RRL is a relational reinforcement learning system based on Q-learning in relational state-action spaces. It aims to enable agents to learn how to act in an environment that has no ...
Abstract. Zigzag pocket machining (or 2D-milling) plays an important role in the manufacturing industry. The objective is to minimize the number of tool retractions in the zigzag m...
Danny Z. Chen, Rudolf Fleischer, Jian Li, Haitao W...
Chang and Lyuu [Chang and Lyuu, 2008] study the spreading of a message in an Erd˝os-R´enyi random graph G(n, p) starting from a set of vertices that are convinced of the message...
We consider finite graphs whose edges are labeled with elements, called colors, taken from a fixed finite alphabet. We study the problem of determining whether there is an infi...
Alessandro Bianco, Marco Faella, Fabio Mogavero, A...
Abstract. This article presents a method for training Dynamic Factor Graphs (DFG) with continuous latent state variables. A DFG includes factors modeling joint probabilities betwee...