An entropy penalized approach for stochastic control problems. Complete version - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year : 2023

An entropy penalized approach for stochastic control problems. Complete version

Abstract

In this paper, we propose an alternative technique to dynamic programming for solving stochastic control problems. We consider a weak formulation that is written as an optimization (minimization) problem on the space of probabilities. We then propose a regularized version of this problem obtained by splitting the minimization variables and penalizing the entropy between the two probabilities to be optimized. We show that the regularized problem provides a good approximation of the original problem when the weight of the entropy regularization term is large enough. Moreover, the regularized problem has the advantage of giving rise to optimization problems that are easy to solve in each of the two optimization variables when the other is fixed. We take advantage of this property to propose an alternating optimization algorithm whose convergence to the infimum of the regularized problem is shown. The relevance of this approach is illustrated by solving a high-dimensional stochastic control problem aimed at controlling consumption in electrical systems.
Fichier principal
Vignette du fichier
BOR_AlternateDir2023.pdf (460.17 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04193113 , version 1 (01-09-2023)

Identifiers

Cite

Thibaut Bourdais, Nadia Oudjane, Francesco Russo. An entropy penalized approach for stochastic control problems. Complete version. 2023. ⟨hal-04193113⟩
12 View
36 Download

Altmetric

Share

Gmail Facebook X LinkedIn More