We present an actor-critic scheme for reinforcement learning in complex domains. The main contribution is to show that planning and I/O dynamics can be separated such that an intra...
Pedro Alejandro Ortega, Daniel Alexander Braun, Si...
Our goal is to identify families of relations that are useful for reasoning about software. We describe such families using decidable quantifier-free classes of logical constraints...
The maintenance of organisation is a prerequisite for all viable systems in dynamic environments. In many living systems this organisation is, in part, achieved through coordinati...
In this paper, we consider an approach to update nonmonotonic knowledge bases represented as extended logic programs under the answer set semantics. In this approach, new informat...
Thomas Eiter, Michael Fink, Giuliana Sabbatini, Ha...
The goal in image segmentation is to label pixels in an image based on the properties of each pixel and its surrounding region. Recently Content-Based Image Retrieval (CBIR) has e...