{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T23:21:56Z","timestamp":1770333716093,"version":"3.49.0"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/R006466\/1"],"award-info":[{"award-number":["EP\/R006466\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/R006377\/1"],"award-info":[{"award-number":["EP\/R006377\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Select. Areas Commun."],"published-print":{"date-parts":[[2019,6]]},"DOI":"10.1109\/jsac.2019.2904366","type":"journal-article","created":{"date-parts":[[2019,3,11]],"date-time":"2019-03-11T18:29:43Z","timestamp":1552328983000},"page":"1424-1440","source":"Crossref","is-referenced-by-count":98,"title":["Reinforcement Learning for Real-Time Optimization in NB-IoT Networks"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5337-890X","authenticated-orcid":false,"given":"Nan","family":"Jiang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1001-7036","authenticated-orcid":false,"given":"Yansha","family":"Deng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8337-5884","authenticated-orcid":false,"given":"Arumugam","family":"Nallanathan","sequence":"additional","affiliation":[]},{"given":"Jonathon A.","family":"Chambers","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","author":"cheng","year":"2018","journal-title":"Polynomial regression as an alternative to neural nets"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-72927-3_23"},{"key":"ref33","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":"ref32","author":"sutton","year":"2017","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref31","year":"2017","journal-title":"Evolved Universal Terrestrial Radio Access (E-UTRA) Requirements for Support of Radio Resource Management"},{"key":"ref30","year":"2017","journal-title":"Evolved Universal Terrestrial Radio Access (E-UTRA) Medium Access Control (MAC) Protocol Specification"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1561\/2200000042"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1613\/jair.678"},{"key":"ref35","first-page":"1","article-title":"Issues in using function approximation for reinforcement learning","author":"thrun","year":"1993","journal-title":"Proc of the Connectionist Models Summer School Hillsdale NJ Erlbaum"},{"key":"ref34","first-page":"7","article-title":"Value function approximation in reinforcement learning using the Fourier basis","volume":"6","author":"konidaris","year":"2011","journal-title":"Proc 25th AAAI Conf Artif Intell"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2010.2059055"},{"key":"ref40","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2003.822330"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/6474768"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422167"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2786680"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2016.2632128"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2812299"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2664418"},{"key":"ref18","author":"azari","year":"2018","journal-title":"Latency-energy tradeoff based on channel scheduling and repetitions in NB-IoT systems"},{"key":"ref19","author":"dahlman","year":"2013","journal-title":"4G LTE\/LTE-Advanced for Mobile Broadband"},{"key":"ref28","year":"2017","journal-title":"Evolved Universal Terrestrial Radio Access (E-UTRA) Physical layer Measurements"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1600510CM"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1201\/9781482276596"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1500269CM"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2016.2527601"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2016.2609914"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2014.2328491"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISWCS.2012.6328420"},{"key":"ref7","first-page":"1","article-title":"Application of Q-learning for RACH access to support M2M traffic over a cellular network","author":"bello","year":"2014","journal-title":"Proc 20th Eur Wireless Conf"},{"key":"ref2","first-page":"76","article-title":"Narrowband Internet of Things whitepaper","volume":"8","author":"schlienz","year":"2016","journal-title":"IEEE Microw Mag"},{"key":"ref9","first-page":"1","article-title":"Distributed frame size selection for a Q learning based slotted ALOHA protocol","author":"yan","year":"2013","journal-title":"Proc Int Symp Wireless Commun Syst (ISWCS)"},{"key":"ref1","first-page":"1","article-title":"Cooperative deep reinforcement learning for multiple-group NB-IoT networks optimization","author":"jiang","year":"2018","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref20","year":"2011","journal-title":"Study on RAN Improvements for Machine-type Communications"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2864756"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2018.2793274"},{"key":"ref42","first-page":"26","article-title":"Lecture 6.5-RMSPROP: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"Neural Netw Mach Learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2318857.2254767"},{"key":"ref41","first-page":"5","article-title":"Deep reinforcement learning with double Q-learning","volume":"2","author":"van hasselt","year":"2016","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref23","year":"2017","journal-title":"Evolved Universal Terrestrial Radio Access (E-UTRA) Physical Channels and Modulation"},{"key":"ref44","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","author":"sunehag","year":"2018","journal-title":"Proc Int'l Joint Conf Autonomous Agents and Multiagent Systems (AAMAS)"},{"key":"ref26","year":"2015","journal-title":"Cellular System Support for Ultra Low Complexity and Low Throughput Internet of Things"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SURV.2013.100713.00203"}],"container-title":["IEEE Journal on Selected Areas in Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/49\/8715825\/08664581.pdf?arnumber=8664581","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:09:13Z","timestamp":1657746553000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8664581\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6]]},"references-count":44,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/jsac.2019.2904366","relation":{},"ISSN":["0733-8716","1558-0008"],"issn-type":[{"value":"0733-8716","type":"print"},{"value":"1558-0008","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,6]]}}}