Evolutionary programming (EP) is one of a class of paradigms for simulating evolution which utilizes the concepts of Darwinian evolution to iteratively generate increasingly appropriate solutions (organisms) in light of a static or dynamically changing environment. This is in sharp contrast to earlier research into artificial intelligence research which largely centered on the search for simple heuristics. Instead of developing a (potentially) complex set of rules which were derived from human experts, EP evolves a set of solutions which exhibit optimal behavior with regard to an environment and desired payoff function. In a most general framework, EP may be considered an optimization technique wherein the algorithm iteratively optimizes behaviors, parameters, or other constructs. As in all optimization algorithms, it is important to note that the point of optimality is completely independent of the search algorithm, and is solely determined by the adaptive topography (i.e. response surface) (Atmar 1992).