Learning in Multiagent Systems: An Introduction from a Game-Theoretic Perspective
Multiagent Systems
2009-09-29 v1 Artificial Intelligence
Abstract
We introduce the topic of learning in multiagent systems. We first provide a quick introduction to the field of game theory, focusing on the equilibrium concepts of iterated dominance, and Nash equilibrium. We show some of the most relevant findings in the theory of learning in games, including theorems on fictitious play, replicator dynamics, and evolutionary stable strategies. The CLRI theory and n-level learning agents are introduced as attempts to apply some of these findings to the problem of engineering multiagent systems with learning agents. Finally, we summarize some of the remaining challenges in the field of learning in multiagent systems.
Cite
@article{arxiv.cs/0308030,
title = {Learning in Multiagent Systems: An Introduction from a Game-Theoretic Perspective},
author = {Jose M. Vidal},
journal= {arXiv preprint arXiv:cs/0308030},
year = {2009}
}