A Time Travel to the Early Theory of Evolution Strategies

Starting Position The starting position is the assumption that one has to cope with experimental optimization, i.e., there is no mathematical description or a simulator for the system to be optimized: you are optimizing a real object at hardware level! Since the interrelationships between the variable input parameters and the dependent output behavior are unknown, we encounter a black box situation in the cybernetic sense: In case of a closed system with high complexity the only thing you can do is the measuring of the input/output relations. In experimental optimization the measure for assessing the behavior or quality of the real object varies but the main optimization loop remains the same: You change some settings (i.e. input parameters) of the system according to some strategy and then you measure some physical quantity that reflects the quality of the system. Depending on the measuring the underlying optimization strategy dictates which settings are to be altered and how.