Abstract: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.
| Subjects: | Machine Learning (stat.ML); Machine Learning (cs.LG) |
| Cite as: | arXiv:2306.02733 [stat.ML] |
| (or arXiv:2306.02733v3 [stat.ML] for this version) | |
| https://doi.org/10.48550/arXiv.2306.02733 arXiv-issued DOI via DataCite |
|
| Related DOI: | https://doi.org/10.1162/neco_a_01713
DOI(s) linking to related resources |
Submission history
From: Thijs van de Laar PhD [view email]
[v1]
Mon, 5 Jun 2023 09:29:46 UTC (1,001 KB)
[v2]
Tue, 11 Jul 2023 08:07:38 UTC (1,007 KB)
[v3]
Thu, 26 Sep 2024 08:45:22 UTC (1,597 KB)