{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T22:20:38Z","timestamp":1757542838006,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"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":[[2020,8]]},"DOI":"10.1109\/pimrc48278.2020.9217110","type":"proceedings-article","created":{"date-parts":[[2020,10,8]],"date-time":"2020-10-08T15:58:06Z","timestamp":1602172686000},"page":"1-6","source":"Crossref","is-referenced-by-count":11,"title":["Deep Reinforcement Learning for Delay-Sensitive LTE Downlink Scheduling"],"prefix":"10.1109","author":[{"given":"Nikhilesh","family":"Sharma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Someshwar Rao","family":"Somayajula Venkata","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Filippo","family":"Malandra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicholas","family":"Mastronarde","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jacob","family":"Chakareski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2016.7511405"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2973125"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2015.7249182"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"ref14","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":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref16","article-title":"Proactive resource management for LTE in unliceused spectrum: A deep learning perspective","volume":"17","author":"challita","year":"7","journal-title":"IEEE Transactions on Wireless Communications"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2018.8647289"},{"key":"ref18","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv I509 0297I"},{"journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming","year":"2014","author":"puterman","key":"ref19"},{"year":"2009","key":"ref4","article-title":"Requirements for Evolved UTRA (E-UTRA) and Evolved UTRAN (E-UTRAN)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7996611"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2012.36"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2013.030413.121120"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"watkins","year":"1992","journal-title":"Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.921846"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2012.6364194"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2921869"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2009.5400270"},{"key":"ref22","article-title":"Deep reinforcement learning in large discrete action spaces","author":"dulac-arnold","year":"2015","journal-title":"arXiv preprint arXiv I5I2 07679"},{"article-title":"Deterministic policy gradient algorithms","year":"2014","author":"silver","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1002\/9780470978504"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SURV.2012.060912.00100"},{"key":"ref26","article-title":"Throughput fairness index: An explanation","volume":"99","author":"jain","year":"1999","journal-title":"ATM Forum Contribution"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/18.212277"}],"event":{"name":"2020 IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications","start":{"date-parts":[[2020,8,31]]},"location":"London, United Kingdom","end":{"date-parts":[[2020,9,3]]}},"container-title":["2020 IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9210501\/9217048\/09217110.pdf?arnumber=9217110","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T17:53:09Z","timestamp":1656438789000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9217110\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/pimrc48278.2020.9217110","relation":{},"subject":[],"published":{"date-parts":[[2020,8]]}}}