A Behavioral Input-Output Parametrization of Control Policies with Suboptimality Guarantees

TL;DR

This paper introduces a behavioral input-output parametrization for control policies that accounts for noise in data, providing suboptimality guarantees and analyzing how data noise impacts control performance.

Contribution

It develops a behavioral input-output parametrization framework that does not require state-space parameters and quantifies the effect of data noise on control performance.

Findings

Performance degrades linearly with behavioral model prediction error.

The framework can be combined with impulse response estimators.

It provides suboptimality bounds for LQG control under noisy data.

Abstract

Recent work in data-driven control has revived behavioral theory to perform a variety of complex control tasks, by directly plugging libraries of past input-output trajectories into optimal control problems. Despite recent advances, a key aspect remains unclear: how and to what extent do noise-corrupted data impact control performance? In this work, we provide a quantitative answer to this question. We formulate a Behavioral version of the Input-Output Parametrization (BIOP) for the optimal predictive control of unknown systems using output-feedback dynamic control policies. The main advantages of the proposed framework are that 1) the state-space parameters and the initial state need not be specified for controller synthesis, 2) it can be used in combination with state-of-the-art impulse response estimators, and 3) it allows to recover suboptimality results on learning the Linear Quadratic Gaussian (LQG) controller, therefore revealing, in a quantitative way, how the level of noise in the data affects the performance of behavioral methods. Specifically, it is shown that the performance degrades linearly with the prediction error of the behavioral model. We conclude the paper with numerical experiments to validate our results.