mlsanityData to 14 Oct 2026

Scalar Federated Learning for Linear Quadratic Regulator

arXiv 2604.05088 ↗First posted 6 Apr 2026eess.SY cs.LG cs.SYcited by 0

Not on the map. Why?

Abstract (arXiv)

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. The method builds on a decomposed projected gradient mechanism, in which each agent communicates only a scalar projection of a local zeroth-order gradient estimate. The server aggregates these scalar messages to reconstruct a global descent direction, reducing per-agent uplink communication from O(d) to O(1), independent of the policy dimension. Crucially, the projection-induced approximation error diminishes as the number of participating agents increases, yielding a favorable scaling law: larger fleets enable more accurate gradient recovery, admit larger stepsizes, and achieve faster linear convergence despite high dimensionality. Under standard regularity conditions for homogeneous agents, all iterates remain stabilizing and the average LQR cost decreases linearly fast. Numerical results demonstrate performance comparable to full-gradient federated LQR with substantially reduced communication, even for heterogeneous (but similar) agents.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 29 references that are in the map. First posted on arXiv 6 Apr 2026.

Builds on

20 of 29 references.

References · 20

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  3. 2019Deep Leakage from Gradientscited by 1,021
  4. 2015An Introduction to Matrix Concentration Inequalitiescited by 397
  5. 2019Challenges of Real-World Reinforcement Learningcited by 291
  6. 2018Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulatorcited by 250
  7. 2017On the Sample Complexity of the Linear Quadratic Regulatorcited by 159
  8. 2021Federated Reinforcement Learning: Techniques, Applications, and Open Challengescited by 81
  9. 2018Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systemscited by 67
  10. 2019LQR through the Lens of First Order Methods: Discrete-time Casecited by 40
  11. 2023Can Forward Gradient Match Backpropagation?cited by 26
  12. 2023Model-free Learning with Heterogeneous Dynamical Systems: A Federated LQR Approachcited by 23
8 more
  1. 2021Global Convergence of Policy Gradient Primal-dual Methods for Risk-constrained LQRscited by 16
  2. 2022Federated Learning Using Variance Reduced Stochastic Gradient for Probabilistically Activated Agentscited by 8
  3. 2024Projected Forward Gradient-Guided Frank-Wolfe Algorithm via Variance Reductioncited by 5
  4. 2023Data-driven Optimal Filtering for Linear Systems with Unknown Noise Covariancescited by 3
  5. 2024Policy Optimization in Control: Geometry and Algorithmic Implicationscited by 2
  6. 2025FedMPDD: Communication-Efficient Federated Learning with Privacy Preservation Attributes via Projected Directional Derivativecited by 2
  7. 2021Data-Driven Structured Policy Iteration for Homogeneous Distributed Systemscited by 1
  8. 2025Harnessing Data from Clustered LQR Systems: Personalized and Collaborative Policy Optimizationcited by 1

Built on by

Not cited yet.