{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T17:59:26Z","timestamp":1775066366505,"version":"3.50.1"},"reference-count":192,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62071230"],"award-info":[{"award-number":["62071230"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62061146002"],"award-info":[{"award-number":["62061146002"]}],"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":["BK20211567"],"award-info":[{"award-number":["BK20211567"]}],"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":[[2022]]},"DOI":"10.1109\/comst.2022.3160697","type":"journal-article","created":{"date-parts":[[2022,3,21]],"date-time":"2022-03-21T20:24:58Z","timestamp":1647894298000},"page":"1240-1279","source":"Crossref","is-referenced-by-count":188,"title":["Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey"],"prefix":"10.1109","volume":"24","author":[{"given":"Tianxu","family":"Li","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6784-5583","authenticated-orcid":false,"given":"Kun","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4299-3456","authenticated-orcid":false,"given":"Nguyen Cong","family":"Luong","sequence":"additional","affiliation":[{"name":"Faculty of Computer Science, Phenikaa University, Hanoi, Vietnam"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7442-7416","authenticated-orcid":false,"given":"Dusit","family":"Niyato","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}]},{"given":"Qihui","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9229-7689","authenticated-orcid":false,"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2863-5441","authenticated-orcid":false,"given":"Bing","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1201\/9781351006620-6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2018.2809722"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/VTCSpring.2018.8417695"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2846694"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2751641"},{"key":"ref7","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"Puterman","year":"2014"},{"key":"ref8","article-title":"A survey of learning in multiagent environments: Dealing with non-stationarity","author":"Hernandez-Leal","year":"2017","journal-title":"arXiv:1707.09183"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.12676\/j.cc.2018.12.002"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3092831"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2904897"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2844341"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2846401"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/JCIN.2019.8917870"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2988367"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2018.1800109"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC.2019.8766739"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref21","article-title":"A brief survey of deep reinforcement learning","author":"Arulkumaran","year":"2017","journal-title":"arXiv:1708.05866"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1561\/2200000071"},{"key":"ref23","volume-title":"Dynamic Programming and Optimal Control","volume":"1","author":"Bertsekas","year":"2000"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.28.1.1"},{"key":"ref25","article-title":"Learning from delayed rewards","author":"Watkins","year":"1989"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"},{"issue":"1","key":"ref27","first-page":"1","article-title":"Learning rates for Q-learning","volume":"5","author":"Even-Dar","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref31","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv:1511.05952"},{"key":"ref32","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref33","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Advances in Neural Information Processing Systems","author":"Sutton","year":"2000"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref35","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv:1506.02438"},{"key":"ref36","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref37","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref38","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref39","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver"},{"key":"ref40","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.39.10.1953"},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611971132","volume-title":"Dynamic Noncooperative Game Theory","author":"Ba\u015far","year":"1998"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4054-9"},{"key":"ref45","first-page":"535","article-title":"An algorithm for distributed reinforcement learning in cooperative multi-agent systems","volume-title":"Proc. 17th Int. Conf. Mach. Learn.","author":"Lauer"},{"key":"ref46","article-title":"QD-learning: A collaborative distributed strategy for multi-agent reinforcement learning through consensus","author":"Kar","year":"2012","journal-title":"arXiv:1205.0047"},{"key":"ref47","first-page":"1659","article-title":"Learning in zero-sum team Markov games using factored value functions","volume-title":"Advances in Neural Information Processing Systems","volume":"15","author":"Lagoudakis","year":"2002"},{"key":"ref48","article-title":"Finite-sample analyses for fully decentralized multi-agent reinforcement learning","author":"Zhang","year":"2018","journal-title":"arXiv:1812.02783"},{"key":"ref49","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"Lowe","year":"2017","journal-title":"arXiv:1706.02275"},{"key":"ref50","first-page":"32","article-title":"The complexity of decentralized control of Markov decision processes","volume-title":"Proc. 16th Conf. Uncertainty Artif. Intell.","author":"Bernstein"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2368731"},{"key":"ref53","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref55","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref56","first-page":"5998","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"ref57","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Iqbal"},{"key":"ref58","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref59","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017","journal-title":"arXiv:1706.05296"},{"key":"ref60","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":"ref61","article-title":"Weighted QMIX: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","author":"Rashid","year":"2020","journal-title":"arXiv:2006.10800"},{"key":"ref62","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","volume-title":"Proc. 12th USENIX Symp. Oper. Syst. Design Implement.","author":"Abadi"},{"key":"ref63","first-page":"1","article-title":"Torch7: A MATLAB-like environment for machine learning","volume-title":"Proc. BigLearn NIPS Workshop","author":"Collobert"},{"key":"ref64","volume-title":"A Guide to NumPy","volume":"1","author":"Oliphant","year":"2006"},{"key":"ref65","article-title":"Efficient distributed auto-differentiation","author":"Baker","year":"2021","journal-title":"arXiv:2102.09631"},{"key":"ref66","article-title":"Openai gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2881533"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2008.070227"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2014.6845058"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422778"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2842738"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2007.914876"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2890210"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1049\/el.2012.0451"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICT.2015.7124665"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2961405"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.23919\/APNOMS50412.2020.9237060"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CCNC.2019.8651796"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2015.10.008"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2016.2631079"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2020.3000274"},{"key":"ref82","first-page":"2613","article-title":"Double Q-learning","volume-title":"Advances in Neural Information Processing Systems","volume":"23","author":"Hasselt","year":"2010"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322150"},{"key":"ref84","article-title":"Parameter sharing is surprisingly useful for multi-agent deep reinforcement learning","author":"Terry","year":"2020","journal-title":"arXiv:2005.13625v4"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/3397166.3413468"},{"key":"ref86","article-title":"Technical specification group radio access network; study on scenarios and requirements for next generation access technologies; (release 14)","year":"2016"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933962"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.2979124"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322537"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"ref93","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017","journal-title":"arXiv:1710.10903"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2933417"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2935201"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3043009"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3022705"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2011.2147784"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2812733"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3001736"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933973"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2011.110609"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.23919\/WiOPT47501.2019.9144098"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1016\/j.matpur.2009.10.010"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2952411"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.2983170"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3051163"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2014.2328102"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3020400"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2017.2777491"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOMW.2017.8269175"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CISS.2018.8362276"},{"key":"ref113","article-title":"Cache-enabled wireless networks with opportunistic interference alignment","author":"He","year":"2017","journal-title":"arXiv:1706.09024"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7996332"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9013115"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2968951"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2894437"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3040768"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322099"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3036416"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9013596"},{"key":"ref122","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","volume-title":"Proc. AAAI\/IAAI","author":"Claus"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/154587"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3046737"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155373"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2882583"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2894403"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8762084"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2018.8647341"},{"key":"ref130","first-page":"18","article-title":"Reinforcement learning approaches to coordination in cooperative multi-agent systems","volume-title":"Adaptive Agents and Multi-Agent Systems","author":"Kapetanakis","year":"2002"},{"key":"ref131","first-page":"1789","article-title":"Collaborative multiagent reinforcement learning by payoff propagation","volume":"7","author":"Kok","year":"2006","journal-title":"J. Mach. Learn. Res."},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.2004.1398426"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1145\/248156.248182"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1145\/346000.346003"},{"key":"ref135","first-page":"151","article-title":"Combinatorial multi-armed bandit: General framework and applications","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/VTCSpring.2017.8108572"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2014.6883600"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3042089"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2006.874390"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.3044298"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.2968326"},{"key":"ref142","article-title":"Dynamic coded caching in wireless networks using multi-agent reinforcement learning","author":"Pedersen","year":"2021","journal-title":"arXiv:2104.06724"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/LNET.2018.2883245"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3066458"},{"key":"ref145","article-title":"A deep-reinforcement learning approach for software-defined networking routing optimization","author":"Stampa","year":"2017","journal-title":"arXiv:1709.07080"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2017.8309082"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422706"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS50562.2020.9162984"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1145\/3404397.3404425"},{"key":"ref150","article-title":"Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Wu","year":"5279"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.3012832"},{"key":"ref152","first-page":"671","article-title":"Packet routing in dynamically changing networks: A reinforcement learning approach","volume-title":"Advances in Neural Information Processing Systems","author":"Boyan","year":"1994"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOMW.2019.8845154"},{"key":"ref154","article-title":"Robust and scalable routing with multi-agent deep reinforcement learning for MANETs","author":"Kaviani","year":"2021","journal-title":"arXiv:2101.03273"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/MILCOM.2018.8599797"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2989924"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/ISWCS.2008.4726117"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2020-Fall49728.2020.9348732"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1587\/transcom.E93.B.1431"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP49622.2020.9259413"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2907944"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2925629"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2910263"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3062091"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3104633"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761794"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2867180"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.3027695"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.2986289"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322539"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.3013599"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2876513"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2012.6195689"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952524"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2018.2815018"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC45663.2020.9120592"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3014788"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2017.7925694"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2019.2904486"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.3390\/app8101911"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/WCSP49889.2020.9299742"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/379"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2930803"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-32-9298-7_17"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v27i2.19000"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2004.842221"},{"key":"ref187","first-page":"368","article-title":"How you act tells a lot: Privacy-leaking attack on deep reinforcement learning","volume-title":"Proc. 18th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Pan"},{"key":"ref188","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014","journal-title":"arXiv:1412.6572"},{"key":"ref189","article-title":"Reward design in cooperative multi-agent reinforcement learning for packet routing","author":"Mao","year":"2020","journal-title":"arXiv:2003.03433"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2016.7564708"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978408"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2016.10.013"}],"container-title":["IEEE Communications Surveys & Tutorials"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9739\/9779264\/09738819.pdf?arnumber=9738819","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T00:21:28Z","timestamp":1705537288000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9738819\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":192,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/comst.2022.3160697","relation":{},"ISSN":["1553-877X","2373-745X"],"issn-type":[{"value":"1553-877X","type":"electronic"},{"value":"2373-745X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}