{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T04:56:08Z","timestamp":1769316968483,"version":"3.49.0"},"reference-count":14,"publisher":"IEEE","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":[],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/globecom38437.2019.9013975","type":"proceedings-article","created":{"date-parts":[[2020,2,28]],"date-time":"2020-02-28T09:59:24Z","timestamp":1582883964000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Reinforcement-Learning-Based Optimization for Content Delivery Policy in Cache-Enabled HetNets"],"prefix":"10.1109","author":[{"given":"Zhaojun","family":"Nan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunjian","family":"Jia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengchuan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2863687"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2016.2605239"},{"key":"ref12","author":"puterman","year":"2005","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2016.2575837"},{"key":"ref14","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2014.2306938"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2794615"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2014.7136382"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2737015"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2869562"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2016.2578922"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2785250"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2018.1701089"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2733001"}],"event":{"name":"GLOBECOM 2019 - 2019 IEEE Global Communications Conference","location":"Waikoloa, HI, USA","start":{"date-parts":[[2019,12,9]]},"end":{"date-parts":[[2019,12,13]]}},"container-title":["2019 IEEE Global Communications Conference (GLOBECOM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8968653\/9013108\/09013975.pdf?arnumber=9013975","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:47:12Z","timestamp":1658094432000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9013975\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/globecom38437.2019.9013975","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}