We study decision making in environments where the reward is only partially observed, but can be modeled as a function of an action and an observed context. This setting, known as...
Object class segmentation (OCS) is a key issue in semantic scene labeling and understanding. Its general principle consists of naming object entities into scenes according to thei...
In this paper three different techniques to predict the channel transfer functions of non flat fading channels in multiple antenna systems are investigated. The prediction is don...
We present a reinforcement learning architecture, Dyna-2, that encompasses both samplebased learning and sample-based search, and that generalises across states during both learni...
In this paper, we identify and analyze structural properties which reflect the functionality of a Web site. These structural properties consider the size, the organization, the co...