Natural policy gradient methods and the covariance matrix adaptation evolution strategy, two variable metric methods proposed for solving reinforcement learning tasks, are contrast...
Presentation of the exponential families, of the mixtures of such distributions and how to learn it. We then present algorithms to simplify mixture model, using Kullback-Leibler di...
The k-Nearest Neighbors algorithm can be easily adapted to classify complex objects (e.g. sets, graphs) as long as a proper dissimilarity function is given over an input space. Bo...
Adam Woznica, Alexandros Kalousis, Melanie Hilario
This work represents the first step towards a task library system in the reinforcement learning domain. Task libraries could be useful in speeding up the learning of new tasks th...
James L. Carroll, Todd S. Peterson, Kevin D. Seppi
We study online learning in an oblivious changing environment. The standard measure of regret bounds the difference between the cost of the online learner and the best decision in...