Abstract. In this paper we describe an approach to the representation and implementation of agent-based systems where the behaviour of an individual agent is represented by a set o...
Partially Observable Markov Decision Processes have been studied widely as a model for decision making under uncertainty, and a number of methods have been developed to find the s...
We consider the problem of grasping novel objects in cluttered environments. If a full 3-d model of the scene were available, one could use the model to estimate the stability and...
We introduce the problem of zero-data learning, where a model must generalize to classes or tasks for which no training data are available and only a description of the classes or...
Game developers are faced with the difficult task of creating non-player characters with convincing behavior. This commonly involves an exhaustive specification of their actions i...