 
Summary: Statistical learning control of uncertain
systems: theory and algorithms q
V. Koltchinskii a,*, C.T. Abdallah b
, M. Ariola c
, P. Dorato b
a
Department of Mathematics and Statistics, University of New Mexico, Albuquerque, NM 87131,
USA
b
Department of EECE, University of New Mexico, Albuquerque, NM 87131, USA
c
Dipartimento di Informatica e Sistemistica, Universita degli Studi di Napoli Federico II, Napoli,
Italy
Abstract
It has recently become clear that many control problems are too dicult to admit
analytic solutions. New results have also emerged to show that the computational
complexity of some ``solved'' control problems is prohibitive. Many of these control
problems can be reduced to decidability problems or to optimization questions. Even
though such questions may be too dicult to answer analytically, or may not be an
swered exactly given a reasonable amount of computational resources, researchers have
