Metraipolis › archive › dc_fa446c8fe5b4

Expected free energy as an information constraint on the Bethe Lagrangian — arXiv:2608.17167

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.17167
License (as archived): CC0-1.0
Archived: 2026-10-18T14:29:12.325Z
SHA-256 of the archived text: 423b69a8f83240642e0f35f9d5d8b3bf2d3e9fd50d13d46adea99a7b0111999a
Stable URL of this page: https://metraipolis.com/documento/dc_fa446c8fe5b4

How to cite

Expected free energy as an information constraint on the Bethe Lagrangian — arXiv:2608.17167 — arXiv (en), https://arxiv.org/abs/2608.17167 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fa446c8fe5b4 (Metraipolis archive dc_fa446c8fe5b4, sha256 423b69a8f83240642e0f35f9d5d8b3bf2d3e9fd50d13d46adea99a7b0111999a)

BibTeX

@misc{dcfa446c8fe5b4,
  title = {Expected free energy as an information constraint on the Bethe Lagrangian — arXiv:2608.17167},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.17167},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fa446c8fe5b4; sha256 423b69a8f83240642e0f35f9d5d8b3bf2d3e9fd50d13d46adea99a7b0111999a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.17167. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Active inference selects actions by minimising an expected free energy functional over predicted futures. However, adding an expectation over yet-unobserved outcomes means the free energy functional no longer has a Kullback-Leibler structure, which hinders message passing treatments of inference procedures. We propose an alternative formulation based on a Bethe free energy functional, fully supporting inference by message passing. The epistemic drive is maintained by imposing an information constraint, next to normalisation, marginalisation and form constraints, insisting that the mutual information between future observations, states and parameters given actions must be at least as large as the entropy of the goal prior. For a specific value of the corresponding Karush-Kuhn-Tucker multiplier, the stationary point of this constrained Bethe Lagrangian recovers the expected free energy solution. We show that, as the information demand is varied, the solved multiplier moves through its inactive, interior, and saturated regimes. In the inactive regime the agent's epistemic drive switches off entirely, while in the saturated regime it is maximal. We compare the performance of the constrained Bethe agent on three tasks against EFE and Q-MDP.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-19 in cs.AI).
Categorie arXiv: Information Theory (cs.IT) ; Artificial Intelligence (cs.AI); Systems and Control (eess.SY); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2608.17167 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T14:27:54.378Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-19?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).