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

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.

arXiv comment8 Pages, 7 Figures, Artificial Life Conference 2021

References in corpus (10)

• Weak pairwise correlations imply strongly correlated network states in a neural population
• Scale-free correlations in bird flocks
• Are biological systems poised at criticality?
• Colloquium: Criticality and dynamical scaling in living systems
• Information-based fitness and the emergence of criticality in living systems
• Self-organization toward criticality by synaptic plasticity
• Feedback mechanisms for self-organization to the edge of a phase transition
• A Critical-like Collective State Leads to Long-range Cell Communication in Dictyostelium discoideum Aggregation
• Evolving generalists via dynamic sculpting of rugged landscapes
• Intrinsic noise and deviations from criticality in Boolean gene-regulatory networks

Cited by in corpus (1)

• Self-organization toward criticality by synaptic plasticity