Random Indexing is a vector space technique that provides an efficient and scalable approximation to distributional similarity problems. We present experiments showing Random Inde...
We focus on neuro-dynamic programming methods to learn state-action value functions and outline some of the inherent problems to be faced, when performing reinforcement learning in...
In this paper we will show that a restricted class of constrained minimum divergence problems, named generalized inference problems, can be solved by approximating the KL divergen...
ABSTRACT. We present PICPA, a new algorithm for tackling constrained continuous multiobjective problems. The algorithm combines constraint propagation techniques and evolutionary c...
We present empirical evidence that the distribution of e ort required to solve CSPs randomly generated at the 50% satis able point, when using a backtracking algorithm, can be app...