What Type of Inference is Active Inference?
2026-06-03 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors explain how a method called Expected Free Energy (EFE), used for making decisions that balance goals and learning, can be better understood by breaking it down into simpler parts related to uncertainty and planning. They show that by adding certain corrections, the decision-making process becomes clearer and more accurate. Their approach also leads to a new way to plan actions using message passing, a technique for updating beliefs efficiently. They tested their ideas in grid-like environments and found that different corrections matter depending on how clear or uncertain the observations are.
Active InferenceExpected Free Energy (EFE)Variational Free Energy (VFE)Generative ModelEpistemic PriorsPolicy OptimizationMessage PassingPlanningEntropyGrid-world Environment
Authors
Wouter W. L. Nuijten, Mykola Lukashchuk, Thijs van de Laar, Bert de Vries
Abstract
Active inference casts decision-making as inference, with the Expected Free Energy (EFE) unifying goal-directed and information-seeking behavior. Recent work showed that EFE minimization can be written as Variational Free Energy (VFE) minimization on a generative model augmented with epistemic priors. We prove that the VFE of the augmented model can be rewritten as the VFE of the predictive model plus explicit entropy-correction terms, making the EFE contribution transparent. We then show that proper EFE-based planning requires combining these epistemic corrections with a planning correction that turns marginal inference into policy optimization, yielding a full variational characterization of EFE-based planning. This clarifies which corrections are needed for cross-entropy planning and for full EFE-based planning. The same entropy-corrected formulation leads to a detailed message-passing scheme for EFE-based planning together with simpler ablations. Experiments on three grid-world environments show that the planning correction already helps when observations are decisive, whereas the additional observation-side epistemic corrections matter most when observations are merely suggestive.