Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Conferences, Workshops, Symposiums, and Seminars
  4. Distributionally Robust Linear Quadratic Control
 
conference paper

Distributionally Robust Linear Quadratic Control

Taskesen, Bahar  
•
Iancu, Dan
•
Kocyigit, Cagil  
Show more
2023
37th Conference on Neural Information Processing Systems (NeurIPS)

Linear-Quadratic-Gaussian (LQG) control is a fundamental control paradigm that is studied in various fields such as engineering, computer science, economics, and neuroscience. It involves controlling a system with linear dynamics and imperfect observations, subject to additive noise, with the goal of minimizing a quadratic cost function for the state and control variables. In this work, we consider a generalization of the discrete-time, finite-horizon LQG problem, where the noise distributions are unknown and belong to Wasserstein ambiguity sets centered at nominal (Gaussian) distributions. The objective is to minimize a worst-case cost across all distributions in the ambiguity set, including non-Gaussian distributions. Despite the added complexity, we prove that a control policy that is linear in the observations is optimal for this problem, as in the classic LQG problem. We propose a numerical solution method that efficiently characterizes this optimal control policy. Our method uses the Frank-Wolfe algorithm to identify the least-favorable distributions within the Wasserstein ambiguity sets and computes the controller's optimal policy using Kalman filter estimation under these distributions.

  • Details
  • Metrics
Type
conference paper
DOI
10.48550/arXiv.2305.17037
Author(s)
Taskesen, Bahar  
Iancu, Dan
Kocyigit, Cagil  
Kuhn, Daniel  
Date Issued

2023

Subjects

Linear-quadratic-Gaussian control

•

Distributionally robust optimization

•

Optimal transport

•

Kalman filter

Editorial or Peer reviewed

REVIEWED

Written at

EPFL

EPFL units
RAO  
Event nameEvent placeEvent date
37th Conference on Neural Information Processing Systems (NeurIPS)

New Orleans

December 10-16, 2023

Available on Infoscience
June 7, 2023
Use this identifier to reference this record
https://infoscience.epfl.ch/handle/20.500.14299/198183
Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés