Universal Learning of Repeated Matrix Games

Simple item page
dc.creatorPoland, Jan
dc.creatorHutter, Marcus
dc.date2005-08-16
dc.date.accessioned2026-07-07T06:33:28Z
dc.date.available2026-07-07T06:33:28Z
dc.descriptionWe 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.
dc.description16 LaTeX pages, 8 eps figures
dc.identifierhttps://arxiv.org/abs/cs/0508073
dc.identifierhttp://arxiv.org/abs/cs/0508073
dc.identifierProc. 15th Annual Machine Learning Conf. of Belgium and The Netherlands (Benelearn 2006) pages 7-14
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/99202
dc.subjectMachine Learning
dc.subjectArtificial Intelligence
dc.titleUniversal Learning of Repeated Matrix Games
dc.typetext

Files

Collections

arXiv