{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T00:11:55Z","timestamp":1773879115410,"version":"3.50.1"},"reference-count":189,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"24","license":[{"start":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T00:00:00Z","timestamp":1702598400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T00:00:00Z","timestamp":1702598400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T00:00:00Z","timestamp":1702598400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100008982","name":"NPRP from the Qatar National Research Fund","doi-asserted-by":"publisher","award":["NPRP13S-0205-200265"],"award-info":[{"award-number":["NPRP13S-0205-200265"]}],"id":[{"id":"10.13039\/100008982","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NPRP","award":["NPRP12S-0305-190231"],"award-info":[{"award-number":["NPRP12S-0305-190231"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2023,12,15]]},"DOI":"10.1109\/jiot.2023.3288050","type":"journal-article","created":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T18:47:29Z","timestamp":1687805249000},"page":"21982-22007","source":"Crossref","is-referenced-by-count":45,"title":["Reinforcement Learning for Intelligent Healthcare Systems: A Review of Challenges, Applications, and Open Research Issues"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3887-2520","authenticated-orcid":false,"given":"Alaa Awad","family":"Abdellatif","sequence":"first","affiliation":[{"name":"College of Engineering, Qatar University, Doha, Qatar"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0211-2666","authenticated-orcid":false,"given":"Naram","family":"Mhaisen","sequence":"additional","affiliation":[{"name":"College of Electrical Engineering, Mathematics, and Computer Science, TU Delft, Delft, The Netherlands"}]},{"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":"College of Science and Engineering, Hamad Bin Khalifa University, Qatar Foundation, Doha, Qatar"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8972-8094","authenticated-orcid":false,"given":"Mohsen","family":"Guizani","sequence":"additional","affiliation":[{"name":"Machine Learning Department, Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.011.2000064"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.011.1900553"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2846609"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/VTCFall.2012.6399230"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/mnet.2019.1900029"},{"key":"ref7","volume-title":"Deep deterministic policy gradient for urban traffic light control","author":"Casas","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref10","volume-title":"Proximal Policy Optimization Algorithms","author":"Schulman","year":"2017"},{"key":"ref11","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3023394"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3063822"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3073036"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2988367"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3040957"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2018.2840971"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2976000"},{"key":"ref20","volume-title":"Deep reinforcement learning for radio resource allocation and management in next generation heterogeneous wireless networks: A survey","author":"Alwarafy","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3073009"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2773600"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/fi11040094"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2943405"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2016.2636665"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MCC.2018.1081063"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2019.2907718"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.17775\/CSEEJPES.2018.00520"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2912200"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CICT48419.2019.9066260"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2020.101964"},{"key":"ref34","article-title":"Deep reinforcement learning: An overview","author":"Li","year":"2017","journal-title":"arXiv:1701.07274"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref36","article-title":"Machine learning for wireless networks with artificial intelligence: A tutorial on neural networks","author":"Chen","year":"2017","journal-title":"arXiv:1710.02913"},{"key":"ref37","volume-title":"Benchmarking deep reinforcement learning for continuous control","author":"Duan","year":"2016"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3477600"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3052910"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-020-0832-5"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2018.09.019"},{"key":"ref42","article-title":"Reinforcement learning in models of adaptive medical treatment strategies","author":"Vincent","year":"2014"},{"key":"ref43","first-page":"305","article-title":"Trajectory inspection: A method for iterative clinician-driven design of reinforcement learning studies","volume":"2021","author":"Ji","year":"2021","journal-title":"AMIA Summits Transl. Sci. Proc."},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.glohj.2020.04.002"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.4236\/jilsa.2017.91001"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2782687"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"ref48","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2001.932842"},{"key":"ref50","first-page":"1015","article-title":"Skill discovery in continuous reinforcement learning domains using skill chaining","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"22","author":"Konidaris"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.1080.0305"},{"key":"ref52","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"Puterman","year":"2014"},{"key":"ref53","article-title":"Introduction to online convex optimization","author":"Hazan","year":"2019","journal-title":"arXiv:1909.05207"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"issue":"3","key":"ref55","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":"ref56","volume-title":"Reinforcement Learning and Optimal Control","author":"Bertsekas","year":"2019"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09421-1"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09938-y"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.23919\/JCC.2020.09.017"},{"key":"ref61","first-page":"2145","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Foerster"},{"key":"ref62","first-page":"2681","article-title":"Deep Decentralized multi-task multi-agent reinforcement learning under partial observability","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Omidshafiei"},{"key":"ref63","first-page":"6382","article-title":"Multi-agent actor\u2013critic for mixed cooperative-competitive environments","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref64","article-title":"R-MADDPG for partially observable environments and limited communication","author":"Wang","year":"2020","journal-title":"arXiv:2002.06684"},{"key":"ref65","first-page":"4295","article-title":"QMix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid"},{"key":"ref66","first-page":"5887","article-title":"QTran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Son"},{"key":"ref67","volume-title":"Gym: A toolkit for developing and comparing reinforcement learning algorithms","year":"2021"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3027048"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052983"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2019.1800083"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3093337.3037698"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3057653"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3053588"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2019.8885533"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2832463"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2016.2524258"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2910272"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3056206"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2930247"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761845"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2019.8904295"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2875926"},{"key":"ref83","first-page":"655","article-title":"OIDPR: Optimized insulin dosage based on privacy-preserving reinforcement learning","volume-title":"Proc. IFIP Netw. Conf. (Netw.)","author":"Ying"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2017.7925829"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2017.2785302"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2718526"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3058037"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2022.3155727"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2793186"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7997286"},{"key":"ref91","article-title":"A deep Q-learning method for downlink power allocation in multi-cell networks","author":"Ahmed","year":"2019","journal-title":"arXiv:1904.13032"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/2775054.2694360"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3001736"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2879433"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2751641"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2017.2776917"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2015.7368826"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/BHI.2018.8333459"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.3045266"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2014.2307069"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2617079"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/lsens.2021.3074183"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2985082"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3067807"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/MCOMSTD.2018.1800018"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ITC-28.2016.136"},{"key":"ref107","volume-title":"How 5G mobile networks are opening the door to remote surgery","year":"2018"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC51071.2022.9771877"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1145\/3360468.3366778"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322106"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.23919\/CNSM46954.2019.9012702"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.3390\/app9112361"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2815418"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CCNC49032.2021.9369546"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/ICCMC48092.2020.ICCMC-00014"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/tsc.2019.2959775"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2793304"},{"key":"ref119","volume-title":"Healthcare report for 1st half of 2018","year":"2020"},{"key":"ref120","volume-title":"Note to nations: Stop hacking hospitals","year":"2020"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3121870"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2019.2896325"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2020.2969178"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/Allerton.2012.6483411"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1145\/2185632.2185653"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2018.1700291"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2018.1800109"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2015.7417078"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1700246"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/asu043"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2016.1155993"},{"issue":"4","key":"ref132","first-page":"640","article-title":"Q- and A-learning methods for estimating optimal dynamic treatment regimes","volume":"29","author":"Schulte","year":"2014","journal-title":"Stat. Sci. Rev. J. Inst. Math. Stat."},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.5705\/ss.2012.364"},{"key":"ref134","article-title":"Robust hybrid learning for estimating personalized dynamic treatment regimens","author":"Liu","year":"2016","journal-title":"arXiv:1611.02314"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2014.8"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.med.59.062606.122232"},{"key":"ref137","volume-title":"Preventing Chronic Diseases: A Vital Investment: WHO Global Report","year":"2005"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-819045-6.00003-0"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1016\/j.diabres.2018.02.023"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1586\/17434440.2013.827515"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2020.3014556"},{"issue":"9","key":"ref142","first-page":"1","article-title":"Agent-based simulation for blood glucose","volume":"3","author":"Yasini","year":"2009","journal-title":"Int. J. Appl. Sci. Eng. Technol."},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2005.1556455"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2013.151"},{"key":"ref145","article-title":"Adaptive control of epileptic seizures using reinforcement learning","author":"Guez","year":"2010"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2018.1537919"},{"key":"ref147","first-page":"1671","article-title":"Adaptive treatment of epilepsy via batch-mode reinforcement learning","volume-title":"Proc. AAAI","author":"Guez"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1002\/sim.3720"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1016\/j.biosystems.2011.07.005"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1016\/j.matcom.2016.05.008"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0213-5"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2015.05.013"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1016\/j.mbs.2017.08.004"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12625"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2020.3008759"},{"key":"ref157","first-page":"1","article-title":"A Markov decision process to suggest optimal treatment of severe infections in intensive care","volume-title":"Proc. Neural Inf. Process. Syst. Workshop Mach. Learn. Health","author":"Komorowski"},{"key":"ref158","article-title":"Deep reinforcement learning for sepsis treatment","author":"Raghu","year":"2017","journal-title":"arXiv:1711.09602"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/ICHI.2019.8904645"},{"key":"ref160","article-title":"The actor search tree critic (ASTC) for off-policy POMDP learning in medical decision making","author":"Li","year":"2018","journal-title":"arXiv:1805.11548"},{"key":"ref161","first-page":"9","article-title":"Treatment recommendation in critical care: A scalable and interpretable approach in partially observable health states","volume-title":"Proc. Int. Conf. Interact. Sci.","author":"Utomo"},{"key":"ref162","article-title":"Continuous state-space models for optimal sepsis treatment\u2014A deep reinforcement learning approach","author":"Raghu","year":"2017","journal-title":"arXiv:1705.08422"},{"key":"ref163","first-page":"887","article-title":"Improving sepsis treatment strategies by combining deep and kernel-based reinforcement learning","volume-title":"Proc. AMIA Annu. Symp.","author":"Peng"},{"key":"ref164","article-title":"Precision medicine as a control problem: Using simulation and deep reinforcement learning to discover adaptive, personalized multi-cytokine therapy for sepsis","author":"Petersen","year":"2018","journal-title":"arXiv:1802.10440"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1002\/asjc.701"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.2006.384865"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2011.15"},{"key":"ref168","first-page":"1","article-title":"EdgeAI: A vision for distributed, edgenative artificial intelligence in future 6G networks","volume-title":"Proc. 1st 6G Wireless Summit","author":"Lov\u00e9n"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.116109"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2022.06.006"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.11.126"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3026589"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3018809"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2917890"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3078514"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3035451"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3081626"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3086623"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3033035"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2020.3031079"},{"key":"ref181","article-title":"Towards 5G enabled tactile robotic telesurgery","author":"Zhang","year":"2018","journal-title":"arXiv:1803.03586"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS50562.2020.9162964"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3066210"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC.2017.7986262"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2994090"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2973314"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/ICIoT48696.2020.9089614"},{"key":"ref188","first-page":"9908","article-title":"Learning efficient multi-agent communication: An information bottleneck approach","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5957"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/10353047\/10162185.pdf?arnumber=10162185","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:22:24Z","timestamp":1705018944000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10162185\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,15]]},"references-count":189,"journal-issue":{"issue":"24"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2023.3288050","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,15]]}}}