What Type of Inference is Active Inference?

• URL: http://arxiv.org/abs/2606.04935v2
• Date: Thu, 11 Jun 2026 14:11:12 GMT
• Title: What Type of Inference is Active Inference?
• Abstract summary: Active inference casts decision-making as inference, with the Expected Free Energy (EFE) unifying goal-directed and information-seeking behavior.<n>Recent work showed that EFE can be written as Variational Free Energy (VFE) minimization on a generative model augmented with epistemic priors.<n>We show that proper EFE-based planning requires combining these epistemic corrections with a planning correction that turns marginal inference into policy optimization.<n>This clarifies which corrections are needed for cross-entropy planning and for full EFE-based planning.
• Score: 1.1654568410166082
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 full EFE-based planning outperforms ablations that omit either the planning correction or the epistemic corrections.

Related papers

• From Inference to Adaptation: A Unified Optimal Transport View of Vision Language Model [81.67708143891319]
  Vision-language models (VLMs) have demonstrated remarkable zero-shot capabilities yet remain sensitive to real-world distribution shifts during inference.<n>We bridge the detached objectives of inference and adaptation forVLMs, and propose a principled VLM TTA method called algname.<n>Experiments demonstrate the effectiveness and efficiency of our methods, outperforming the best-performing methods by up to 7% with state-of-the-art efficiency.
  arXiv  Detail & Related papers  (2026-08-18T21:44:32Z)
• Expected Free Energy-based Planning as Variational Inference [1.2731778729620478]
  We show that EFE-based planning can be formulated as Variational Free Energy minimization.<n>Our main result demonstrates that minimizing a Variational Free Energy functional with appropriately chosen priors yields a decomposition into expected plan costs.
  arXiv  Detail & Related papers  (2026-06-09T08:09:48Z)
• AEGPO: Adaptive Entropy-Guided Policy Optimization for Diffusion Models [54.56296715999545]
  Reinforcement learning from human feedback shows promise for aligning diffusion and flow models.<n>Policy optimization methods such as GRPO suffer from inefficient and static sampling strategies.<n>We propose Adaptive Entropy-Guided Policy Optimization (AEGPO), a novel dual-signal, dual-level adaptive optimization strategy.
  arXiv  Detail & Related papers  (2026-02-06T16:09:50Z)
• The Procrustean Bed of Time Series: The Optimization Bias of Point-wise Loss [53.542743390809356]
  This paper aims to provide a first-principles analysis of the Expectation of Optimization Bias (EOB)<n>Our analysis reveals a fundamental paradigm paradox: the more deterministic and structured the time series, the more severe the bias by point-wise loss function.<n>We present a concrete solution that simultaneously achieves both principles via DFT or DWT.
  arXiv  Detail & Related papers  (2025-12-21T06:08:22Z)
• Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning [59.11663802446183]
  Flow and diffusion generative models can be adapted to optimize task-specific objectives while preserving prior information.<n>We introduce Flow Density Control (FDC), a simple algorithm that reduces this complex problem to a specific sequence of simpler fine-tuning tasks.<n>We derive convergence guarantees for the proposed scheme under realistic assumptions by leveraging recent understanding of mirror flows.
  arXiv  Detail & Related papers  (2025-11-27T17:19:01Z)
• Active Inference is a Subtype of Variational Inference [0.0]
  We build on theory recasting EFE minimization as variational inference, formally unifying it with Planning-as-Inference and showing the drive as a unique entropic contribution.<n>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.
  arXiv  Detail & Related papers  (2025-11-24T10:14:09Z)
• Expected Free Energy-based Planning as Variational Inference [2.5935401957183846]
  We show that EFE-based planning arises naturally from minimizing a variational free energy functional on a generative model.<n>This result reinforces theoretical consistency with the Free Energy Principle by casting planning under uncertainty itself as a form of variational inference.<n>Our formulation yields policies that jointly support goal achievement and information gain, while incorporating a complexity term that accounts for bounded computational resources.
  arXiv  Detail & Related papers  (2025-04-21T07:09:05Z)
• Platform-Aware Mission Planning [50.56223680851687]
  We introduce the problem of Platform-Aware Mission Planning (PAMP), addressing it in the setting of temporal durative actions.<n>The first baseline approach amalgamates the mission and platform levels, while the second is based on an abstraction-refinement loop.<n>We prove the soundness and completeness of the proposed approaches and validate them experimentally.
  arXiv  Detail & Related papers  (2025-01-16T16:20:37Z)
• Revisiting Essential and Nonessential Settings of Evidential Deep Learning [70.82728812001807]
  Evidential Deep Learning (EDL) is an emerging method for uncertainty estimation. We propose Re-EDL, a simplified yet more effective variant of EDL.
  arXiv  Detail & Related papers  (2024-10-01T04:27:07Z)
• Value of Information and Reward Specification in Active Inference and POMDPs [7.120454740315046]
  Expected free energy (EFE) is a central quantity in active inference. We show that EFE approximates the Bayes optimal RL policy via information value.
  arXiv  Detail & Related papers  (2024-08-13T00:32:05Z)
• Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference [53.419249906014194]
  We study generative modeling for planning with datasets repurposed from offline reinforcement learning.<n>We introduce the Latent Plan Transformer (), a novel model that leverages a latent variable to connect a Transformer-based trajectory generator and the final return.
  arXiv  Detail & Related papers  (2024-02-07T08:18:09Z)
• Planning as In-Painting: A Diffusion-Based Embodied Task Planning Framework for Environments under Uncertainty [56.30846158280031]
  Task planning for embodied AI has been one of the most challenging problems. We propose a task-agnostic method named 'planning as in-painting' The proposed framework achieves promising performances in various embodied AI tasks.
  arXiv  Detail & Related papers  (2023-12-02T10:07:17Z)
• Counterfactual Plans under Distributional Ambiguity [12.139222986297263]
  We study the counterfactual plans under model uncertainty, in which the distribution of the model parameters is partially prescribed. First, we propose an uncertainty quantification tool to compute the lower and upper bounds of the probability of validity for any given counterfactual plan. We then provide corrective methods to adjust the counterfactual plan to improve the validity measure.
  arXiv  Detail & Related papers  (2022-01-29T03:41:47Z)
• Variational Inference with Holder Bounds [68.8008396694788]
  We present a careful analysis of the thermodynamic variational objective (TVO) We reveal how the pathological geometry of thermodynamic curves negatively affects TVO. This motivates our new VI objectives, named the Holder bounds, which flatten the thermodynamic curves and promise to achieve a one-step approximation of the exact marginal log-likelihood.
  arXiv  Detail & Related papers  (2021-11-04T15:35:47Z)
• Active Inference and Epistemic Value in Graphical Models [3.9457043990895904]
  The Free Energy Principle (FEP) postulates that biological agents perceive and interact with their environment in order to minimize a Variational Free Energy (VFE) with respect to a generative model of their environment. This paper approaches epistemic behavior from a constrained Bethe Free Energy (CBFE) perspective. We illustrate resulting behavior of the CBFE by planning and interacting with a simulated T-maze environment.
  arXiv  Detail & Related papers  (2021-09-01T16:43:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.