{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:28:20Z","timestamp":1774538900406,"version":"3.50.1"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","funder":[{"name":"Telstra Corporation Ltd., titled \u201cDevelopment of an open programmable scheduler for LTE networks,\u201d"},{"DOI":"10.13039\/100015539","name":"Australian Government Research Training Program Scholarship","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015539","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001774","name":"two Postgraduate Research Supplementary Scholarships of The University of Sydney","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001774","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council Discovery Early Career Research Award","doi-asserted-by":"publisher","award":["DE150101704"],"award-info":[{"award-number":["DE150101704"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council Laureate Fellowship","doi-asserted-by":"publisher","award":["FL160100032"],"award-info":[{"award-number":["FL160100032"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Select. Areas Commun."],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1109\/jsac.2021.3078498","type":"journal-article","created":{"date-parts":[[2021,5,10]],"date-time":"2021-05-10T19:49:46Z","timestamp":1620676186000},"page":"2014-2028","source":"Crossref","is-referenced-by-count":82,"title":["Knowledge-Assisted Deep Reinforcement Learning in 5G Scheduler Design: From Theoretical Framework to Implementation"],"prefix":"10.1109","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9457-1135","authenticated-orcid":false,"given":"Zhouyou","family":"Gu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0193-9784","authenticated-orcid":false,"given":"Changyang","family":"She","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6775-8682","authenticated-orcid":false,"given":"Wibowo","family":"Hardjawana","sequence":"additional","affiliation":[]},{"given":"Simon","family":"Lumb","sequence":"additional","affiliation":[]},{"given":"David","family":"McKechnie","sequence":"additional","affiliation":[]},{"given":"Todd","family":"Essery","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2700-2001","authenticated-orcid":false,"given":"Branka","family":"Vucetic","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2677046.2677053"},{"key":"ref38","year":"2017","journal-title":"Study on New Radio (NR) Access Technology Physical Layer Aspects (Release 14)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2791598"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2014.2318726"},{"key":"ref31","year":"2018","journal-title":"Physical layer procedures for data"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WFCS.2018.8402373"},{"key":"ref37","article-title":"Parameter space noise for exploration","author":"plappert","year":"2018","journal-title":"Proc ICLR"},{"key":"ref36","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"Proc ICLR (Poster)"},{"key":"ref35","first-page":"5398","article-title":"Hybrid reward architecture for reinforcement learning","volume":"30","author":"van seijen","year":"2017","journal-title":"Proc NIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511841224"},{"key":"ref10","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":"ref40","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume":"32","author":"paszke","year":"2019","journal-title":"Proc NIPS"},{"key":"ref11","author":"sutton","year":"2011","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref12","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2869350"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS.2017.00024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2898744"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICII.2019.00044"},{"key":"ref17","year":"2012","journal-title":"Analysis on Traffic Model and Characteristics for Mtc and Text Proposal"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2013.2278705"},{"key":"ref19","year":"2017","journal-title":"Study on Scenarios and Requirements for Next Generation Access Technologies"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2959182"},{"key":"ref4","year":"2018","journal-title":"Service requirements for cyber-physical control applications in vertical domains"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2976585"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1601092"},{"key":"ref6","first-page":"678","article-title":"Performance comparison between round robin and proportional fair scheduling methods for LTE","volume":"2","author":"kawser","year":"2012","journal-title":"Int J Inf Electron Eng"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2980159.2980163"},{"key":"ref5","first-page":"207","article-title":"GPF: A GPU-based design to achieve $100~\\mu\\text{s}$\n scheduling for 5G NR","author":"huang","year":"2018","journal-title":"Proc 24th Annu Int Conf Mobile Comput Netw"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2010.5757800"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2000.832234"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2867029"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.011.1900630"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2878265"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCW.2019.8757174"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2020.2997036"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2019.2922961"},{"key":"ref42","year":"2009","journal-title":"Physical layer procedures"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2927067"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/VETECS.2007.260"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3300061.3345431"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2988255"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2019.1800447"},{"key":"ref43","article-title":"An overview of deep learning architectures in few-shot learning domain","author":"jadon","year":"2020","journal-title":"arXiv 2008 06365"},{"key":"ref25","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume":"99","author":"ng","year":"1999","journal-title":"Proc ICML"}],"container-title":["IEEE Journal on Selected Areas in Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/49\/9457209\/09427224.pdf?arnumber=9427224","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T20:41:33Z","timestamp":1635280893000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9427224\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7]]},"references-count":44,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/jsac.2021.3078498","relation":{},"ISSN":["0733-8716","1558-0008"],"issn-type":[{"value":"0733-8716","type":"print"},{"value":"1558-0008","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7]]}}}