Viscosity-Informed Generative Actor-Critic for High-Dimensional Stochastic Optimal Control

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Golpashin, Alen E., Puthumanaillam, Gokul, Ornik, Melkior, Conway, Bruce A.
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911687884406784
author Golpashin, Alen E.
Puthumanaillam, Gokul
Ornik, Melkior
Conway, Bruce A.
author_facet Golpashin, Alen E.
Puthumanaillam, Gokul
Ornik, Melkior
Conway, Bruce A.
contents We introduce a method for approximating viscosity solutions of stationary degenerate elliptic Hamilton--Jacobi--Bellman equations on bounded domains arising in stochastic exit-time control. Viscosity enforcement is formulated as a min--max problem over an envelope-generated test family parameterized by symmetric positive definite matrices. Under structural and asymptotic assumptions, any uniform limit point of the value function approximations satisfies the viscosity inequalities on the sampled test family. Numerical experiments show that the proposed method reduces empirical viscosity violations and improves robustness under perturbed dynamics.
format Preprint
id arxiv_https___arxiv_org_abs_2605_15668
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Viscosity-Informed Generative Actor-Critic for High-Dimensional Stochastic Optimal Control
Golpashin, Alen E.
Puthumanaillam, Gokul
Ornik, Melkior
Conway, Bruce A.
Optimization and Control
49L25, 49L20, 93E20, 65M99
We introduce a method for approximating viscosity solutions of stationary degenerate elliptic Hamilton--Jacobi--Bellman equations on bounded domains arising in stochastic exit-time control. Viscosity enforcement is formulated as a min--max problem over an envelope-generated test family parameterized by symmetric positive definite matrices. Under structural and asymptotic assumptions, any uniform limit point of the value function approximations satisfies the viscosity inequalities on the sampled test family. Numerical experiments show that the proposed method reduces empirical viscosity violations and improves robustness under perturbed dynamics.
title Viscosity-Informed Generative Actor-Critic for High-Dimensional Stochastic Optimal Control
topic Optimization and Control
49L25, 49L20, 93E20, 65M99
url https://arxiv.org/abs/2605.15668