Context Matters: Adaptive Mutation for Grammars

Published in 26th European Conference on Genetic Programming (EuroGP), held in Brno (Czech Republic), 2023

Pedro Carvalho, Jessica Mégane, Nuno Lourenço, and Penousal Machado

Nominated for Best Paper of EuroGP



This work proposes Adaptive Facilitated Mutation, a self-adaptive mutation method for Structured Grammatical Evolution (SGE), biologically inspired by the theory of facilitated variation. In SGE, the genotype of individuals contains a list for each non-terminal of the grammar that defines the search space. In our proposed mutation, each individual contains an array with a different, self-adaptive mutation rate for each non-terminal. We also propose Function Grouped Grammars, a grammar design procedure to enhance the benefits of the propose mutation. Experiments were conducted on three symbolic regression benchmarks using Probabilistic Structured Grammatical Evolution (PSGE), a variant of SGE. Results show our approach is similar or better when compared with the standard grammar and mutation.



Carvalho, P., Mégane, J., Lourenço, N., Machado, P. (2023). Context Matters: Adaptive Mutation for Grammars. In: Pappa, G., Giacobini, M., Vasicek, Z. (eds) Genetic Programming. EuroGP 2023. Lecture Notes in Computer Science, vol 13986. Springer, Cham.