analiza aiqbench
This paper provides a rigorous variational characterization of Active Inference by decomposing Expected Free Energy into predictive and explicit entropy-correction terms. The authors demonstrate that effective planning requires combining epistemic corrections with specific policy optimization adjustments, with empirical results showing these corrections are critical when observations are merely suggestive rather than decisive. This theoretical clarification offers a clearer framework for implementing EFE-based planning in complex decision-making systems.
What Type of Inference is Active Inference?
arXiv:2606.04935v1 Announce Type: new 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.
Title:What Type of Inference is Active Inference?
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.
Artificial Intelligence (cs.AI)
arXiv:2606.04935 [cs.AI]
(or arXiv:2606.04935v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.04935 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 260 cuvinte
Subiecte conexe
Sophisticated Policies from Epistemic Priors
arXiv · 23 iul. 2026
Belief-Based Maximum Occupancy Principle and Active Inference
arXiv · 1 oct. 2026
What Type of Inference is Active Inference?
arXiv · 12 iun. 2026
Active Inference as a Convex Markov Decision Process
arXiv · 23 iul. 2026