Statistical learning control of uncertain systems: theory and algorithms

It has recently become clear that many control problems are too difficult t o 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 t o optimization questions. Even though such questions may be too difficult t o answer analytically, or may not be answered exactly given a reasonable am ount of computational resources, researchers have shown that we can "approx imately'' answer these questions "most of the time", and have "high confide nce" in the correctness of the answers. (C) 2001 Elsevier Science Inc. All rights reserved.