Computer Science – Learning
Scientific paper
2005-08-16
Proc. 15th Annual Machine Learning Conf. of Belgium and The Netherlands (Benelearn 2006) pages 7-14
Computer Science
Learning
16 LaTeX pages, 8 eps figures
Scientific paper
We study and compare the learning dynamics of two universal learning
algorithms, one based on Bayesian learning and the other on prediction with
expert advice. Both approaches have strong asymptotic performance guarantees.
When confronted with the task of finding good long-term strategies in repeated
2x2 matrix games, they behave quite differently.
Hutter Marcus
Poland Jan
No associations
LandOfFree
Universal Learning of Repeated Matrix 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 Universal Learning of Repeated Matrix Games, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Universal Learning of Repeated Matrix Games will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-131017