Decomposability and Parallel Computation of Multi-Agent LQR

TL;DR

This paper introduces a parallel reinforcement learning scheme for multi-agent linear quadratic regulator design, leveraging structural properties to decompose the problem into smaller, decoupled subproblems, significantly speeding up learning.

Contribution

It proposes a novel decomposition method exploiting graph structures in LQR for multi-agent systems, enabling parallel RL and computational efficiency.

Findings

Significant speed-up in learning process.

Maintains optimality in homogeneous systems.

Robustness when applied to non-homogeneous systems.

Abstract

Individual agents in a multi-agent system (MAS) may have decoupled open-loop dynamics, but a cooperative control objective usually results in coupled closed-loop dynamics thereby making the control design computationally expensive. The computation time becomes even higher when a learning strategy such as reinforcement learning (RL) needs to be applied to deal with the situation when the agents dynamics are not known. To resolve this problem, we propose a parallel RL scheme for a linear quadratic regulator (LQR) design in a continuous-time linear MAS. The idea is to exploit the structural properties of two graphs embedded in the $Q$ and $R$ weighting matrices in the LQR objective to define an orthogonal transformation that can convert the original LQR design to multiple decoupled smaller-sized LQR designs. We show that if the MAS is homogeneous then this decomposition retains closed-loop optimality. Conditions for decomposability, an algorithm for constructing the transformation matrix, a parallel RL algorithm, and robustness analysis when the design is applied to non-homogeneous MAS are presented. Simulations show that the proposed approach can guarantee significant speed-up in learning without any loss in the cumulative value of the LQR cost.