Log In Sign Up

Regret Bounds for Learning Decentralized Linear Quadratic Regulator with Partially Nested Information Structure

by   Lintao Ye, et al.

We study the problem of learning decentralized linear quadratic regulator under a partially nested information constraint, when the system model is unknown a priori. We propose an online learning algorithm that adaptively designs a control policy as new data samples from a single system trajectory become available. Our algorithm design uses a disturbance-feedback representation of state-feedback controllers coupled with online convex optimization with memory and delayed feedback. We show that our online algorithm yields a controller that satisfies the desired information constraint and enjoys an expected regret that scales as √(T) with the time horizon T.


page 1

page 2

page 3

page 4


Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems

We study the problem of adaptive control in partially observable linear ...

Regret Minimization in Partially Observable Linear Quadratic Control

We study the problem of regret minimization in partially observable line...

Online Learning for Unknown Partially Observable MDPs

Solving Partially Observable Markov Decision Processes (POMDPs) is hard....

Learning Controllers for Unstable Linear Quadratic Regulators from a Single Trajectory

We present the first approach for learning – from a single trajectory – ...

Minimal Expected Regret in Linear Quadratic Control

We consider the problem of online learning in Linear Quadratic Control s...

Scalable regret for learning to control network-coupled subsystems with unknown dynamics

We consider the problem of controlling an unknown linear quadratic Gauss...

Online Control of Unknown Time-Varying Dynamical Systems

We study online control of time-varying linear systems with unknown dyna...