Abstract. We propose a novel probabilistic method, based on latent variable models, for unsupervised topographic visualisation of dynamically evolving, coherent textual information...
Eligibility traces have been shown to speed reinforcement learning, to make it more robust to hidden states, and to provide a link between Monte Carlo and temporal-difference meth...
Doina Precup, Richard S. Sutton, Satinder P. Singh
Finding the optimal teaching strategy for an individual student is difficult even for an experienced teacher. Identifying and incorporating multiple optimal teaching strategies fo...
— In this paper, we studied how a mobile robot equipped with a 3D laser scanner can start from primitive behaviors and learn to use them to achieve goal-directed behaviors. For t...
Mehmet Remzi Dogar, Maya Cakmak, Emre Ugur, Erol S...
We present a new framework to represent and analyze dynamic facial motions using a decomposable generative model. In this paper, we consider facial expressions which lie on a one d...