I find the implementation of various methods for candidate selection and clustering in the generation of individuals truly interesting. You have incorporated models discussed in class, allowing us to observe differences among them in terms of fitness calls and, most importantly, fitness values.
This approach enables to understand which of the following models performs best and requires a lower number of calls (that is the goal of the lab) . I also found the different crossover functions, that permits to have different genotype division, very intriguing. This allows for the creation of highly distinct genotypes, significantly expanding the search space.
Great job, and the code is well-commented, clear, and precise. The results are easily understandable for the user.
I find the implementation of various methods for candidate selection and clustering in the generation of individuals truly interesting. You have incorporated models discussed in class, allowing us to observe differences among them in terms of fitness calls and, most importantly, fitness values.
This approach enables to understand which of the following models performs best and requires a lower number of calls (that is the goal of the lab) . I also found the different crossover functions, that permits to have different genotype division, very intriguing. This allows for the creation of highly distinct genotypes, significantly expanding the search space.
Great job, and the code is well-commented, clear, and precise. The results are easily understandable for the user.