Abstract. Solving equations in equational theories is a relevant programming paradigm which integrates logic and equational programming into one unified framework. Efficient metho...
This paper introduces a gradient-based reward prediction update mechanism to the XCS classifier system as applied in neuralnetwork type learning and function approximation mechani...
Martin V. Butz, David E. Goldberg, Pier Luca Lanzi
This paper addresses the problem of efficient information theoretic, non-parametric data clustering. We develop a procedure for adapting the cluster memberships of the data pattern...
Robert Jenssen, Deniz Erdogmus, Kenneth E. Hild II...
This paper presents a general method to derive tight rates of convergence for numerical approximations in optimal control when we consider variable resolution grids. We study the ...
A simple learning rule is derived, the VAPS algorithm, which can be instantiated to generate a wide range of new reinforcementlearning algorithms. These algorithms solve a number ...