Salvato in:
Dettagli Bibliografici
Autori principali: Polatov, Yishay, Sabag, Oron
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2604.23760
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911623416905728
author Polatov, Yishay
Sabag, Oron
author_facet Polatov, Yishay
Sabag, Oron
contents We study the control of finite-state systems driven by exogenous disturbances, and design causal policies that track the performance of a lookahead benchmark controller. This objective is formalized through dynamic regret, so that favorable disturbance sequences are compared against a strong benchmark, while under adverse disturbance sequences the comparison accounts for the benchmark's degraded performance. This benchmark-relative framework provides an alternative to classical MDP formulations, which assume i.i.d. disturbances, and to robust control approaches, which optimize against worst-case disturbances. Our main result is a nested dynamic-programming solution that computes both the optimal worst-case regret and a regret-optimal policy. In particular, we introduce the Regret-Bellman operator, whose fixed-point value function feeds into a finite-horizon dynamic program. Numerical examples show that regret-optimal policies interpolate nicely between MDP-based and robust controllers without requiring knowledge of the disturbance distribution, and can even outperform both under i.i.d. or structured disturbances.
format Preprint
id arxiv_https___arxiv_org_abs_2604_23760
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Regret-Optimal Control for Finite-State Systems
Polatov, Yishay
Sabag, Oron
Optimization and Control
We study the control of finite-state systems driven by exogenous disturbances, and design causal policies that track the performance of a lookahead benchmark controller. This objective is formalized through dynamic regret, so that favorable disturbance sequences are compared against a strong benchmark, while under adverse disturbance sequences the comparison accounts for the benchmark's degraded performance. This benchmark-relative framework provides an alternative to classical MDP formulations, which assume i.i.d. disturbances, and to robust control approaches, which optimize against worst-case disturbances. Our main result is a nested dynamic-programming solution that computes both the optimal worst-case regret and a regret-optimal policy. In particular, we introduce the Regret-Bellman operator, whose fixed-point value function feeds into a finite-horizon dynamic program. Numerical examples show that regret-optimal policies interpolate nicely between MDP-based and robust controllers without requiring knowledge of the disturbance distribution, and can even outperform both under i.i.d. or structured disturbances.
title Regret-Optimal Control for Finite-State Systems
topic Optimization and Control
url https://arxiv.org/abs/2604.23760