On the Learning Behavior of Stochastic Automata Under a Nonstationary Random Environment

Abstract

We propose a new nonstationary random environment R(C <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> (t,ω),...,C <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">r</sub> (t,ω)), where t represents time and ω ∈ Ω, Ω being the supporting set of a probability measure space (Ω,B,μ). Moreover, the learning performance of the L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">r-1</sub> scheme under R(C <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> (t,ω),..., C <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">r</sub> (t,ω)) is discussed.