{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T18:30:09Z","timestamp":1773772209059,"version":"3.50.1"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["ECCS-1554576"],"award-info":[{"award-number":["ECCS-1554576"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["ECCS-1610874"],"award-info":[{"award-number":["ECCS-1610874"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CNS-1816908"],"award-info":[{"award-number":["CNS-1816908"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy, Office of Science","doi-asserted-by":"publisher","award":["DE-AC02-06CH11357"],"award-info":[{"award-number":["DE-AC02-06CH11357"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Select. Areas Commun."],"published-print":{"date-parts":[[2021,4]]},"DOI":"10.1109\/jsac.2020.3018804","type":"journal-article","created":{"date-parts":[[2020,8,25]],"date-time":"2020-08-25T20:12:12Z","timestamp":1598386332000},"page":"1101-1115","source":"Crossref","is-referenced-by-count":94,"title":["Constrained Deep Reinforcement Learning for Energy Sustainable Multi-UAV Based Random Access IoT Networks With NOMA"],"prefix":"10.1109","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6730-7267","authenticated-orcid":false,"given":"Sami","family":"Khairy","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0292-5715","authenticated-orcid":false,"given":"Prasanna","family":"Balaprakash","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8509-0452","authenticated-orcid":false,"given":"Lin X.","family":"Cai","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4837-3370","authenticated-orcid":false,"given":"Yu","family":"Cheng","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"241","article-title":"Learning algorithms for discounted MDPS with constraints","volume":"21","author":"geibel","year":"2012","journal-title":"International Journal of Mathematics Game Theory and Algebra"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2004.08.007"},{"key":"ref33","first-page":"325","article-title":"A geometric approach to multi-criterion reinforcement learning","volume":"5","author":"mannor","year":"2004","journal-title":"J Mach Learn Res"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2900630"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2017.2671522"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.2514\/6.2007-6461"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2010.08.013"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-012-9989-5"},{"key":"ref35","volume":"7","author":"altman","year":"1999","journal-title":"Constrained Markov Decision Processes"},{"key":"ref34","first-page":"3483","article-title":"Multi-objective reinforcement learning using sets of Pareto dominating policies","volume":"15","author":"van moffaert","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1007\/s10846-009-9383-1","article-title":"A survey of motion planning algorithms from the perspective of autonomous UAV guidance","volume":"57","author":"goerzen","year":"2009","journal-title":"J Intell Robot Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2020-Spring48590.2020.9128380"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2633562"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2018.2857799"},{"key":"ref1","year":"2017","journal-title":"Cisco Visual Networking Index Global Mobile Data Traffic Forecast Update"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353711"},{"key":"ref22","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/AERO.2016.7500855"},{"key":"ref24","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref23","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2906622"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2895831"},{"key":"ref50","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref51","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"arXiv 1802 09477"},{"key":"ref57","year":"2020","journal-title":"OpenAI Spinning up in Deep RL Repository"},{"key":"ref56","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref55","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"arXiv 1506 02438 [cs]"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref53","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"arXiv 1801 01290"},{"key":"ref52","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2016.2578312"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2864376"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1666"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2019.2910080"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2789293"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2872736"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9013924"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2920284"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2876513"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2018.1800161"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2902862"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.04.162"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2936837"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2017.2766778"},{"key":"ref5","year":"2020","journal-title":"FCC Opens 6 GHz Band to Wi-Fi and Other Unlicensed Uses"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/EuCNC.2018.8442662"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2825462"},{"key":"ref49","first-page":"-387i","article-title":"Deterministic policy gradient algorithms","volume":"32","author":"silver","year":"2014","journal-title":"Proc 31st Int Conf Int Conf Mach Learn (ICML)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2016.2633248"},{"key":"ref46","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref45","first-page":"22","article-title":"Constrained policy optimization","author":"achiam","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref48","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref47","first-page":"2","article-title":"Markov decision processes","author":"kallenberg","year":"2020","journal-title":"Lect Notes Univ Leiden"},{"key":"ref42","article-title":"Accelerated primal-dual policy optimization for safe reinforcement learning","author":"liang","year":"2018","journal-title":"arXiv 1802 06480"},{"key":"ref41","article-title":"Reward constrained policy optimization","author":"tessler","year":"2018","journal-title":"arXiv 1805 11074"},{"key":"ref44","first-page":"6070","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"chow","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref43","article-title":"Risk-sensitive reinforcement learning: A constrained optimization viewpoint","author":"a","year":"2018","journal-title":"arXiv 1810 09126"}],"container-title":["IEEE Journal on Selected Areas in Communications"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/49\/9379968\/9177252-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/49\/9379968\/09177252.pdf?arnumber=9177252","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:48:11Z","timestamp":1649443691000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9177252\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4]]},"references-count":57,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/jsac.2020.3018804","relation":{},"ISSN":["0733-8716","1558-0008"],"issn-type":[{"value":"0733-8716","type":"print"},{"value":"1558-0008","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4]]}}}