Markov Blanket Density and Free Energy Minimization

Abstract

This paper presents a continuous, information-theoretic extension of the Free Energy Principle through the concept of Markov blanket density, i.e., a scalar field that quantifies the degree of conditional independence between internal and external states at each point in space (ranging from 0 for full coupling to 1 for full separation). It demonstrates that active inference dynamics, including the minimization of variational and expected free energy, naturally emerge from spatial gradients in this density, making Markov blanket density a necessary foundation for the Free Energy Principle. These ideas are developed through a mathematically framework that links density gradients to precise and testable dynamics, offering a foundation for novel predictions and simulation paradigms.