XCSF is a novel version of learning classifier systems (LCS) which extends the typical concept of LCS by introducing computable classifier prediction. In XCSF Classifier predictio...
We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
We provide an analytical comparison between discounted and average reward temporal-difference (TD) learning with linearly parameterized approximations. We first consider the asympt...
We are interested in this paper to study scheduling problems in systems where many users compete to perform their respective jobs on shared parallel resources. Each user has speci...
Abstract. We present a novel approach for classification using a discretised function representation which is independent of the data locations. We construct the classifier as a su...