Metraipolis › archive › dc_375edccf8b6f

Lucid Dreaming for World Models: Learning to Doubt Imagination and Decide by Trust — arXiv:2609.37156

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.37156
License (as archived)
CC0-1.0
Archived
2026-10-07T16:26:57.230Z
SHA-256 of the archived text
f671576be7c1026777785f6c596ca615fd1c6d0151fd1f71ffe856274ab3098f
Stable URL of this page
https://metraipolis.com/documento/dc_375edccf8b6f

How to cite

Lucid Dreaming for World Models: Learning to Doubt Imagination and Decide by Trust — arXiv:2609.37156 — arXiv (en), https://arxiv.org/abs/2609.37156 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_375edccf8b6f (Metraipolis archive dc_375edccf8b6f, sha256 f671576be7c1026777785f6c596ca615fd1c6d0151fd1f71ffe856274ab3098f)
BibTeX
@misc{dc375edccf8b6f,
  title = {Lucid Dreaming for World Models: Learning to Doubt Imagination and Decide by Trust — arXiv:2609.37156},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37156},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_375edccf8b6f; sha256 f671576be7c1026777785f6c596ca615fd1c6d0151fd1f71ffe856274ab3098f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37156. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

World models enable agents to learn and plan in imagination, but predictions beyond their experience can become unreliable and mislead decisions. Existing uncertainty estimates derived from predictions can remain overconfident on unfamiliar state-action pairs. We propose the Lucid World Model (LucidWM), which learns doubt from experience and propagates trust through imagination. By integrating Subjective Logic into categorical latent transitions, LucidWM distinguishes predicted outcomes from their evidential support and assigns each transition a degree of doubt. The complement of this doubt defines transition-level trust, which accumulates multiplicatively along imagined trajectories to reweight returns for policy learning and guide action selection. Uncertainty estimation requires no additional parameters or forward passes. Evaluated on four base world models against seventeen uncertainty readouts, LucidWM detects environmental changes and signals uncertainty during action-corrupted rollouts. In a controlled navigation case study, acting on trust reduces the number of steps required to reach the goal from 362 to 190. Fifteen demonstration videos show how LucidWM doubts its dreams and acts on that doubt. Videos are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.37156 — 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 2026-10-07T15:54:53.949Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).