The enormous growth in wireless communications and miniaturized handheld devices in the last few years, have given rise to a vast range of new services, for heterogeneous user env...
—Reinforcement learning (RL) is a valuable learning method when the systems require a selection of control actions whose consequences emerge over long periods for which input– ...
ELeGI, the European Learning Grid Infrastructure, has the ambitious goal of fostering effective learning and knowledge construction through the dynamic provision of service-based ...
— We aim to perform robust and fast vision-based localization using a pre-existing large map of the scene. A key step in localization is associating the features extracted from t...
In this paper we apply the recent notion of anytime universal intelligence tests to the evaluation of a popular reinforcement learning algorithm, Q-learning. We show that a general...