{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T07:48:12Z","timestamp":1786607292627,"version":"3.56.0"},"reference-count":101,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3027152","type":"journal-article","created":{"date-parts":[[2020,9,29]],"date-time":"2020-09-29T18:47:11Z","timestamp":1601405231000},"page":"176598-176623","source":"Crossref","is-referenced-by-count":47,"title":["A Systematic Review on Reinforcement Learning-Based Robotics Within the Last Decade"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1729-4071","authenticated-orcid":false,"given":"Md. Al-Masrur","family":"Khan","sequence":"first","affiliation":[{"name":"Electronics and Communication Engineering Discipline, Khulna University, Khulna, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md Rashed Jaowad","family":"Khan","sequence":"additional","affiliation":[{"name":"Electronics and Communication Engineering Discipline, Khulna University, Khulna, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abul","family":"Tooshil","sequence":"additional","affiliation":[{"name":"Electronics and Communication Engineering Discipline, Khulna University, Khulna, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9016-6105","authenticated-orcid":false,"given":"Niloy","family":"Sikder","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering Discipline, Khulna University, Khulna, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1905-6800","authenticated-orcid":false,"given":"M. A. Parvez","family":"Mahmud","sequence":"additional","affiliation":[{"name":"School of Engineering, Deakin University, Geelong, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6292-1214","authenticated-orcid":false,"given":"Abbas Z.","family":"Kouzani","sequence":"additional","affiliation":[{"name":"School of Engineering, Deakin University, Geelong, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2391-5767","authenticated-orcid":false,"given":"Abdullah-Al","family":"Nahid","sequence":"additional","affiliation":[{"name":"Electronics and Communication Engineering Discipline, Khulna University, Khulna, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1","article-title":"An implementation of vision based deep reinforcement learning for humanoid robot locomotion","author":"kaymak","year":"2019","journal-title":"Proc IEEE Int Symp Innov Intell Syst Appl (INISTA)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ISIE.2019.8781522"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152707"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICARM.2017.8273233"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5772\/10528"},{"key":"ref30","article-title":"Benchmarking reinforcement learning algorithms on real-world robots","author":"mahmood","year":"2018","journal-title":"arXiv 1809 07731"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2019.104985"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/RCAR.2016.7784001"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1186\/s40638-018-0091-9"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRoM.2015.7367790"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2186565"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10339-011-0404-1"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2018.00035"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV.2006.345353"},{"key":"ref22","author":"yang","year":"2014","journal-title":"Multiagent reinforcement learning for multi-robot systems A survey"},{"key":"ref21","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garc\u00eda","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-017-5666-0"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2015.2425359"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2777827"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2051435"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/mti2030057"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICRAE48301.2019.9043822"},{"key":"ref51","article-title":"On-line Q-learning using connectionist systems","volume":"166","author":"rummery","year":"1994","journal-title":"CUED\/F-INFENG\/TR"},{"key":"ref59","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9904-1954-09848-8"},{"key":"ref57","article-title":"VOSviewer manual","author":"van eck","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref55","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347v2 [cs LG]"},{"key":"ref54","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"arXiv 1502 05477 [cs]"},{"key":"ref53","first-page":"449","article-title":"A distributional perspective on reinforcement learning","author":"bellemare","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref52","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/AUTEEE48671.2019.9033166"},{"key":"ref4","author":"russell","year":"2018","journal-title":"Artificial Intelligence A Modern Approach"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"rumelhart","year":"1986","journal-title":"Nature"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992695"},{"key":"ref5","article-title":"Unsupervised learning: Foundations of neural computation a review","volume":"22","author":"wang","year":"2001","journal-title":"AI Mag"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1995.525277"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/RoMoCo.2019.8787360"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(92)90058-6"},{"key":"ref9","first-page":"1607","article-title":"Relative Entropy Policy Search","author":"peters","year":"2010","journal-title":"Proc 24th AAAI Conf Artif Intell (AAAI)"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.5194\/isprs-archives-XLII-2-W13-857-2019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2019.00-24"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/URAI.2019.8768681"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2018.8445099"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793505"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCKE.2017.8167920"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ECMR.2019.8870964"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509181"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0316-z"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2012.03.004"},{"key":"ref70","first-page":"20","article-title":"Learning control in robotics trajectory-based optimal control techniques","volume":"17","author":"schall","year":"2010","journal-title":"IEEE Robot Automat Mag"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1088\/1748-3182\/7\/2\/025009"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2012.2227719"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0087253"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/JOE.2012.2205638"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.09.015"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2011.2106494"},{"key":"ref60","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume":"32","author":"silver","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-015-0310-2"},{"key":"ref61","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"arXiv 1604 06778 [cs]"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.218"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3389\/fncir.2012.00099"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2009.10.006"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2013.09.001"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2007.4282709"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2016.03.016"},{"key":"ref2","first-page":"433","article-title":"Mind a quarterly review of psychology and philosophy","volume":"236","author":"turing","year":"1950","journal-title":"Computing machinery and intelligence"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4818"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/0166-4972(94)90101-5"},{"key":"ref95","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1109\/TSMCB.2009.2026289","article-title":"Impedance learning for robotic contact tasks using natural actor-critic algorithm","volume":"40","author":"kim","year":"2010","journal-title":"IEEE Trans Syst Man Cybern B Cybern"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2012.2209879"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5223-6"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2010.24"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910369715"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2509646"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2478857"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2314294"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.009"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095096"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISMCR47492.2019.8955697"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SII.2017.8279360"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2006.03.002"},{"key":"ref14","first-page":"377","article-title":"Optimizing production manufacturing using reinforcement learning","author":"mahadevan","year":"1998","journal-title":"Proc 11th FLAIRS Conf"},{"key":"ref15","article-title":"Safe, multi-agent, reinforcement learning for autonomous driving","author":"shalev-shwartz","year":"2016","journal-title":"arXiv 1610 03295"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.11"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913490324"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2010.5686841"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2010.06.019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/3296874"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-05181-4_10"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913499192"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2011.07.004"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0468-y"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2011.07.004"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2010.VI.020"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_18"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09206554.pdf?arnumber=9206554","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T20:47:29Z","timestamp":1756154849000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9206554\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":101,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3027152","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}