Computer Science – Multiagent Systems
Scientific paper
2009-03-12
Computer Science
Multiagent Systems
8 pages, 2 figures. To Appear in Proceedings of the Eighth International Conference on Autonomous Agents and Multiagent System
Scientific paper
In large systems, it is important for agents to learn to act effectively, but sophisticated multi-agent learning algorithms generally do not scale. An alternative approach is to find restricted classes of games where simple, efficient algorithms converge. It is shown that stage learning efficiently converges to Nash equilibria in large anonymous games if best-reply dynamics converge. Two features are identified that improve convergence. First, rather than making learning more difficult, more agents are actually beneficial in many settings. Second, providing agents with statistical information about the behavior of others can significantly reduce the number of observations needed.
Friedman Eric J.
Halpern Joseph Y.
Kash Ian A.
No associations
LandOfFree
Multiagent Learning in Large Anonymous Games does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Multiagent Learning in Large Anonymous Games, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Multiagent Learning in Large Anonymous Games will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-228153