Active Inference in Discrete State Spaces from First Principles

• URL: http://arxiv.org/abs/2511.20321v1
• Date: Tue, 25 Nov 2025 13:54:10 GMT
• Title: Active Inference in Discrete State Spaces from First Principles
• Authors: Patrick Kenny,
• Abstract summary: We seek to clarify the concept of active inference by disentangling it from the Free Energy Principle.<n>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.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• FEAT: Free energy Estimators with Adaptive Transport [56.65918359070768]
  We present Free energy Estimators with Adaptive Transport (FEAT), a novel framework for free energy estimation.<n>FEAT provides consistent, minimum-variance estimators based on escorted Jarzynski equality and controlled Crooks theorem.<n> Experimental validation on toy examples, molecular simulations, and quantum field theory demonstrates improvements over existing learning-based methods.
  arXiv  Detail & Related papers  (2025-04-15T15:16:18Z)
• Reframing the Expected Free Energy: Four Formulations and a Unification [3.9121134770873733]
  Active inference is based on the expected free energy. This paper seek to formalize the problem of deriving these formulations from a single root expected free energy definition.
  arXiv  Detail & Related papers  (2024-02-22T11:38:43Z)
• Sampling with Mollified Interaction Energy Descent [57.00583139477843]
  We present a new optimization-based method for sampling called mollified interaction energy descent (MIED) MIED minimizes a new class of energies on probability measures called mollified interaction energies (MIEs) We show experimentally that for unconstrained sampling problems our algorithm performs on par with existing particle-based algorithms like SVGD.
  arXiv  Detail & Related papers  (2022-10-24T16:54:18Z)
• Deriving time-averaged active inference from control principles [6.625391013374865]
  Active inference offers a principled account of behavior as minimizing average sensory surprise over time. We derive an infinite-horizon, average-surprise formulation of active inference from optimal control principles.
  arXiv  Detail & Related papers  (2022-08-22T21:20:04Z)
• Correspondence Between the Energy Equipartition Theorem in Classical Mechanics and its Phase-Space Formulation in Quantum Mechanics [62.997667081978825]
  In quantum mechanics, the energy per degree of freedom is not equally distributed. We show that in the high-temperature regime, the classical result is recovered.
  arXiv  Detail & Related papers  (2022-05-24T20:51:03Z)
• Open-system approach to nonequilibrium quantum thermodynamics at arbitrary coupling [77.34726150561087]
  We develop a general theory describing the thermodynamical behavior of open quantum systems coupled to thermal baths. Our approach is based on the exact time-local quantum master equation for the reduced open system states.
  arXiv  Detail & Related papers  (2021-09-24T11:19:22Z)
• Active inference, Bayesian optimal design, and expected utility [1.433758865948252]
  We describe how active inference combines Bayesian decision theory and optimal Bayesian design principles to minimize expected free energy. It is this aspect of active inference that allows for the natural emergence of information-seeking behavior. Our Tmaze simulations show optimizing expected free energy produces goal-directed information-seeking behavior while optimizing expected utility induces purely exploitive behavior.
  arXiv  Detail & Related papers  (2021-09-21T20:56:32Z)
• Free Energy Minimization: A Unified Framework for Modelling, Inference, Learning,and Optimization [42.275148861039895]
  Free energy minimization is first introduced, here and historically, as a thermodynamic principle. The mentioned applications to modelling, inference, learning, and optimization are covered starting from basic principles.
  arXiv  Detail & Related papers  (2020-11-25T11:29:03Z)
• Strictly Batch Imitation Learning by Energy-based Distribution Matching [104.33286163090179]
  Consider learning a policy purely on the basis of demonstrated behavior -- that is, with no access to reinforcement signals, no knowledge of transition dynamics, and no further interaction with the environment. One solution is simply to retrofit existing algorithms for apprenticeship learning to work in the offline setting. But such an approach leans heavily on off-policy evaluation or offline model estimation, and can be indirect and inefficient. We argue that a good solution should be able to explicitly parameterize a policy, implicitly learn from rollout dynamics, and operate in an entirely offline fashion.
  arXiv  Detail & Related papers  (2020-06-25T03:27:59Z)
• The Two Kinds of Free Energy and the Bayesian Revolution [0.0]
  We argue that there are essentially two different notions of free energy in current models of intelligent agency. One appears when trading off accuracy and uncertainty based on a general maximum entropy principle. The other formulates action selection in terms of minimizing an error measure that quantifies deviations of beliefs and policies from given reference models.
  arXiv  Detail & Related papers  (2020-04-24T14:09:28Z)
• Targeted free energy estimation via learned mappings [66.20146549150475]
  Free energy perturbation (FEP) was proposed by Zwanzig more than six decades ago as a method to estimate free energy differences. FEP suffers from a severe limitation: the requirement of sufficient overlap between distributions. One strategy to mitigate this problem, called Targeted Free Energy Perturbation, uses a high-dimensional mapping in configuration space to increase overlap.
  arXiv  Detail & Related papers  (2020-02-12T11:10:00Z)

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.