Hands-On Neuroevolution with Python

Creation of the population of the objective function candidates

The genotype encoding the phenotype of the objective function candidates must produce phenotype configurations that have at least one input node and two output nodes, as discussed previously. We implement the population creation in the create_objective_fun function as follows:

    params = create_objective_fun_params()    # Genome has one input (0.5) and two outputs (a and b)    genome = NEAT.Genome(0, 1, 1, 2, False,         NEAT.ActivationFunction.TANH, # hidden layer activation        NEAT.ActivationFunction.UNSIGNED_SIGMOID, # output layer activation        1, params, 0)    pop = NEAT.Population(genome, params, True, 1.0, seed)    pop.RNG.Seed(seed)    obj_archive = archive.NoveltyArchive( metric=maze.maze_novelty_metric_euclidean) ...