A challenge in evolutionary computation is to create representations as evolvable as those in natural evolution. This paper hypothesizes that extinction events, i.e. mass extinctions, can significantly increase evolvability, but only when combined with a divergent search algorithm, i.e. a search driven towards diversity (instead of optimality). Extinctions amplify diversity-generation by creating unpredictable evolutionary bottlenecks. Persisting through multiple such bottlenecks is more likely for lineages that diversify across many niches, resulting in indirect selection pressure for the capacity to evolve. This hypothesis is tested through experiments in two evolutionary robotics domains. The results show that combining extinction events with divergent search increases evolvability, while combining them with convergent search offers no similar benefit. The conclusion is that extinction events may provide a simple and effective mechanism to enhance performance of divergent search algorithms.

PDF

To Appear In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2015), Madrid, Spain 2015.

@inproceedings{lehman:gecco15, title={Enhancing Divergent Search through Extinction Events}, author={Joel Lehman and Risto Miikkulainen}, booktitle={Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2015)}, address={Madrid, Spain}, url="http://www.cs.utexas.edu/users/ai-lab?lehman:gecco15", year={2015} }