Potential-based shaping was designed as a way of introducing background knowledge into model-free reinforcement-learning algorithms. By identifying states that are likely to have ...
Gradiance On-Line Accelerated Learning GOAL is a system for creating and automatically grading homeworks, programming laboratories, and tests. Through the concept of root questi...
Axelrod’s original experiments for evolving IPD player strategies involved the use of a basic GA. In this paper we examine how well a simple GA performs against the more recent P...
The main purpose behind the design of this experience is the idea of obtaining useful information to know how the online courses in our University have been developed, and trying t...
We show how to use unlabeled data and a deep belief net (DBN) to learn a good covariance kernel for a Gaussian process. We first learn a deep generative model of the unlabeled da...