Free-Energy Minimizing Policies Under Generative Model Ambiguity
Optimization and Control
2026-04-10 v1
Abstract
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.
Cite
@article{arxiv.2604.08222,
title = {Free-Energy Minimizing Policies Under Generative Model Ambiguity},
author = {Arash Shafiei and Caio César Graciani Rodrigues and Giovanni Russo},
journal= {arXiv preprint arXiv:2604.08222},
year = {2026}
}