DeepAI
Log In Sign Up

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

03/22/2021
by   Jan Prosi, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

03/24/2017

Balancing Selection Pressures, Multiple Objectives, and Neural Modularity to Coevolve Cooperative Agent Behavior

Previous research using evolutionary computation in Multi-Agent Systems ...
03/19/2013

Inferring Fitness in Finite Populations with Moran-like dynamics

Biological fitness is not an observable quantity and must be inferred fr...
10/22/2017

Moderate Environmental Variation Promotes Adaptation in Artificial Evolution

In this paper we analyze the role of environmental variations in the evo...
04/20/2011

Emergent Criticality Through Adaptive Information Processing in Boolean Networks

We study information processing in populations of Boolean networks with ...
11/20/2021

The downside of heterogeneity: How established relations counteract systemic adaptivity in tasks assignments

We study the lock-in effect in a network of task assignments. Agents hav...
11/03/2020

Levels of Coupling in Dyadic Interaction: An Analysis of Neural and Behavioral Complexity

From an enactive approach, some previous studies have demonstrated that ...
08/23/2013

How Did Humans Become So Creative? A Computational Approach

This paper summarizes efforts to computationally model two transitions i...