# Learning Distributed Stabilizing Controllers for Multi-Agent Systems

arXiv: https://arxiv.org/abs/2103.04480 · HTML: https://mlsanity.com/paper/2103.04480/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Mar 2021.

## Built on by (most cited first, 6 of 6)

- [Asynchronous Distributed Reinforcement Learning for LQR Control via Zeroth-Order Block Coordinate Descent](https://mlsanity.com/paper/2107.12416/) (2021)
- [Scalable regret for learning to control network-coupled subsystems with unknown dynamics](https://mlsanity.com/paper/2108.07970/) (2021)
- [Scalable Reinforcement Learning for Linear-Quadratic Control of Networks](https://mlsanity.com/paper/2401.16183/) (2024)
- [A Moreau Envelope Approach for LQR Meta-Policy Estimation](https://mlsanity.com/paper/2403.17364/) (2024)
- [Exploiting inter-agent coupling information for efficient reinforcement learning of cooperative LQR](https://mlsanity.com/paper/2504.20927/) (2025)
- [Federated Learning for Data-Driven Feedforward Control: A Case Study on Vehicle Lateral Dynamics](https://mlsanity.com/paper/2503.02693/) (2025)

## Abstract (arXiv)

We address the problem of model-free distributed stabilization of heterogeneous multi-agent systems using reinforcement learning (RL). Two algorithms are developed. The first algorithm solves a centralized linear quadratic regulator (LQR) problem without knowing any initial stabilizing gain in advance. The second algorithm builds upon the results of the first algorithm, and extends it to distributed stabilization of multi-agent systems with predefined interaction graphs. Rigorous proofs are provided to show that the proposed algorithms achieve guaranteed convergence if specific conditions hold. A simulation example is presented to demonstrate the theoretical results.