A Measure-Valued HJB Perspective on Bayesian Optimal Adaptive Control
SIAM Journal on Control and Optimization · 31.08.2026 · 64 (4) · 3050-3079
DOI: 10.1137/25m1735081 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Control and Optimization, online erschienen am 12.08.2026. Verfasst von Alexander M. G. Cox und 2 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Gefördert von: Chinese Council Scholarship, Engineering and Physical Sciences Research Council, Vetenskapsrådet.
Abstract (Originalsprache)
We consider a Bayesian adaptive optimal stochastic control problem where a hidden static signal has a nonseparable influence on the drift of a noisy observation. Being allowed to control the specific form of this dependence, we aim at optimizing a cost functional depending on the posterior distribution of the hidden signal. Our setup is in sharp contrast to existing work: we include costs that depend on the full posterior distribution in a form that admits a large class of nonlinear relationships. Expressing the dynamics of this posterior distribution in the observation filtration, we embed our problem into a genuinely infinite-dimensional stochastic control problem using measure-valued martingales. We address this problem by use of viscosity theory and approximation arguments. Specifically, we show equivalence to a corresponding weak formulation, characterize the optimal value of the problem in terms of the unique continuous viscosity solution of an associated HJB equation, and construct a piecewise constant and arbitrarily-close-to-optimal control to our main problem of study. As a by-product of our analysis, we also provide a novel stability result for a class of measure-valued SDEs which we believe is of independent interest.
Förderung
- Chinese Council Scholarship
- Engineering and Physical Sciences Research Council
- Vetenskapsrådet
Zitieren
APA
Cox, A. M. G., Källblad, S., & Wang, C. (2026). A Measure-Valued HJB Perspective on Bayesian Optimal Adaptive Control. SIAM Journal on Control and Optimization, 64(4), 3050-3079. https://doi.org/10.1137/25m1735081
Vancouver
Cox AMG, Källblad S, Wang C. A Measure-Valued HJB Perspective on Bayesian Optimal Adaptive Control. SIAM Journal on Control and Optimization. 2026;64(4):3050-3079. doi:10.1137/25m1735081
BibTeX
@article{Cox2026,
author = {Cox, Alexander M. G. and Källblad, Sigrid and Wang, Chaorui},
title = {A Measure-Valued HJB Perspective on Bayesian Optimal Adaptive Control},
journal = {SIAM Journal on Control and Optimization},
year = {2026},
volume = {64},
number = {4},
pages = {3050--3079},
doi = {10.1137/25m1735081}
}
EUVIMED