We introduce a concept of so-called disjoint ordering for any collection of finite sets. It can be viewed as a generalization of a system of distinctive representatives for the s...
We consider model-based reinforcement learning in finite Markov Decision Processes (MDPs), focussing on so-called optimistic strategies. Optimism is usually implemented by carryin...
Abstract--With General Purpose programmable GPUs becoming more and more popular, automated tools are needed to bridge the gap between achievable performance from highly parallel ar...
Abstract-- This paper considers a recently proposed framework for experiment design in system identification for control. We will consider model based control design methods, such ...
We describe a new boosting algorithm that is the first such algorithm to be both smooth and adaptive. These two features make possible performance improvements for many learning ...