Abstract. Ensemble methods are popular learning methods that usually increase the predictive accuracy of a classifier though at the cost of interpretability and insight in the deci...
Abstract. We present a new reinforcement learning approach for deterministic continuous control problems in environments with unknown, arbitrary reward functions. The difficulty of...
Abstract. In order to organize huge document collections, labeled hierarchical structures are used frequently. Users are most efficient in navigating such hierarchies, if they refl...
Although Virtual Learning Environments have become popular educational tools, they remain a very active research topic. Two important aspects being discussed for next-generation V...
Abstract. We consider the design of online master algorithms for combining the predictions from a set of experts where the absolute loss of the master is to be close to the absolut...
Jacob Abernethy, John Langford, Manfred K. Warmuth