A "Good" Regulator May Provide a World Model for Intelligent Systems

TL;DR

This paper revisits the classic Every Good Regulator Theorem (EGRT) to explore how intelligent systems can develop and utilize compressed world models for effective regulation across diverse and complex environments.

Contribution

It modernizes the EGRT framework, extending it to second-order cybernetics and physical phenomena, to inform the development of adaptable world models in autonomous systems.

Findings

EGRT can be recast to include internal models supervising system behavior.

Physical phenomena like temporal criticality inform regulatory relationships.

Tightly-coupled regulation may be challenged in non-uniform environments.

Abstract

One classic idea from the cybernetics literature is the Every Good Regulator Theorem (EGRT). The EGRT provides a means to identify good regulation, or the conditions under which an agent (regulator) can match the dynamical behavior of a system. We reevaluate and recast the EGRT in a modern context to provide insight into how intelligent autonomous learning systems might utilize a compressed global representation (world model). One-to-one mappings between a regulator (R) and the corresponding system (S) provide a reduced representation that preserves useful variety to match all possible outcomes of a system. The EGRT also extends to second-order cybernetics, where an internal model (M) observes the behavior of S and supervises a S-R closed loop mapping. Secondarily, we demonstrate how physical phenomena such as temporal criticality, non-normal denoising, and alternating procedural acquisition can recast behavior as statistical mechanics and yield regulatory relationships. These diverse physical systems challenge the notion of tightly-coupled good regulation when applied to non-uniform and out-of-distribution phenomena. Overall, we aim to recast the EGRT as a potential approach for developing world models that adapt and respond to a wide range of task environments.