A number of representation schemes have been presented for use within Learning Classifier Systems, ranging from binary encodings to neural networks. This paper presents results fr...
Two mathematical and two computational theories from the field of human and animal learning are combined to produce a more general theory of adaptive behavior. The cornerstone of ...
J. J. McDowell, Paul L. Soto, Jesse Dallery, Saule...
The goal of this work is the design and construction of adaptive tutorials based on the application of algorithms for the automatic resolution of problems which can be used to aut...
We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...
We consider the problem of browsing the top ranked portion of the documents returned by an information retrieval system. We describe an interactive relevance feedback agent that a...