The role of degenerate robustness in the evolvability of multi-agent systems in dynamic environments

James M. WHITACRE, Philipp ROHLFSHAGEN, Axel BENDER, Xin YAO

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

15 Citations (Scopus)

Abstract

It has been proposed that degeneracy plays a fundamental role in biological evolution by facilitating robustness and adaptation within heterogeneous and time-variant environments. Degeneracy occurs whenever structurally distinct agents display similar functions within some contexts but unique functions in others. In order to test the broader applicability of this hypothesis, especially to the field of evolutionary dynamic optimisation, we evolve multi-agent systems (MAS) in time-variant environments and investigate how degeneracy amongst agents influences the system's robustness and evolvability. We find that degeneracy freely emerges within our framework, leading to MAS architectures that are robust towards a set of similar environments and quickly adaptable to large environmental changes. Detailed supplementary experiments, aimed particularly at the scaling behaviour of these results, demonstrate a broad range of validity for our findings and suggest that important general distinctions may exist between evolution in degenerate and non-degenerate agent-based systems. © 2010 Springer-Verlag.
Original languageEnglish
Title of host publicationParallel Problem Solving from Nature, PPSN XI : 11th International Conference, Krakov, Poland, September 11-15, 2010, Proceedings, Part I
EditorsRobert SCHAEFER, Carlos COTTA, Joanna KOŁODZIEJ, Günter RUDOLPH
PublisherSpringer Berlin Heidelberg
Pages284-293
Number of pages10
ISBN (Electronic)9783642158445
ISBN (Print)9783642158438
DOIs
Publication statusPublished - 2010
Externally publishedYes
Event11th International Conference on Parallel Problem Solving from Nature, PPSN 2010 - Krakov, Poland
Duration: 11 Sept 201015 Sept 2010

Conference

Conference11th International Conference on Parallel Problem Solving from Nature, PPSN 2010
Country/TerritoryPoland
CityKrakov
Period11/09/1015/09/10

Keywords

  • Neutral Network
  • Dynamic Optimisation Problem
  • Mutational Robustness
  • Cryptic Genetic Variation
  • Adaptive Improvement

Fingerprint

Dive into the research topics of 'The role of degenerate robustness in the evolvability of multi-agent systems in dynamic environments'. Together they form a unique fingerprint.

Cite this