{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:45:41Z","timestamp":1753602341015,"version":"3.37.3"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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. Commun."],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/tcomm.2020.2974216","type":"journal-article","created":{"date-parts":[[2020,2,18]],"date-time":"2020-02-18T08:07:52Z","timestamp":1582013272000},"page":"2823-2837","source":"Crossref","is-referenced-by-count":8,"title":["On Sampled Reinforcement Learning in Wireless Networks: Exploitation of Policy Structures"],"prefix":"10.1109","volume":"68","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0123-942X","authenticated-orcid":false,"given":"Libin","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8896-1177","authenticated-orcid":false,"given":"Urbashi","family":"Mitra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1002\/0471722162"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638850"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1186\/1687-1499-2012-278"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2012.6503723"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2017.8262875"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CISS.2018.8362275"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2664049"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7039519"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2010.5717273"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human level control through deep reinforcement learning","volume":"518","author":"minh","year":"2015","journal-title":"Nature"},{"key":"ref19","article-title":"Spectral graph theory","author":"chung","year":"1997","journal-title":"Proc CBMS Reg Conf Ser Math"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/0096-3003(95)00298-7"},{"article-title":"Learning from delayed rewards","year":"1989","author":"watkins","key":"ref4"},{"key":"ref27","first-page":"1","article-title":"Learning rates for Q-learning","volume":"5","author":"even-dar","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref3","volume":"2","author":"bertsekas","year":"2005","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904329"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2007.897859"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7997229"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422586"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7997440"},{"key":"ref2","volume":"1","author":"bertsekas","year":"2005","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2238935"},{"journal-title":"Reinforcement Learning An Introduction","year":"2017","author":"sutton","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2235192"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511807213"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2899620"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1963.tb00955.x"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1960.tb03959.x"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2015.2496721"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/BF00994018"}],"container-title":["IEEE Transactions on Communications"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/26\/9094270\/9000735-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/26\/9094270\/09000735.pdf?arnumber=9000735","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T13:47:15Z","timestamp":1651067235000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9000735\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":30,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcomm.2020.2974216","relation":{},"ISSN":["0090-6778","1558-0857"],"issn-type":[{"type":"print","value":"0090-6778"},{"type":"electronic","value":"1558-0857"}],"subject":[],"published":{"date-parts":[[2020,5]]}}}