. . "Stepwise Evolutionary Learning using Deep Learned Guidance Functions"^^ . . . . . . . . . . "This paper explores how Learned Guidance Functions (LGFs)\u2014 a pre-training method used to smooth search landscapes\u2014can be used as a fitness function for evolutionary algorithms. A new form of LGF is introduced, based on deep neural network learning, and it is shown how this can be used as a fitness function. This is applied to a test problem: unscrambling the Rubik\u2019s Cube. Comparisons are made with a previous LGF approach based on random forests, and with a baseline approach based on traditional error-based fitness."^^ . . . . . "2019-11-19" . . . . . . . . "11927" . . . . . . .