Coordinated Reinforcement Learning for Optimizing Mobile Networks

by   Maxime Bouton, et al.

Mobile networks are composed of many base stations and for each of them many parameters must be optimized to provide good services. Automatically and dynamically optimizing all these entities is challenging as they are sensitive to variations in the environment and can affect each other through interferences. Reinforcement learning (RL) algorithms are good candidates to automatically learn base station configuration strategies from incoming data but they are often hard to scale to many agents. In this work, we demonstrate how to use coordination graphs and reinforcement learning in a complex application involving hundreds of cooperating agents. We show how mobile networks can be modeled using coordination graphs and how network optimization problems can be solved efficiently using multi- agent reinforcement learning. The graph structure occurs naturally from expert knowledge about the network and allows to explicitly learn coordinating behaviors between the antennas through edge value functions represented by neural networks. We show empirically that coordinated reinforcement learning outperforms other methods. The use of local RL updates and parameter sharing can handle a large number of agents without sacrificing coordination which makes it well suited to optimize the ever denser networks brought by 5G and beyond.



There are no comments yet.


page 1

page 2

page 3

page 4


Deep Coordination Graphs

This paper introduces the deep coordination graph (DCG) for collaborativ...

Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning

Multi-agent reinforcement learning (MARL) requires coordination to effic...

KnowSR: Knowledge Sharing among Homogeneous Agents in Multi-agent Reinforcement Learning

Recently, deep reinforcement learning (RL) algorithms have made great pr...

Depthwise Convolution for Multi-Agent Communication with Enhanced Mean-Field Approximation

Multi-agent settings remain a fundamental challenge in the reinforcement...

Extendable NFV-Integrated Control Method Using Reinforcement Learning

Network functions virtualization (NFV) enables telecommunications servic...

FireCommander: An Interactive, Probabilistic Multi-agent Environment for Joint Perception-Action Tasks

The purpose of this tutorial is to help individuals use the FireCommande...

Strategic Maneuver and Disruption with Reinforcement Learning Approaches for Multi-Agent Coordination

Reinforcement learning (RL) approaches can illuminate emergent behaviors...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.