In many real world tasks, only a small fraction of the available inputs are important at any particular time. This paper presents a method for ascertaining the relevance of inputs...
This paper presents a direct reinforcement learning algorithm, called Finite-Element Reinforcement Learning, in the continuous case, i.e. continuous state-space and time. The eval...
The Virtual Reality Modeling Language (VRML) and the World Wide Web (WWW) offer new opportunities to communicate an architect’s design intent throughout the design process. We h...
This paper presents a shallow dialogue analysis model, aimed at human-human dialogues in the context of staff or business meetings. Four components of the model are defined, and ...
Andrei Popescu-Belis, Alexander Clark, Maria Georg...
Abstract. In contrast to the standard inductive inference setting of predictive machine learning, in real world learning problems often the test instances are already available at ...