When to Be Critical? Performance and Evolvability in Different Regimes of Neural Ising Agents
- 1 January 2022
- journal article
- research article
- Published by MIT Press in Artificial Life
- Vol. 28 (4), 458-478
- https://doi.org/10.1162/artl_a_00383
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.This publication has 40 references indexed in Scilit:
- Scale-free correlations in starling flocksProceedings of the National Academy of Sciences of the United States of America, 2010
- Parameter-exploring policy gradientsNeural Networks, 2010
- Critical Dynamics in Genetic Regulatory Networks: Examples from Four KingdomsPLOS ONE, 2008
- Robustness and evolvability in genetic regulatory networksJournal of Theoretical Biology, 2007
- Perturbation avalanches and criticality in gene regulatory networksJournal of Theoretical Biology, 2006
- Optimal dynamical range of excitable networks at criticalityNature Physics, 2006
- Weak pairwise correlations imply strongly correlated network states in a neural populationNature, 2006
- Real-Time Computation at the Edge of Chaos in Recurrent Neural NetworksNeural Computation, 2004
- Neuronal Avalanches Are Diverse and Precise Activity Patterns That Are Stable for Many Hours in Cortical Slice CulturesJournal of Neuroscience, 2004
- Towards a general theory of adaptive walks on rugged landscapesJournal of Theoretical Biology, 1987