In large extensive form games with imperfect information, Counterfactual Regret Minimization (CFR) is a popular, iterative algorithm for computing approximate Nash equilibria. Whi...
Richard G. Gibson, Marc Lanctot, Neil Burch, Duane...
In this paper, it is shown how to extract a hypothesis with small risk from the ensemble of hypotheses generated by an arbitrary on-line learning algorithm run on an independent an...
The problem of characterizing learnability is the most basic question of statistical learning theory. A fundamental and long-standing answer, at least for the case of supervised c...
Games are used to evaluate and advance Multiagent and Artificial Intelligence techniques. Most of these games are deterministic with perfect information (e.g. Chess and Checkers)....
We address the problem of evaluating the risk of a given model accurately at minimal labeling costs. This problem occurs in situations in which risk estimates cannot be obtained f...
Christoph Sawade, Niels Landwehr, Steffen Bickel, ...