Abstract--In the Relational Reinforcement learning framework, we propose an algorithm that learns an action model allowing to predict the resulting state of each action in any give...
The stochastic approximation method is behind the solution to many important, actively-studied problems in machine learning. Despite its farreaching application, there is almost n...
The problem of business-IT alignment is of widespread economic concern. As one way of addressing the problem, this paper describes an online system that functions as a kind of Wik...
In huge online games where great numbers of players can be connected at the same time, social interaction is complex and conflicts become part of everyday life. There is a set of ...
Competitive on-line prediction (also known as universal prediction of individual sequences) is a strand of learning theory avoiding making any stochastic assumptions about the way...