{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T20:20:43Z","timestamp":1777494043389,"version":"3.51.4"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Open J. Commun. Soc."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/ojcoms.2024.3514785","type":"journal-article","created":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T14:19:36Z","timestamp":1733753976000},"page":"7941-7953","source":"Crossref","is-referenced-by-count":7,"title":["Actor\u2013Critic Reinforcement Learning for Throughput-Optimized Power Allocation in Energy Harvesting NOMA Relay-Assisted Networks"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3168-9480","authenticated-orcid":false,"given":"Faeik T.","family":"Al Rabee","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, Faculty of Engineering Technology, Al-Balqa Applied University, Salt, Jordan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8754-6898","authenticated-orcid":false,"given":"Ala'Eddin","family":"Masadeh","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Al-Huson University College, Al-Balqa Applied University, Salt, Jordan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2275-6621","authenticated-orcid":false,"given":"Sharief","family":"Abdel-Razeq","sequence":"additional","affiliation":[{"name":"Department of Telecommunications Engineering, Hijjawi Faculty for Engineering Technology, Yarmouk University, Irbid, Jordan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3429-7212","authenticated-orcid":false,"given":"Haythem","family":"Bany Salameh","sequence":"additional","affiliation":[{"name":"Department of Telecommunications Engineering, Hijjawi Faculty for Engineering Technology, Yarmouk University, Irbid, Jordan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2022.9749229"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2016.2530695"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2017.07.002"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2602318"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSIEID52046.2020.00067"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICECA.2018.8474584"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422892"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WAMICON.2017.7930242"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.4018\/AWTT"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/ett.3887"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICET.2017.8281755"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/INFOTEH53737.2022.9751269"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SIU49456.2020.9302126"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3124076"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9010032"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2933835"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1049\/iet-com.2019.0841"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292075"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRAE48301.2019.9043821"},{"key":"ref21","first-page":"1","article-title":"Actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Konda"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2018.2801725"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2769644"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3124090"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2020.2984524"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2015.7081085"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2021.3077635"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3306880"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICICT57646.2023.10133954"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2024.103139"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCChina.2018.8641248"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM46510.2021.9685102"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2015.2391811"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2015.2402662"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2015.2391651"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2012.6364174"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2013.052013.120565"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2016.2607229"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2013.052213.121561"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCS.2010.5686445"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2017.2724438"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2016.2578925"},{"key":"ref43","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2815005"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2017.2744640"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2650987"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-021-03365-6"},{"key":"ref48","first-page":"1","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Sutton"},{"key":"ref49","volume-title":"Lecture 7: Policy gradient: UCL Course RL","author":"Silver","year":"2015"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.33564\/ijeast.2020.v04i12.054"},{"key":"ref51","article-title":"Successive convex approximation: Analysis and applications","author":"Razaviyayn","year":"2014"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/MSSC.2010.936667"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2017.2703855"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2020.3026453"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2016.7511405"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.est.2023.109144"}],"container-title":["IEEE Open Journal of the Communications Society"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8782661\/10362961\/10787238.pdf?arnumber=10787238","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T04:39:59Z","timestamp":1752813599000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10787238\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/ojcoms.2024.3514785","relation":{},"ISSN":["2644-125X"],"issn-type":[{"value":"2644-125X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}