Realising Synthetic Active Inference Agents, Part II: Variational Message Updates

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: van de Laar, Thijs, Koudahl, Magnus, de Vries, Bert
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913630201577472
author van de Laar, Thijs
Koudahl, Magnus
de Vries, Bert
author_facet van de Laar, Thijs
Koudahl, Magnus
de Vries, Bert
contents The Free Energy Principle (FEP) describes (biological) agents as minimising a variational Free Energy (FE) with respect to a generative model of their environment. Active Inference (AIF) is a corollary of the FEP that describes how agents explore and exploit their environment by minimising an expected FE objective. In two related papers, we describe a scalable, epistemic approach to synthetic AIF, by message passing on free-form Forney-style Factor Graphs (FFGs). A companion paper (part I) introduces a Constrained FFG (CFFG) notation that visually represents (generalised) FE objectives for AIF. The current paper (part II) derives message passing algorithms that minimise (generalised) FE objectives on a CFFG by variational calculus. A comparison between simulated Bethe and generalised FE agents illustrates how the message passing approach to synthetic AIF induces epistemic behaviour on a T-maze navigation task. Extension of the T-maze simulation to 1) learning goal statistics, and 2) a multi-agent bargaining setting, illustrate how this approach encourages reuse of nodes and updates in alternative settings. With a full message passing account of synthetic AIF agents, it becomes possible to derive and reuse message updates across models and move closer to industrial applications of synthetic AIF.
format Preprint
id arxiv_https___arxiv_org_abs_2306_02733
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Realising Synthetic Active Inference Agents, Part II: Variational Message Updates
van de Laar, Thijs
Koudahl, Magnus
de Vries, Bert
Machine Learning
The Free Energy Principle (FEP) describes (biological) agents as minimising a variational Free Energy (FE) with respect to a generative model of their environment. Active Inference (AIF) is a corollary of the FEP that describes how agents explore and exploit their environment by minimising an expected FE objective. In two related papers, we describe a scalable, epistemic approach to synthetic AIF, by message passing on free-form Forney-style Factor Graphs (FFGs). A companion paper (part I) introduces a Constrained FFG (CFFG) notation that visually represents (generalised) FE objectives for AIF. The current paper (part II) derives message passing algorithms that minimise (generalised) FE objectives on a CFFG by variational calculus. A comparison between simulated Bethe and generalised FE agents illustrates how the message passing approach to synthetic AIF induces epistemic behaviour on a T-maze navigation task. Extension of the T-maze simulation to 1) learning goal statistics, and 2) a multi-agent bargaining setting, illustrate how this approach encourages reuse of nodes and updates in alternative settings. With a full message passing account of synthetic AIF agents, it becomes possible to derive and reuse message updates across models and move closer to industrial applications of synthetic AIF.
title Realising Synthetic Active Inference Agents, Part II: Variational Message Updates
topic Machine Learning
url https://arxiv.org/abs/2306.02733