Metraipolis › archive › dc_daae26d4c047

When Does Dynamics Randomization Test Context Inference? — arXiv:2610.32414

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.32414
License (as archived)
CC0-1.0
Archived
2026-10-26T20:12:04.461Z
SHA-256 of the archived text
6e9ce3601e88b693d70fcea9bc3d9c519ad681ffd5e1f4279e82152eeec72288
Stable URL of this page
https://metraipolis.com/documento/dc_daae26d4c047

How to cite

When Does Dynamics Randomization Test Context Inference? — arXiv:2610.32414 — arXiv (en), https://arxiv.org/abs/2610.32414 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_daae26d4c047 (Metraipolis archive dc_daae26d4c047, sha256 6e9ce3601e88b693d70fcea9bc3d9c519ad681ffd5e1f4279e82152eeec72288)
BibTeX
@misc{dcdaae26d4c047,
  title = {When Does Dynamics Randomization Test Context Inference? — arXiv:2610.32414},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.32414},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_daae26d4c047; sha256 6e9ce3601e88b693d70fcea9bc3d9c519ad681ffd5e1f4279e82152eeec72288},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32414. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Environments with randomized dynamics are widely used to ask whether world models need explicit context inference. However, randomization can leave little predictive information for a context encoder to add, because distinct latent parameters may produce similar transitions at visited states, or those states may already reveal the active context. We formalize the remaining one-step information as predictive headroom and compare kernels under fixed and visited state--action distributions to distinguish changes in query coverage from changes in context weights. We analyze discrete and continuous environments and find low headroom both when kernels differ little and when visitation reduces an otherwise large discrepancy. At the same time, resetting state components increases headroom, showing that context evidence accumulates in state. We propose reporting this headroom alongside the randomized parameters, so that gains from explicit context inference can be interpreted relative to the information missing from the current state and action.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.32414 — 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 2026-10-26T19:49:03.398Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).