Score: 0

Active Inference in Discrete State Spaces from First Principles

Published: November 25, 2025 | arXiv ID: 2511.20321v1

By: Patrick Kenny

Potential Business Impact:

Helps brains learn by guessing and checking.

Business Areas:
Artificial Intelligence Artificial Intelligence, Data and Analytics, Science and Engineering, Software

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.

Page Count
56 pages

Category
Computer Science:
Artificial Intelligence