A "Good" Regulator May Provide a World Model for Intelligent Systems
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. Secondarily, we question the role of purpose or autonomy in this process, demonstrating how physical paradigms 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. Modern definitions of intelligence are found to be inadequate, and can be improved upon by viewing intelligence as embodied non-purposeful good regulation. Overall, we aim to recast the EGRT as a tool for contemporary Artificial Intelligence (AI) architectures by considering the role of good regulation in the implementation of world models.