We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
Abstract. Good teachers know their students, and exploit this knowledge to adapt or optimise their instruction. Teachers know their students because they interact with them face-to...
Table is a commonly used presentation scheme, especially for describing relational information. However, table understanding remains an open problem. In this paper, we consider th...
ind this work was to extract a relatively abstract level of information from each sentence , using only a limited vocabulary that was hand-crafted to handle a restricted set of tar...
Wendy G. Lehnert, Claire Cardie, David Fisher, Ell...
Designing a secure and dependable system is not just a technical issue, it involves also a deep analysis of the organizational and the social environment in which the system will ...
Yudistira Asnar, Paolo Giorgini, Roberto Bonato, V...