[evolvingstuff]

Standard hill-climbing would indeed work better under the assumption that the fitness landscape is fairly unimodal, in terms of local optima. In this problem that may or may not be the case. I think that this is the motivation for a somewhat more "global" search strategy (something that can escape local optima) like genetic algorithms.

That being said, amongst the possible candidates for search strategies, genetic algorithms are fairly lousy. Differential Evolution or CMA-ES would likely work far better.