The Pontryagin maximum principle and $Q$-functions in rough environments

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ashkarian, Estepan, Chakraborty, Prakash, Honnappa, Harsha, Tindel, Samy
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917191371194368
author Ashkarian, Estepan
Chakraborty, Prakash
Honnappa, Harsha
Tindel, Samy
author_facet Ashkarian, Estepan
Chakraborty, Prakash
Honnappa, Harsha
Tindel, Samy
contents We derive the Pontryagin maximum principle and $Q$-functions for the relaxed control of noisy rough differential equations. Our main tool is the development of a novel differentiation procedure along `spike variation' perturbations of the optimal state-control pair. We then exploit our development of the infinitesimal $Q$-function (also known as the $q$-function) to derive a policy improvement algorithm for settings with entropic cost constraints.
format Preprint
id arxiv_https___arxiv_org_abs_2601_05354
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle The Pontryagin maximum principle and $Q$-functions in rough environments
Ashkarian, Estepan
Chakraborty, Prakash
Honnappa, Harsha
Tindel, Samy
Optimization and Control
Probability
We derive the Pontryagin maximum principle and $Q$-functions for the relaxed control of noisy rough differential equations. Our main tool is the development of a novel differentiation procedure along `spike variation' perturbations of the optimal state-control pair. We then exploit our development of the infinitesimal $Q$-function (also known as the $q$-function) to derive a policy improvement algorithm for settings with entropic cost constraints.
title The Pontryagin maximum principle and $Q$-functions in rough environments
topic Optimization and Control
Probability
url https://arxiv.org/abs/2601.05354