By Topic

Multi-agent learning for control of Internet traffic routing

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $33
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
P. R. J. Tillotson ; Liverpool Univ., UK ; Q. H. Wu ; P. M. Hughes

This paper discusses the use of multi-agent learning to control routing within an Internet. The agents are distributed throughout the network. They use reinforcement learning to adapt their behaviour to network conditions. These agents are based on Watkin's Q-learning algorithm (1992). Simulation results are provided to show the contribution of multi-agent learning to both network reliability and efficiency

Published in:

Learning Systems for Control (Ref. No. 2000/069), IEE Seminar

Date of Conference: