Evolving symmetric and modular neural networks for distributed control

  • Authors:

  • Vinod K. Valsalam;Risto Miikkulainen

  • Affiliations:

  • The University of Texas at Austin, Austin, TX, USA;The University of Texas at Austin, Austin, TX, USA

  • Venue:
  • Proceedings of the 11th Annual conference on Genetic and evolutionary computation
  • Year:
  • 2009

  • Evolving neural networks

    Proceedings of the 11th Annual Conference Companion on Genetic and Evolutionary Computation Conference: Late Breaking Papers

  • Evolving neural networks

    Proceedings of the 12th annual conference companion on Genetic and evolutionary computation

  • Evolving neural networks

    Proceedings of the 13th annual conference companion on Genetic and evolutionary computation

  • Evolving neural networks

    Proceedings of the 15th annual conference companion on Genetic and evolutionary computation

Quantified Score

Hi-index 0.00

Visualization

Abstract

Problems such as the design of distributed controllers are characterized by modularity and symmetry. However, the symmetries useful for solving them are often difficult to determine analytically. This paper presents a nature-inspired approach called Evolution of Network Symmetry and mOdularity (ENSO) to solve such problems. It abstracts properties of generative and developmental systems, and utilizes group theory to represent symmetry and search for it systematically, making it more evolvable than randomly mutating symmetry. This approach is evaluated by evolving controllers for a quadruped robot in physically realistic simulations. On flat ground, the resulting controllers are as effective as those having hand-designed symmetries. However, they are significantly faster when evolved on inclined ground, where the appropriate symmetries are difficult to determine manually. The group-theoretic symmetry mutations of ENSO were also significantly more effective at evolving such controllers than random symmetry mutations. Thus, ENSO is a promising approach for evolving modular and symmetric solutions to distributed control problems, as well as multiagent systems in general.