Distributed Reinforcement Learning for Networked Dynamical Systems

doi:10.1109/TCNS.2023.3332779

Distributed Reinforcement Learning for Networked Dynamical Systems

2024-06-01

0

OA

AI

DOI：10.1109/TCNS.2023.3332779

Original

Original request for help

Save

Abstract

En 中文

In this article, we propose a scalable algorithm for learning distributed optimal controllers for networked dynamical systems. Assuming that the network is comprised of nearly homogeneous subsystems, each subcontroller is trained by the local state and input information from its corresponding subsystem and filtered information from its neighbors. Thus, the costs of both learning and control become independent of the number of subsystems. We show the optimality and convergence of the algorithm for the case when the individual subsystems are identical, based on an algebraic property of such networks. Thereafter, we show the robustness of the algorithm when applied to general heterogeneous networks. The effectiveness of the design is investigated through numerical simulations.

Keywords:

Heuristic algorithms

Network systems

Convergence

Observers

Network topology

Dynamical systems

Topology

Distributed control

distributed reinforcement learning (RL)

networked dynamical systems (NDS)

scalability

Distributed Reinforcement Learning for Networked Dynamical Systems

Abstract

Journal

Organization