Skip to main content

Realising Active Inference in Variational Message Passing: the Outcome-blind Certainty Seeker

Champion, Théophile, Grześ, Marek, Bowman, Howard (2021) Realising Active Inference in Variational Message Passing: the Outcome-blind Certainty Seeker. Neural Computation, . ISSN 0899-7667. E-ISSN 1530-888X. (In press) (KAR id:88015)

PDF Author's Accepted Manuscript
Language: English
Download (913kB) Preview
[thumbnail of champion21AIwithVMP.pdf]
Preview
This file may not be suitable for users of assistive technology.
Request an accessible format

Abstract

Active inference is a state-of-the-art framework in neuroscience that offers a unified theoryof brain function. It is also proposed as a framework for planning in AI. Unfortunately, thecomplex mathematics required to create new models — can impede application of activeinference in neuroscience and AI research. This paper addresses this problem by providinga complete mathematical treatment of the active inference framework — in discrete timeand state spaces — and the derivation of the update equations for any new model. Weleverage the theoretical connection between active inference and variational message passingas describe by John Winn and Christopher M. Bishop in 2005. Since, variational messagepassing is a well-defined methodology for deriving Bayesian belief update equations, thispaper opens the door to advanced generative models for active inference. We show thatusing a fully factorized variational distribution simplifies the expected free energy — that furnishes priors over policies — so that agents seek unambiguous states. Finally, we considerfuture extensions that support deep tree searches for sequential policy optimisation — basedupon structure learning and belief propagation.

Item Type: Article
Uncontrolled keywords: Active Inference, Variational Message Passing, Free Energy Principle, Reinforcement Learning, Kullback Leibler Control
Subjects: Q Science > QA Mathematics (inc Computing science) > QA 75 Electronic computers. Computer science
Divisions: Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing
Depositing User: Marek Grzes
Date Deposited: 10 May 2021 10:38 UTC
Last Modified: 11 May 2021 08:02 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/88015 (The current URI for this page, for reference purposes)
Grześ, Marek: https://orcid.org/0000-0003-4901-1539
Bowman, Howard: https://orcid.org/0000-0003-4736-1869
  • Depositors only (login required):

Downloads

Downloads per month over past year