{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T00:58:19Z","timestamp":1768352299857,"version":"3.49.0"},"reference-count":153,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T00:00:00Z","timestamp":1654646400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T00:00:00Z","timestamp":1654646400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,6,8]]},"DOI":"10.23919\/acc53348.2022.9867643","type":"proceedings-article","created":{"date-parts":[[2022,9,5]],"date-time":"2022-09-05T20:24:10Z","timestamp":1662409450000},"page":"342-357","source":"Crossref","is-referenced-by-count":47,"title":["Fusion of Machine Learning and MPC under Uncertainty: What Advances Are on the Horizon?"],"prefix":"10.23919","author":[{"given":"Ali","family":"Mesbah","sequence":"first","affiliation":[{"name":"University of California,Department of Chemical and Biomolecular Engineering,Berkeley,CA,USA,94720"}]},{"given":"Kim P.","family":"Wabersich","sequence":"additional","affiliation":[{"name":"Institute for Dynamic Systems and Control,ETH Zürich,Zürich,Switzerland,CH-8092"}]},{"given":"Angela P.","family":"Schoellig","sequence":"additional","affiliation":[{"name":"University of Toronto,Institute for Aerospace Studies,Toronto,Canada,M3H 5T6"}]},{"given":"Melanie N.","family":"Zeilinger","sequence":"additional","affiliation":[{"name":"Institute for Dynamic Systems and Control,ETH Zürich,Zürich,Switzerland,CH-8092"}]},{"given":"Sergio","family":"Lucia","sequence":"additional","affiliation":[{"name":"TU Dortmund,Laboratory of Process Automation Systems,Dortmund,Germany"}]},{"given":"Thomas A.","family":"Badgwell","sequence":"additional","affiliation":[{"name":"Chief Technology Officer at Collaborative Systems Integration,Austin,TX,USA,78704"}]},{"given":"Joel A.","family":"Paulson","sequence":"additional","affiliation":[{"name":"The Ohio State University,Department of Chemical and Biomolecular Engineering,Columbus,OH,USA,43210"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2017.03.031"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1201\/b14884"},{"key":"ref33","article-title":"Conservative decision-making and inference in uncertain dynamical systems","author":"calliess","year":"2014","journal-title":"Ph D Dissertation"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2005.08.011"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2015.12.006"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2008.12.002"},{"key":"ref37","author":"murphy","year":"2012","journal-title":"Machine Learning A Probabilistic Perspective"},{"key":"ref36","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.1265"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2018.5522"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.10.036"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1080\/002071799220218"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2018.8550494"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/37.466261"},{"key":"ref22","article-title":"A data-driven convex programming approach to worst-case robust tracking controller design","author":"xu","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3000182"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(91)90134-N"},{"key":"ref23","article-title":"Distributionally robust chance constrained data-enabled predictive control","author":"coulson","year":"2021","journal-title":"IEEE Transactions on Automatic Control"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/s11081-018-9417-2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2019.02.023"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.2017.1316017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2004.02.002"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3131988"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683134"},{"key":"ref153","article-title":"Newton’s method for reinforcement learning and model predictive control","author":"bertsekas","year":"2022"},{"key":"ref150","first-page":"1701","article-title":"Data-efficient reinforcement learning with probabilistic model predictive control","author":"kamthe","year":"2018","journal-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1002\/aic.17658"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.118346"},{"key":"ref146","article-title":"Temporal differences-based policy iteration and applications in neuro-dynamic programming","author":"bertsekas","year":"1996","journal-title":"Lab for Info and Decision Systems Report LIDS-P-2349 MIT"},{"key":"ref147","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1016\/S0005-1098(99)00214-9","article-title":"Constrained model predictive control: Stability and optimality","volume":"36","author":"mayne","year":"2000","journal-title":"Automatica"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2010.06.007"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2009.5399917"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2004.08.019"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(01)00051-6"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2018.11.036"},{"key":"ref55","article-title":"Meta learning MPC using finite-dimensional gaussian process approximations","author":"arcari","year":"2020"},{"key":"ref54","article-title":"Meta reinforcement learning with latent variable Gaussian processes","author":"saemundsson","year":"2018","journal-title":"Proceedings of the Conference on Uncertainty in Artificial Intelligence"},{"key":"ref53","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","author":"nagabandi","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2021.3122269"},{"key":"ref40","first-page":"2977","article-title":"Experience-based model selection to enable long-term, safe control for repetitive tasks under changing conditions","author":"mckinnon","year":"2018","journal-title":"Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.10.128"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-011-0300-6"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1109\/MCS.2016.2602087","article-title":"Stochastic model predictive control: An overview and perspectives for future research","volume":"36","author":"mesbah","year":"2016","journal-title":"IEEE Control Systems"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-24853-0","author":"kouvaritakis","year":"2016","journal-title":"Model Predictive Control Classical Robust and Stochastic"},{"key":"ref8","article-title":"Robust constraint satisfaction: Invariant sets and predictive control","author":"kerrigan","year":"2001","journal-title":"Ph D Dissertation"},{"key":"ref49","first-page":"424","article-title":"On simulation and trajectory prediction with Gaussian process dynamics","author":"hewing","year":"2020","journal-title":"Proceedings of Learning for Dynamics and Control"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-090419-075625"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1768-8_11"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2021.3069825"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619572"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2018.8550458"},{"key":"ref47","first-page":"529","article-title":"Multiple-step ahead prediction for non linear dynamic systems–a Gaussian process treatment with propagation of the uncertainty","volume":"15","author":"girard","year":"2002","journal-title":"Advances in neural information processing systems"},{"key":"ref42","author":"rasmussen","year":"2006","journal-title":"Gaussian Processes for Machine Learning"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3049335"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2018.8550162"},{"key":"ref43","first-page":"908","article-title":"Safe model-based reinforcement learning with stability guarantees","author":"berkenkamp","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6911(97)00005-4"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.11.004"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2018.2843682"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9303895"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273546"},{"key":"ref72","first-page":"1","article-title":"Tuning hyperparameters without grad students: Scalable and robust Bayesian optimisation with Dragonfly","volume":"21","author":"kandasamy","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2999556"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2021.08.249"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029310"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2021.3050356"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11288"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814335"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1002\/oca.2817"},{"key":"ref74","first-page":"841","article-title":"Variational heteroscedastic Gaussian process regression","author":"l\u00e1zaro-gredilla","year":"2011","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1002\/aic.17591"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.1208"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-77935-5_9"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8431275"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683046"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.2980479"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2022.107770"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/PC52310.2021.9447448"},{"key":"ref135","article-title":"Reliably-stabilizing piecewise-affine neural network controllers","author":"fabiani","year":"2021"},{"key":"ref138","doi-asserted-by":"crossref","DOI":"10.1002\/9780470182963","volume":"703","author":"powell","year":"2007","journal-title":"Approximate Dynamic Programming Solving the Curses of Dimensionality"},{"key":"ref137","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2013.08.008"},{"key":"ref139","article-title":"Approximate dynamic programming","author":"bertsekas","year":"2008"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.3999"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2011.09.048"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.2017.1323351"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619328"},{"key":"ref140","first-page":"263","article-title":"Approximate dynamic programming strategies and their applicability for process control: A review and future directions","volume":"2","author":"lee","year":"2004","journal-title":"International Journal of Control Automation and Systems"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.paerosci.2008.11.001"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.1566"},{"key":"ref66","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1109\/JPROC.2015.2494218","article-title":"Taking the human out of the loop: A review of Bayesian optimization","volume":"104","author":"shahriari","year":"2015","journal-title":"Proceedings of the IEEE"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref67","article-title":"A tutorial on Bayesian optimization","author":"frazier","year":"2018"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2019.2913347"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref2","volume":"2","author":"rawlings","year":"2017","journal-title":"Model Predictive Control Theory Computation and Design"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3040599"},{"key":"ref145","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1007\/BF00114723","article-title":"Linear least-squares algorithms for temporal difference learning","volume":"22","author":"bradtke","year":"1996","journal-title":"Machine Learning"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0098-1354(98)00301-9"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(95)00044-W"},{"key":"ref95","author":"boyd","year":"2011","journal-title":"Distributed optimization and statistical learning via the alternating direction method of multipliers"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2014.2382571"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2012.6315076"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2011.2141410"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1137\/120897547"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/PC.2013.6581440"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2011.2176389"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2007.11.027"},{"key":"ref91","first-page":"543","article-title":"A method for solving the convex programming problem with convergence rate O(1\/kˆ2)","volume":"269","author":"nesterov","year":"1983","journal-title":"Dokl Akad Nauk SSSR"},{"key":"ref104","doi-asserted-by":"crossref","first-page":"243","DOI":"10.3182\/20090712-4-TR-2008.00037","article-title":"Explicit robust model predictive control","volume":"42","author":"pistikopoulos","year":"2009","journal-title":"IFAC Proceedings Volumes"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2015.2459211"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(01)00174-1"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2017.08.1946"},{"key":"ref111","first-page":"2979","article-title":"Depth-width tradeoffs in approximating natural functions with neural networks","author":"safran","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref112","first-page":"2924","article-title":"On the number of linear regions of deep neural networks","author":"montufar","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref110","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of GO with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1002\/oca.2152"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-004-0559-y"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CONTROL.2018.8516834"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/3210754"},{"key":"ref10","article-title":"Safe learning in robotics: From learning-based control to safe reinforcement learning","author":"brunke","year":"2021"},{"key":"ref11","article-title":"Active learning for nonlinear system identification with guarantees","author":"mania","year":"2020"},{"key":"ref12","author":"zhu","year":"2001","journal-title":"Multivariable System Identification for Process Control"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2017.11.001"},{"key":"ref14","first-page":"455","article-title":"Stability of Gaussian process learning based output feedback model predictive control","author":"maiworm","year":"2018","journal-title":"Proceedings of the IFAC Conference on Nonlinear Model Predictive Control"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2970146"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3124983"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.10.013"},{"key":"ref82","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"sutton","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2021.107266"},{"key":"ref17","first-page":"1280","article-title":"Probabilistic recurrent state-space models","author":"doerr","year":"2018","journal-title":"Machine Learning Research"},{"key":"ref81","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2021.09.005"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.1196"},{"key":"ref119","article-title":"Ten-sorFlow: Large-scale machine learning on heterogeneous systems","author":"abadi","year":"2015"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920953902"},{"key":"ref83","article-title":"An overview of gradient descent optimization algorithms","author":"ruder","year":"2016"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2021.109947"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2018.8550234"},{"key":"ref116","doi-asserted-by":"crossref","first-page":"584","DOI":"10.1016\/j.ifacol.2021.08.305","article-title":"An adaptive correction scheme for offset-free asymptotic performance in deep learning-based economic MPC","volume":"54","author":"krishnamoorthy","year":"2021","journal-title":"IFAC-PapersOnLine"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-053018-023825"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2969729"},{"key":"ref120","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2013.6669541"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.5696"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/JESTPE.2020.2968475"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9482849"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3024161"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9482765"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/s12532-014-0071-1"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1002\/oca.2652"}],"event":{"name":"2022 American Control Conference (ACC)","location":"Atlanta, GA, USA","start":{"date-parts":[[2022,6,8]]},"end":{"date-parts":[[2022,6,10]]}},"container-title":["2022 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9866948\/9867142\/09867643.pdf?arnumber=9867643","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T20:24:35Z","timestamp":1665433475000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9867643\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,8]]},"references-count":153,"URL":"https:\/\/doi.org\/10.23919\/acc53348.2022.9867643","relation":{},"subject":[],"published":{"date-parts":[[2022,6,8]]}}}