Metraipolis › archive › dc_0b74b4be5366

Considering Context: When World Models Need Context Encoders — arXiv:2610.06651

Source
arXiv
Original
https://arxiv.org/abs/2610.06651
License (as archived)
CC0-1.0
Archived
2026-10-06T05:31:43.129Z
SHA-256 of the archived text
bb7fc5e31bdd7b3789ce6b41c04f886a4350d653753e3489f5d648c9310d750a
Stable URL of this page
https://metraipolis.com/documento/dc_0b74b4be5366

How to cite

Considering Context: When World Models Need Context Encoders — arXiv:2610.06651 — arXiv, https://arxiv.org/abs/2610.06651 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0b74b4be5366 (Metraipolis archive dc_0b74b4be5366, sha256 bb7fc5e31bdd7b3789ce6b41c04f886a4350d653753e3489f5d648c9310d750a)
BibTeX
@misc{dc0b74b4be5366,
  title = {Considering Context: When World Models Need Context Encoders — arXiv:2610.06651},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.06651},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0b74b4be5366; sha256 bb7fc5e31bdd7b3789ce6b41c04f886a4350d653753e3489f5d648c9310d750a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06651. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Methods for generalization in model-based reinforcement learning typically assume that an agent cannot recover the latent context governing the environment dynamics from its own experience, and therefore supplies it externally. We formalize and test this assumption with \emph{predictive sufficiency}, which quantifies what access to the context adds to next-step prediction under the visitation distribution an agent induces, and separates that quantity into a history-recoverable part, a residual requiring the true context, and the deficit added by a finite model. We classify context-aware algorithms by the predictive risk their conditioning set can target and demonstrate across environments of increasing identification difficulty that the headroom does not follow the MDP class. The same task under different priors leaves predictive headroom in one setting and nothing distinguishable from zero in another, where the agent's behavior implicitly identifies the context and any benefit of such a mechanism cannot be attributed to missing information. Where headroom persists, the learned state exposes it only partially, and adding the true context still lowers the risk. Our contribution is a practical criterion for matching contextual mechanisms to the information available to them, estimated from the ordinary trained agent without a reference policy.

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/2610.06651 — 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 2026-10-06T05:27:05.900Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).