Metraipolis › archive › dc_2f11dd01c879
Belief-Based Maximum Occupancy Principle and Active Inference — arXiv:2609.39342
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39342
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T12:45:14.861Z
- SHA-256 of the archived text
258ec48e076c5ad0a9842a6775355e1c55e23836f6d5202737d2ddee8857264a- Stable URL of this page
https://metraipolis.com/documento/dc_2f11dd01c879
How to cite
Belief-Based Maximum Occupancy Principle and Active Inference — arXiv:2609.39342 — arXiv (en), https://arxiv.org/abs/2609.39342 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2f11dd01c879 (Metraipolis archive dc_2f11dd01c879, sha256 258ec48e076c5ad0a9842a6775355e1c55e23836f6d5202737d2ddee8857264a)
BibTeX
@misc{dc2f11dd01c879,
title = {Belief-Based Maximum Occupancy Principle and Active Inference — arXiv:2609.39342},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39342},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2f11dd01c879; sha256 258ec48e076c5ad0a9842a6775355e1c55e23836f6d5202737d2ddee8857264a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39342. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Intrinsic motivation plays a central role in adaptive and goal-directed behavior by conferring agents reward-independent objectives and biases useful to act in noisy and uncertain environments. Active Inference addresses the problem of acting in a partially observable environment through a principled framework for belief updating and action selection. A key component of Active Inference is the specification of prior preferences, which shapes behavior by encoding desirable future outcomes. An intrinsic motivation approach called the Maximum Occupancy Principle (MOP) proposes that agents act so as to maximize occupancy over future paths of states and actions, with no preferences or epistemic targets. Despite its simple formulation, MOP gives rise to rich and adaptive behaviors that combine exploratory variability with goal-directed dynamics. In this work, we extend MOP to partially observable environments and introduce a Bellman reformulation of the Expected Free Energy for Active Inference, both incorporating belief-based inference over hidden states as part of the agent state. The Bellman formulation enables tractable offline computation via value iteration over the full belief-state space. We compare the resulting behaviors in a set of minimal experimental settings with uncertain food sources. We find that MOP agents switch between goal-directed (food seeking) behavior and exploration between different food sources, depending on their energy available and their belief state. In contrast, Active Inference agents mostly inhabit regions around a single food source, a strategy having both high pragmatic and epistemic value. We finally compare with Empowerment, which is shown to be qualitatively similar to Active Inference. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI). Categorie arXiv: Neurons and Cognition (q-bio.NC) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.39342 — 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 2026-10-07T12:14:14.058Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).