betaFeedback

WorksMathematics

Stochastic control representations for extremal solutions of HJB Dirichlet problems with measurable coefficients

Abstract

We study stochastic control problems for uniformly elliptic controlled diffusions on bounded domains whose coefficients are merely measurable in the state variable and whose drift is dominated by an LdL_d-function. The associated Hamilton-Jacobi-Bellman (HJB) Dirichlet problems may have more than one LpL_p-viscosity solution, so that the equation alone does not determine the value function. We show that the control problem selects the minimal solution: for all pp in a range (d0,d)(d_0,d) determined by the spatial dimension, the ellipticity constant and the drift bound, the value function is the minimal LpL_p-viscosity supersolution of the HJB Dirichlet problem. In particular, every continuous LpL_p-viscosity supersolution bounds the optimal cost from above, which yields a one-sided verification theorem without regularity assumptions. We further prove the existence of optimal relaxed control rules for running costs dominated by an LpL_p-function, and the lower semicontinuity of the value function under perturbations of the coefficients. An example shows that upper semicontinuity may fail even when the coefficients are Lipschitz continuous in the control variable and the approximating coefficients are smooth, so that regularization may overestimate the optimal cost. The proof approximates arbitrary supersolutions from below by Sobolev supersolutions of HJB equations whose coefficients are modified only on sets of vanishing measure, and passes to the limit by means of Krylov estimates and martingale problem techniques.

Paper details

vlnc:W_aw3eqj9s
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
arXiv nonexclusive license
Usage

views · 0

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Mathematics

ChatGPT 6, Claude Opus 5.5

View statement
Looking for related papers…