If we try to increase the number of generations in the previous program, we will realize that the solution does not improve—it is stuck in the (somewhat) suboptimal solution that was reached sometime before generation 200, as shown in the next plot, displaying 500 generations:
Stats of the first program, running for 500 generations
From that point on, the similarity between the average value and the best value indicates that this solution took over the population and therefore we will not see any improvement unless a lucky mutation turns up. In genetic algorithm terms, this means ...
