Robust Learning-Based Control via Bootstrapped Multiplicative Noise

arXiv2002.10069MaRDI QIDQ6335431

Author name not available (Why is that?)

Publication date: 23 February 2020

Abstract: Despite decades of research and recent progress in adaptive control and reinforcement learning, there remains a fundamental lack of understanding in designing controllers that provide robustness to inherent non-asymptotic uncertainties arising from models estimated with finite, noisy data. We propose a robust adaptive control algorithm that explicitly incorporates such non-asymptotic uncertainties into the control design. The algorithm has three components: (1) a least-squares nominal model estimator; (2) a bootstrap resampling method that quantifies non-asymptotic variance of the nominal model estimate; and (3) a non-conventional robust control design method using an optimal linear quadratic regulator (LQR) with multiplicative noise. A key advantage of the proposed approach is that the system identification and robust control design procedures both use stochastic uncertainty representations, so that the actual inherent statistical estimation uncertainty directly aligns with the uncertainty the robust controller is being designed against. We show through numerical experiments that the proposed robust adaptive controller can significantly outperform the certainty equivalent controller on both expected regret and measures of regret risk.

Has companion code repository: https://github.com/TSummersLab/robust-adaptive-control-multinoise

This page was built for publication: Robust Learning-Based Control via Bootstrapped Multiplicative Noise

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6335431)