We consider model-based reinforcement learning in finite Markov Decision Processes (MDPs), focussing on so-called optimistic strategies. Optimism is usually implemented by carryin...
We propose a novel approach to optimize Partially Observable Markov Decisions Processes (POMDPs) defined on continuous spaces. To date, most algorithms for model-based POMDPs are ...
Josep M. Porta, Nikos A. Vlassis, Matthijs T. J. S...
Abstract. Conventional artificial neural network models lack many physiological properties of the neuron. Current learning algorithms are more concerned to computational performanc...
Stochastic games are a natural model for open reactive processes: one player represents the controller and his opponent represents a hostile environment. The evolution of the syste...
Optimal Component Analysis (OCA) is a linear method for feature extraction and dimension reduction. It has been widely used in many applications such as face and object recognitio...