Efficiently evolving programs through the search for novelty

10 years 4 months ago
Efficiently evolving programs through the search for novelty
A significant challenge in genetic programming is premature convergence to local optima, which often prevents evolution from solving problems. This paper introduces to genetic programming a method that originated in neuroevolution (i.e. the evolution of artificial neural networks) that circumvents the problem of deceptive local optima. The main idea is to search only for behavioral novelty instead of for higher fitness values. Although such novelty search abandons following the gradient of the fitness function, if such gradients are deceptive they may actually occlude paths through the search space towards the objective. Because there are only so many ways to behave, the search for behavioral novelty is often computationally feasible and differs significantly from random search. Counterintuitively, in both a deceptive maze navigation task and the artificial ant benchmark task, genetic programming with novelty search, which ignores the objective, outperforms traditional genetic program...
Joel Lehman, Kenneth O. Stanley
Added 02 Sep 2010
Updated 02 Sep 2010
Type Conference
Year 2010
Authors Joel Lehman, Kenneth O. Stanley
Comments (0)