{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T18:47:47Z","timestamp":1785178067671,"version":"3.55.0"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":["IEEE Trans. Cogn. Commun. Netw."],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/tccn.2019.2952909","type":"journal-article","created":{"date-parts":[[2019,11,12]],"date-time":"2019-11-12T21:27:04Z","timestamp":1573594024000},"page":"1125-1139","source":"Crossref","is-referenced-by-count":109,"title":["A Deep Actor-Critic Reinforcement Learning Framework for Dynamic Multichannel Access"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3934-4436","authenticated-orcid":false,"given":"Chen","family":"Zhong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyang","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7352-1013","authenticated-orcid":false,"given":"M. Cenk","family":"Gursoy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1430-1555","authenticated-orcid":false,"given":"Senem","family":"Velipasalar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WOCC.2011.5872298"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1155\/2010\/876216"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2809581"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2879433"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2068950"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LCN.2010.5735689"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SAHCNW.2008.12"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/T-WC.2008.071349"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2009.2025561"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2012.020812.110025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2014.2366559"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2017.2778156"},{"key":"ref16","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":"ref17","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of Go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2904897"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SAHCN.2014.6990328"},{"key":"ref4","first-page":"1064","article-title":"Monte carlo POMDPs","author":"thrun","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422168"},{"key":"ref3","first-page":"2164","article-title":"Monte-carlo planning in large POMDPs","author":"silver","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCS.2014.7024826"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2802450"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2018.2809722"},{"key":"ref2","first-page":"576","article-title":"MAA*: A heuristic search algorithm for solving decentralized POMDPs","author":"szer","year":"2005","journal-title":"Proc 21st Conf Uncertainty Artif Intell"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2007.070409"},{"key":"ref1","first-page":"520","article-title":"Heuristic search value iteration for POMDPs","author":"smith","year":"2004","journal-title":"Proc 20th Conf Uncertainty Artif Intell"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2782726"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCW.2018.8403505"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2017.2703855"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422586"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2814606"},{"key":"ref26","article-title":"Reinforcement-learning-based resource allocation in fog radio access networks for various IoT environments","author":"nassar","year":"2018","journal-title":"arXiv preprint arXiv 1806 04582"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2769644"}],"container-title":["IEEE Transactions on Cognitive Communications and Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6687307\/8930661\/08896945.pdf?arnumber=8896945","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:44:23Z","timestamp":1657745063000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8896945\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":35,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tccn.2019.2952909","relation":{},"ISSN":["2332-7731","2372-2045"],"issn-type":[{"value":"2332-7731","type":"electronic"},{"value":"2372-2045","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,12]]}}}