{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T22:20:13Z","timestamp":1778192413753,"version":"3.51.4"},"reference-count":133,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100002457","name":"Chosun University, 2020","doi-asserted-by":"publisher","award":["K202160030"],"award-info":[{"award-number":["K202160030"]}],"id":[{"id":"10.13039\/501100002457","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3058388","type":"journal-article","created":{"date-parts":[[2021,2,19]],"date-time":"2021-02-19T07:46:35Z","timestamp":1613720795000},"page":"27552-27587","source":"Crossref","is-referenced-by-count":91,"title":["Reinforcement Learning-Based Routing Protocols for Vehicular Ad Hoc Networks: A Comparative Survey"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0652-6711","authenticated-orcid":false,"given":"Rezoan Ahmed","family":"Nazib","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9175-3400","authenticated-orcid":false,"given":"Sangman","family":"Moh","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007678930559"},{"key":"ref38","first-page":"243","article-title":"An alternative softmax operator for reinforcement learning","author":"asadi","year":"2017","journal-title":"Proc PMLR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11277-017-3987-8"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s12530-013-9093-6"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.1090.0295"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1561\/2300000021"},{"key":"ref37","first-page":"203","article-title":"Adaptive-greedy exploration in reinforcement learning based on value differences","author":"michel","year":"2010","journal-title":"Proc Annu Conf Artif Intell"},{"key":"ref36","article-title":"Tight performance bounds on greedy policies based on imperfect value functions","author":"williams","year":"1992"},{"key":"ref35","article-title":"Efficient exploration in reinforcement learning","author":"thrun","year":"1993"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917306"},{"key":"ref28","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2011.102"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-642-27645-3_1","article-title":"Reinforcement learning and Markov decision processes","volume":"12","author":"van otterlo","year":"2012","journal-title":"Adaptation Learning and Optimization"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIT47043.2019.8987282"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2018.04.037"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2019.11.011"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/978-3-642-21937-5_1","article-title":"A survey of reinforcement learning based routing protocols for mobile ad-hoc networks","volume":"162","author":"chettibi","year":"2011","journal-title":"Recent Trends in Wireless and Mobile Networks"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2003.1208920"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/VTCSpring.2015.7145689"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1177\/0037549709345997"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2015.2502949"},{"key":"ref50","first-page":"618","article-title":"Deep reinforcement learning based dynamic resource allocation in cloud radio access networks","author":"tasnim rodoshi","year":"2020","journal-title":"Proc Int Conf Inf Commun Technol Converg (ICTC)"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2957778"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.vehcom.2018.01.006"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1111\/coin.12261"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC.2013.6583700"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/FGCN.2015.17"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/PCCC.2014.7017079"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/NMIC.2019.00008"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2016.10.014"},{"key":"ref52","first-page":"1021","article-title":"Rational and convergent learning in stochastic games","author":"bowling","year":"2001","journal-title":"Proc IJCAI Int Jt Artif Intell"},{"key":"ref40","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","author":"fujimoto","year":"2019","journal-title":"Proc PMLR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2016.2611524"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICETET.2013.18"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICVES.2012.6294332"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICTIS.2019.8883680"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICSESS.2015.7339127"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref7","first-page":"1","article-title":"Performance analysis of secure & efficient AODV (SE-AODV) with AODV routing protocol using NS2","author":"singh","year":"2015","journal-title":"Proc 3rd Int Conf Rel Infocom Technol Optim Trends Future Directions (ICRITO)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IC3I.2014.7019587"},{"key":"ref46","first-page":"417","article-title":"Q-learning in continuous state and action spaces","author":"gaskett","year":"1999","journal-title":"Proc Australas Joint Conf Artif Intell"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/VTCSpring.2019.8746494"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref42","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref41","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref44","first-page":"170","article-title":"Optimal route selection in complex multi-stage supply chain networks using SARSA($\\lambda$\n)","author":"habib","year":"2016","journal-title":"Proc 19th Int Conf Comput Inf Technol (ICCIT)"},{"key":"ref43","first-page":"9971","article-title":"Non-delusional Q-learning and value iteration","author":"google","year":"2018","journal-title":"Proc NIPS"},{"key":"ref127","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2019\/2423915","article-title":"A comprehensive survey on VANET security services in traffic management system","volume":"2019","author":"sheikh","year":"2019","journal-title":"Wireless Commun Mobile Comput"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2790704"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1016\/j.vehcom.2017.01.002"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1049\/iet-com.2010.0258"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ITOEC49072.2020.9141805"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2016.7794599"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2891073"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s00779-012-0600-8"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1007\/s11235-017-0280-9"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2004.1261816"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/IMSAA.2009.5439454"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1145\/3007748.3007762"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3272036.3272037"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2871606"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC48107.2020.9148237"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1016\/j.adhoc.2018.11.011"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/ICOS.2016.7882000"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCS.2018.8689228"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1016\/j.vehcom.2017.04.004"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2789466"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2963850"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.3390\/s20195685"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-6571-2_303"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICICES.2014.7033833"},{"key":"ref64","doi-asserted-by":"crossref","first-page":"1394","DOI":"10.1016\/j.procs.2015.07.456","article-title":"Q-learning based point to point data transfer in VANETs","volume":"57","author":"valantina","year":"2015","journal-title":"Procedia Comput Sci"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2013.2273945"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11277-018-5809-z"},{"key":"ref67","doi-asserted-by":"crossref","first-page":"1431","DOI":"10.1587\/transcom.E93.B.1431","article-title":"Distributed reinforcement learning approach for vehicular ad-hoc networks","volume":"e93 b","author":"wu","year":"2010","journal-title":"IEICE Trans Commun"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2015.2481464"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-018-1368-y"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.15837\/ijccc.2020.5.3928"},{"key":"ref1","first-page":"138","article-title":"A survey on intrusion detection systems and honeypot based proactive security mechanisms in VANETs and VANET cloud","volume":"12","author":"sharma","year":"2018","journal-title":"Veh Commun"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-5915.1978.tb00753.x"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1002\/wcm.859"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/WC-M.2006.250355"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2009.5281251"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/ICCMC.2019.8819723"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2841901"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2017.07.017"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2879758"},{"key":"ref105","first-page":"1","article-title":"MRV-M: A cluster stability in highway VANET using minimum relative velocity based on K-medoids","author":"adrian","year":"2019","journal-title":"Proc 5th Int Conf Sci Technol (ICST)"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2020.3034600"},{"key":"ref104","first-page":"391","article-title":"Empirical study of traffic velocity distribution and its effect on VANETs connectivity","author":"abuelenin","year":"2014","journal-title":"Proc Int Conf Connected Vehicles Expo (ICCVE)"},{"key":"ref90","article-title":"V2 VR: Reliable hybrid-network-oriented V2 V data transmission and routing considering RSUs and connectivity probability","author":"gao","year":"2020","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00121-2"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1016\/S0377-2217(02)00363-6"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2913776"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref110","first-page":"1","article-title":"A survey of propagation models used in vehicular ad hoc network (VANET) research","author":"van eenennaam","year":"2009"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CISIS.2013.18"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2004.1354517"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/s11277-012-0594-6"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2008.80"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICSESS.2010.5552320"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JCN.2019.000056"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2989790"},{"key":"ref13","author":"mitchell","year":"2013","journal-title":"An Artificial Intelligence Approach"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/THS.2017.7943477"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CAIS.2019.8769454"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/AiDAS47888.2019.8970890"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"2708","DOI":"10.3390\/s20092708","article-title":"Resource management in cloud radio access network: Conventional and new approaches","volume":"20","author":"rodoshi","year":"2020","journal-title":"SENSORS"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2875739"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2015.2482904"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICPHYS.2018.8390808"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2944399"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MoWNet.2016.7496597"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2016.2607748"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-200-7.50075-1"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2005.846390"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-018-0819-y"},{"key":"ref114","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1049\/iet-ifs.2010.0160","article-title":"Light-weight trust-based routing protocol for mobile ad hoc networks","volume":"6","author":"marchang","year":"2012","journal-title":"IET Inf Secur"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2017.1600117"},{"key":"ref116","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1007\/978-3-319-74439-1_10","article-title":"Control overhead reduction in cluster-based VANET routing protocol","author":"abuashour","year":"2018","journal-title":"Ad Hoc Networks"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2018.8647426"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2020.3017751"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICTEmSys.2019.8695963"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2007.4407231"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1016\/j.pmcj.2018.07.004"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCI.2017.8126198"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2542923"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2009.5198623"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.3390\/app10124077"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ISADS.2011.22"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2011.2173510"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09351930.pdf?arnumber=9351930","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T08:26:54Z","timestamp":1643272014000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9351930\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":133,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3058388","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}