A key component of any reinforcement learning algorithm is the underlying representation used by the agent. While reinforcement learning (RL) agents have typically relied on hand-...
—In this work we develop a distributed boundary detection algorithm, dubbed Coconut, for 3D wireless sensor networks. It first constructs a tetrahedral structure to delineate th...
Abstract. We study the dynamics of cellular automata, and more specifically their transitivity and expansivity, when the set of configurations is endowed with a shift-invariant (p...
Abstract We develop a distance metric for clustering and classification algorithms which is invariant to affine transformations and includes priors on the transformation parameters...
Metric distances and the more general concept of dissimilarities are widely used tools in instance-based learning methods and very especially in the nearestneighbor classification...