Indirectly Encoded Sodarace for Artificial Life
Paul Szerlip, Kenneth Owen Stanley · 2013
The aim of this paper is to introduce a lightweight two-dimensional domain for evolving diverse and interesting arti-ficial creatures. The hope is that this domain will fill a need for such an easily-accessible option for researchers who wish to focus more on the evolutionary dynamics of artificial life scenarios than on building simulators and creature encodings. The proposed domain is inspired by Sodarace, a construc-tion set for two-dimensional creatures made of masses and springs. However, unlike the original Sodarace, the indi-rectly encoded Sodarace (IESoR) system introduced in this paper allows evolution to discover a wide range of com-plex and regular ambulating creature morphologies by en-coding them with compositional pattern producing networks (CPPNs), which are an established indirect encoding orig-inally introduced for encoding large-scale neural networks. The result, demonstrated through a technique called novelty search with local competition (which are combined through multiobjective search), is that IESoR can discover a wide breadth of interesting and functional creatures, suggesting its potential utility for future experiments in artificial life.