We introduce relational temporal difference learning as an effective approach to solving multi-agent Markov decision problems with large state spaces. Our algorithm uses temporal ...
If appropriately used, prior knowledge can significantly improve the predictive accuracy of learning algorithms or reduce the amount of training data needed. In this paper we intr...
In this paper, we extend the recently proposed Core Vector Machine algorithm to the regression setting by generalizing the underlying minimum enclosing ball problem. The resultant...
Many real-world classification tasks involve the prediction of multiple, inter-dependent class labels. A prototypical case of this sort deals with prediction of a sequence of labe...
We compute a common feature selection or kernel selection configuration for multiple support vector machines (SVMs) trained on different yet inter-related datasets. The method is ...