{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T15:45:38Z","timestamp":1787499938234,"version":"build-2736575974"},"reference-count":92,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Multiscale Model. Simul."],"published-print":{"date-parts":[[2022,3]]},"abstract":"<jats:p>We consider a stochastic optimal exit time feedback control problem. The Bellman equation is solved approximatively via the Policy Iteration algorithm on a polynomial ansatz space by a sequence of linear equations. As high degree multipolynomials are needed, the corresponding equations suffer from the curse of dimensionality even in moderate dimensions. We employ Tensor-Train methods to account for this problem. The approximation process within the Policy Iteration is done via a Least-Squares ansatz and the integration is done via Monte-Carlo methods. Numerical evidences are given for the (multidimensional) double-well potential, a three-hole potential, and a 40-dimensional stochastic Van der Pol oscillator.<\/jats:p>","DOI":"10.1137\/20m1372500","type":"journal-article","created":{"date-parts":[[2022,3,21]],"date-time":"2022-03-21T10:10:28Z","timestamp":1647857428000},"page":"379-403","source":"Crossref","is-referenced-by-count":13,"title":["Approximative Policy Iteration for Exit Time Feedback Control Problems Driven by Stochastic Differential Equations using Tensor Train Format"],"prefix":"10.1137","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4373-3672","authenticated-orcid":true,"given":"Konstantin","family":"Fackeldey","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mathias","family":"Oster","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7102-7767","authenticated-orcid":true,"given":"Leon","family":"Sallandt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0529-7467","authenticated-orcid":true,"given":"Reinhold","family":"Schneider","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2022,3,21]]},"reference":[{"key":"atypb1","first-page":"183","author":"Akian M.","year":"2018","journal-title":"Cham"},{"key":"atypb2","doi-asserted-by":"crossref","unstructured":"L. Arnold,\n                      Random Dynamical Systems\n                      , Springer Monogr. Math., Springer, Berlin, Heidelberg, 1998.","DOI":"10.1007\/978-3-662-12878-7"},{"key":"atypb3","doi-asserted-by":"publisher","DOI":"10.1007\/BF01192196"},{"key":"atypb4","doi-asserted-by":"publisher","DOI":"10.1093\/imanum\/drx052"},{"key":"atypb5","doi-asserted-by":"publisher","DOI":"10.1137\/17M111626X"},{"key":"atypb6","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-016-9317-9"},{"key":"atypb7","doi-asserted-by":"crossref","unstructured":"M. Bardi and I. Capuzzo-Dolcetta,\n                      Optimal Control and Viscosity Solutions of Hamilton-Jacobi-Bellman Equations\n                      , Birk\u00e4user, Boston, 1997,https:\/\/doi.org\/10.1007\/978-0-8176-4755-1.","DOI":"10.1007\/978-0-8176-4755-1"},{"key":"atypb8","doi-asserted-by":"publisher","DOI":"10.1080\/00036819308840158"},{"key":"atypb9","unstructured":"C. Beck, S. Becker, P. Grohs, N. Jaafari, and A. Jentzen,\n                      Solving the Kolmogorov PDE by Means of Deep Learning\n                      , preprint,https:\/\/arxiv.org\/abs\/1806.00421, 2018."},{"key":"atypb10","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.41.10.743"},{"key":"atypb11","unstructured":"R. Bellman,\n                      Dynamic Programming\n                      , Princeton University Press, Princeton, NJ, 1961."},{"key":"atypb12","unstructured":"D. Bertsekas,\n                      Dynamic Programming and Optimal Control\n                      , Vol. 2, Approximate Dynamic Programming, 4th ed., Athena Scientific, Belmont, MA, 2019."},{"key":"atypb13","doi-asserted-by":"publisher","DOI":"10.1007\/s11768-011-1005-3"},{"key":"atypb14","doi-asserted-by":"publisher","DOI":"10.1137\/1020004"},{"key":"atypb15","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-012-9648-x"},{"key":"atypb16","doi-asserted-by":"publisher","DOI":"10.1051\/m2an:2004034"},{"key":"atypb17","doi-asserted-by":"publisher","DOI":"10.1137\/S0036142901387336"},{"key":"atypb18","doi-asserted-by":"publisher","DOI":"10.1137\/140998160"},{"key":"atypb19","doi-asserted-by":"publisher","DOI":"10.1063\/1.4772195"},{"key":"atypb20","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492904000182"},{"key":"atypb21","unstructured":"A. Cohen and G. Migliorati,\n                      Optimal Weighted Least-squares Methods\n                      , 2016,https:\/\/hal.archives-ouvertes.fr\/hal-01354003."},{"key":"atypb22","unstructured":"N. \u010crnjari\u0107-\u017dic, S. Ma\u0107e\u0161i\u0107, and I. Mezi\u0107,\n                      Koopman Operator Spectrum for Random Dynamical Systems\n                      , preprint,https:\/\/arxiv.org\/abs\/1711.03146, 2017."},{"key":"atypb23","doi-asserted-by":"publisher","DOI":"10.1090\/S0273-0979-01-00923-5"},{"key":"atypb24","doi-asserted-by":"crossref","unstructured":"G. Da Prato and J. Zabczyk,\n                      Stochastic Equations in Infinite Dimensions\n                      , Encyclopedia of Mathematics and Its Applications, Cambridge University Press, Cambridge, 1992,https:\/\/doi.org\/10.1017\/CBO9780511666223.","DOI":"10.1017\/CBO9780511666223"},{"key":"atypb25","doi-asserted-by":"publisher","DOI":"10.1002\/nla.2091"},{"key":"atypb26","first-page":"483","author":"Debrabant K.","year":"2014","journal-title":"MO"},{"key":"atypb27","doi-asserted-by":"publisher","DOI":"10.1088\/0951-7715\/13\/4\/310"},{"key":"atypb28","doi-asserted-by":"publisher","DOI":"10.1137\/S0036142996313002"},{"key":"atypb29","doi-asserted-by":"crossref","unstructured":"S. Dolgov, D. Kalise, and K. Kunisch,\n                      Tensor Decomposition Approach for High-Dimensional Hamilton-Jacobi-Bellman Equations\n                      , preprint,https:\/\/arxiv.org\/abs\/1908.01533, 2019.","DOI":"10.1515\/9783110543599"},{"key":"atypb30","unstructured":"M. Eigel, R. Schneider, and P. Trunschke,\n                      Convergence Bounds for Empirical Nonlinear Least-squares\n                      , preprint,https:\/\/arxiv.org\/abs\/2001.00639, 2020."},{"key":"atypb31","doi-asserted-by":"publisher","DOI":"10.1007\/s10444-019-09723-8"},{"key":"atypb32","doi-asserted-by":"crossref","unstructured":"G. Fabbri, F. Gozzi, and A. Swieech,\n                      Stochastic Optimal Control in Infinite Dimension\n                      , Probab. Theory Stoch. Model. 82, Springer, Cham, 2017,https:\/\/doi.org\/10.1007\/978-3-319-53067-3.","DOI":"10.1007\/978-3-319-53067-3"},{"key":"atypb33","doi-asserted-by":"publisher","DOI":"10.1007\/BF01442644"},{"key":"atypb34","doi-asserted-by":"crossref","unstructured":"M. Falcone and R. Ferretti,\n                      Semi-Lagrangian Approximation Schemes for Linear and Hamilton-Jacobi Equations\n                      , SIAM, Philadelphia, 2013,https:\/\/doi.org\/10.1137\/1.9781611973051.","DOI":"10.1137\/1.9781611973051"},{"key":"atypb35","first-page":"407","author":"Fleming W. H.","year":"1999","journal-title":"Dordrecht"},{"key":"atypb36","unstructured":"W. H. Fleming and H. Soner,\n                      Control Markov Processes and Viscosity Solutions\n                      , 2nd ed., Springer, New York, 2006."},{"key":"atypb37","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-016-0240-7"},{"key":"atypb38","unstructured":"I. Goodfellow, Y. Bengio, and A. Courville,\n                      Deep Learning\n                      , MIT Press, Cambridge, 2016,http:\/\/www.deeplearningbook.org."},{"key":"atypb39","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917753994"},{"key":"atypb40","doi-asserted-by":"crossref","unstructured":"W. Hackbusch,\n                      Tensor Spaces and Numerical Tensor Calculus\n                      , Springer Ser. Comput. Math. 42, Springer, Berlin, Heidelberg, 2012,https:\/\/doi.org\/10.1007\/978-3-642-28027-6.","DOI":"10.1007\/978-3-642-28027-6"},{"key":"atypb41","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492914000087"},{"key":"atypb42","first-page":"237","author":"Hackbusch W.","year":"2014","journal-title":"Cham"},{"key":"atypb43","unstructured":"J. Han and W. E,\n                      Deep Learning Approximation for Stochastic Control Problems\n                      , preprint,https:\/\/arxiv.org\/abs\/1611.07422, 2016."},{"key":"atypb44","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1718942115"},{"key":"atypb45","doi-asserted-by":"publisher","DOI":"10.3390\/e16010350"},{"key":"atypb46","doi-asserted-by":"publisher","DOI":"10.1063\/1.5090271"},{"key":"atypb47","doi-asserted-by":"publisher","DOI":"10.3390\/e19110626"},{"key":"atypb48","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/2012\/11\/P11004"},{"key":"atypb49","doi-asserted-by":"publisher","DOI":"10.1137\/100818893"},{"key":"atypb50","doi-asserted-by":"publisher","DOI":"10.1007\/s00211-011-0419-7"},{"key":"atypb51","unstructured":"R. A. Howard,\n                      Dynamic Programming and Markov Processes\n                      , The Technology Press of the MIT, Cambridge MA, John Wiley & Sons, New York, 1960."},{"key":"atypb52","unstructured":"B. Huber and S. Wolf,\n                      Xerus - A General Purpose Tensor Library\n                      ,https:\/\/libxerus.org\/, 2017."},{"key":"atypb53","doi-asserted-by":"publisher","DOI":"10.1063\/1.474863"},{"key":"atypb54","doi-asserted-by":"publisher","DOI":"10.1137\/110856198"},{"key":"atypb55","doi-asserted-by":"publisher","DOI":"10.1016\/j.apm.2012.08.013"},{"key":"atypb56","doi-asserted-by":"publisher","DOI":"10.1016\/j.chemolab.2011.09.001"},{"key":"atypb57","doi-asserted-by":"crossref","unstructured":"F. C. Klebaner,\n                      Introduction to Stochastic Calculus with Applications\n                      , 3rd ed., Imperial College Press, London, 2012,https:\/\/doi.org\/10.1142\/p821.","DOI":"10.1142\/p821"},{"key":"atypb58","doi-asserted-by":"crossref","first-page":"51","DOI":"10.3934\/jcd.2016003","volume":"3","author":"Klus S.","year":"2016","journal-title":"J. Comput. Dynam."},{"key":"atypb59","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.17.5.315"},{"key":"atypb60","doi-asserted-by":"publisher","DOI":"10.1137\/17M115253X"},{"key":"atypb61","doi-asserted-by":"publisher","DOI":"10.1016\/j.laa.2018.01.012"},{"key":"atypb62","doi-asserted-by":"crossref","unstructured":"A. Lasota and M. C. Mackey,\n                      Chaos, Fractals, and Noise: Stochastic Aspects of Dynamics\n                      , 2nd ed., Appl. Math. Sci. 97, Springer, New York, 1994.","DOI":"10.1007\/978-1-4612-4286-4"},{"key":"atypb63","doi-asserted-by":"crossref","unstructured":"J. Lawton and R. W. Beard,\n                      Numerically efficient approximations to the Hamilton-Jacobi-Bellman equation\n                      , in Proceedings of the 1998 American Control Conference. ACC (IEEE Cat. 98CH36207), Vol. 1, 1998, pp. 195-199,https:\/\/doi.org\/10.1109\/ACC.1998.694657.","DOI":"10.1109\/ACC.1998.694657"},{"key":"atypb64","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.10.056"},{"key":"atypb65","doi-asserted-by":"crossref","unstructured":"A. Mauroy, I. Mezi\u0107, and Y. Susuki,\n                      The Koopman Operator in System and Control\n                      , Lect. Notes Control Inf. Sci. 484, Springer, Cham, 2019.","DOI":"10.1007\/978-3-030-35713-9"},{"key":"atypb66","doi-asserted-by":"crossref","unstructured":"M. Nisio,\n                      Stochastic Control Theory\n                      , 2nd ed., Springer, Japan, 2015,https:\/\/doi.org\/10.1007\/978-4-431-55123-2.","DOI":"10.1007\/978-4-431-55123-2"},{"key":"atypb67","doi-asserted-by":"crossref","unstructured":"N. N\u00fcsken and L. Richter,\n                      Solving High-dimensional Hamilton-Jacobi-Bellman PDEs using Neural Networks: Perspectives from the Theory of Controlled Diffusions and Measures on Path Space\n                      , preprint,https:\/\/arxiv.org\/abs\/2005.05409, 2020.","DOI":"10.1007\/s42985-021-00102-x"},{"key":"atypb68","unstructured":"T. E. Oliphant,\n                      A Guide to NumPy\n                      , Trelgol Publishing, 2006."},{"key":"atypb69","doi-asserted-by":"crossref","unstructured":"B. \u00d8ksendal,\n                      Stochastic Differential Equations: An Introduction with Applications\n                      , Springer, Berlin, Heidelberg, 2003.","DOI":"10.1007\/978-3-642-14394-6"},{"key":"atypb70","doi-asserted-by":"publisher","DOI":"10.1137\/090752286"},{"key":"atypb71","doi-asserted-by":"publisher","DOI":"10.1137\/090748330"},{"key":"atypb72","unstructured":"M. Oster, L. Sallandt, and R. Schneider,\n                      Approximating the Stationary Bellman Equation by Hierarchical Tensor Products\n                      , preprint,https:\/\/arxiv.org\/abs\/1911.00279, 2021."},{"key":"atypb73","doi-asserted-by":"publisher","DOI":"10.1063\/1.1570396"},{"key":"atypb74","doi-asserted-by":"crossref","unstructured":"G. A. Pavliotis,\n                      Stochastic Processes and Applications: Diffusion Processes, the Fokker-Planck and Langevin Equations\n                      , Texts Appl. Math. 60, Springer, New York, 2014.","DOI":"10.1007\/978-1-4939-1323-7"},{"key":"atypb75","doi-asserted-by":"publisher","DOI":"10.1080\/17442509208833749"},{"key":"atypb76","doi-asserted-by":"crossref","unstructured":"Y. Peng and J. Li,\n                      Stochastic Optimal Control of Structures\n                      , Springer, 2019.","DOI":"10.1007\/978-981-13-6764-9"},{"key":"atypb77","doi-asserted-by":"crossref","unstructured":"H. Pham, X. Warin, and M. Germain,\n                      Neural Networks-based Backward Scheme for Fully Nonlinear PDEs\n                      , preprint,https:\/\/arxiv.org\/abs\/1908.00412, 2020.","DOI":"10.1007\/s42985-020-00062-8"},{"key":"atypb78","doi-asserted-by":"publisher","DOI":"10.1214\/aop\/1176988477"},{"key":"atypb79","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2018.10.045"},{"key":"atypb80","first-page":"905","volume":"11","author":"Rosasco L.","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"atypb81","doi-asserted-by":"crossref","unstructured":"B. Sch\u00f6lkopf and A. J. Smola,\n                      Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond\n                      , MIT Press, Cambridge, MA, 2001.","DOI":"10.7551\/mitpress\/4175.001.0001"},{"key":"atypb82","doi-asserted-by":"publisher","DOI":"10.1006\/jcph.1999.6231"},{"key":"atypb83","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-012-0547-6"},{"key":"atypb84","doi-asserted-by":"publisher","DOI":"10.1016\/j.jat.2009.01.001"},{"key":"atypb85","doi-asserted-by":"crossref","unstructured":"I. Steinwart and A. Christmann,\n                      Support Vector Machines\n                      , Springer, New York, 2008.","DOI":"10.1007\/978-0-387-77242-4"},{"key":"atypb86","doi-asserted-by":"publisher","DOI":"10.1002\/qua.24898"},{"key":"atypb87","doi-asserted-by":"crossref","unstructured":"D. Tonon, M. Aronna, and D. Kalise,\n                      Optimal Control: Novel Directions and Applications\n                      , Springer, Cham, 2017,https:\/\/doi.org\/10.1007\/978-3-319-60771-9.","DOI":"10.1007\/978-3-319-60771-9"},{"key":"atypb88","unstructured":"P. Trunschke,\n                      Convergence Bounds for Nonlinear Least Squares and Applications to Tensor Recovery\n                      , preprint,https:\/\/arxiv.org\/abs\/2108.05237, 2021."},{"key":"atypb89","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2011.37"},{"key":"atypb90","doi-asserted-by":"crossref","unstructured":"P. Virtanen, R. Gommers, T. E. Oliphant, M. Haberland, T. Reddy, D. Cournapeau, E. Burovski, P. Peterson, W. Weckesser, J. Bright, S. J. van der Walt, M. Brett, J. Wilson, K. Jarrod Millman, N. Mayorov, A. R. J. Nelson, E. Jones, R. Kern, E. Larson, C. Carey, \u0130. Polat, Y. Feng, E. W. Moore, J. Vand erPlas, D. Laxalde, J. Perktold, R. Cimrman, I. Henriksen, E. A. Quintero, C. R. Harris, A. M. Archibald, A. H. Ribeiro, F. Pedregosa, P. van Mulbregt, and SciPy 1.0 Contributors,\n                      SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python\n                      , Nature Methods, 17 (2020), pp. 261-272,https:\/\/doi.org10.1038\/s41592-019-0686-2.","DOI":"10.1038\/s41592-020-0772-5"},{"key":"atypb91","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.83.056215"},{"key":"atypb92","doi-asserted-by":"publisher","DOI":"10.1137\/21M1402303"}],"container-title":["Multiscale Modeling &amp; Simulation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/epubs.siam.org\/doi\/pdf\/10.1137\/20M1372500","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T13:51:35Z","timestamp":1787233895000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/20M1372500"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3]]},"references-count":92,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["10.1137\/20M1372500"],"URL":"https:\/\/doi.org\/10.1137\/20m1372500","relation":{},"ISSN":["1540-3459","1540-3467"],"issn-type":[{"value":"1540-3459","type":"print"},{"value":"1540-3467","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3]]}}}