HybrID: a hybridization of indirect and direct encodings for evolutionary computation

Authors:
Jeff Clune;Benjamin E. Beckmann;Robert T. Pennock;Charles Ofria
Affiliations:
Department of Computer Science and Engineering, Michigan State University, East Lansing, MI;Department of Computer Science and Engineering, Michigan State University, East Lansing, MI;Department of Computer Science and Engineering, Michigan State University, East Lansing, MI and Department of Philosophy and Lyman Briggs College;Department of Computer Science and Engineering, Michigan State University, East Lansing, MI
Venue:
ECAL'09 Proceedings of the 10th European conference on Advances in artificial life: Darwin meets von Neumann - Volume Part II
Year:
2009

Citing 9
Cited 2

Automatic definition of modular neural networks

Adaptive Behavior
Evolving neural networks through augmenting topologies

Evolutionary Computation
A Taxonomy for artificial embryogeny

Artificial Life
Compositional pattern producing networks: A novel abstraction of development

Genetic Programming and Evolvable Machines
How a Generative Encoding Fares as Problem-Regularity Decreases

Proceedings of the 10th international conference on Parallel Problem Solving from Nature: PPSN X
A hypercube-based encoding for evolving large-scale neural networks

Artificial Life
The sensitivity of HyperNEAT to different geometric representations of a problem

Proceedings of the 11th Annual conference on Genetic and evolutionary computation
Evolving coordinated quadruped gaits with the HyperNEAT generative encoding

CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Parameter control in evolutionary algorithms

IEEE Transactions on Evolutionary Computation

Investigating whether hyperNEAT produces modular neural networks

Proceedings of the 12th annual conference on Genetic and evolutionary computation
Evolving neural fields for problems with large input and output spaces

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

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 Hyper-NEAT, 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.