This paper is concerned with the complexity of computing winning strategies for poset games. While it is reasonably clear that such strategies can be computed in PSPACE, we give a ...
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...
—Recently, game theory has been proposed as a tool for cooperative control. Specifically, the interactions of a multiagent distributed system are modeled as a non-cooperative ga...
We present an anytime multiagent learning approach to satisfy any given optimality criterion in repeated game self-play. Our approach is opposed to classical learning approaches fo...
Two-way alternating automata were introduced by Vardi in order to study the satisfiability problem for the modal µ-calculus extended with backwards modalities. In this paper, we ...