A developmental algorithm for multi-agent swarms with scalable hierarchies

In this paper we present a novel developmental, evolutionary approach for evolving scalable, hierarchical control structures for large (100-1000 agent), multi-agent swarms. Although hierarchical, the control structure does not suffer from single point of failures as do many hierarchical structures. The results show that for some problems using an evolved control hierarchy to guide the agents leads to significantly better performance and scaling properties than fully distributed swarms using standard behavioral rules.