This paper analyzes the complexity of on-line reinforcement learning algorithms, namely asynchronous realtime versions of Q-learning and value-iteration, applied to the problem of...
We develop a dynamic, free-form surface model which is useful for representing a broad class of objects with symmetries and topological variability. The new model is based upon sw...
We review a neuroplanner architecture for use in constructing subcognitive controllers and new application that uses it. These controllers have wo important properties: (1) the ab...
Bintrees based on longest edge bisection and hierarchies of diamonds are popular multiresolution techniques on regularly sampled terrain datasets. In this work, we consider sparse...
We present various results of the last twenty years converging towards a homotopical theory of computation. This new theory is based on two crucial notions : polygraphs (introduce...