The Evolution of Heterogeneous Logic: An Analysis of the Buffet Method

Prior work using the Buffet method showed that Markov brains will not only evolve to specialize on different tasks, but when provided with different logical components, will tend to create solutions that favor the data processing units best suited for each task. In this work, we replicate these results using new implementations (a true replication) and conduct a more extensive analysis. We consider not only component usage in aggregate but also look at gate usage in individual solutions. We find that hybrid solutions are common. However, different tasks tend to utilize different component types, and each task results in unique rates of component mixing.