paper-with-me

홈 › Papers

What Type of Inference is Active Inference?

2026-06-03 · Wouter W. L. Nuijten, Mykola Lukashchuk, Thijs van de Laar, Bert de Vries arxiv

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 full EFE-based planning outperforms ablations that omit either the planning correction or the epistemic corrections.

📄 PDF Abstract BibTeX arXiv:2606.04935

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Sophisticated Inference

2020-06-07 · Karl Friston, Lancelot Da Costa, Danijar Hafner, Casper Hesp 외

Active inference offers a first principle account of sentient behaviour, from which special and important cases can be derived, e.g., reinforcement learning, active learning, Bayes optimal inference, Bayes optimal design…

Active LearningcounterfactualForm

Addressing the Subsumption Thesis: A Formal Bridge between Microeconomics and Active Inference

2025-03-06 · Noe Kuhn

As a unified theory of sentient behaviour, active inference is formally intertwined with multiple normative theories of optimal behaviour. Specifically, we address what we call the subsumption thesis: The claim that expe…

Prior preferences in active inference agents: soft, hard, and goal shaping

2025-12-02 · Filippo Torresan, Ryota Kanai, Manuel Baltieri arxiv

Active inference proposes expected free energy as an objective for planning and decision-making to adequately balance exploitative and explorative drives in learning agents. The exploitative drive, or what an agent wants…

Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory

2023-10-27 · Niloofar Mireshghallah, Hyunwoo Kim, Xuhui Zhou, Yulia Tsvetkov 외

The interactive use of large language models (LLMs) in AI assistants (at work, home, etc.) introduces a new set of inference-time privacy risks: LLMs are fed different types of information from multiple sources in their …

Privacy Preserving

Active Inference is a Subtype of Variational Inference

2025-11-24 · Wouter W. L. Nuijten, Mykola Lukashchuk arxiv

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 (EF…