Hands-On Neuroevolution with Python

The modified maze experiment runner

Now, when we have implemented all the necessary routines to create co-evolving populations and to evaluate the fitness of individuals within these populations, we are ready to start implementing the experiment runner loop.

The complete details can be found in the run_experiment function in the maze_experiment_safe.py file at https://github.com/PacktPublishing/Hands-on-Neuroevolution-with-Python/blob/master/Chapter9/maze_experiment_safe.py.

Here, we discuss the essential details of the implementation:

1. We start with the creation of the corresponding populations of the co-evolving species:

    robot = create_robot(maze_env, seed=seed)    obj_func = create_objective_fun(seed)

2. Next, we start the evolution loop ...