Metraipolis › archive › dc_ca12f21c8fa5
Physical Experience Builds Continual Spatial World Models — arXiv:2611.04016
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04016
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T19:05:08.112Z
- SHA-256 of the archived text
6ff181c3694c1cb8359877cf3e5fd831f575b0a4a7d6ea246b7bccbec4be0ed0- Stable URL of this page
https://metraipolis.com/documento/dc_ca12f21c8fa5
How to cite
Physical Experience Builds Continual Spatial World Models — arXiv:2611.04016 — arXiv (en), https://arxiv.org/abs/2611.04016 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca12f21c8fa5 (Metraipolis archive dc_ca12f21c8fa5, sha256 6ff181c3694c1cb8359877cf3e5fd831f575b0a4a7d6ea246b7bccbec4be0ed0)
BibTeX
@misc{dcca12f21c8fa5,
title = {Physical Experience Builds Continual Spatial World Models — arXiv:2611.04016},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04016},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca12f21c8fa5; sha256 6ff181c3694c1cb8359877cf3e5fd831f575b0a4a7d6ea246b7bccbec4be0ed0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04016. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
World models are increasingly used to support prediction and planning in embodied agents, but the knowledge is usually established before deployment and then carried into later encounters. Continual operation faces a different problem. A familiar environment may change, and the agent must use previous experience without allowing old expectations to override current physical evidence. This study asks what repeated physical experience must contribute for a spatial world model to become progressively more useful rather than simply more persistent. A physics-grounded dynamic maze separates recurring spatial change from the continuous consequences of action. Cross-episode Spatial Change Memory learns relations among environmental transformations, while state-action-outcome experience refines predictions of motion. Structured experience progressively reduces the need for future route correction and transfers to spatial transitions not encountered during learning. The advantage disappears when past changes contain no information about future ones. Continuous navigation further shows that predictive memory changes behavior when a previous decision becomes invalid but leaves behavior unchanged when the decision remains correct. Physical tests expose a complementary limit: correct topology does not guarantee correct action prediction, and accumulated physical experience reduces this mismatch within the modeled dynamics. The results characterize continual world knowledge as experience that improves future prediction and action beyond stored episodes while remaining revisable by the physical outcomes it is intended to predict. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2611.04016 — 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 2026-11-04T18:39:52.387Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).