A Worked Example of Fokker-Planck based Active Inference

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

The Free Energy Principle (FEP) and its corollary active inference describe a complex theoretical framework with a substantial statistical mechanics foundation that is often expressed in terms of the Fokker-Planck equation. Easy-to-follow examples of this formalism are scarce, leaving a high barrier of entry to the field. In this paper we provide a worked example of an active inference agent as a hierarchical Gaussian generative model. We proceed to write its equations of motion explicitly as a Fokker-Planck equation, providing a clear mapping between theoretical accounts of FEP and practical implementation. Code is available at github.com/biaslab/ai_workshop_2020.

Original languageEnglish
Title of host publicationActive Inference - First International Workshop, IWAI 2020, Co-located with ECML/PKDD 2020, Proceedings
EditorsTim Verbelen, Pablo Lanillos, Christopher L. Buckley, Cedric De Boom
Pages28-34
Number of pages7
DOIs
Publication statusPublished - Sep 2020
EventInternational Workshop on Active Inference - Ghent, Belgium
Duration: 14 Sep 2020 → …
Conference number: 1
https://iwaiworkshop.github.io/

Publication series

NameCommunications in Computer and Information Science
Volume1326
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Workshop

WorkshopInternational Workshop on Active Inference
Abbreviated titleIWAI
CountryBelgium
CityGhent
Period14/09/20 → …
Internet address

Keywords

  • Active inference
  • Fokker-Planck equation
  • Free energy

Fingerprint Dive into the research topics of 'A Worked Example of Fokker-Planck based Active Inference'. Together they form a unique fingerprint.

Cite this