English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  The dynamical regime and its importance for evolvability, task performance and generalization

Prosi, J., Khajehabdollahi, S., Giannakakis, E., Martius, G., & Levina, A. (2021). The dynamical regime and its importance for evolvability, task performance and generalization. In Artificial Life Conference Proceedings (pp. 1-9). MIT Press. doi:10.1162/isal_a_00412.

Item is

Basic

show hide
Genre: Conference Paper

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Prosi, J1, 2, Author              
Khajehabdollahi, S, Author
Giannakakis, E1, 2, Author              
Martius, G.3, Author              
Levina, A1, 2, Author              
Affiliations:
1Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              
2Department of Computational Neuroscience, Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_3017468              
3Max Planck Research Group Autonomous Learning, Max Planck Institute for Intelligent Systems, Max Planck Society, ou_2575693              

Content

show
hide
Free keywords: -
 Abstract: It has long been hypothesized that operating close to the critical state is beneficial for natural and artificial systems. We test this hypothesis by evolving foraging agents controlled by neural networks that can change the system's dynamical regime throughout evolution. Surprisingly, we find that all populations, regardless of their initial regime, evolve to be subcritical in simple tasks and even strongly subcritical populations can reach comparable performance. We hypothesize that the moderately subcritical regime combines the benefits of generalizability and adaptability brought by closeness to criticality with the stability of the dynamics characteristic for subcritical systems. By a resilience analysis, we find that initially critical agents maintain their fitness level even under environmental changes and degrade slowly with increasing perturbation strength. On the other hand, subcritical agents originally evolved to the same fitness, were often rendered utterly inadequate and degraded faster. We conclude that although the subcritical regime is preferable for a simple task, the optimal deviation from criticality depends on the task difficulty: for harder tasks, agents evolve closer to criticality. Furthermore, subcritical populations cannot find the path to decrease their distance to criticality. In summary, our study suggests that initializing models near criticality is important to find an optimal and flexible solution.

Details

show
hide
Language(s):
 Dates: 2021-07
 Publication Status: Published online
 Pages: 9
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1162/isal_a_00412
 Degree: -

Event

show
hide
Title: ALIFE 2021: The 2021 Conference on Artificial Life
Place of Event: Praha, Czech Republic
Start-/End Date: 2021-07-19 - 2021-07-23

Legal Case

show

Project information

show

Source 1

show
hide
Title: Artificial Life Conference Proceedings
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: MIT Press
Pages: - Volume / Issue: 2021 Sequence Number: 79 Start / End Page: 1 - 9 Identifier: -