Active Inference is a Subtype of Variational Inference

TL;DR

This paper demonstrates that Active Inference can be viewed as a form of variational inference, introducing a scalable message-passing algorithm that enhances decision-making under uncertainty in complex environments.

Contribution

It presents a novel message-passing scheme that unifies Active Inference with variational inference, enabling scalable planning in high-dimensional factored-state MDPs.

Findings

Unified Active Inference and variational inference framework.

Developed a scalable message-passing algorithm.

Improved planning in high-dimensional environments.

Abstract

Automated decision-making under uncertainty requires balancing exploitation and exploration. Classical methods treat these separately using heuristics, while Active Inference unifies them through Expected Free Energy (EFE) minimization. However, EFE minimization is computationally expensive, limiting scalability. We build on recent theory recasting EFE minimization as variational inference, formally unifying it with Planning-as-Inference and showing the epistemic drive as a unique entropic contribution. Our main contribution is a novel message-passing scheme for this unified objective, enabling scalable Active Inference in factored-state MDPs and overcoming high-dimensional planning intractability.