Reinforcement learning induces non-stationarity at several levels. Adaptation to non-stationary environments is of course a desired feature of a fair RL algorithm. Yet, even if the...
HW/SW communication mode makes significant impact on HW/SW communication efficiency. Based on the characteristics of the hardware functions, this paper presents an adaptive HW/SW ...
It was recently proven that sets of points maximizing the hypervolume indicator do not give a good multiplicative approximation of the Pareto front. We introduce a new “logarith...
—This paper proposes a model-based text line segmentation algorithm for machine-printed document images. The model is based on geometric configuration which uses the interline sp...
This paper deals with a congestion control framework for elastic and real-time traffic, where the user's application is associated with a utility function. We allow users to ...