Abstract
Genetic encodings and their particular properties are known to have a strong influence on the success of evolutionary systems. However, the literature has widely focused on studying the effects that encodings have on performance, i.e., fitness-oriented studies. Notably, this anchoring of the literature to performance is limiting, considering that performance provides bounded information about the behavior of a robot system. In this paper, we investigate how genetic encodings constrain the space of robot phenotypes and robot behavior. In summary, we demonstrate how two generative encodings of different nature lead to very different robots and discuss these differences. Our principal contributions are creating awareness about robot encoding biases, demonstrating how such biases affect evolved morphological, control, and behavioral traits, and finally scrutinizing the trade-offs among different biases.
Highlights
There are two main classes of genetic encodings, namely, direct encodings and indirect encodings; the latter are known as generative encodings
Though the two encodings naturally present an improvement in novelty in generation 49, this novelty is significantly lower with the compositional pattern producing networks (CPPNs) for both median and first quartile
We experimented with two different generative encodings, namely, CPPN and L-System, and investigated their effects on phenotypic and behavioral robot traits
Summary
There are two main classes of genetic encodings, namely, direct encodings and indirect encodings; the latter are known as generative encodings. When working with evolutionary algorithms, it is well known that an encoding benefits from a high locality (Gottlieb and Raidl, 1999; Rothlauf and Goldberg, 1999; Rothlauf and Goldberg, 2000). This means that small changes in the genotype should result in smooth changes to the phenotype, and smooth changes to the fitness (Jones and Forrest, 1995). The importance of reuse is corroborated by research on modularity and its relevance for evo-devo (Bolker, 2000; Kuratani, 2009)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.