Hands-On Neuroevolution with Python

The experiment runner function

The runner function has many similarities to the runner function introduced in the previous chapter, but, at the same time, it has unique features that are specific to the NS optimization algorithm.

Here, we consider the most significant parts of the implementation:

1. It starts with selecting a specific seed value for a random number generator, based on the current system time:

    seed = int(time.time())    random.seed(seed)

2. After that, it loads the NEAT algorithm configuration and creates an initial population of genomes:

config = neat.Config(neat.DefaultGenome,                      neat.DefaultReproduction,                      neat.DefaultSpeciesSet,                      neat.DefaultStagnation,                      config_file)p = neat.Population(config) 

3. To hold the intermediate results ...