Saved in:
Bibliographic Details
Main Authors: He, Zixuan, Charalambous, Charalambos D., Stavrou, Photios A.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.02812
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909768079114240
author He, Zixuan
Charalambous, Charalambos D.
Stavrou, Photios A.
author_facet He, Zixuan
Charalambous, Charalambos D.
Stavrou, Photios A.
contents This paper studies a finite-horizon Markov decision problem with information-theoretic constraints, where the goal is to minimize directed information from the controlled source process to the control process, subject to stage-wise cost constraints, aiming for an optimal control policy. We propose a new way of approximating a solution for this problem, which is known to be formulated as an unconstrained MDP with a continuous information-state using Q-factors. To avoid the computational complexity of discretizing the continuous information-state space, we propose a truncated rollout-based backward-forward approximate dynamic programming (ADP) framework. Our approach consists of two phases: an offline base policy approximation over a shorter time horizon, followed by an online rollout lookahead minimization, both supported by provable convergence guarantees. We supplement our theoretical results with a numerical example where we demonstrate the cost improvement of the rollout method compared to a previously proposed policy approximation method, and the computational complexity observed in executing the offline and online phases for the two methods.
format Preprint
id arxiv_https___arxiv_org_abs_2509_02812
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Rollout-Based Approximate Dynamic Programming for MDPs with Information-Theoretic Constraints
He, Zixuan
Charalambous, Charalambos D.
Stavrou, Photios A.
Systems and Control
Information Theory
This paper studies a finite-horizon Markov decision problem with information-theoretic constraints, where the goal is to minimize directed information from the controlled source process to the control process, subject to stage-wise cost constraints, aiming for an optimal control policy. We propose a new way of approximating a solution for this problem, which is known to be formulated as an unconstrained MDP with a continuous information-state using Q-factors. To avoid the computational complexity of discretizing the continuous information-state space, we propose a truncated rollout-based backward-forward approximate dynamic programming (ADP) framework. Our approach consists of two phases: an offline base policy approximation over a shorter time horizon, followed by an online rollout lookahead minimization, both supported by provable convergence guarantees. We supplement our theoretical results with a numerical example where we demonstrate the cost improvement of the rollout method compared to a previously proposed policy approximation method, and the computational complexity observed in executing the offline and online phases for the two methods.
title Rollout-Based Approximate Dynamic Programming for MDPs with Information-Theoretic Constraints
topic Systems and Control
Information Theory
url https://arxiv.org/abs/2509.02812