Hands-On Neuroevolution with Python

Function to evaluate the fitness of all genomes in the population

The first function evaluates the list of all genomes in the population and assigns a fitness score to each of them. This function is passed by reference into the neuroevolution runner of the NEAT-Python library. The source code of this function is as follows:

def eval_genomes(genomes, config):    for genome_id, genome in genomes:        genome.fitness = 0.0        net = neat.nn.FeedForwardNetwork.create(genome, config)        fitness = cart.eval_fitness(net)        if fitness >= config.fitness_threshold:            # do additional steps of evaluation with random initial states            # to make sure that we found stable control strategy rather             # than special case for particular initial state success_runs = evaluate_best_net(net, ...