Metraipolis › archive › dc_a4e80ebbed51

CausalWAM: Learning the Causes of Actions in World Action Models — arXiv:2610.42096

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.42096
License (as archived): CC0-1.0
Archived: 2026-11-02T07:09:42.401Z
SHA-256 of the archived text: 1c0e42d62ebea08e933b0432e3b8eaab1e4aa901650e948a492c50d6b04a3e44
Stable URL of this page: https://metraipolis.com/documento/dc_a4e80ebbed51

How to cite

CausalWAM: Learning the Causes of Actions in World Action Models — arXiv:2610.42096 — arXiv (en), https://arxiv.org/abs/2610.42096 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a4e80ebbed51 (Metraipolis archive dc_a4e80ebbed51, sha256 1c0e42d62ebea08e933b0432e3b8eaab1e4aa901650e948a492c50d6b04a3e44)

BibTeX

@misc{dca4e80ebbed51,
  title = {CausalWAM: Learning the Causes of Actions in World Action Models — arXiv:2610.42096},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.42096},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a4e80ebbed51; sha256 1c0e42d62ebea08e933b0432e3b8eaab1e4aa901650e948a492c50d6b04a3e44},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.42096. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

World action models (WAMs) learn latent variables from observations and use these to both predict the evolution of the scene and to generate actions. The prediction has to be of the whole scene, whereas only a portion of the scene causes actions. WAMs fitted to demonstrations do not, in general, guarantee that they will generate actions solely from the latent causes of the demonstrated actions (the action-relevant latent variables), as the model could just as well learn to imitate in this way whilst entangling the action-relevant latent variables with the nuisance variables. We therefore separate out what causes action from what prediction depends on. We prove that under a sparsity constraint the latent variables used to generate actions are an invertible function of the action-relevant latent variables alone and the true structure is identified up to a permutation of the latent variables. This requires neither sufficient temporal dependence nor any assumptions on how the unobserved regimes evolve and holds even when the action-relevant latent variables are statistically dependent on the rest. We therefore propose CWAM (Causal WAM), which incorporates the constraint into a pretrained WAM by adding a sparse routing path to its action head, with the world modeling objective remaining unchanged. Experiments on both synthetic data and real-world robots validate the theory as well as showcase the improved efficiency in closed-loop success.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Robotics (cs.RO); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.42096 — 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 2026-11-02T07:06:59.384Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).