Handling Bloat in GP



Bloat can be defined as an excess of code growth without a corresponding improvement in fitness. This problem has been one of the most intensively studied subjects since the beginnings of Genetic Programming. After briefly addressing past bloat research, this tutorial concentrates on the new Crossover Bias theory and the bloat control method it inspired, Operator Equalisation. Although still recent and requiring improvements, Operator Equalisation has already proven to be more than just a bloat control method. It reveals novel evolutionary dynamics that allow a successful search without code growth, and shows great potential to be extended and integrated into several different elements of the evolutionary process. We will explain in detail how to implement the two variants of Operator Equalisation developed so far, discussing the pros and cons of each. We will also look at some of the evolutionary dynamics of Operator Equalisation, and discuss how they can help us solve the many open questions that still surround such a new technique. Finally, we will address the possible integration of the Operator Equalisation ideas into different elements of the evolution.


Genetic Programming, Bloat, Tutorial


Genetic Programming

PDF File

Cited by

No citations found