HybrID: A Hybridization of Indirect and Direct Encodings for Evolutionary Computation
Evolutionary algorithms typically use direct encodings, where each element of the phenotype is specified independently in the genotype. Because direct encodings have difficulty evolving modular and symmetric phenotypes, some researchers use indirect encodings, wherein one genomic element can influence multiple parts of a phenotype. We have previously shown that HyperNEAT, an indirect encoding, outperforms FT-NEAT, a direct-encoding control, on many problems, especially as the regularity of the problem increases. However, HyperNEAT is no panacea; it had difficulty accounting for irregularities in problems. In this paper, we propose a new algorithm, a Hybridized Indirect and Direct encoding (HybrID), which discovers the regularity of a problem with an indirect encoding and accounts for irregularities via a direct encoding. In three different problem domains, HybrID outperforms HyperNEAT in most situations, with performance improvements as large as 40%. Our work suggests that hybridizing indirect and direct encodings can be an effective way to improve the performance of evolutionary algorithms.
KeywordsIndirect (generative developmental) encodings (representations) artificial neural networks neuroevolution evolutionary algorithms
Unable to display preview. Download preview PDF.
- 3.Clune, J., Beckmann, B.E., Ofria, C., Pennock, R.T.: Evolving coordinated quadruped gaits with the hyperneat generative encoding. In: IEEE Congress on Evolutionary Computing (CEC), Trondheim, Norway, pp. 2674–2771 (2009)Google Scholar
- 8.Stanley, K.O., D’Ambrosio, D.B., Gauci, J.: A hypercube-based indirect encoding for evolving large-scale neural networks. Artificial Life 15(2) (2009)Google Scholar
- 10.Clune, J., Ofria, C., Pennock, R.T.: The sensitivity of hyperneat to different geometric representations of a problem. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), Montreal, Canada, pp. 675–682 (2009)Google Scholar