{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T16:44:55Z","timestamp":1784825095724,"version":"3.55.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Project of China","award":["2019YFB1802702"],"award-info":[{"award-number":["2019YFB1802702"]}]},{"DOI":"10.13039\/501100001809","name":"National NSF of China","doi-asserted-by":"publisher","award":["61941106"],"award-info":[{"award-number":["61941106"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Commun."],"published-print":{"date-parts":[[2021,4]]},"DOI":"10.1109\/tcomm.2020.3045050","type":"journal-article","created":{"date-parts":[[2020,12,15]],"date-time":"2020-12-15T21:01:42Z","timestamp":1608066102000},"page":"2457-2472","source":"Crossref","is-referenced-by-count":18,"title":["Decentralized Multi-Agent Multi-Armed Bandit Learning With Calibration for Multi-Cell Caching"],"prefix":"10.1109","volume":"69","author":[{"given":"Xianzhe","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meixia","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2017.2658999"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2986803"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2017.2713384"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.2968326"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2966599"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2863364"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2894403"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2016.2636139"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/VTCSpring.2019.8746321"},{"key":"ref34","article-title":"Multi-agent reinforcement learning for cooperative coded caching via homotopy optimization","author":"wu","year":"2020","journal-title":"arXiv 2006 13565"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2016.2536728"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1100.0465"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.3022896"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2873723"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2016.2552164"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2014.6883600"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2014.6874793"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ISWCS.2018.8491205"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2017.7925848"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CISS.2018.8362276"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2956554"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ISWCS.2014.6933484"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2013.6495773"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3030973"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/35.841844"},{"key":"ref6","first-page":"1","article-title":"Cache-enabled small cell networks: Modeling and tradeoffs","volume":"2015","author":"ba?tu?","year":"2015","journal-title":"EURASIP J Wireless Commun Netw"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2878231"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2014.2306938"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2015.7248843"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2013.2281606"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2014.6871674"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2682240"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2014.6736753"},{"key":"ref46","first-page":"746","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","author":"claus","year":"1998","journal-title":"Proc AAAI\/IAAI"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1006\/game.1999.0738"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.1999.749260"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2787979"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1134\/S1064230710050102"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2870521"},{"key":"ref42","first-page":"1789","article-title":"Collaborative multiagent reinforcement learning by payoff propagation","volume":"7","author":"kok","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2016.7524380"},{"key":"ref41","first-page":"1523","article-title":"Multiagent planning with factored MDPs","author":"guestrin","year":"2002","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2880482"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.2140\/pjm.1956.6.1"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2937519"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2010.5462144"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2596042"}],"container-title":["IEEE Transactions on Communications"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/26\/9405515\/9294055-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/26\/9405515\/09294055.pdf?arnumber=9294055","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:48:34Z","timestamp":1652194114000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9294055\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4]]},"references-count":48,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcomm.2020.3045050","relation":{},"ISSN":["0090-6778","1558-0857"],"issn-type":[{"value":"0090-6778","type":"print"},{"value":"1558-0857","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4]]}}}