Metraipolis › archive › dc_515cd3339e25

Towards Zero-Shot Task Transfer with Neurosymbolic World Models — arXiv:2608.17959

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.17959
License (as archived)
CC0-1.0
Archived
2026-10-18T14:28:53.349Z
SHA-256 of the archived text
055aaf7a5a3c8431b7e5d0dcbb2a216f16f675e0319c9ba3f739daff1d920ed1
Stable URL of this page
https://metraipolis.com/documento/dc_515cd3339e25

How to cite

Towards Zero-Shot Task Transfer with Neurosymbolic World Models — arXiv:2608.17959 — arXiv (en), https://arxiv.org/abs/2608.17959 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_515cd3339e25 (Metraipolis archive dc_515cd3339e25, sha256 055aaf7a5a3c8431b7e5d0dcbb2a216f16f675e0319c9ba3f739daff1d920ed1)
BibTeX
@misc{dc515cd3339e25,
  title = {Towards Zero-Shot Task Transfer with Neurosymbolic World Models — arXiv:2608.17959},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.17959},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_515cd3339e25; sha256 055aaf7a5a3c8431b7e5d0dcbb2a216f16f675e0319c9ba3f739daff1d920ed1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.17959. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

State-of-the-art model-based reinforcement learning methods learn neural world models that allow policy improvement by planning in a latent space, without assumptions on the structure of the underlying environment. While expressive, these models are generally task-dependent: they learn uninterpretable latent representations that are tied to the training task and thus hard to generalize to new tasks. In this work, we present a novel world model formulation where the reward prediction only depends on a subset of structured, symbolic components of the whole latent state. Decoupling observation reconstruction and reward prediction allows us to learn world models that can adapt zero-shot, i.e. without further environment interactions, to new reward functions defined over the same symbolic state space. We discuss the main advantages and challenges of learning these neurosymbolic world models and demonstrate the strong generalisation properties of our approach over purely neural methods.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-19 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.17959 — 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 2026-10-18T14:27:54.317Z 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).