English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Conference Paper

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

MPS-Authors
/persons/resource/persons263815

Prosi,  J
Department of Computational Neuroscience, Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons263811

Giannakakis,  E
Institutional Guests, Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons173580

Levina,  A
Institutional Guests, Max Planck Institute for Biological Cybernetics, Max Planck Society;

External Resource
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)
There are no public fulltexts stored in PuRe
Supplementary Material (public)
There is no public supplementary material available
Citation

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. MIT Press. doi:10.1162/isal_a_00412.


Cite as: https://hdl.handle.net/21.11116/0000-0008-387B-0
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.