Deriving time-averaged active inference from control principles

TL;DR

This paper derives an infinite-horizon, average-surprise formulation of active inference from control principles, unifying it with optimal feedback control and neurophysiological foundations.

Contribution

It introduces a new formulation of active inference based on infinite-horizon, average-surprise, connecting it to optimal control and neuroanatomy.

Findings

Reconciles active inference with infinite-horizon control

Provides a unified sensorimotor control objective

Enables reference states to vary over time

Abstract

Active inference offers a principled account of behavior as minimizing average sensory surprise over time. Applications of active inference to control problems have heretofore tended to focus on finite-horizon or discounted-surprise problems, despite deriving from the infinite-horizon, average-surprise imperative of the free-energy principle. Here we derive an infinite-horizon, average-surprise formulation of active inference from optimal control principles. Our formulation returns to the roots of active inference in neuroanatomy and neurophysiology, formally reconnecting active inference to optimal feedback control. Our formulation provides a unified objective functional for sensorimotor control and allows for reference states to vary over time.