lative Novelty to Identify Useful Temporal Abstractions in Reinforcement Learning ?Ozg?ur S?im?sek ozgur@cs.umass.edu Andrew G. Barto barto@cs.umass.edu Department of Computer Scie...
Abstract. Many supervised and unsupervised learning algorithms depend on the choice of an appropriate distance metric. While metric learning for supervised learning tasks has a lon...
Transfer learning can be described as the tion of abstract knowledge from one learning domain or task and the reuse of that knowledge in a related domain or task. In categorizatio...
Kevin R. Canini, Mikhail M. Shashkov, Thomas L. Gr...
Abstract. We propose a novel active learning strategy based on the compression framework of [9] for label ranking functions which, given an input instance, predict a total order ov...
Abstract. Learning of recursive functions refutably means that for every recursive function, the learning machine has either to learn this function or to refute it, i.e., to signal...
Sanjay Jain, Efim B. Kinber, Rolf Wiehagen, Thomas...