Action-graph games (AGGs) are a fully expressive game representation which can compactly express both strict and context-specific independence between players' utility functi...
The Nash equilibria set (NES) is described as an intersection of graphs of best response mappings. The problem of NES computing for multi-matrix extended games is considered. A me...
Here, we present a constrained object recognition task that has been robustly solved largely with simple machine learning methods, using a small corpus of about 100 images taken u...
Monte-Carlo tree search has recently been very successful for game playing particularly for games where the evaluation of a state is difficult to compute, such as Go or General Gam...
We use game theory to analyze meta-learning algorithms. The objective of meta-learning is to determine which algorithm to apply on a given task. This is an instance of a more gene...