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...
We introduce a constrained mechanism design setting called internal implementation, in which the mechanism designer is explicitly modeled as a player in the game of interest. This...
In this essay we discuss the origin, central results, and some perspectives of algorithmic synthesis of nonterminating reactive programs. We recall the fundamental questions raised...
Agents engaged in noncooperative interaction may seek to achieve a Nash equilibrium; this requires that agents be aware of others’ rewards. Misinformation about rewards leads to...
The implementation of AI in commercial games is usually based on low level designs that makes the control predictable, unadaptive, and non reusable. Reorithms such as HTN or GOAP p...