{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T05:36:39Z","timestamp":1783748199013,"version":"3.55.0"},"reference-count":239,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3160709","type":"journal-article","created":{"date-parts":[[2022,3,21]],"date-time":"2022-03-21T20:25:00Z","timestamp":1647894300000},"page":"32190-32212","source":"Crossref","is-referenced-by-count":63,"title":["Toward Data-Driven Optimal Control: A Systematic Review of the Landscape"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4821-8151","authenticated-orcid":false,"given":"Krupa","family":"Prag","sequence":"first","affiliation":[{"name":"School of Computer Science and Applied Mathematics, University of the Witwatersrand, Johannesburg, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4902-851X","authenticated-orcid":false,"given":"Matthew","family":"Woolway","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and the Built Environment, University of Johannesburg, Johannesburg, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6925-6010","authenticated-orcid":false,"given":"Turgay","family":"Celik","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, University of the Witwatersrand, Johannesburg, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-060117-105215"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-018-0832-6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-090419-075625"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2753460"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2959924"},{"key":"ref6","article-title":"Data-driven model predictive control with stability and robustness guarantees","author":"Berberich","year":"2019","journal-title":"arXiv:1906.04679"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2018.09.005"},{"key":"ref8","volume-title":"Continuous and Discrete Control Systems","author":"Dorsey","year":"2002"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/b978-0-7506-5100-4.x5000-1"},{"key":"ref10","volume-title":"The Penguin Dictionary of Mathematics","author":"Nelson","year":"2008"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0313-1_8"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-6331-7"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1080\/00224065.1995.11979608"},{"key":"ref14","volume-title":"Control Sysytem Design","author":"Astrom","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2006.1580160"},{"key":"ref16","volume-title":"Optimal Control: An Introduction to the Theory and Its Applications","author":"Athans","year":"2013"},{"key":"ref17","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.17705\/1cais.03743"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1002\/acs.2862"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2012.07.014"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2010.5531089"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2019.05.029"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2020.106886"},{"key":"ref24","first-page":"270","article-title":"On governors","volume":"16","author":"Maxwell","year":"1867","journal-title":"Proc. Roy. Soc. London"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/37.506394"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/37.506395"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/BF02546511"},{"issue":"47","key":"ref28","first-page":"1930","volume-title":"A History of Control Engineering","author":"Bennett","year":"1993"},{"issue":"1","key":"ref29","first-page":"51","article-title":"Modern control theory","volume":"15","author":"Andrei","year":"2006","journal-title":"Stud. Informat. Control"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/2.53"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-1873-4_1"},{"key":"ref32","volume-title":"An Introduction to the Kalman Filter","author":"Welch","year":"1995"},{"issue":"1","key":"ref33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/02331880309257","article-title":"Bayesian filtering: From Kalman filters to particle filters, and beyond","volume":"182","author":"Chen","year":"2003","journal-title":"Statistics"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2966228"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2006.883415"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/S0020-7373(80)80050-2"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/21.52552"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3056454"},{"key":"ref39","doi-asserted-by":"crossref","first-page":"8170","DOI":"10.1016\/j.matpr.2021.02.536","article-title":"Fuzzy logic based load frequency control of power system","volume":"45","author":"Thenmalar","year":"2021","journal-title":"Mater. Today, Proc."},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2012.2236994"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(89)90002-2"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1968.1098847"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(78)90001-8"},{"issue":"17","key":"ref44","first-page":"72","article-title":"Dynamic matrix control? A computer control algorithm","volume-title":"Proc. Joint Autom. control Conf.","author":"Cutler"},{"issue":"17","key":"ref45","first-page":"73","article-title":"Optimization and constrained multivariable control of a catalytic cracking unit","volume-title":"Proc. Joint Autom. control Conf.","author":"Prett"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2006.10.019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.1251"},{"issue":"2","key":"ref48","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1109\/TCST.2009.2017934","article-title":"Online Optimization","volume":"18","author":"Wang","year":"2010","journal-title":"IEEE Trans. Control Syst. Technol."},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/MIE.2013.2290138"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2016.2625238"},{"key":"ref51","volume-title":"System Identification-Theory for the User","author":"Ljung","year":"1999"},{"key":"ref52","first-page":"1","article-title":"Data center cooling using model-predictive control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lazic"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2019.05.025"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CCA.2016.7587882"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-011-0300-6"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2017.06.036"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cps.2017.0013"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2690401"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.12.012"},{"key":"ref60","article-title":"Robust stability analysis of a simple data-driven model predictive control approach","author":"Bongard","year":"2021","journal-title":"arXiv:2103.00851"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1115\/1.2899060"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2015.2458491"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2016.2636126"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.9746\/sicetr1965.14.706"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1002\/rob.4620010203"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2006.1636313"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0110114"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2006.11.013"},{"key":"ref69","first-page":"1040","article-title":"Learning from demonstration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schaal"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8263812"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/37.126844"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(94)00011-O"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1126\/science.153.3731.34"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/4939.003.0007"},{"key":"ref75","first-page":"493","article-title":"Approximate dynamic programming for realtime control and neural modelling","volume-title":"Handbook of Intelligent Control: Neural, Fuzzy and Adaptive Approaches","author":"Werbos","year":"1992"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-47766-4_3"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.3724\/SP.J.1004.2013.00303"},{"key":"ref78","first-page":"155","article-title":"Postface to model predictive control: Theory and design","volume":"5","author":"Rawlings","year":"2012","journal-title":"Nob Hill Pub"},{"key":"ref79","volume-title":"Model Predictive Control: Theory, Computation, and Design","volume":"2","author":"Rawlings","year":"2017"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9816.003.0050"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2009.06.007"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(01)00174-1"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2015.2500269"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3098169"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2021.102253"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2021.12.003"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS.2018.8453468"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2935201"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05097-x"},{"issue":"4","key":"ref90","first-page":"41","article-title":"IDGTE social visit","volume":"5","author":"Qin","year":"2001","journal-title":"Power Eng."},{"key":"ref91","volume-title":"Chapter 20 Model Predictive Control 20.1 OVERVIEW OF MODEL PREDICTIVE CONTROL","year":"2003"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICA.2013.6734056"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2018.02.126"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2019.106204"},{"key":"ref95","volume-title":"Control of Dead-Time Processes","volume":"462","author":"Normey-Rico","year":"2007"},{"key":"ref96","volume-title":"Handbook of Model Predictive Control","author":"Rakovi\u0107","year":"2018"},{"issue":"6","key":"ref97","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-24853-0","volume-title":"Model Predictive Control: Classical, Robust, Stochastic","volume":"36","author":"Kouvaritakis","year":"2016"},{"key":"ref98","first-page":"1119","article-title":"Algorithmic control of industrial processes","volume-title":"Proc. 4th IFAC Symp. Identification System Parameter Estimation","author":"Richalet"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(87)90088-4"},{"key":"ref100","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1016\/S0967-0661(02)00186-7","article-title":"Process control dynamic","volume":"11","author":"Qin","year":"2003","journal-title":"Control Eng. Pract."},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2016.2602087"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2012.2221469"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CCA.2012.6402735"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.2514\/1.G002507"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8431585"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2018.06.004"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2009.12.001"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562025"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsv.2019.04.024"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2020.132416"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2020.132830"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.02.060"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.10.035"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2015.2511587"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2017.03.031"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2017.7963748"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8264027"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619268"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2020.110120"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.3390\/en14196251"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.3390\/machines9030052"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3083559"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1002\/aic.17246"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1287\/moor.12.2.262"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1007\/BF00453370"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3000182"},{"key":"ref127","article-title":"Data-driven model predictive and reinforcement learning based control for building energy management: A survey","author":"Zhang","year":"2021","journal-title":"arXiv:2106.14450"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2021.129172"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechatronics.2021.102633"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1007\/s10922-020-09574-5"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3061307"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2929987"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/9.855559"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2007.7068802"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2005.861689"},{"key":"ref136","first-page":"2208","article-title":"An application of the virtual reference feedback tuning for an MIMO process","volume-title":"Proc. SICE Annu. Conf.","volume":"3","author":"Nakamoto"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2005.02.008"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/37.710876"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1002\/9780470686652.eae495"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1007\/BF01582136"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1002\/acs.825"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2007.02.006"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1002\/acs.714"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2011.0204"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-6670(17)36391-7"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.11591\/ijai.v7.i4.pp165-169"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.1997.611815"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1360\/aas-007-1061"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2010.2093136"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2011.2176141"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1080\/00207178508933432"},{"key":"ref152","article-title":"Adaptive control: Stability","volume-title":"Convergence and Robustness","author":"Shastry","year":"1994"},{"key":"ref153","volume-title":"Linear and Nonlinear Iterative Learning Control","volume":"291","author":"Xu","year":"2003"},{"key":"ref154","volume-title":"Learning control: The state of the art and perspective","author":"Xu","year":"2005"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(96)89431-3"},{"issue":"1","key":"ref156","doi-asserted-by":"crossref","first-page":"4825","DOI":"10.1016\/j.ifacol.2017.08.969","article-title":"Data-driven progressive and iterative learning control","volume":"50","author":"Chen","year":"2017","journal-title":"IFAC-PapersOnLine"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1080\/00207721.2020.1793427"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1002\/acs.4480040605"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/9.109644"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1993.325542"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1049\/ip-cta:19960244"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/37.257895"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1016\/S0950-7051(98)00066-5"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-48873-1_26"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2012.03.004"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2005.1505122"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.7554\/elife.20944.012"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.1994.735224"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2009.09.006"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1201\/9781439821091"},{"issue":"3","key":"ref171","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":"ref172","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2006.09.019"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2009.2020850"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.05.002"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-47766-4"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2015.11.304"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1201\/9781351006620"},{"key":"ref179","article-title":"Learning continuous control policies by stochastic value gradients","author":"Heess","year":"2015","journal-title":"arXiv:1510.09142"},{"key":"ref180","article-title":"Learning to perform physics experiments via deep reinforcement learning","author":"Denil","year":"2016","journal-title":"arXiv:1611.01843"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/ICMIC.2018.8529962"},{"key":"ref182","article-title":"Learning from delayed rewards","author":"Watkins","year":"1989"},{"key":"ref183","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref184","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver"},{"key":"ref185","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref186","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref187","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.11591\/ijai.v7.i4.pp165-169"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1016\/0045-7906(93)90053-T"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1007\/BF00437601"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/9.718605"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1002\/0471669784"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50790-3"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2014.2308133"},{"key":"ref197","article-title":"Exploring deep and recurrent architectures for optimal control","author":"Levine","year":"2013","journal-title":"arXiv:1311.1761"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.2015.1060362"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-100819-063206"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/MPEL.2020.3047506"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2019.01.145"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2019.07.019"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-019-01078-y"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3053269"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.35833\/MPCE.2020.000267"},{"issue":"7","key":"ref207","first-page":"1","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"Taylor","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01424-7_27"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1007\/s10732-007-9031-5"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-43645-5_2"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44668-0_13"},{"key":"ref214","article-title":"RL2: Fast reinforcement learning via slow reinforcement learning","author":"Duan","year":"2016","journal-title":"arXiv:1611.02779"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.3390\/pr5030046"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483063"},{"key":"ref217","volume-title":"Openai. Openai\/Gym","year":"2022"},{"key":"ref218","article-title":"Transfer from simulation to real world through learning deep inverse dynamics model","author":"Christiano","year":"2016","journal-title":"arXiv:1610.03518"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907423"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139550"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2419431"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2019.02.031"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12463"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1016\/j.mfglet.2018.02.006"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2873186"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2998358"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2018.01.006"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2019.01.014"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1080\/09537287.2020.1768450"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-019-01512-w"},{"key":"ref231","first-page":"8024","article-title":"Programmatically interpretable reinforcement learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","volume":"11","author":"Verma"},{"key":"ref232","article-title":"Interpretable multi-objective reinforcement learning through policy orchestration","author":"Noothigattu","year":"2018","journal-title":"arXiv:1809.08343"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57321-8_5"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.3390\/e23010018"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-022-01756-8"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2894586"},{"key":"ref237","article-title":"Transfer learning in deep reinforcement learning: A survey","author":"Zhu","year":"2020","journal-title":"arXiv:2009.07888"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1109\/CASE48305.2020.9216872"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-32156-1_5"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09738649.pdf?arnumber=9738649","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T23:58:14Z","timestamp":1705535894000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9738649\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":239,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3160709","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}