{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T17:54:30Z","timestamp":1775066070928,"version":"3.50.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100008982","name":"Qatar National Research Fund","doi-asserted-by":"publisher","award":["NPRP12S- 0305-190231"],"award-info":[{"award-number":["NPRP12S- 0305-190231"]}],"id":[{"id":"10.13039\/100008982","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Commun. Netw."],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1109\/tccn.2022.3155727","type":"journal-article","created":{"date-parts":[[2022,3,2]],"date-time":"2022-03-02T20:25:19Z","timestamp":1646252719000},"page":"1287-1300","source":"Crossref","is-referenced-by-count":49,"title":["Multi-Agent Reinforcement Learning for Network Selection and Resource Allocation in Heterogeneous Multi-RAT Networks"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3883-2588","authenticated-orcid":false,"given":"Mhd Saria","family":"Allahham","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Qatar University, Doha, Qatar"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3887-2520","authenticated-orcid":false,"given":"Alaa Awad","family":"Abdellatif","sequence":"additional","affiliation":[{"name":"College of Engineering, Qatar University, Doha, Qatar"}]},{"given":"Naram","family":"Mhaisen","sequence":"additional","affiliation":[{"name":"Qatar University, Doha, Qatar"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1583-7503","authenticated-orcid":false,"given":"Amr","family":"Mohamed","sequence":"additional","affiliation":[{"name":"College of Engineering, Qatar University, Doha, Qatar"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7565-5253","authenticated-orcid":false,"given":"Aiman","family":"Erbad","sequence":"additional","affiliation":[{"name":"Division of Information and Computing Technology, College of Science and Engineering, Hamad Bin Khalifa University, Ar-Rayyan, Qatar"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8972-8094","authenticated-orcid":false,"given":"Mohsen","family":"Guizani","sequence":"additional","affiliation":[{"name":"Machine Learning Department, MBZUAI, Abu Dhabi, UAE"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.011.1900553"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2017.7925829"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3059896"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.1900516"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2015.2467174"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2898205"},{"key":"ref7","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref8","first-page":"330","article-title":"Multi-agent reinforcement learning: Independent versus cooperative agents","volume-title":"Proc. Tenth Int. Conf. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref9","first-page":"1334","article-title":"Hierarchical reinforcement learning in communication-mediated multiagent coordination","volume-title":"Proc. 3rd Int. Joint Conf. Auton. Agents Multiagent Syst.","volume":"3","author":"Fischer"},{"key":"ref10","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Advances in Neural Information Processing Systems","volume":"29","author":"Foerster","year":"2016"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102372"},{"key":"ref12","article-title":"Deep recurrent Q-learning for partially observable MDPs","author":"Hausknecht","year":"2015","journal-title":"arXiv:1507.06527"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3397166.3413468"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3020400"},{"key":"ref15","article-title":"Cellular-connected uavs over 5G: Deep reinforcement learning for interference management","author":"Challita","year":"2018","journal-title":"arXiv:1801.05500"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3023936"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/JCC.2020.09.017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2019.08.001"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2021.04.018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MCE.2016.2614419"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2856752"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2871142"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2007.907072"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2015.2416987"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2014.6812287"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46140-3_13"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/VETECS.2006.1682964"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/BMSB.2017.7986194"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCN.2007.4317990"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2005.1452853"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2013.040413.120676"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2008.2004588"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2718526"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3058037"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2793186"},{"key":"ref36","article-title":"Encoding distortion modeling for DWT-based wireless EEG monitoring system","author":"Awad","year":"2016","journal-title":"arXiv:1602.04974"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/QSHINE.2014.6928668"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/b978-0-12-819045-6.00003-0"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC.2011.5982690"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2014.09.003"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2004.1373867"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2011.2159845"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IEEESTD.2012.6198737"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICC42927.2021.9500548"},{"key":"ref46","first-page":"709","article-title":"Dynamic programming for partially observable stochastic games","volume-title":"Proc. AAAI","volume":"4","author":"Hansen"},{"key":"ref47","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"Lowe","year":"2020","journal-title":"arXiv:1706.02275"},{"key":"ref48","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2019","journal-title":"arXiv:1509.02971"},{"key":"ref49","article-title":"A deeper look at experience replay","author":"Zhang","year":"2017","journal-title":"arXiv:1712.01275"},{"key":"ref50","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2017","journal-title":"arXiv:1412.6980"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2017.2785302"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3027048"}],"container-title":["IEEE Transactions on Cognitive Communications and Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6687307\/9790075\/09726129.pdf?arnumber=9726129","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T23:26:43Z","timestamp":1705534003000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9726129\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":52,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tccn.2022.3155727","relation":{},"ISSN":["2332-7731","2372-2045"],"issn-type":[{"value":"2332-7731","type":"electronic"},{"value":"2372-2045","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6]]}}}