Hands-On Neuroevolution with Python

The experiment runner function

The second function configures, executes, and outputs the results of the neuroevolution process. Here, we outline some critical places in the implementation of the experiment runner function:

1. The function begins with the loading of the hyperparameters from the configuration file and spawns the initial population using the loaded configuration:

    # Load configuration.    config = neat.Config(neat.DefaultGenome,                          neat.DefaultReproduction,                         neat.DefaultSpeciesSet,                          neat.DefaultStagnation,                         config_file)    # Create the population, which is the top-level object     # for a NEAT run.    p = neat.Population(config)

2. After that, it configures statistics' reporters to collect the statistics regarding execution of the evolutionary ...