Implementation of a genetic algorithm for two-dimensional arrays using the numpy library for python

The paper implements a genetic algorithm for optimizing two-dimensional arrays using the NumPy library for Python. The main stages of the genetic algorithm, including selection, crossover, and mutation, are analyzed. The influence of various algorithm parameters on its efficiency and convergence rate is studied. It is revealed that the use of NumPy significantly accelerates computational processes due to the vectorization of operations. It is determined that the optimal settings of the algorithm parameters provide the best results when testing on various tasks. It is established that the developed algorithm demonstrates high performance and flexibility in application. The code structure is formed, allowing easy modification of the algorithm for various tasks. Recommendations for further improvement of the algorithm and its adaptation to more complex scenarios are proposed.