We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
Global illumination dramatically improves realistic appearance of rendered scenes, but usually it is neglected in VR systems due to its high costs. In this work we present an effi...
Kirill Dmitriev, Thomas Annen, Grzegorz Krawczyk, ...
Automated handling of tutoring and training functions in educational systems requires the availability of articulate domain models. In this article we further develop the applicat...
Kees de Koning, Bert Bredeweg, Joost Breuker, Bob ...
This articles submits the thesis that visual data modeling and programming languages are conveniently conceived as rendering, or ‘styling’, of conventional, textual languages....
The quality of multi-stage stochastic optimization models as they appear in asset liability management, energy planning, transportation, supply chain management, and other applicat...