Most existing dialogue systems have been developed specifically for some predefined task domain(s), thus the issues of extensibility and reuse of the dialogue model are often no...
Abstract— This paper proposes a simulation-based active policy learning algorithm for finite-horizon, partially-observed sequential decision processes. The algorithm is tested i...
Ruben Martinez-Cantin, Nando de Freitas, Arnaud Do...
This paper considers the problem of designing an active observer to plan a sequence of decisions regarding what target to look at, through a foveal-sensing action. We propose a fr...
We consider prediction-model evaluation in the context of marketing-campaign planning. In order to evaluate and compare models with specific campaign objectives in mind, we need t...
Saharon Rosset, Einat Neumann, Uri Eick, Nurit Vat...
Providing accurate image-guidance for soft-tissue interventions remains a complex task. Most of the time, preoperative models and planning data are no more valid during the surgic...