Active Inference in Discrete State Spaces from First Principles

2025-11-25

AI Summary

Active inference has long been tightly coupled with the free energy principle (FEP), limiting its conceptual flexibility and interpretability. Method: This work proposes a decoupled framework for active inference in discrete state spaces, reformulating it as a constrained divergence minimization problem—entirely independent of expected free energy. Perception is equivalent to standard variational free energy minimization, while action selection is explicitly optimized via an entropy-regularized objective. The framework integrates mean-field variational inference with information-geometric divergence minimization and embeds probabilistic graphical models to jointly optimize perception and action. Contribution/Results: This is the first formalization of active inference that does not rely on FEP. It preserves behavioral equivalence with classical active inference methods while substantially enhancing interpretability and computational transparency, offering a principled, modular foundation for future theoretical and applied developments in goal-directed behavior modeling.

Technology Category

• Reasoning under Uncertainty: Probabilistic Inference
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Machine Learning: Active Learning

Application Category

• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

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.

Problem

• Clarify active inference by separating it from Free Energy Principle
• Formulate discrete active inference as constrained divergence minimization
• Differentiate action modeling from expected free energy using entropy regularization

Innovation

• Active inference without Free Energy Principle
• Constrained divergence minimization for optimization
• Mean field methods replace expected free energy