Learning to Control Under Communication Constraints

Shubham Aggarwal, Raj Kiriti Velicheti, Tamer Basar

Research output: Contribution to journalArticlepeer-review


How to effectively communicate over wireless networks characterized by link failures is central to understanding the fundamental limits in the performance of a networked control system. In this letter, we study the online remote control of linear-quadratic Gaussian systems over unreliable wireless channels (with random packet drops), where the controller is a priori oblivious to the cost parameters. We first reformulate the problem using a semi-definite program and consequently compute a stabilizing policy from its solution. We then derive a O(-T) regret bound (against a best offline policy in hindsight) for a projected online gradient algorithm, where T is the length of the horizon of interest. In the process, we introduce finite-time notions of the classical mean-square stability, which may be of independent interest. Finally, we provide a numerical example to validate the theoretical results, demonstrating the limitations induced by lossy communication on the control performance.

Original languageEnglish (US)
Pages (from-to)2137-2142
Number of pages6
JournalIEEE Control Systems Letters
StatePublished - 2023


  • Networked control systems
  • constrained control
  • optimization

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Control and Optimization


Dive into the research topics of 'Learning to Control Under Communication Constraints'. Together they form a unique fingerprint.

Cite this