Following Tesauro’s work on TD-Gammon, we used a 4000 parameter feed-forward neural network to develop a competitive backgammon evaluation function. Play proceeds by a roll of t...
Supervised learning deals with the inference of a distribution over an output or label space Y conditioned on points in an observation space X , given a training dataset D of pair...
: Processes usually are defined according to underlying standards (ISO 15504, ESA ECSS, ISO 9001, ...) and are described with process steps to be performed by roles and producing r...
Richard Messnarz, Damjan Ekert, Michael Reiner, Ge...
We propose a generic method for obtaining quickly good upper bounds on the minimal value of a multistage stochastic program. The method is based on the simulation of a feasible dec...
Real-Time Strategy games present an interesting problem domain for Artificial Intelligence research. We review current approaches to developing AI systems for such games, noting th...