English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  When to Be Critical? Performance and Evolvability in Different Regimes of Neural Ising Agents

Khajehabdollahi, S., Prosi, J., Giannakakis, E., Martius, G., & Levina, A. (2022). When to Be Critical? Performance and Evolvability in Different Regimes of Neural Ising Agents. Artificial Life, 28(4), 458-478. doi:10.1162/artl_a_00383.

Item is

Files

show Files

Creators

show
hide
 Creators:
Khajehabdollahi, S1, Author           
Prosi, J1, Author           
Giannakakis, E1, Author           
Martius, G, Author
Levina, A1, Author           
Affiliations:
1Department of Computational Neuroscience, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_3017468              

Content

show
hide
Free keywords: -
 Abstract: It has long been hypothesized that operating close to the critical state is beneficial for natural and artificial evolutionary systems. We put this hypothesis to test in a system of evolving foraging agents controlled by neural networks that can adapt the agents' dynamical regime throughout evolution. Surprisingly, we find that all populations that discover solutions evolve to be subcritical. By a resilience analysis, we find that there are still benefits of starting the evolution in the critical regime. Namely, initially critical agents maintain their fitness level under environmental changes (for example, in the lifespan) and degrade gracefully when their genome is perturbed. At the same time, initially subcritical agents, even when evolved to the same fitness, are often inadequate to withstand the changes in the lifespan and degrade catastrophically with genetic perturbations. Furthermore, we find the optimal distance to criticality depends on the task complexity. To test it we introduce a hard task and a simple task: For the hard task, agents evolve closer to criticality, whereas more subcritical solutions are found for the simple task. We verify that our results are independent of the selected evolutionary mechanisms by testing them on two principally different approaches: a genetic algorithm and an evolutionary strategy. In summary, our study suggests that although optimal behaviour in the simple task is obtained in a subcritical regime, initializing near criticality is important to be efficient at finding optimal solutions for new tasks of unknown complexity.

Details

show
hide
Language(s):
 Dates: 2022-082022-11
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1162/artl_a_00383
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Artificial Life
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Cambridge, MA : MIT Press
Pages: - Volume / Issue: 28 (4) Sequence Number: - Start / End Page: 458 - 478 Identifier: ISSN: 1064-5462
CoNE: https://pure.mpg.de/cone/journals/resource/954925600667