Criticality as It Could Be: organizational invariance as self-organized criticality in embodied agents
This work addresses the challenge of understanding criticality in biological and cognitive systems through a novel synthetic method, though it is incremental in applying known principles to embodied agents.
The paper tackled the problem of designing adaptive agents that self-organize to critical points by using a synthetic approach that maintains organizational invariance, achieving criticality in neural controllers for two reinforcement learning tasks (Mountain Car and Acrobot) where it coincided with behavioral regime transitions and maximized mutual information.
This paper outlines a methodological approach for designing adaptive agents driving themselves near points of criticality. Using a synthetic approach we construct a conceptual model that, instead of specifying mechanistic requirements to generate criticality, exploits the maintenance of an organizational structure capable of reproducing critical behavior. Our approach exploits the well-known principle of universality, which classifies critical phenomena inside a few universality classes of systems independently of their specific mechanisms or topologies. In particular, we implement an artificial embodied agent controlled by a neural network maintaining a correlation structure randomly sampled from a lattice Ising model at a critical point. We evaluate the agent in two classical reinforcement learning scenarios: the Mountain Car benchmark and the Acrobot double pendulum, finding that in both cases the neural controller reaches a point of criticality, which coincides with a transition point between two regimes of the agent's behaviour, maximizing the mutual information between neurons and sensorimotor patterns. Finally, we discuss the possible applications of this synthetic approach to the comprehension of deeper principles connected to the pervasive presence of criticality in biological and cognitive systems.