{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T19:03:13Z","timestamp":1778785393597,"version":"3.51.4"},"reference-count":220,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20444"],"award-info":[{"award-number":["U21A20444"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202222"],"award-info":[{"award-number":["62202222"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61971366"],"award-info":[{"award-number":["61971366"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22B2062"],"award-info":[{"award-number":["U22B2062"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20220880"],"award-info":[{"award-number":["BK20220880"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Commun. Surv. Tutorials"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/comst.2022.3224279","type":"journal-article","created":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T15:22:06Z","timestamp":1669303326000},"page":"425-466","source":"Crossref","is-referenced-by-count":89,"title":["Reinforcement Learning-Based Physical Cross-Layer Security and Privacy in 6G"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8247-0353","authenticated-orcid":false,"given":"Xiaozhen","family":"Lu","sequence":"first","affiliation":[{"name":"Department of Information and Communication Engineering, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2402-611X","authenticated-orcid":false,"given":"Liang","family":"Xiao","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Engineering, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2979-7493","authenticated-orcid":false,"given":"Pengmin","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Engineering, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7333-9975","authenticated-orcid":false,"given":"Xiangyang","family":"Ji","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9171-2596","authenticated-orcid":false,"given":"Chenren","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4485-6743","authenticated-orcid":false,"given":"Shui","family":"Yu","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0488-511X","authenticated-orcid":false,"given":"Weihua","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3108618"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2933899"},{"issue":"4","key":"ref3","doi-asserted-by":"crossref","first-page":"3682","DOI":"10.1109\/COMST.2019.2916180","article-title":"Security for 5G and beyond","volume":"21","author":"Ahmad","year":"2019","journal-title":"IEEE Commun. Surveys Tuts."},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2019.1800418"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2954595"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.3011561"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2000218"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2016.2621116"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1600863"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.011.1900567"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2019.1800430"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.3004197"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2016.1600193CM"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2015.7120012"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2927379"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2018.1700291"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2017.2746007"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.1900159"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.2985548"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.2968973"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3155775"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2878767"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2018.1701148"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.23919\/JCC.2021.08.006"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.1900664"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2875926"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref29","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Mnih"},{"key":"ref30","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Rep. (ICLR)","author":"Lillicrap"},{"key":"ref31","article-title":"Proximal policy optimization algorithms","volume-title":"arXiv:1707.06347","author":"Schulman","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2930247"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121870"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2019.2903655"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2019.1800376"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.21143"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2021.3078081"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/SURV.2011.041110.00022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2016.2535906"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/SURV.2009.090404"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2782726"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2018.2884910"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2967026"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2843769"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2014.2344013"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2016.2573304"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.1900028"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2986008"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2018.1700140"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2016.2548426"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2017.2746344"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2013.6523808"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2791428"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.2995371"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2865107"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2017.1600290"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2948302"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2693965"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2825478"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2013.131120"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2939179"},{"key":"ref63","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Sutton"},{"issue":"3-4","key":"ref64","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Mach. Learn."},{"key":"ref65","first-page":"1021","article-title":"Rational and convergent learning in stochastic games","volume-title":"Proc. Int. Joint Conf. Artif. Intell. (IJCAI)","volume":"17","author":"Bowling"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2789466"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2016.2524258"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM46510.2021.9685317"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1997.652501"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2016.2647624"},{"key":"ref71","volume-title":"On-Line Q-Learning Using Connectionist Systems","author":"Rummery","year":"1994"},{"key":"ref72","first-page":"2613","article-title":"Double Q-learning","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"23","author":"Hasselt"},{"key":"ref73","first-page":"2827","article-title":"Neural episodic control","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Pritzel"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref75","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Silver"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2760281"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2991956"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2979456"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3169813"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2021.3089476"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933973"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933762"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2981320"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2018.2877317"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2878025"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2974281"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14435-6_7"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2785414"},{"key":"ref89","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Foerster"},{"key":"ref90","first-page":"6379","article-title":"Multi-agent actor\u2013critic for mixed cooperative-competitive environments","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"30","author":"Lowe"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2961405"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3036962"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.3027695"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3051163"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682983"},{"key":"ref96","first-page":"1","article-title":"Reward constrained policy optimization","volume-title":"Proc. Int. Conf. Learn. Rep. (ICLR)","author":"Tessler"},{"key":"ref97","first-page":"14093","article-title":"Reinforcement learning with convex constraints","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Miryoosefi"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.3007742"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11396"},{"issue":"7","key":"ref100","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"Taylor","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6924"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1145\/2739480.2754798"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10518"},{"issue":"1","key":"ref104","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1022140919877","article-title":"Recent advances in hierarchical reinforcement learning","volume":"13","author":"Barto","year":"2003","journal-title":"Discr. Event Dyn. Syst."},{"key":"ref105","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Kulkarni"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3056206"},{"key":"ref107","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Vezhnevets"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2020.3000655"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3037767"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3077662"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2019.2932068"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2018.8647173"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.2978192"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CloudCom.2016.0061"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2876750"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.3002386"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3106956"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3024860"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3103062"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2018.2802902"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.2983170"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2019.8885667"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2017.2750106"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2947921"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2904741"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2019.1800458"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3012090"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2912227"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2999721"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2831687"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2904440"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOMW.2019.8845312"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3038902"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-018-0609-x"},{"key":"ref135","article-title":"Securing the insecure: A first-line-of-defense for Nanoscale communication systems operating in THz band","volume-title":"arXiv:2007.06818","author":"Aman","year":"2020"},{"key":"ref136","article-title":"Reflections in the sky: Joint trajectory and passive Beamforming design for secure UAV networks with reconfigurable intelligent surface","author":"Long","year":"2020","journal-title":"arXiv:2005.10559"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2019.2919685"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.1900107"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3012721"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3007043"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.3024621"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2825820"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2017.2734666"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.2969576"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2825138"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2017.2776944"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2938757"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2885286"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2954748"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2016.2551685"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2901825"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2916209"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2939742"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.011.1900321"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2948283"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2955128"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2018.2829886"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3027586"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2890203"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2957400"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2961707"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3170900"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3143222"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2022.3143880"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3196143"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2018.1800021"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3038407"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.2986879"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2016.2615853"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2772826"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2931068"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2948068"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.14778\/2757807.2757811"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2020.3010967"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2878718"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2973705"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.23919\/JCC.2021.06.019"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3104833"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488789"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3200111"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3053770"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2017.2713341"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2957791"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2797023"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2848659"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2773646"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3062659"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2021.3087787"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-3170-2"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3014788"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2021.3095315"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2020.3014385"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.011.2100068"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3118446"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3088655"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2906228"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.1900207"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3194074"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3025684"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3030496"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2019.2933639"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3057653"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2980587"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3048345"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2022.3140231"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3142348"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3005931"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3123787"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3130163"},{"key":"ref210","first-page":"1","article-title":"Distributed distributional deterministic policy gradients","volume-title":"Proc. Int. Conf. Learn. Rep. (ICLR)","author":"Barth-Maron"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993104"},{"key":"ref212","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Finn"},{"key":"ref213","first-page":"2063","article-title":"Transfer learning for related reinforcement learning tasks via image-to-image translation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Gamrian"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3149396"},{"key":"ref215","first-page":"9105","article-title":"Learning safe policies with expert guidance","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Huang"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3023126"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-32020-w"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2986024"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3002988"}],"container-title":["IEEE Communications Surveys & Tutorials"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9739\/10051138\/09961877.pdf?arnumber=9961877","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:14:17Z","timestamp":1706757257000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9961877\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":220,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/comst.2022.3224279","relation":{},"ISSN":["1553-877X","2373-745X"],"issn-type":[{"value":"1553-877X","type":"electronic"},{"value":"2373-745X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}