Ecological approaches to diversity maintenance in evolutionary algorithms

Evolutionary algorithms have shown great promise in evolving novel solutions to real-world problems, but the complexity of those solutions is limited, unlike the apparently open-ended evolution that occurs in the natural world. In part, nature surmounts these complexity barriers with natural ecological dynamics that generate an incredibly diverse array of raw materials for the evolutionary process to build upon, the efficacy of which has been demonstrated in the artificial life system Avida [1]. Here, we introduce a method to integrate ecological factors promoting diversity into an EA using limited resources. We show that populations evolving with this method are able to find and cover multiple niches in a simple string-matching problem, and we analyze the conditions that lead to specialists vs. generalists in this environment. These concepts lay a groundwork for building a more comprehensive ecology-based evolutionary algorithm able to achieve higher levels of complexity.