We present four new reinforcement learning algorithms based on actor-critic and natural-gradient ideas, and provide their convergence proofs. Actor-critic reinforcement learning m...
Shalabh Bhatnagar, Richard S. Sutton, Mohammad Gha...
: The mathematical nature of description logics has meant that domain experts find it hard to understand. This forms a significant impediment to the creation and adoption of ontolo...
Previous research shows that most software systems contain significant amounts of duplicated, or cloned, code. Some clones are exact duplicates of each other, while others differ ...
Abstract. This paper describes a few ideas concerned with geographical information systems (GIS) development. Those ideas come from a GIS development project named GeKon, which is ...
Mobile devices with small screens are becoming more common, and will soon be powerful enough to run desktop software. However, the large interfaces of desktop applications do not ...