Programs with Stringent Performance Objectives Will Often Exhibit Chaotic Behavior

Abstract

Software for the resolution of certain kind of problems, those that rate high in the Stringent Performance Objectives adjustment factor (IFPUG scheme), can be described using a combination of game theory and autonomous systems. From this description it can be shown that some of those problems exhibit chaotic behavior, an important fact in understanding the functioning of the related software. As a relatively simple example, it is shown that chess exhibits chaotic behavior in its configuration space. This implies that static evaluators in chess programs have intrinsic limitations.