Showing 2026 · eess.SYShow all
2 papers · 2 filters
eess.SY2026
Scalar Federated Learning for Linear Quadratic Regulator
Mohammadreza Rostami, Shahriar Talebi, Solmaz S. Kia
We propose ScalarFedLQR, a communication-efficient federated algorithm for model-free learning of a common policy in linear quadratic regulator (LQR) control of cooperative agents.…
eess.SY2026
Learning Kalman Policy for Singular Unknown Covariances via Riemannian Regularization
Larsen Bier, Shahriar Talebi
Kalman filtering is a cornerstone of estimation theory, yet learning the optimal filter under unknown and potentially singular noise covariances remains a fundamental challenge. In…