The role of diploid genetic algorithms in deceptive problems

Abstract EN

The working of a simple tripartite genetic algorithm (sGA) is based 011 the schema theorem, which implies that an optimal or near-optimal solution is formed by the combination of low-order building blocks ill successive generations.

There exists, however, a class of functions where low-order building blocks may not combine to form higher- order building blocks.

These function are termed as GA-deceptive functions.

In these functions, Sgaigressfi-oni the globally optinial solution and converge to a false solution.

Diploid GA (dGA) has been used their diploidy-dominance operators to support the GA population with a specified level of diversity in the population to prevent convergence problem occurred in sGA.

This point has triggered us to examine whether these diversity-prolonging operators in dGA could tackle deceptive problems more better than sGA.