A version space is a collection of concepts consistent with a given set of positive and negative examples. Mitchell [Mit82] proposed representing a version space by its boundary s...
The problem of consciousness has captured the imagination of philosophers, neuroscientists, and the general public, but has received little attention within AI. However, concepts ...
TD-Gammon is a neural network that is able to teach itself to play backgammon solely by playing against itself and learning from the results. Starting from random initial play, TD...
Efficient Learning Equilibrium (ELE) is a natural solution concept for multi-agent encounters with incomplete information. It requires the learning algorithms themselves to be in ...
This paper presents a multi-agent oriented method for solving CSPs (Constraint Satisfaction Problems). In this method, distributed agents represent variables and a two-dimensional...