":"Yiding","family":"Yu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9454-4997","authenticated-orcid":false,"given":"Taotao","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7055-6483","authenticated-orcid":false,"given":"Soung Chang","family":"Liew","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1504\/IJSNET.2006.012027"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISWCS.2012.6328420"},{"key":"ref12","author":"luong","year":"2018","journal-title":"Applications of deep reinforcement learning in communications and networking A survey"},{"key":"ref13","author":"sun","year":"2018","journal-title":"Application of machine learning in wireless networks Key techniques and open issues"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2879433"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2018.2809722"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2872441"},{"key":"ref17","author":"zhang","year":"2018","journal-title":"Deep reinforcement learning based modulation and coding scheme selection in cognitive heterogeneous networks"},{"key":"ref18","first-page":"1","article-title":"Deep learning for proactive resource allocation in LTE-U networks","author":"challita","year":"2017","journal-title":"Proc 23th Eur Wireless Conf"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422168"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2014.2358639"},{"key":"ref3","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1155\/2010\/876216"},{"key":"ref5","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref8","first-page":"1705","article-title":"Spectrum management of cognitive radio using multi-agent reinforcement learning","author":"wu","year":"2010","journal-title":"Proc 9th Int Conf Auton Agents Multiagent Syst Ind Track"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LCN.2010.5735689"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WOCC.2011.5872298"},{"key":"ref1","year":"2018","journal-title":"DARPA SC2 Website"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","author":"chollet","year":"2015","journal-title":"Keras"},{"key":"ref21","first-page":"550","article-title":"Residual networks behave like ensembles of relatively shallow networks","author":"veit","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422168"},{"key":"ref23","first-page":"26","article-title":"Lecture 6.5-RMSPROP: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"Neural Netw Mach Learning"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5232-5"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/90.879343"}],"container-title":["IEEE Journal on Selected Areas in Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/49\/8715825\/08665952.pdf?arnumber=8665952","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:09:13Z","timestamp":1657746553000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8665952\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6]]},"references-count":27,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/jsac.2019.2904329","relation":{},"ISSN":["0733-8716","1558-0008"],"issn-type":[{"value":"0733-8716","type":"print"},{"value":"1558-0008","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,6]]}}}