English

Universal Learning of Repeated Matrix Games

Machine Learning 2007-05-23 v1 Artificial Intelligence

Abstract

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.

Keywords

Cite

@article{arxiv.cs/0508073,
  title  = {Universal Learning of Repeated Matrix Games},
  author = {Jan Poland and Marcus Hutter},
  journal= {arXiv preprint arXiv:cs/0508073},
  year   = {2007}
}

Comments

16 LaTeX pages, 8 eps figures