{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T22:29:04Z","timestamp":1757456944488,"version":"3.40.5"},"reference-count":96,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T00:00:00Z","timestamp":1733702400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T00:00:00Z","timestamp":1733702400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["442047500"],"award-info":[{"award-number":["442047500"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017142","name":"Gruppo Nazionale per il Calcolo Scientifico","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017142","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Dyn Games Appl"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s13235-024-00610-6","type":"journal-article","created":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T05:21:56Z","timestamp":1733721716000},"page":"454-480","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Comparison Study of Supervised Learning Techniques for the Approximation of High Dimensional Functions and Feedback Control"],"prefix":"10.1007","volume":"15","author":[{"given":"Mathias","family":"Oster","sequence":"first","affiliation":[]},{"given":"Luca","family":"Saluzzi","sequence":"additional","affiliation":[]},{"given":"Tizian","family":"Wenzel","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,9]]},"reference":[{"issue":"3731","key":"610_CR1","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1126\/science.153.3731.34","volume":"153","author":"R Bellman","year":"1966","unstructured":"Bellman R (1966) Dynamic programming. Science 153(3731):34\u201337","journal-title":"Science"},{"key":"610_CR2","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-8176-4755-1","volume-title":"Optimal control and viscosity solutions of Hamilton\u2013Jacobi\u2013Bellman equations","author":"M Bardi","year":"1997","unstructured":"Bardi M, Capuzzo-Dolcetta I (1997) Optimal control and viscosity solutions of Hamilton\u2013Jacobi\u2013Bellman equations. Birk\u00e4user, Boston"},{"key":"610_CR3","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611973051","volume-title":"Semi-Lagrangian approximation schemes for linear and Hamilton\u2013Jacobi equations","author":"M Falcone","year":"2013","unstructured":"Falcone M, Ferretti R (2013) Semi-Lagrangian approximation schemes for linear and Hamilton\u2013Jacobi equations. SIAM, Philadelphia, PA"},{"issue":"2","key":"610_CR4","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1137\/17M1116635","volume":"40","author":"D Kalise","year":"2018","unstructured":"Kalise D, Kunisch K (2018) Polynomial approximation of high-dimensional Hamilton\u2013Jacobi\u2013Bellman equations and applications to feedback control of semilinear parabolic PDEs. SIAM J Sci Comput 40(2):629\u2013652","journal-title":"SIAM J Sci Comput"},{"issue":"1","key":"610_CR5","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1137\/130932284","volume":"37","author":"A Alla","year":"2015","unstructured":"Alla A, Falcone M, Kalise D (2015) An efficient policy iteration algorithm for dynamic programming equations. SIAM J Sci Comput 37(1):181\u2013200","journal-title":"SIAM J Sci Comput"},{"key":"610_CR6","doi-asserted-by":"crossref","unstructured":"Zhao Z, Yang Y, Li H, Liu D (2014) Approximate finite-horizon optimal control with policy iteration. In: Proceedings of the 33rd Chinese control conference, pp 8895\u20138900","DOI":"10.1109\/ChiCC.2014.6896497"},{"key":"610_CR7","doi-asserted-by":"crossref","unstructured":"Tahirovic A, Astolfi A (2019) Optimal control for continuous-time nonlinear systems based on a linear-like policy iteration. In: 2019 IEEE 58th conference on decision and control (CDC), pp 5238\u20135243","DOI":"10.1109\/CDC40024.2019.9029697"},{"issue":"2","key":"610_CR8","doi-asserted-by":"crossref","first-page":"549","DOI":"10.1109\/TNNLS.2019.2905715","volume":"31","author":"S He","year":"2020","unstructured":"He S, Fang H, Zhang M, Liu F, Ding Z (2020) Adaptive optimal control for a class of nonlinear systems: the online policy iteration approach. IEEE Trans Neural Netw Learn Syst 31(2):549\u2013558","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"12","key":"610_CR9","doi-asserted-by":"crossref","first-page":"3281","DOI":"10.1016\/j.automatica.2014.10.056","volume":"50","author":"B Luo","year":"2014","unstructured":"Luo B, Wu H-N, Huang T, Liu D (2014) Data-based approximate policy iteration for affine nonlinear continuous-time optimal control design. Automatica 50(12):3281\u20133290","journal-title":"Automatica"},{"issue":"6","key":"610_CR10","doi-asserted-by":"crossref","first-page":"3022","DOI":"10.1002\/asjc.2689","volume":"24","author":"S Pakkhesal","year":"2022","unstructured":"Pakkhesal S, Shamaghdari S (2022) Sum-of-squares-based policy iteration for suboptimal control of polynomial time-varying systems. Asian J Control 24(6):3022\u20133031","journal-title":"Asian J Control"},{"issue":"3","key":"610_CR11","doi-asserted-by":"crossref","first-page":"686","DOI":"10.1109\/LCSYS.2020.2990632","volume":"4","author":"N Yazdani","year":"2020","unstructured":"Yazdani N, Moghaddam R, Kiumarsi B, Modares H (2020) A safety-certified policy iteration algorithm for control of constrained nonlinear systems. IEEE Control Syst Lett 4(3):686\u2013691","journal-title":"IEEE Control Syst Lett"},{"key":"610_CR12","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-60771-9","volume-title":"Optimal control: novel directions and applications","author":"D Tonon","year":"2017","unstructured":"Tonon D, Aronna M, Kalise D (2017) Optimal control: novel directions and applications. Springer International"},{"key":"610_CR13","unstructured":"Debrabant K, Jakobsen E (2014) Semi-Lagrangian schemes for linear and fully non-linear Hamilton\u2013Jacobi\u2013Bellman equations. In: Hyperbolic problems: theory, numerics, applications. Springer International, pp 483\u2013490"},{"issue":"1","key":"610_CR14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/BF01442644","volume":"15","author":"M Falcone","year":"1987","unstructured":"Falcone M (1987) A numerical approach to the infinite horizon problem of deterministic control theory. Appl Math Optim 15(1):1\u201313","journal-title":"Appl Math Optim"},{"issue":"2","key":"610_CR15","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/0168-9274(94)00017-4","volume":"15","author":"M Falcone","year":"1994","unstructured":"Falcone M, Lanucara P, Seghini A (1994) A splitting algorithm for Hamilton\u2013Jacobi\u2013Bellman equations. Appl Numer Math 15(2):207\u2013218","journal-title":"Appl Numer Math"},{"issue":"6","key":"610_CR16","doi-asserted-by":"crossref","first-page":"3917","DOI":"10.1016\/j.apm.2012.08.013","volume":"37","author":"B Kafash","year":"2013","unstructured":"Kafash B, Delavarkhalafi A, Karbassi SM (2013) Application of variational iteration method for Hamilton\u2013Jacobi\u2013Bellman. Appl Math Model 37(6):3917\u20133928","journal-title":"Appl Math Model"},{"key":"610_CR17","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1016\/j.apnum.2019.11.023","volume":"155","author":"A Alla","year":"2020","unstructured":"Alla A, Saluzzi L (2020) A HJB-POD approach for the control of nonlinear PDEs on a tree structure. Appl Numer Math 155:192\u2013207","journal-title":"Appl Numer Math"},{"key":"610_CR18","doi-asserted-by":"crossref","unstructured":"Akian M, Gaubert S, Lakhoua A (2009) Convergence analysis of the max-plus finite element method for solving deterministic optimal control problems. In: Proceedings of the IEEE conference on decision and control, pp 927\u2013934. IEEE, NY","DOI":"10.1109\/CDC.2008.4739501"},{"key":"610_CR19","first-page":"183","volume-title":"Probabilistic max-plus schemes for solving Hamilton\u2013Jacobi\u2013Bellman equations","author":"M Akian","year":"2018","unstructured":"Akian M, Fodjo E (2018) Probabilistic max-plus schemes for solving Hamilton\u2013Jacobi\u2013Bellman equations. Springer International, pp 183\u2013209"},{"key":"610_CR20","unstructured":"Pontryagin L, Boltyanskii V, Gamkrelidze R, Mishchenko E (1962) The mathematical theory of optimal processes. Translated from the Russian by K. N. Trirogoff; LW Neustadt (ed), Wiley, New York, NY"},{"issue":"1","key":"610_CR21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1023\/A:1004607114958","volume":"107","author":"S Beeler","year":"2000","unstructured":"Beeler S, Tran H, Banks H (2000) Feedback control methodologies for nonlinear systems. J Optim Theory Appl 107(1):1\u201333","journal-title":"J Optim Theory Appl"},{"issue":"2","key":"610_CR22","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1007\/s10589-017-9910-0","volume":"68","author":"W Kang","year":"2017","unstructured":"Kang W, Wilcox L (2017) Mitigating the curse of dimensionality: sparse grid characteristics method for optimal feedback control and HJB equations. Comput Optim Appl 68(2):289\u2013315","journal-title":"Comput Optim Appl"},{"issue":"2","key":"610_CR23","doi-asserted-by":"crossref","first-page":"1221","DOI":"10.1137\/19M1288802","volume":"43","author":"T Nakamura-Zimmerer","year":"2021","unstructured":"Nakamura-Zimmerer T, Gong Q, Kang W (2021) Adaptive deep learning for high-dimensional Hamilton\u2013Jacobi\u2013Bellman equations. SIAM J Sci Comput 43(2):1221\u20131247","journal-title":"SIAM J Sci Comput"},{"key":"610_CR24","first-page":"1","volume":"22","author":"B Azmi","year":"2021","unstructured":"Azmi B, Kalise D, Kunisch K (2021) Optimal feedback law recovery by gradient-augmented sparse polynomial regression. J Mach Learn Res 22:1\u201332","journal-title":"J Mach Learn Res"},{"key":"610_CR25","unstructured":"Vapnik V (1992) Principles of risk minimization for learning theory. Adv Neural Inf Process Syst 831\u2013838"},{"key":"610_CR26","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-77242-4","volume-title":"Support vector machines","author":"I Steinwart","year":"2008","unstructured":"Steinwart I, Christmann A (2008) Support vector machines. Springer, Berlin"},{"key":"610_CR27","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-28027-6","volume-title":"Tensor spaces and numerical tensor calculus","author":"W Hackbusch","year":"2012","unstructured":"Hackbusch W (2012) Tensor spaces and numerical tensor calculus. Springer, Berlin"},{"key":"610_CR28","doi-asserted-by":"crossref","first-page":"3744","DOI":"10.1137\/090748330","volume":"31","author":"I Oseledets","year":"2009","unstructured":"Oseledets I, Tyrtyshnikov E (2009) Breaking the curse of dimensionality, or how to use SVD in many dimensions. SIAM J Sci Comput 31:3744\u20133759","journal-title":"SIAM J Sci Comput"},{"issue":"5","key":"610_CR29","doi-asserted-by":"crossref","first-page":"2295","DOI":"10.1137\/090752286","volume":"33","author":"IV Oseledets","year":"2011","unstructured":"Oseledets IV (2011) Tensor-train decomposition. SIAM J Sci Comput 33(5):2295\u20132317","journal-title":"SIAM J Sci Comput"},{"issue":"1","key":"610_CR30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.chemolab.2011.09.001","volume":"110","author":"BN Khoromskij","year":"2011","unstructured":"Khoromskij BN (2011) Tensors-structured numerical methods in scientific computing: survey on recent advances. Chemom Intell Lab Syst 110(1):1\u201319","journal-title":"Chemom Intell Lab Syst"},{"key":"610_CR31","first-page":"237","volume-title":"Tensor spaces and hierarchical tensor representations","author":"W Hackbusch","year":"2014","unstructured":"Hackbusch W, Schneider R (2014) Tensor spaces and hierarchical tensor representations. Springer, Cham, pp 237\u2013261"},{"issue":"6","key":"610_CR32","doi-asserted-by":"crossref","first-page":"1423","DOI":"10.1007\/s10208-016-9317-9","volume":"16","author":"M Bachmayr","year":"2016","unstructured":"Bachmayr M, Schneider R, Uschmajew A (2016) Tensor networks and hierarchical tensors for the solution of high-dimensional partial differential equations. Found Comput Math 16(6):1423\u20131472","journal-title":"Found Comput Math"},{"issue":"19","key":"610_CR33","doi-asserted-by":"crossref","first-page":"1342","DOI":"10.1002\/qua.24898","volume":"115","author":"S Szalay","year":"2015","unstructured":"Szalay S, Pfeffer M, Murg V, Barcza G, Verstraete F, Schneider R (2015) Legeza: tensor product methods and entanglement optimization for ab initio quantum chemistry. Int J Quant Chem 115(19):1342\u20131391","journal-title":"Int J Quant Chem"},{"key":"610_CR34","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1017\/S0962492914000087","volume":"23","author":"W Hackbusch","year":"2014","unstructured":"Hackbusch W (2014) Numerical tensor calculus. Acta Numer 23:651\u2013742","journal-title":"Acta Numer"},{"issue":"3","key":"610_CR35","doi-asserted-by":"crossref","first-page":"1625","DOI":"10.1137\/19M1305136","volume":"43","author":"S Dolgov","year":"2021","unstructured":"Dolgov S, Kalise D, Kunisch K (2021) Tensor decomposition methods for high-dimensional Hamilton\u2013Jacobi\u2013Bellman equations. SIAM J Sci Comput 43(3):1625\u20131650","journal-title":"SIAM J Sci Comput"},{"issue":"3","key":"610_CR36","doi-asserted-by":"crossref","first-page":"746","DOI":"10.1137\/21M1412190","volume":"44","author":"M Oster","year":"2022","unstructured":"Oster M, Sallandt L, Schneider R (2022) Approximating optimal feedback controllers of finite horizon control problems using hierarchical tensor formats. SIAM J Sci Comput 44(3):746\u2013770","journal-title":"SIAM J Sci Comput"},{"issue":"3","key":"610_CR37","doi-asserted-by":"crossref","first-page":"638","DOI":"10.4208\/jcm.2112-m2021-0084","volume":"42","author":"M Oster","year":"2024","unstructured":"Oster M, Sallandt L, Schneider R (2024) Approximating the stationary bellman equation by hierarchical tensor products. J Comput Math 42(3):638\u2013661","journal-title":"J Comput Math"},{"key":"610_CR38","doi-asserted-by":"crossref","unstructured":"Stefansson E, Leong Y (2016) Sequential alternating least squares for solving high dimensional linear Hamilton\u2013Jacobi\u2013Bellman equation. In: 2016 IEEE\/RSJ international conference on intelligent robots and systems (IROS), pp 3757\u20133764","DOI":"10.1109\/IROS.2016.7759553"},{"key":"610_CR39","doi-asserted-by":"crossref","unstructured":"Horowitz A, Damle M, Burdick J (2014) Linear Hamilton Jacobi Bellman equations in high dimensions. In: 53rd IEEE conference on decision and control, pp 5880\u20135887. IEEE","DOI":"10.1109\/CDC.2014.7040310"},{"issue":"1","key":"610_CR40","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1137\/20M1372500","volume":"20","author":"K Fackeldey","year":"2022","unstructured":"Fackeldey K, Oster M, Sallandt L, Schneider R (2022) Approximative policy iteration for exit time feedback control problems driven by stochastic differential equations using tensor train format. Multiscale Modeli Simul 20(1):379\u2013403","journal-title":"Multiscale Modeli Simul"},{"issue":"2\u20133","key":"610_CR41","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1177\/0278364917753994","volume":"37","author":"A Gorodetsky","year":"2018","unstructured":"Gorodetsky A, Karaman S, Marzouk Y (2018) High-dimensional stochastic optimal control using continuous tensor decompositions. Int J Robot Res 37(2\u20133):340\u2013377","journal-title":"Int J Robot Res"},{"issue":"5","key":"610_CR42","doi-asserted-by":"crossref","first-page":"2153","DOI":"10.1137\/22M1498401","volume":"45","author":"S Dolgov","year":"2023","unstructured":"Dolgov S, Kalise D, Saluzzi L (2023) Data-driven tensor train gradient cross approximation for Hamilton\u2013Jacobi\u2013Bellman equations. SIAM J Sci Comput 45(5):2153\u20132184","journal-title":"SIAM J Sci Comput"},{"key":"610_CR43","doi-asserted-by":"crossref","DOI":"10.3389\/fams.2021.702486","volume":"7","author":"M G\u00f6tte","year":"2021","unstructured":"G\u00f6tte M, Schneider R, Trunschke P (2021) A block-sparse tensor train format for sample-efficient high-dimensional polynomial regression. Front Appl Math Stat 7:702486","journal-title":"Front Appl Math Stat"},{"issue":"1","key":"610_CR44","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.laa.2009.07.024","volume":"432","author":"IV Oseledets","year":"2010","unstructured":"Oseledets IV, Tyrtyshnikov EE (2010) TT-cross approximation for multidimensional arrays. Linear Algebra Appl 432(1):70\u201388","journal-title":"Linear Algebra Appl"},{"key":"610_CR45","doi-asserted-by":"crossref","unstructured":"Savostyanov DV, Oseledets IV (2011) Fast adaptive interpolation of multi-dimensional arrays in tensor train format. In: Proceedings of 7th international workshop on multidimensional systems (nDS). IEEE, NY","DOI":"10.1109\/nDS.2011.6076873"},{"issue":"2","key":"610_CR46","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1007\/s00791-015-0247-x","volume":"17","author":"L Grasedyck","year":"2015","unstructured":"Grasedyck L, Kriemann R, L\u00f6bbert C, N\u00e4gel A, Wittum G, Xylouris K (2015) Parallel tensor sampling in the hierarchical Tucker format. Comput Vis Sci 17(2):67\u201378","journal-title":"Comput Vis Sci"},{"key":"610_CR47","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1016\/j.laa.2014.06.006","volume":"458","author":"DV Savostyanov","year":"2014","unstructured":"Savostyanov DV (2014) Quasioptimality of maximum-volume cross interpolation of tensors. Linear Algebra Appl 458:217\u2013244","journal-title":"Linear Algebra Appl"},{"key":"610_CR48","volume-title":"Scattered data approximation. Cambridge monographs on applied and computational mathematics","author":"H Wendland","year":"2005","unstructured":"Wendland H (2005) Scattered data approximation. Cambridge monographs on applied and computational mathematics, vol 17. Cambridge University Press, Cambridge"},{"key":"610_CR49","doi-asserted-by":"crossref","unstructured":"Berner J, Grohs P, Kutyniok G, Petersen P (2022) The modern mathematics of deep learning. In: Mathematical aspects of deep learning, pp 1\u2013111. Cambridge University Press, Cambridge","DOI":"10.1017\/9781009025096.002"},{"key":"610_CR50","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1017\/S0962492921000052","volume":"30","author":"RA DeVore","year":"2021","unstructured":"DeVore RA, Hanin B, Petrova G (2021) Neural network approximation. Acta Numer 30:327\u2013444","journal-title":"Acta Numer"},{"key":"610_CR51","unstructured":"E W, Ma C, Wojtowytsch S, Wu L (2020) Towards a mathematical understanding of neural network-based machine learning: What we know and what we don\u2019t"},{"issue":"4","key":"610_CR52","doi-asserted-by":"crossref","first-page":"860","DOI":"10.1137\/18M1165748","volume":"61","author":"CF Higham","year":"2019","unstructured":"Higham CF, Higham DJ (2019) Deep learning: an introduction for applied mathematicians. SIAM Rev 61(4):860\u2013891","journal-title":"SIAM Rev"},{"key":"610_CR53","doi-asserted-by":"crossref","unstructured":"Pak M, Kim S (2017) A review of deep learning in image recognition. In: 2017 4th international conference on computer applications and information processing technology (CAIPT), pp 1\u20133","DOI":"10.1109\/CAIPT.2017.8320684"},{"issue":"6","key":"610_CR54","doi-asserted-by":"crossref","first-page":"3697","DOI":"10.3934\/dcdsb.2022238","volume":"28","author":"C Beck","year":"2023","unstructured":"Beck C, Hutzenthaler M, Jentzen A, Kuckuck B (2023) An overview on deep learning-based approximation methods for partial differential equations. Discrete Contin Dyn Syst B 28(6):3697\u20133746","journal-title":"Discrete Contin Dyn Syst B"},{"key":"610_CR55","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1051\/cocv\/2021009","volume":"27","author":"K Kunisch","year":"2021","unstructured":"Kunisch K, Walter D (2021) Semiglobal optimal feedback stabilization of autonomous systems via deep neural network approximation. ESAIM Control Optim Calc Var 27:16","journal-title":"ESAIM Control Optim Calc Var"},{"key":"610_CR56","doi-asserted-by":"crossref","unstructured":"Kunisch K, Walter D (2023) Optimal feedback control of dynamical systems via value-function approximation. arXiv Preprint at arXiv:2302.13122","DOI":"10.5802\/crmeca.199"},{"issue":"3","key":"610_CR57","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s40687-020-00215-6","volume":"7","author":"J Darbon","year":"2020","unstructured":"Darbon J, Langlois GP, Meng T (2020) Overcoming the curse of dimensionality for some Hamilton\u2013Jacobi partial differential equations via neural network architectures. Res Math Sci 7(3):1\u201350","journal-title":"Res Math Sci"},{"issue":"4","key":"610_CR58","first-page":"1","volume":"2","author":"N N\u00fcsken","year":"2021","unstructured":"N\u00fcsken N, Richter L (2021) Solving high-dimensional Hamilton\u2013Jacobi\u2013Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space. Partial Diff Equ Appl 2(4):1\u201348","journal-title":"Partial Diff Equ Appl"},{"issue":"2","key":"610_CR59","first-page":"1","volume":"21","author":"K Ito","year":"2020","unstructured":"Ito K, Reisinger C, Zhang Y (2020) A neural network-based policy iteration algorithm with global $$h^{2}$$ -superlinear convergence for stochastic games on domains. Found Comput Math 21(2):1\u201344","journal-title":"Found Comput Math"},{"key":"610_CR60","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1016\/j.camwa.2023.05.004","volume":"143","author":"N Demo","year":"2023","unstructured":"Demo N, Strazzullo M, Rozza G (2023) An extended physics informed neural network for preliminary analysis of parametric optimal control problems. Comput Math Appl 143:383\u2013396","journal-title":"Comput Math Appl"},{"issue":"34","key":"610_CR61","doi-asserted-by":"crossref","first-page":"8505","DOI":"10.1073\/pnas.1718942115","volume":"115","author":"J Han","year":"2018","unstructured":"Han J, Jentzen A, WE (2018) Solving high-dimensional partial differential equations using deep learning. Proc Natil Acad Sci 115(34):8505\u20138510","journal-title":"Proc Natil Acad Sci"},{"key":"610_CR62","doi-asserted-by":"publisher","unstructured":"Meng T, Zhang Z, Darbon J, Karniadakis GE (2022) SympOCnet: solving optimal control problems with applications to high-dimensional multi-agent path planning problems. https:\/\/doi.org\/10.48550\/ARXIV.2201.05475","DOI":"10.48550\/ARXIV.2201.05475"},{"issue":"6","key":"610_CR63","doi-asserted-by":"crossref","first-page":"4043","DOI":"10.1137\/21M1402303","volume":"43","author":"M Zhou","year":"2021","unstructured":"Zhou M, Han J, Lu J (2021) Actor-critic method for high dimensional static Hamilton\u2013Jacobi\u2013Bellman partial differential equations based on neural networks. SIAM J Sci Comput 43(6):4043\u20134066","journal-title":"SIAM J Sci Comput"},{"key":"610_CR64","doi-asserted-by":"crossref","unstructured":"Onken D, Nurbekyan L, Li X, Fung SW, Osher S, Ruthotto L (2021) A neural network approach applied to multi-agent optimal control. In: 2021 European control conference (ECC). IEEE, NY","DOI":"10.23919\/ECC54610.2021.9655103"},{"issue":"17","key":"610_CR65","doi-asserted-by":"crossref","first-page":"9183","DOI":"10.1073\/pnas.1922204117","volume":"117","author":"L Ruthotto","year":"2020","unstructured":"Ruthotto L, Osher SJ, Li W, Nurbekyan L, Fung SW (2020) A machine learning framework for solving high-dimensional mean field game and mean field control problems. Proc Natl Acad Sci 117(17):9183\u20139193","journal-title":"Proc Natl Acad Sci"},{"key":"610_CR66","doi-asserted-by":"crossref","first-page":"836","DOI":"10.1109\/LCSYS.2021.3086697","volume":"6","author":"G Albi","year":"2022","unstructured":"Albi G, Bicego S, Kalise D (2022) Gradient-augmented supervised learning of optimal feedback laws using state-dependent Riccat equations. IEEE Control Syst Lett 6:836\u2013841","journal-title":"IEEE Control Syst Lett"},{"key":"610_CR67","doi-asserted-by":"crossref","unstructured":"Gr\u00fcne L (2020) Computing Lyapunov functions using deep neural networks. arXiv Preprint at arXiv:2005.08965","DOI":"10.3934\/jcd.2021006"},{"issue":"1","key":"610_CR68","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1007\/s00245-021-09769-5","volume":"84","author":"K Kunisch","year":"2021","unstructured":"Kunisch K, Rodrigues SS, Walter D (2021) Learning an optimal feedback operator semiglobally stabilizing semilinear parabolic equations. Appl Math Optim 84(1):277\u2013318","journal-title":"Appl Math Optim"},{"key":"610_CR69","first-page":"1","volume":"24","author":"K Kunisch","year":"2023","unstructured":"Kunisch K, V\u00e1squez-Varas D, Walter D (2023) Learning optimal feedback operators and their sparse polynomial approximations. J Mach Learn Res 24:1\u201338","journal-title":"J Mach Learn Res"},{"issue":"48","key":"610_CR70","first-page":"1","volume":"22","author":"B Azmi","year":"2021","unstructured":"Azmi B, Kalise D, Kunisch K (2021) Optimal feedback law recovery by gradient-augmented sparse polynomial regression. J Mach Learn Res 22(48):1\u201332","journal-title":"J Mach Learn Res"},{"issue":"2","key":"610_CR71","doi-asserted-by":"crossref","first-page":"3761","DOI":"10.3182\/20080706-5-KR-1001.00635","volume":"41","author":"T \u00c7imen","year":"2008","unstructured":"\u00c7imen T (2008) State-dependent Riccati equation (SDRE) control: a survey. IFAC Proc Volumes 41(2):3761\u20133775","journal-title":"IFAC Proc Volumes"},{"key":"610_CR72","doi-asserted-by":"publisher","unstructured":"Alla A, Kalise D, Simoncini V (2021) State-dependent Riccati equation feedback stabilization for nonlinear PDEs. OPT. https:\/\/doi.org\/10.48550\/ARXIV.2106.07163","DOI":"10.48550\/ARXIV.2106.07163"},{"issue":"2","key":"610_CR73","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1007\/s10589-007-9015-2","volume":"37","author":"HT Banks","year":"2007","unstructured":"Banks HT, Lewis BM, Tran HT (2007) Nonlinear feedback controllers and compensators: a state-dependent Riccati equation approach. Comput Optim Appl 37(2):177\u2013218","journal-title":"Comput Optim Appl"},{"issue":"3","key":"610_CR74","doi-asserted-by":"crossref","first-page":"1191","DOI":"10.1137\/20M1314653","volume":"10","author":"PB Rohrbach","year":"2022","unstructured":"Rohrbach PB, Dolgov S, Grasedyck L, Scheichl R (2022) Rank bounds for approximating Gaussian densities in the Tensor-Train format. SIAM\/ASA J Uncertain Quantif 10(3):1191\u20131224","journal-title":"SIAM\/ASA J Uncertain Quantif"},{"issue":"2","key":"610_CR75","doi-asserted-by":"crossref","first-page":"683","DOI":"10.1137\/100818893","volume":"34","author":"S Holtz","year":"2012","unstructured":"Holtz S, Rohwedder T, Schneider R (2012) The alternating linear scheme for tensor optimization in the tensor train format. SIAM J Sci Comput 34(2):683\u2013713","journal-title":"SIAM J Sci Comput"},{"key":"610_CR76","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1142\/9789812836021_0015","volume-title":"Matrix methods: theory, algorithms, applications","author":"SA Goreinov","year":"2010","unstructured":"Goreinov SA, Oseledets IV, Savostyanov DV, Tyrtyshnikov EE, Zamarashkin NL (2010) How to find a good submatrix. In: Olshevsky V, Tyrtyshnikov E (eds) Matrix methods: theory, algorithms, applications. World Scientific, Hackensack, NY, NY, pp 247\u2013256"},{"key":"610_CR77","volume":"447","author":"Y Chen","year":"2021","unstructured":"Chen Y, Hosseini B, Owhadi H, Stuart AM (2021) Solving and learning nonlinear PDEs with Gaussian processes. J Comput Phys 447:110668","journal-title":"J Comput Phys"},{"key":"610_CR78","unstructured":"Meanti G, Carratino L, De\u00a0Vito E, Rosasco L (2022) Efficient hyperparameter tuning for large scale kernel ridge regression. In: International conference on artificial intelligence and statistics, pp 6554\u20136572"},{"key":"610_CR79","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.jcp.2019.03.040","volume":"389","author":"H Owhadi","year":"2019","unstructured":"Owhadi H, Yoo GR (2019) Kernel flows: from learning kernels from data into the abyss. J Comput Phys 389:22\u201347","journal-title":"J Comput Phys"},{"issue":"8","key":"610_CR80","doi-asserted-by":"crossref","first-page":"2123","DOI":"10.1162\/neco_a_00984","volume":"29","author":"JA Suykens","year":"2017","unstructured":"Suykens JA (2017) Deep restricted kernel machines using conjugate feature duality. Neural Comput 29(8):2123\u20132163","journal-title":"Neural Comput"},{"issue":"1","key":"610_CR81","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1137\/23M1551201","volume":"46","author":"T Wenzel","year":"2024","unstructured":"Wenzel T, Marchetti F, Perracchione E (2024) Data-driven kernel designs for optimized greedy schemes: a machine learning perspective. SIAM J Sci Comput 46(1):101\u2013126","journal-title":"SIAM J Sci Comput"},{"issue":"250","key":"610_CR82","doi-asserted-by":"crossref","first-page":"743","DOI":"10.1090\/S0025-5718-04-01708-9","volume":"74","author":"F Narcowich","year":"2005","unstructured":"Narcowich F, Ward J, Wendland H (2005) Sobolev bounds on functions with scattered zeros, with applications to radial basis function surface fitting. Math Comput 74(250):743\u2013763","journal-title":"Math Comput"},{"issue":"4","key":"610_CR83","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1007\/s00211-005-0637-y","volume":"101","author":"H Wendland","year":"2005","unstructured":"Wendland H, Rieger C (2005) Approximate interpolation with applications to selecting smoothing parameters. Numer Math 101(4):729\u2013748","journal-title":"Numer Math"},{"issue":"1","key":"610_CR84","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1007\/s00365-022-09592-3","volume":"57","author":"T Wenzel","year":"2023","unstructured":"Wenzel T, Santin G, Haasdonk B (2023) Analysis of target data-dependent greedy kernel algorithms: convergence rates for f-, f$$\\cdot $$ P-and f\/P-greedy. Constr Approx 57(1):45\u201374","journal-title":"Constr Approx"},{"key":"610_CR85","first-page":"360","volume":"1","author":"S Ma","year":"2019","unstructured":"Ma S, Belkin M (2019) Kernel machines that adapt to GPUS for effective large batch training. Proc Mach Learn Syst 1:360\u2013373","journal-title":"Proc Mach Learn Syst"},{"key":"610_CR86","volume-title":"Deep learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT Press, Cambridge"},{"key":"610_CR87","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv Preprint at arXiv:1412.6980"},{"key":"610_CR88","unstructured":"Telgarsky M (2015) Representation benefits of deep feedforward networks. arXiv Preprint at arXiv:1509.08101"},{"key":"610_CR89","unstructured":"Jacot A, Gabriel F, Hongler C (2018) Neural tangent kernel: Convergence and generalization in neural networks. Adv Neural Inf Process Syst 31"},{"issue":"3","key":"610_CR90","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1007\/s10444-024-10128-5","volume":"50","author":"T Ehring","year":"2024","unstructured":"Ehring T, Haasdonk B (2024) Hermite kernel surrogates for the value function of high-dimensional nonlinear optimal control problems. Adv Comput Math 50(3):36","journal-title":"Adv Comput Math"},{"issue":"30","key":"610_CR91","doi-asserted-by":"crossref","first-page":"510","DOI":"10.1016\/j.ifacol.2022.11.104","volume":"55","author":"S Dolgov","year":"2022","unstructured":"Dolgov S, Kalise D, Saluzzi L (2022) Optimizing semilinear representations for state-dependent Riccati equation-based feedback control. IFAC-PapersOnLine 55(30):510\u2013515","journal-title":"IFAC-PapersOnLine"},{"key":"610_CR92","doi-asserted-by":"crossref","unstructured":"Jones A, Astolfi A (2020) On the solution of optimal control problems using parameterized state-dependent Riccati equations. In: 2020 59th IEEE conference on decision and control (CDC), pp 1098\u20131103","DOI":"10.1109\/CDC42340.2020.9304343"},{"issue":"1","key":"610_CR93","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1109\/TAC.1968.1098829","volume":"13","author":"D Kleinman","year":"1968","unstructured":"Kleinman D (1968) On an iterative technique for Riccati equation computations. IEEE Trans Autom Control 13(1):114\u2013115","journal-title":"IEEE Trans Autom Control"},{"issue":"1","key":"610_CR94","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1109\/9.654908","volume":"43","author":"P Benner","year":"1998","unstructured":"Benner P, Byers R (1998) An exact line search method for solving generalized continuous-time algebraic Riccati equations. IEEE Trans Autom Control 43(1):101\u2013107","journal-title":"IEEE Trans Autom Control"},{"key":"610_CR95","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1051\/cocv\/2021009","volume":"27","author":"K Kunisch","year":"2021","unstructured":"Kunisch K, Walter D (2021) Semiglobal optimal feedback stabilization of autonomous systems via deep neural network approximation. ESAIM Control Optim Cal Var 27:16","journal-title":"ESAIM Control Optim Cal Var"},{"key":"610_CR96","doi-asserted-by":"crossref","DOI":"10.1016\/j.sysconle.2020.104829","volume":"148","author":"T Breiten","year":"2021","unstructured":"Breiten T, Kunisch K (2021) Neural network based nonlinear observers. Syst Control Lett 148:104829","journal-title":"Syst Control Lett"}],"container-title":["Dynamic Games and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13235-024-00610-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13235-024-00610-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13235-024-00610-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T07:11:22Z","timestamp":1747638682000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13235-024-00610-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,9]]},"references-count":96,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["610"],"URL":"https:\/\/doi.org\/10.1007\/s13235-024-00610-6","relation":{},"ISSN":["2153-0785","2153-0793"],"issn-type":[{"type":"print","value":"2153-0785"},{"type":"electronic","value":"2153-0793"}],"subject":[],"published":{"date-parts":[[2024,12,9]]},"assertion":[{"value":"26 November 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 December 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}}]}}