Compositional Q-Learning (CQ-L) (Singh 1992) is a modular approach to learning to performcomposite tasks made up of several elemental tasks by reinforcement learning. Skills acqui...
Predictive state representations (PSRs) are models that represent the state of a dynamical system as a set of predictions about future events. The existing work with PSRs focuses ...
Britton Wolfe, Michael R. James, Satinder P. Singh
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. ...
Real-world case studies are important to complement the academic skills and knowledge acquired by computer science students. In this paper we relate our experiences with a course ...
Klaas Sikkel, Ton A. M. Spil, Rob L. W. van de Weg
Programs that use animations or visualizations attract student interest and offer feedback that can enhance different learning styles as students work to master programming and pr...