Abstract. This paper investigates the methods for learning predictive classifiers based on Bayesian belief networks (BN) – primarily unrestricted Bayesian networks and Bayesian m...
Reachability analysis and simulation tools for high-level nets spend a significant amount of the computing time in performing enabling tests, determining the assignments under whi...
We give the first rigorous upper bounds on the error of temporal difference (td) algorithms for policy evaluation as a function of the amount of experience. These upper bounds pr...
Abstract. Ambiguity in dynamic programming arises from two independent sources, the non-uniqueness of optimal solutions and the particular recursion scheme by which the search spac...
We present a purely functional implementation of the computational differentiation tools — the well known numeric (i.e., not symbolic) techniques which permit one to compute poin...