Graph Neural Networks for Decentralized Controllers

• URL: http://arxiv.org/abs/2003.10280v2
• Date: Wed, 21 Oct 2020 13:54:48 GMT
• Title: Graph Neural Networks for Decentralized Controllers
• Authors: Fernando Gama, Ekaterina Tolstaya, Alejandro Ribeiro
• Abstract summary: Dynamical systems comprised of autonomous agents arise in many relevant problems such as robotics, smart grids, or smart cities. Optimal centralized controllers are readily available but face limitations in terms of scalability and practical implementation. We propose a framework using graph neural networks (GNNs) to learn decentralized controllers from data.
• Score: 171.6642679604005
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dynamical systems comprised of autonomous agents arise in many relevant problems such as multi-agent robotics, smart grids, or smart cities. Controlling these systems is of paramount importance to guarantee a successful deployment. Optimal centralized controllers are readily available but face limitations in terms of scalability and practical implementation. Optimal decentralized controllers, on the other hand, are difficult to find. In this paper, we propose a framework using graph neural networks (GNNs) to learn decentralized controllers from data. While GNNs are naturally distributed architectures, making them perfectly suited for the task, we adapt them to handle delayed communications as well. Furthermore, they are equivariant and stable, leading to good scalability and transferability properties. The problem of flocking is explored to illustrate the potential of GNNs in learning decentralized controllers.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.