We study the problem of control policy design for decentralized state-feedback linear quadratic with a partially nested information structure, when system model is unknown. propose model-based learning solution, which consists two steps. First, we estimate unknown from single trajectory finite length, using least squares estimation. Next, based on estimated model, that satisfies desired structu...

This paper studies the problem of steering a linear system subject to state and input constraints towards goal location that may be inferred only through noisy partial observations. We assume mixed-observable settings, where system's is fully observable environment's defining partially observed. In these planning an infinite-dimensional optimization objective minimize expected cost. show how re...

In this paper the H2-optimal control problem of systems with multiple i/o delays is presented. The problem is first converted to an equivalent H2 regulator problem with multiple delays. The idea is to view the regulator problem in time-domain as a linear quadratic regulator problem with multiple input delays. It is shown that the rational part of the optimal controller has the same dimension as...

This work is devoted to numerical studies of nearly optimal controls of systems driven by singularly perturbed Markov chains. Our approach is based on the ideas of hierarchical controls applicable to many large-scale systems. A discrete-time linear quadratic control problem is examined. Its corresponding limit system is derived. The associated asymptotic properties and near optimality are demon...