Multi-Agent Reinforcement Learning for Power Control in Wireless Networks via Adaptive Graphs

TL;DR

This paper proposes a graph-based multi-agent reinforcement learning approach using graph neural networks to improve power control in wireless networks, enhancing convergence and generalization across various network sizes and configurations.

Contribution

It introduces a novel graph-induced framework with GNNs for adaptive communication among agents, addressing convergence issues in MADRL for wireless network optimization.

Findings

Effective mitigation of convergence challenges in MADRL

Enhanced generalization to larger and diverse networks

Superior performance demonstrated through simulations

Abstract

The ever-increasing demand for high-quality and heterogeneous wireless communication services has driven extensive research on dynamic optimization strategies in wireless networks. Among several possible approaches, multi-agent deep reinforcement learning (MADRL) has emerged as a promising method to address a wide range of complex optimization problems like power control. However, the seamless application of MADRL to a variety of network optimization problems faces several challenges related to convergence. In this paper, we present the use of graphs as communication-inducing structures among distributed agents as an effective means to mitigate these challenges. Specifically, we harness graph neural networks (GNNs) as neural architectures for policy parameterization to introduce a relational inductive bias in the collective decision-making process. Most importantly, we focus on modeling the dynamic interactions among sets of neighboring agents through the introduction of innovative methods for defining a graph-induced framework for integrated communication and learning. Finally, the superior generalization capabilities of the proposed methodology to larger networks and to networks with different user categories is verified through simulations.