Mutual Information Optimal Control of Discrete-Time Linear Systems
Optimization and Control
2025-07-15 v1 Machine Learning
Systems and Control
Systems and Control
Machine Learning
Abstract
In this paper, we formulate a mutual information optimal control problem (MIOCP) for discrete-time linear systems. This problem can be regarded as an extension of a maximum entropy optimal control problem (MEOCP). Differently from the MEOCP where the prior is fixed to the uniform distribution, the MIOCP optimizes the policy and prior simultaneously. As analytical results, under the policy and prior classes consisting of Gaussian distributions, we derive the optimal policy and prior of the MIOCP with the prior and policy fixed, respectively. Using the results, we propose an alternating minimization algorithm for the MIOCP. Through numerical experiments, we discuss how our proposed algorithm works.
Cite
@article{arxiv.2507.04712,
title = {Mutual Information Optimal Control of Discrete-Time Linear Systems},
author = {Shoju Enami and Kenji Kashima},
journal= {arXiv preprint arXiv:2507.04712},
year = {2025}
}