@inproceedings{e172970497db4f17aecf70dbda46d82a,
title = "Learning Minimax-Optimal Terminal State Estimators and Smoothers",
abstract = "We develop the first model-free policy gradient (PG) algorithm for the minimax state estimation of discrete-time linear dynamical systems, where adversarial disturbances could corrupt both dynamics and measurements. Specifically, the proposed algorithm learns a minimax-optimal solution for three fundamental tasks in robust (minimax) estimation, namely terminal state filtering, terminal state prediction, and smoothing, in a unified fashion. We further establish convergence and finite sample complexity guarantees for the proposed PG algorithm. Additionally, we propose a model-free algorithm to evaluate the attenuation (robustness) level of any estimator or smoother, which serves as a model-free solution to identify the maximum size of the disturbance under which the estimator will still be robust. We demonstrate the effectiveness of the proposed algorithms through extensive numerical experiments.",
keywords = "Minimax Filtering, Policy Gradient, Prediction, Sample Complexity, Smoothing",
author = "Xiangyuan Zhang and Velicheti, {Raj Kiriti} and Tamer Basar",
note = "Research of the authors was supported in part by the US Army Research Laboratory (ARL) Cooperative Agreement W911NF-17-2-0196, and in part by the Army Research Office (ARO) MURI Grant AG285. Research of the authors was supporteΣ in part bΠ the US ArmΠ Research LaboratorΠ (ARL) Cooperative Agreement W911NF-17-∆-0196, anΣ in part bΠ the ArmΠ Research Office (ARO) MURI Grant AG∆85.; 22nd IFAC World Congress ; Conference date: 09-07-2023 Through 14-07-2023",
year = "2023",
month = jul,
day = "1",
doi = "10.1016/j.ifacol.2023.10.447",
language = "English (US)",
series = "IFAC-PapersOnLine",
publisher = "Elsevier B.V.",
number = "2",
pages = "11545--11550",
editor = "Hideaki Ishii and Yoshio Ebihara and Jun-ichi Imura and Masaki Yamakita",
booktitle = "IFAC-PapersOnLine",
edition = "2",
}