{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T08:29:53Z","timestamp":1725956993754},"reference-count":34,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/glocom.2017.8254101","type":"proceedings-article","created":{"date-parts":[[2018,1,15]],"date-time":"2018-01-15T17:50:54Z","timestamp":1516038654000},"page":"1-7","source":"Crossref","is-referenced-by-count":77,"title":["Deep Multi-User Reinforcement Learning for Dynamic Spectrum Access in Multichannel Wireless Networks"],"prefix":"10.1109","author":[{"given":"Oshri","family":"Naparstek","sequence":"first","affiliation":[]},{"given":"Kobi","family":"Cohen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2004.835596"},{"key":"ref32","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"AAAI"},{"journal-title":"Deep recurrent q-learning for partially observable mdps","year":"2015","author":"hausknecht","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"journal-title":"Deep multi-agent reinforcement learning for dynamic spectrum access in cognitive wireless networks","year":"0","author":"naparstek","key":"ref34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1155\/2010\/876216"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref12","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"2016","journal-title":"Advances in neural information processing systems"},{"journal-title":"Deep reinforcement learning An overview","year":"2017","author":"li","key":"ref13"},{"journal-title":"Dueling network architectures for deep reinforcement learning","year":"2015","author":"wang","key":"ref14"},{"journal-title":"Playing atari with deep reinforcement learning","year":"2013","author":"mnih","key":"ref15"},{"key":"ref16","article-title":"Deep reinforcement learning for dynamic multichannel access","author":"wang","year":"2017","journal-title":"International Conference on Computing Networking and Communications (ICNC)"},{"journal-title":"Proactive resource management in LTE-U systems A deep learning perspective","year":"2017","author":"challita","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2068950"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2012.6195522"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2015.7105641"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2013.131109"},{"journal-title":"Distributed Medium Access Control for Energy Efficient Transmission in Cognitive Radios","year":"2014","author":"naparstek","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2012.083112.120371"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2007.070409"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2015.2414918"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2285512"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2011.2170684"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2009.2025561"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2012.120108"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2014.7094730"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2007.361604"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2230215"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2008.080905"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2005.852826"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2013.2241076"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/GAMENETS.2009.5137452"},{"key":"ref26","article-title":"Distributed learning algorithms for spectrum sharing in spatial random access wireless networks","author":"cohen","year":"2016","journal-title":"IEEE Transactions on Automatic Control"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2015.2431121"}],"event":{"name":"2017 IEEE Global Communications Conference (GLOBECOM 2017)","start":{"date-parts":[[2017,12,4]]},"location":"Singapore","end":{"date-parts":[[2017,12,8]]}},"container-title":["GLOBECOM 2017 - 2017 IEEE Global Communications Conference"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8253768\/8253909\/08254101.pdf?arnumber=8254101","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,2,19]],"date-time":"2018-02-19T19:14:41Z","timestamp":1519067681000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8254101\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/glocom.2017.8254101","relation":{},"subject":[],"published":{"date-parts":[[2017,12]]}}}