Exercises

1. Try to decrease the value of the params.PopulationSize hyperparameter and see what happens. How did this affect the algorithm's performance?
2. Try to set zero probabilities for the values of the following hyperparameters: params.ActivationFunction_SignedGauss_Prob, params.ActivationFunction_SignedSigmoid_Prob, and params.ActivationFunction_SignedSine_Prob. Was a successful solution found with these changes? How did this affect the configuration of the substrate connections?
3. Print out the winning genome, try to come up with a visualization, then see how your intuition from looking at the genome matches with the visualized CPPN.