An entropy penalized approach for stochastic control problems

DOI10.1137/25M1741364MaRDI QIDQ6864611zbMATH OpenFDO

Authors Thibaut Bourdais, Nadia Oudjane, Francesco Russo

Publication date 3 February 2026

Published in SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/25M1741364

zbMATH Keywords

demand-side managementDonsker-Varadhan representationexponential twistoptimizationrelative entropystochastic control

Mathematics Subject Classification ID

Existence of optimal solutions to problems involving randomness (49J55) Optimality conditions for problems involving randomness (49K45) Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Diffusion processes (60J60) Monte Carlo methods (65C05)

Cites work

• A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem
• A fully backward representation of semilinear PDEs applied to the control of thermostatic loads in power systems
• A survey of the Schrödinger problem and some of its connections with optimal transport
• Adaptive importance sampling in least-squares Monte Carlo algorithms for backward stochastic differential equations
• Advances in filtering and optimal stochastic control. Proceedings of the IFIP-WG 7/1 Working Conference, Cocoyoc, Mexico, February 1-6, 1982
• Approximation error analysis of some deep backward schemes for nonlinear PDEs
• Compactification methods in the control of degenerate diffusions: existence of an optimal control
• Controlled diffusion processes. Translated by A. B. Aries
• Deep backward schemes for high-dimensional nonlinear PDEs
• Duality theorem for the stochastic optimal control problem
• Explicit solution of relative entropy weighted control
• First-order methods in optimization
• scientific article; zbMATH DE number 3872359 (Why is no real title available?)
• scientific article; zbMATH DE number 3954798 (Why is no real title available?)
• scientific article; zbMATH DE number 51724 (Why is no real title available?)
• scientific article; zbMATH DE number 1153603 (Why is no real title available?)
• scientific article; zbMATH DE number 1376935 (Why is no real title available?)
• Importance sampling for backward SDEs
• Iterative Bregman projections for regularized transportation problems
• Machine learning for semi linear PDEs
• Mean field games via controlled martingale problems: existence of Markovian equilibria
• Minimization of the Kullback information of diffusion processes
• Multidimensional diffusion processes.
• Numerical optimization. Theoretical and practical aspects. Transl. from the French
• On the Existence of Optimal Controls
• On the relation between optimal transport and Schrödinger bridges: a stochastic control viewpoint
• Optimal Control and Nonlinear Filtering for Nondegenerate Diffusion Processes
• Optimal transportation under controlled stochastic dynamics
• Solving BSDE with Adaptive Control Variate
• Solving high-dimensional partial differential equations using deep learning
• The <scp>Data‐Driven</scp> Schrödinger Bridge

Cited in

(1)

• Exponential twist of probability measures: drift correction in term of a generalized gradient

This page was built for publication: An entropy penalized approach for stochastic control problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6864611)