Deriving Time-Averaged Active Inference from Control Principles
Published in Active Inference: Third International Workshop, 2022
Recommended citation: Sennesh, E., Theriault, J., van de Meent, J. W., Barrett, L. F., & Quigley, K. (2022, September). Deriving time-averaged active inference from control principles. In International Workshop on Active Inference (pp. 355-370). Cham: Springer Nature Switzerland. http://esennesh.github.io/files/iwai_timeavg_actinf_2022.pdf
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.
Recommended citation:
@inproceedings{sennesh2022deriving,
title={Deriving time-averaged active inference from control principles},
author={Sennesh, Eli and Theriault, Jordan and van de Meent, Jan-Willem and Barrett, Lisa Feldman and Quigley, Karen},
booktitle={International Workshop on Active Inference},
pages={355--370},
year={2022},
organization={Springer}
}