OpenNERO is an open source game platform designed for game AI research. The software package combines features commonly available in modern game engines (such as 3D graphics, phys...
This paper presents a mixed-initiative assistant that supports a subject matter expert to extend the ontology of a learning agent, in order to express the subtle distinctions he ma...
We present an actor-critic scheme for reinforcement learning in complex domains. The main contribution is to show that planning and I/O dynamics can be separated such that an intra...
Pedro Alejandro Ortega, Daniel Alexander Braun, Si...
Most real-world data is stored in relational form. In contrast, most statistical learning methods work with "flat" data representations, forcing us to convert our data i...
Lise Getoor, Nir Friedman, Daphne Koller, Benjamin...
Supervised learning deals with the inference of a distribution over an output or label space $\CY$ conditioned on points in an observation space $\CX$, given a training dataset $D$...