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.
CITATION STYLE
Sennesh, E., Theriault, J., van de Meent, J. W., Barrett, L. F., & Quigley, K. (2023). Deriving Time-Averaged Active Inference from Control Principles. In Communications in Computer and Information Science (Vol. 1721 CCIS, pp. 355–370). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-28719-0_25
Mendeley helps you to discover research relevant for your work.