Active Inference in Discrete State Spaces from First Principles

TL;DR

This paper clarifies active inference in discrete spaces by formulating it as divergence minimization, avoiding reliance on free energy concepts, and showing its equivalence or differences in perception and action modeling.

Contribution

It introduces a divergence minimization framework for active inference in discrete spaces, separating it from the Free Energy Principle and providing standard solution methods.

Findings

Perception divergence criterion matches variational free energy.

Action divergence differs from expected free energy by an entropy regularizer.

Standard mean field methods can solve the formulated optimization problems.

Abstract

We seek to clarify the concept of active inference by disentangling it from the Free Energy Principle. We show how the optimizations that need to be carried out in order to implement active inference in discrete state spaces can be formulated as constrained divergence minimization problems which can be solved by standard mean field methods that do not appeal to the idea of expected free energy. When it is used to model perception, the perception/action divergence criterion that we propose coincides with variational free energy. When it is used to model action, it differs from an expected free energy functional by an entropy regularizer.