Adaptation to criticality through organizational invariance in embodied agents

TL;DR

This paper proposes a simple learning rule enabling embodied agents to adaptively maintain criticality in their neural controllers, leading to behavioral regime transitions in reinforcement learning tasks, which may explain the prevalence of criticality in biological systems.

Contribution

It introduces a novel adaptive mechanism that maintains neural systems at criticality, demonstrated in embodied agents controlling neural networks at critical points.

Findings

Agents' neural controllers reach criticality during tasks

Criticality coincides with behavioral regime transitions

The mechanism offers a potential explanation for biological criticality

Abstract

Many biological and cognitive systems do not operate deep within one or other regime of activity. Instead, they are poised at critical points located at phase transitions in their parameter space. The pervasiveness of criticality suggests that there may be general principles inducing this behaviour, yet there is no well-founded theory for understanding how criticality is generated at a wide span of levels and contexts. In order to explore how criticality might emerge from general adaptive mechanisms, we propose a simple learning rule that maintains an internal organizational structure from a specific family of systems at criticality. We implement the mechanism in artificial embodied agents controlled by a neural network maintaining a correlation structure randomly sampled from an Ising model at critical temperature. Agents are evaluated in two classical reinforcement learning scenarios: the Mountain Car and the Acrobot double pendulum. In both cases the neural controller appears to reach a point of criticality, which coincides with a transition point between two regimes of the agent's behaviour. These results suggest that adaptation to criticality could be used as a general adaptive mechanism in some circumstances, providing an alternative explanation for the pervasive presence of criticality in biological and cognitive systems.