cs.MANov 18, 2026

Resilient Federated LQR over Noisy and Lossy Uplinks via Scalar Communication

Authors: Mohammadreza Rostami, Shahriar Talebi, Solmaz S. Kia

Organizations: University of California, Irvine, CA, US · University of California, Los Angeles, CA, US

Abstract

This paper studies model-free federated learning of a common LQR controller for a fleet of similar systems that communicate with a server over an uplink subject to limited bandwidth, packet dropout, and additive noise. We propose ResiFedLQR, a scalar communication scheme in which each agent sends one real number per packet, with redundancy, instead of full gradient estimates. The scalars can be gradient coordinates, projections of the gradient onto random directions reproduced at the server from a shared seed, or the rollout costs themselves. For the projection encoding, we prove that, with high probability, every iterate stabilizes all agents and the fleet-average cost converges linearly to a neighborhood of the optimum whose radius separates heterogeneity, sampling, and communication effects, and we derive a rule for choosing the number of transmissions from the channel parameters and the fleet size. We then compare the encodings with full-gradient transmission under the same uplink budget and identify the signal-to-noise regime and power constraint under which each is preferable. Numerical experiments on a heterogeneous fleet evaluate stability and convergence under varying noise levels and dropout probabilities.

Figures & tables

Explore similar work

CardsList
  1. Scalar Federated Learning for Linear Quadratic Regulator

    Apr 6, 2026Mohammadreza Rostami, Shahriar Talebi, Solmaz S. KiaFederated LearningLinear Quadratic Regulator

  2. Personalized Rollout Allocation for Federated LQR Policy Optimization under Heterogeneous Process Noise

    Oct 31, 2026Mohammadreza Rostami, Shahriar Talebi, Solmaz S. KiaLinear Quadratic RegulatorFederated Learning

  3. Robust Federated Q-Learning with Almost No Communication

    Aug 24, 2026Sreejeet Maity, Aritra MitraFederated RLQ-Learning