A Study on Scalable Representations for Evolutionary Optimization of Ground Structures

Authors

Abstract

This paper presents a comparative study of two indirect representations, a generative and an ontogenic one, on a set of well-known 2D truss design problems. The generative representation encodes the parameters of a trusses design as a mapping from a 2D space. We test both, a trivial generative approach as well as the state-of-the-art NEAT approach. The ontogenic representation encodes truss design parameters as a truss transformation iterated several times, starting from a trivial initial truss. We focus both on the best objective value obtained and the computational cost to reach a given level of optimality. The study shows that the two representations behave very differently. For experimental settings with equal complexity, with the same optimization algorithm and settings, the generative representation provides results which are far from optimal, whereas the ontogenic representation delivers near-optimal solutions. The ontogenic representation is also much less computationally expensive than a direct representation until very close to the global optimum. The study questions the scalability of the generative representations, while the results for the ontogenic representation display a much better scalability.

Keywords

Evolutionary Computation, EC, Ontogenic Representation, Generative Representation, Truss Design, Artificial Neural Networks, ANN, NeuroEvolution of Augmenting Topologies, NEAT, Real Vector-based Search Spaces, Covariance Matrix Adaptation Evolution Strategy, CMA-ES

BibTeX

@article{DWT2011ASOSRFEOOGS,
  author                    = {Alexandre Devert and Thomas Weise and K{\={e}} T{\'{a}}ng},
  title                     = {{A Study on Scalable Representations for Evolutionary Optimization of Ground Structures}},
  publisher                 = {{MIT Press: {Cambridge, MA, USA}}},
  journal                   = {Evolutionary Computation},
  volume                    = {20},
  year                      = {2012},
  url                       = {http://www.marmakoide.org/download/publications/devweita-ecj-preprint.pdf},
  doi                       = {10.1162/EVCO_a_00054},
  key                       = {DWT2011ASOSRFEOOGS},
},

Links