Genetic Algorithms, Pyevolve, Python

Pyevolve: the effect of Linear Scaling

There’s an interesting graph in Pyevolve which is a heat-like graph of the population raw and fitness scores. In this graph you can note the effect of Linear Scaling over the scores, the raw scores graph is in left and the fitness scaled scores is in the right, this plot uses the Gaussian interpolation method.

linear

This graph feature is very interesting to study the effects of selections and scaling schemes and even to see the propagation of best individuals on the population while evolving, I think this graph should be more explored.