Active Inference or Control as Inference? A Unifying View

arXiv (Cornell University)

Abstract

Active inference (AI) is a persuasive theoretical framework from computational neuroscience that seeks to describe action and perception as inference-based computation. However, this framework has yet to provide practical sensorimotor control algorithms that are competitive with alternative approaches. In this work, we frame active inference through the lens of control as inference (CaI), a body of work that presents trajectory optimization as inference. From the wider view of `probabilistic numerics', CaI offers principled, numerically robust optimal control solvers that provide uncertainty quantification, and can scale to nonlinear problems with approximate inference. We show that AI may be framed as partially-observed CaI when the cost function is defined specifically in the observation states.

Authors 3

1. Joe Watson Aachen

   RWTH Aachen University · Technische Universität Darmstadt

   Affiliation as printed

   IAS , Technical University Darmstadt , Germany

   RWTH Aachen University

2. Abraham Imohiosen Aachen

   RWTH Aachen University · Technische Universität Darmstadt

   Affiliation as printed

   RWTH Aachen University , Germany

   Technische Universität Darmstadt,

3. Jan Peters

   Technische Universität Darmstadt

   Affiliation as printed

   IAS , Technical University Darmstadt , Germany

   Technische Universität Darmstadt,