Learning Minimax-Optimal Terminal State Estimators and Smoothers

Xiangyuan Zhang, Raj Kiriti Velicheti, Tamer Basar

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish (US)
Title of host publicationIFAC-PapersOnLine
EditorsHideaki Ishii, Yoshio Ebihara, Jun-ichi Imura, Masaki Yamakita
PublisherElsevier B.V.
Pages11545-11550
Number of pages6
Edition2
ISBN (Electronic)9781713872344
DOIs
StatePublished - Jul 1 2023
Externally publishedYes
Event22nd IFAC World Congress - Yokohama, Japan
Duration: Jul 9 2023Jul 14 2023

Publication series

NameIFAC-PapersOnLine
Number2
Volume56
ISSN (Electronic)2405-8963

Conference

Conference22nd IFAC World Congress
Country/TerritoryJapan
CityYokohama
Period7/9/237/14/23

Keywords

  • Minimax Filtering
  • Policy Gradient
  • Prediction
  • Sample Complexity
  • Smoothing

ASJC Scopus subject areas

  • Control and Systems Engineering

Fingerprint

Dive into the research topics of 'Learning Minimax-Optimal Terminal State Estimators and Smoothers'. Together they form a unique fingerprint.

Cite this