Diffusive limit approximation of pure jump optimal ergodic control problems

arXiv2209.15284MaRDI QIDQ6412441FDOQ6412441

Authors: Marc Abeille, Bruno Bouchard, Lorenzo Croissant 

Publication date: 30 September 2022

Abstract: Motivated by the design of fast reinforcement learning algorithms, we study the diffusive limit of a class of pure jump ergodic stochastic control problems. We show that, whenever the intensity of jumps is large enough, the approximation error is governed by the H{"o}lder continuity of the Hessian matrix of the solution to the limit ergodic partial differential equation. This extends to this context the results of [1] obtained for finite horizon problems. We also explain how to construct a first order error correction term under appropriate smoothness assumptions. Finally, we quantify the error induced by the use of the Markov control policy constructed from the numerical finite difference scheme associated to the limit diffusive problem, this seems to be new in the literature and of its own interest. This approach permits to reduce very significantly the numerical resolution cost.

This page was built for publication: Diffusive limit approximation of pure jump optimal ergodic control problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6412441)