We study the notion of learning in an oblivious changing environment. Existing online learning algorithms which minimize regret are shown to converge to the average of all locally...
k. The model we study can be interpreted as a broad, abstract extension of the well-studied on-line prediction model to a general decision-theoretic setting. We show that the multi...
Our goal is to provide learning mechanisms to game agents so they are capable of adapting to new behaviors based on the actions of other agents. We introduce a new on-line reinfor...
It has recently been shown that only a small number of samples from a low-rank matrix are necessary to reconstruct the entire matrix. We bring this to bear on computer vision prob...
The goal of adaptive game AI is to enhance computercontrolled game-playing agents with (1) the ability to selfcorrect mistakes, and (2) creativity in responding to new situations....
Timor Timuri, Pieter Spronck, H. Jaap van den Heri...