GasNets and CTRNNs - A Comparison in Terms of Evolvability

摘要

In the last few years a lot of work has been done to discover why GasNets outperform other network types in terms of evolvability. In this work GasNets are again compared to CTRNNs on a shape discrimination task. This task is used as to solve it, or gain an advantage, a controller does not need timers or pattern generators. We show that GasNets are outperformed by CTRNNs in terms of evolvability on this task and possible reasons for the disadvantages of GasNets are investigated. It is shown that, on a simple task where there is no necessity for a timer or pattern generator, there may be other issues which are better tackled by CTRNNs.