Using Collective Intelligence to Route Internet Traffic

TL;DR

This paper introduces Collective Intelligence (COIN), a set of reinforcement learning algorithms designed to optimize internet traffic routing, demonstrating superior performance over existing RL-based shortest path algorithms.

Contribution

The paper develops the theory of COINs and applies it to internet traffic routing, showing improved results over prior RL-based methods.

Findings

COINs outperform previous RL-based routing algorithms

Experiments demonstrate improved traffic routing efficiency

Theoretical framework supports automated design of collective RL systems

Abstract

A COllective INtelligence (COIN) is a set of interacting reinforcement learning (RL) algorithms designed in an automated fashion so that their collective behavior optimizes a global utility function. We summarize the theory of COINs, then present experiments using that theory to design COINs to control internet traffic routing. These experiments indicate that COINs outperform all previously investigated RL-based, shortest path routing algorithms.