Saved in:
Bibliographic Details
Main Authors: Shafiei, Arash, Rodrigues, Caio César Graciani, Russo, Giovanni
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.08222
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910116574396416
author Shafiei, Arash
Rodrigues, Caio César Graciani
Russo, Giovanni
author_facet Shafiei, Arash
Rodrigues, Caio César Graciani
Russo, Giovanni
contents We present a variational free-energy formulation for distributionally robust decision-making with ambiguity in the generative model. The formulation, related to a broad range of learning and control frameworks, yields a minimax optimal control problem where maximization is over an uncertainty set that represents ambiguities. We prove that computing the optimal policy requires solving a non-convex minimization problem and propose an algorithm with convergence guarantees to find the solution. The effectiveness of our results is illustrated via simulations on a pendulum swing-up problem.
format Preprint
id arxiv_https___arxiv_org_abs_2604_08222
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Free-Energy Minimizing Policies Under Generative Model Ambiguity
Shafiei, Arash
Rodrigues, Caio César Graciani
Russo, Giovanni
Optimization and Control
We present a variational free-energy formulation for distributionally robust decision-making with ambiguity in the generative model. The formulation, related to a broad range of learning and control frameworks, yields a minimax optimal control problem where maximization is over an uncertainty set that represents ambiguities. We prove that computing the optimal policy requires solving a non-convex minimization problem and propose an algorithm with convergence guarantees to find the solution. The effectiveness of our results is illustrated via simulations on a pendulum swing-up problem.
title Free-Energy Minimizing Policies Under Generative Model Ambiguity
topic Optimization and Control
url https://arxiv.org/abs/2604.08222