{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T19:05:20Z","timestamp":1780513520079,"version":"3.54.1"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2018,12,1]],"date-time":"2018-12-01T00:00:00Z","timestamp":1543622400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Framework of the Horizon 2020 Project NEWTON","award":["ICT-688503"],"award-info":[{"award-number":["ICT-688503"]}]},{"DOI":"10.13039\/501100000780","name":"European Union","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw. Serv. Manage."],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/tnsm.2018.2863563","type":"journal-article","created":{"date-parts":[[2018,8,17]],"date-time":"2018-08-17T19:39:20Z","timestamp":1534534760000},"page":"1661-1675","source":"Crossref","is-referenced-by-count":90,"title":["Towards 5G: A Reinforcement Learning-Based Scheduling Solution for Data Traffic Management"],"prefix":"10.1109","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9121-0286","authenticated-orcid":false,"given":"Ioan-Sorin","family":"Comsa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sijing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4890-5648","authenticated-orcid":false,"given":"Mehmet Emin","family":"Aydin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pierre","family":"Kuonen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3315-3081","authenticated-orcid":false,"given":"Ramona","family":"Trestian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2578-5580","authenticated-orcid":false,"given":"Gheorghita","family":"Ghinea","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2011.2148710"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2371046"},{"key":"ref30","first-page":"4387","article-title":"Adaptive proportional fair parameterization based LTE scheduling using continuous actor-critic reinforcement learning","author":"com?a","year":"2014","journal-title":"Proc IEEE Global Communication Conf (GLOBECOM)"},{"key":"ref10","author":"sutton","year":"2012","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SURV.2012.100412.00017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2016.2571695"},{"key":"ref13","first-page":"19","article-title":"D4.1: Technical results for service specific multi-node\/multiantenna solutions","author":"pratas","year":"2016","journal-title":"The Framework European Project Flexible Air Interface for Scalable Service Delivery Within Wireless Communication Networks of the 5th Generation (FANTASTIC-5G)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2005.1561930"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2010.2091660"},{"key":"ref16","year":"2013","journal-title":"Technical Specification Group Services and System Aspects Policy 1164 and Charging Control Architecture Release 12 V 12 2 0"},{"key":"ref17","author":"szepesvari","year":"2010","journal-title":"Algorithms for Reinforcement Learning Synthesis Lectures on Artificial Intelligence and Machine Learning"},{"key":"ref18","author":"com?a","year":"2014","journal-title":"Sustainable Scheduling Policies for Radio Access Networks Based on LTE Technology"},{"key":"ref19","author":"van hasselt","year":"2011","journal-title":"Insights in Reinforcement Learning Formal Analysis and Empirical Evaluation of Temporal-Difference Learning Algorithms Utrecht"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2016.2531291"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2016.2550765"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/VTCFall.2014.6966162"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2014.2328098"},{"key":"ref6","author":"ghosh","year":"2010","journal-title":"Fundamentals of LTE"},{"key":"ref29","first-page":"418","article-title":"Scheduling policies based on dynamic throughput and fairness tradeoff control in LTE-A networks","author":"com?a","year":"2014","journal-title":"Proc IEEE Conf Local Computer Netw (LCN)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2014.6957145"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2009\/510617","article-title":"Downlink scheduling for multiclass traffic in LTE","volume":"2009","author":"sadiq","year":"2009","journal-title":"EURASIP J Wireless Commun Netw"},{"key":"ref7","first-page":"462","article-title":"Scheduling of real\/non-real time services: Adaptive EXP\/PF algorithm","author":"rhee","year":"2003","journal-title":"Proc IEEE Veh Technol Conf vol"},{"key":"ref2","year":"2016","journal-title":"White Paper 5G Radio Access"},{"key":"ref9","first-page":"364","article-title":"An efficient downlink packet scheduling algorithm for real time traffics in LTE systems","author":"liu","year":"2013","journal-title":"Proc IEEE Consum Commun Netw Conf (CCNC)"},{"key":"ref1","year":"2015","journal-title":"5G White Paper"},{"key":"ref20","first-page":"17","article-title":"QV(lambda)-learning: A new on-policy reinforcement learning algorithm","author":"wiering","year":"2005","journal-title":"Proc of European Workshop on Reinforcement Learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2009.5178745"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2009.4927532"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2014.2374237"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/AHICI.2009.5340336"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2016.7511221"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2014.7136431"}],"container-title":["IEEE Transactions on Network and Service Management"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4275028\/8576790\/08425580.pdf?arnumber=8425580","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T02:33:46Z","timestamp":1643250826000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8425580\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":32,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnsm.2018.2863563","relation":{},"ISSN":["1932-4537","2373-7379"],"issn-type":[{"value":"1932-4537","type":"electronic"},{"value":"2373-7379","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12]]}}}