The Dynamics of Reinforcement Learning in Cooperative Multiagent Systems

Caroline Claus and Craig Boutilier

In this paper, we begin to address some of these questions in a very specific context, namely, repeated games in which agents have commoninterests (i.e., cooperative MASs). focus our attention on Q-learning, due to its relative simplicity (certainly not for its general efficacy), and consider some of the factors that may influence the dynamics of multiagent Q-learning, and provide partial answers to these questions.

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.