{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T21:17:05Z","timestamp":1774473425889,"version":"3.50.1"},"reference-count":329,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100004686","name":"Deanship of Scientific Research, Vice Presidency for Graduate Studies and Scientific Research, King Faisal University, Saudi Arabia","doi-asserted-by":"publisher","award":["KFU261307"],"award-info":[{"award-number":["KFU261307"]}],"id":[{"id":"10.13039\/501100004686","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3674539","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T20:24:47Z","timestamp":1773779087000},"page":"42809-42837","source":"Crossref","is-referenced-by-count":0,"title":["A Comprehensive Review of Reinforcement Learning Algorithms for Control Systems: Applications, Challenges, and Future Directions"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1908-5521","authenticated-orcid":false,"given":"A. H.","family":"Abdul Hafez","sequence":"first","affiliation":[{"name":"Department of Computer Science, College of Computer Sciences and Information Technology, King Faisal University, Al Ahsa, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9707-8271","authenticated-orcid":false,"given":"Ufuk","family":"Demircioglu","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and Natural Sciences, Sivas University of Science and Technology, Sivas, T&#x00FC;rkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Halit","family":"Bakir","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and Natural Sciences, Sivas University of Science and Technology, Sivas, T&#x00FC;rkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6651-8342","authenticated-orcid":false,"given":"Raid","family":"Alzubi","sequence":"additional","affiliation":[{"name":"Department of Computer Science, College of Computer Sciences and Information Technology, King Faisal University, Al Ahsa, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2017.05.001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.paerosci.2004.06.001"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/pr11113171"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5424\/sjar\/2012104-487-11"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2017.02.002"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/02564602.2014.890838"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11768-009-7130-6"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1631\/fitee.1900533"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2017.08.1217"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.115036"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09997-9"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-8971-8_25"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2022.07.004"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2012.03.004"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/en15103526"},{"key":"ref16","article-title":"A review of off-policy evaluation in reinforcement learning","author":"Uehara","year":"2022","journal-title":"arXiv:2212.06355"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/msp.2017.2743240"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.25299\/itjrd.2023.13474"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.caeo.2024.100175"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/app13042443"},{"key":"ref21","article-title":"A survey of deep reinforcement learning in video games","author":"Shao","year":"2019","journal-title":"arXiv:1912.10944"},{"key":"ref22","article-title":"Shaping advice in deep reinforcement learning","author":"Xiao","year":"2022","journal-title":"arXiv:2202.09489"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04105-y"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/make1010002"},{"key":"ref25","article-title":"Automatic goal generation for reinforcement learning agents","author":"Florensa","year":"2017","journal-title":"arXiv:1705.06366"},{"key":"ref26","volume-title":"Reinforcement Learning Toolbox Documentation","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.ics.2006.04.003"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/aim.2009.5229901"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tie.2015.2420792"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/siu.2018.8404287"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2017.2767083"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/a11100148"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ivs.2018.8500630"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-03748-2_40"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/access.2019.2901295"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/access.2019.2950166"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/en12030436"},{"issue":"1","key":"ref38","first-page":"126","article-title":"Q-learning based supervisory PID controller for damping frequency oscillations in a hybrid mini\/micro-grid","volume":"15","author":"Younesi","year":"2019","journal-title":"Int. J. Electr. Power Energy Syst."},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3233\/jifs-169443"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/icra40945.2020.9196749"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-020-00146-7"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tte.2020.2991079"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2018.2870075"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/iiphdw.2019.8755430"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11804-019-00089-3"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.23919\/ecc.2019.8795878"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ibssc47189.2019.8973068"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2018.2884649"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/itsc.2019.8917076"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2018.2884797"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.3001143"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/southeastcon44009.2020.9368267"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2019.2912018"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ias44978.2020.9334865"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2020.565702"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/access.2021.3055651"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/access.2021.3073704"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2021.110860"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1964\/4\/042076"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/tie.2020.3001849"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/access.2022.3156924"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.10.070"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/icma54519.2022.9856292"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.23919\/ccc55666.2022.9902520"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/etfa52439.2022.9921714"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/smc53654.2022.9945504"},{"key":"ref67","article-title":"Path planning and control for omni-directional mobile robot using Q-learning and CLIK algorithm for home environment","volume-title":"Proc. Int. Conf.","author":"Sachan"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/cvci56766.2022.9965093"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/iceccme55909.2022.9988506"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ccdc55256.2022.10034123"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.3390\/s22030941"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.est.2021.103925"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.23919\/jsee.2022.000017"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.3390\/automation3010011"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/icirca57980.2023.10220591"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/hora58378.2023.10155782"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1080\/17445302.2022.2126121"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.3390\/act11120374"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3085358"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.18280\/jesa.550514"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/tmech.2021.3120628"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpowsour.2022.231841"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.23940\/ijpe.22.09.p5.644653"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3055761"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.3390\/su14148825"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.20517\/ces.2022.28"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.104797"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2022.03.006"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/pimrc56721.2023.10293891"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2023.3329785"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/s43153-023-00422-y"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/icstcc59206.2023.10308475"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/icaige58321.2023.10346406"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.3390\/e25020299"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/tmech.2022.3233705"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2023.3235967"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.37934\/araset.30.3.6978"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2023.10.1388"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.119770"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/jas.2023.123624"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1016\/j.jobe.2023.106805"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2022.3228969"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2023.110816"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1021\/acs.est.3c00353"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-34540-x"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1016\/j.segan.2023.101162"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.22190\/fume231011044z"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.3390\/systems11030136"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1002\/ird.2684"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2022.107727"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107714"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.3390\/sym12101685"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.3390\/sym11091139"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.2118\/193769-ms"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.3906\/elk-1311-129"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechatronics.2014.05.007"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.23919\/iccas59377.2023.10316988"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/codit58514.2023.10284335"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2022.3218705"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/access.2022.3195530"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2019.2950809"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1016\/j.promfg.2020.01.384"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/urai.2017.7992767"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/tsmcc.2011.2106494"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/pecon.2008.4762658"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-54531-w"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.3233\/jifs-232795"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1016\/j.asej.2024.102670"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2023.110546"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.3390\/buildings12111787"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.3390\/app12147194"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.3390\/robotics11020044"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1080\/0951192x.2021.1992669"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1007\/s40295-021-00288-7"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2021.110856"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1177\/00202940211000380"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.4271\/2020-01-0728"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2022.3198259"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2022.3233087"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/bigdata59044.2023.10386803"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43129-6_19"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/eurocon56442.2023.10198954"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/rast57548.2023.10197999"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/isqed57927.2023.10129362"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2022.3184795"},{"issue":"16","key":"ref146","first-page":"188","article-title":"Comprehensive survey on agent based deep learning techniques for space landing missions","volume":"12","author":"Moholkar","year":"2024","journal-title":"Int. J. Intell. Syst. Appl. Eng."},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/vppc55846.2022.10003470"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/3ict56508.2022.9990801"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.23919\/acc53348.2022.9867627"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/oceanschennai45887.2022.9775236"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1145\/3486611.3488727"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/iccae51876.2021.9426091"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/cac51589.2020.9327385"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/southeastcon44009.2020.9249654"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/reduas47371.2019.8999689"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/ictai.2019.00135"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/IMCEC46724.2019.8983893"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2024.122737"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.3390\/en17030581"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1007\/s13369-023-07934-2"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1007\/s42235-023-00472-5"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-023-02003-0"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1016\/j.dche.2023.100108"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.3390\/drones7080499"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1016\/j.apor.2023.103591"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2023.10.1012"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1177\/10597123231201655"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1080\/15599612.2023.2222146"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.10.016"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1177\/1045389x221093351"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.109450"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-022-10034-z"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-93842-0_14"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1139\/juvs-2021-0010"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.05.029"},{"issue":"4","key":"ref176","article-title":"Control method for path following and collision avoidance of autonomous ship based on deep reinforcement learning","volume":"27","author":"Zhao","year":"2019","journal-title":"J. Mar. Sci. Technol."},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/taes.2024.3351608"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8021-5_2"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2022.3219428"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/mlccim60412.2023.00085"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/ccdc58219.2023.10326621"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/access.2023.3330215"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-44865-2_8"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.23919\/ccc58697.2023.10240038"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-2100-3_39"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/cacre58689.2023.10208497"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.23919\/acc55779.2023.10156267"},{"key":"ref188","article-title":"Real-time reinforcement learning for vision-based robotics utilizing local and remote computers","author":"Wang","year":"2022","journal-title":"arXiv:2210.02317"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.23919\/ecc57647.2023.10178182"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/cac57257.2022.10055122"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/icrom57054.2022.10025140"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/yac57282.2022.10023694"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/lars\/sbr\/wre56824.2022.9995835"},{"key":"ref194","article-title":"Reinforcement learning for attitude control of a spacecraft with flexible appendages","volume-title":"Proc. 73rd Int. Astron. Congr. (IAC)","author":"Mahfouz"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/vlsid2022.2022.00044"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/aero53065.2022.9843777"},{"key":"ref197","article-title":"Multiagent model-based credit assignment for continuous control","author":"Han","year":"2021","journal-title":"arXiv:2112.13937"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/access.2022.3185424"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-9492-9_33"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/icsecs52883.2021.00043"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2021.3063698"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1109\/access.2021.3083087"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/icc54714.2021.9703140"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/iciis51140.2020.9342690"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.36001\/phmconf.2020.v12i1.1296"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2020.3026111"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1109\/smc42975.2020.9282951"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2020.3013906"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1109\/ipec49694.2020.9115162"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.2514\/6.2021-0668"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2021.04.227"},{"key":"ref212","first-page":"12567","article-title":"Deep coherent exploration for continuous control","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59535-7_6"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1109\/aim.2019.8868711"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1109\/icuas.2019.8798254"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.26868\/25222708.2019.211427"},{"key":"ref217","article-title":"Reinforcement learning for spacecraft attitude control","volume-title":"Proc. Int. Astron. Congr. (IAC)","author":"Allison"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/785"},{"key":"ref219","first-page":"1817","article-title":"Low-thrust optimal control via reinforcement learning","volume-title":"Proc. 29th AAS\/AIAA Space Flight Mechanics Meeting","volume":"168","author":"Miller"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1002\/cjce.24508"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/459"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2021.3051456"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1109\/asap.2018.8445099"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1016\/j.jobe.2023.108157"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.3233\/ica-230724"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1017\/s0263574724000134"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1080\/15325008.2023.2220313"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.108372"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2023.108609"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.3390\/app13169153"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.3390\/aerospace10070590"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.3390\/app13116847"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2023.108232"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.1177\/09544100221138911"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1007\/s42235-022-00309-7"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.3934\/mbe.2023463"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1117\/12.2671152"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1115\/1.4055680"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.3390\/app12199703"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.1016\/j.advengsoft.2022.103245"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.3390\/drones6090251"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.3390\/app12136629"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.06.096"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.37917\/ijeee.18.2.15"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.3390\/en15062208"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-2375-1_44"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_36"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.1080\/08839514.2022.2084473"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.3390\/app12199869"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2022.021917"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1049\/csy2.12036"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.3390\/s21238161"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2021.107056"},{"key":"ref254","doi-asserted-by":"publisher","DOI":"10.1115\/1.4048796"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.1016\/j.epsr.2020.106959"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.5755\/j01.itc.50.3.25979"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.116117"},{"key":"ref258","doi-asserted-by":"publisher","DOI":"10.2514\/6.2020-1849"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.1504\/ijmic.2019.105972"},{"key":"ref260","doi-asserted-by":"publisher","DOI":"10.5194\/isprs-archives-xlii-2-w13-857-2019"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1109\/cvci59596.2023.10397295"},{"key":"ref262","doi-asserted-by":"publisher","DOI":"10.1109\/indin51400.2023.10217854"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.1109\/ecai58194.2023.10193912"},{"key":"ref264","doi-asserted-by":"publisher","DOI":"10.23919\/acc55779.2023.10155918"},{"key":"ref265","doi-asserted-by":"publisher","DOI":"10.1109\/aset56582.2023.10180752"},{"key":"ref266","doi-asserted-by":"publisher","DOI":"10.1177\/09544070231191842"},{"key":"ref267","doi-asserted-by":"publisher","DOI":"10.1109\/aset56582.2023.10180597"},{"key":"ref268","doi-asserted-by":"publisher","DOI":"10.1109\/isspit.2018.8642777"},{"key":"ref269","doi-asserted-by":"publisher","DOI":"10.1109\/tns.2022.3187662"},{"key":"ref270","doi-asserted-by":"publisher","DOI":"10.1109\/tase.2021.3088004"},{"key":"ref271","doi-asserted-by":"publisher","DOI":"10.1109\/tcst.2021.3102476"},{"key":"ref272","doi-asserted-by":"publisher","DOI":"10.1109\/icrae56463.2022.10056204"},{"key":"ref273","doi-asserted-by":"publisher","DOI":"10.1109\/icrom57054.2022.10025345"},{"key":"ref274","doi-asserted-by":"publisher","DOI":"10.1109\/lars\/sbr\/wre56824.2022.9995792"},{"key":"ref275","doi-asserted-by":"publisher","DOI":"10.1109\/icus55513.2022.9986833"},{"key":"ref276","doi-asserted-by":"publisher","DOI":"10.1109\/iros47612.2022.9981335"},{"key":"ref277","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn55064.2022.9892099"},{"key":"ref278","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-13835-5_18"},{"key":"ref279","doi-asserted-by":"publisher","DOI":"10.1109\/ismr48347.2022.9807609"},{"key":"ref280","doi-asserted-by":"publisher","DOI":"10.1117\/12.2631179"},{"key":"ref281","doi-asserted-by":"publisher","DOI":"10.1109\/itsc48978.2021.9564494"},{"key":"ref282","doi-asserted-by":"publisher","DOI":"10.1109\/rcar52367.2021.9517436"},{"key":"ref283","doi-asserted-by":"publisher","DOI":"10.1109\/icras52289.2021.9476365"},{"key":"ref284","doi-asserted-by":"publisher","DOI":"10.1109\/cac53003.2021.9727937"},{"key":"ref285","doi-asserted-by":"publisher","DOI":"10.1109\/icc54714.2021.9703155"},{"key":"ref286","doi-asserted-by":"publisher","DOI":"10.1109\/icac353642.2021.9697116"},{"key":"ref287","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-27544-0_7"},{"key":"ref288","doi-asserted-by":"publisher","DOI":"10.3390\/s23135799"},{"key":"ref289","doi-asserted-by":"publisher","DOI":"10.3390\/math10244667"},{"key":"ref290","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2021.107527"},{"key":"ref291","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-98883-8_17"},{"key":"ref292","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/8874619"},{"key":"ref293","doi-asserted-by":"publisher","DOI":"10.1109\/taes.2023.3321260"},{"key":"ref294","doi-asserted-by":"publisher","DOI":"10.1016\/j.mfglet.2023.08.055"},{"key":"ref295","doi-asserted-by":"publisher","DOI":"10.1109\/itecasia-pacific59272.2023.10372318"},{"key":"ref296","doi-asserted-by":"publisher","DOI":"10.1109\/iceccme57830.2023.10252829"},{"key":"ref297","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10160862"},{"key":"ref298","doi-asserted-by":"publisher","DOI":"10.1109\/iraset57153.2023.10153024"},{"key":"ref299","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2023.03.047"},{"key":"ref300","doi-asserted-by":"publisher","DOI":"10.1109\/icarm54641.2022.9959439"},{"key":"ref301","doi-asserted-by":"publisher","DOI":"10.1109\/icstcc55426.2022.9931844"},{"key":"ref302","doi-asserted-by":"publisher","DOI":"10.1109\/access.2022.3154388"},{"key":"ref303","doi-asserted-by":"publisher","DOI":"10.1109\/cac53003.2021.9728176"},{"key":"ref304","doi-asserted-by":"publisher","DOI":"10.1109\/icecet52533.2021.9698758"},{"key":"ref305","doi-asserted-by":"publisher","DOI":"10.1109\/icecet52533.2021.9698687"},{"key":"ref306","doi-asserted-by":"publisher","DOI":"10.1109\/ee53374.2021.9628297"},{"key":"ref307","doi-asserted-by":"publisher","DOI":"10.1109\/icus50048.2020.9274962"},{"key":"ref308","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123202"},{"key":"ref309","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2023.116540"},{"key":"ref310","doi-asserted-by":"publisher","DOI":"10.3390\/photonics10121371"},{"key":"ref311","volume-title":"Distributed Reinforcement Learning-Based Vehicle Control Algorithm Study","year":"2023"},{"key":"ref312","doi-asserted-by":"publisher","DOI":"10.1177\/09544062231174127"},{"key":"ref313","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2023.104385"},{"key":"ref314","doi-asserted-by":"publisher","DOI":"10.1007\/s12204-023-2631-x"},{"key":"ref315","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2022.109362"},{"key":"ref316","doi-asserted-by":"publisher","DOI":"10.3390\/en14227572"},{"key":"ref317","doi-asserted-by":"publisher","DOI":"10.3390\/s21175907"},{"key":"ref318","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2023.10.1369"},{"key":"ref319","doi-asserted-by":"publisher","DOI":"10.1109\/ictc58733.2023.10393822"},{"key":"ref320","doi-asserted-by":"publisher","DOI":"10.1109\/syscon53073.2023.10131174"},{"key":"ref321","doi-asserted-by":"publisher","DOI":"10.1109\/iceeict56924.2023.10156999"},{"key":"ref322","doi-asserted-by":"publisher","DOI":"10.1109\/robosoft55895.2023.10121927"},{"key":"ref323","doi-asserted-by":"publisher","DOI":"10.1109\/iros47612.2022.9981913"},{"key":"ref324","doi-asserted-by":"publisher","DOI":"10.23919\/apsipaasc55919.2022.9980219"},{"key":"ref325","doi-asserted-by":"publisher","DOI":"10.23919\/acc53348.2022.9867835"},{"key":"ref326","doi-asserted-by":"publisher","DOI":"10.1109\/sami54271.2022.9780803"},{"key":"ref327","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3084685"},{"key":"ref328","doi-asserted-by":"publisher","DOI":"10.1109\/iccar52225.2021.9463495"},{"key":"ref329","doi-asserted-by":"publisher","DOI":"10.23919\/ccc50068.2020.9188886"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11435905.pdf?arnumber=11435905","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T19:58:14Z","timestamp":1774468694000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11435905\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":329,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3674539","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}