Metraipolis › archive › dc_a682dfcde902

Directed Temporal Representations for Offline Visual Control — arXiv:2610.08960

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.08960
License (as archived)
CC0-1.0
Archived
2026-10-08T11:56:09.822Z
SHA-256 of the archived text
e1f7ed121315442ca2ee4785249f771888b4764e8b5e2b6bb77bb506968ceb34
Stable URL of this page
https://metraipolis.com/documento/dc_a682dfcde902

How to cite

Directed Temporal Representations for Offline Visual Control — arXiv:2610.08960 — arXiv (en), https://arxiv.org/abs/2610.08960 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a682dfcde902 (Metraipolis archive dc_a682dfcde902, sha256 e1f7ed121315442ca2ee4785249f771888b4764e8b5e2b6bb77bb506968ceb34)
BibTeX
@misc{dca682dfcde902,
  title = {Directed Temporal Representations for Offline Visual Control — arXiv:2610.08960},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.08960},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a682dfcde902; sha256 e1f7ed121315442ca2ee4785249f771888b4764e8b5e2b6bb77bb506968ceb34},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08960. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Predictive world models provide compact visual representations for control. Control requires a latent geometry aligned with temporal reachability rather than predictive similarity alone. We introduce Directed Temporal Representations for Control (DTRC), which learns such a geometry from offline visual trajectories on top of frozen LeWorldModel (LeWM) features. DTRC constructs a directed temporal quasimetric over the learned control representation. Short-range temporal offsets calibrate the distance scale. Bootstrapped targets extend temporal reachability across longer horizons. Action-conditioned consistency aligns the representation with local transition dynamics. The resulting distance estimates temporal reaching cost, and its change across a transition defines goal-relative temporal progress. We use this progress signal as a temporal critic for direct goal-conditioned policy learning. Model-assisted targets provide an additional training-time refinement under behavior-support and dynamics-agreement constraints. Across ten visual control tasks, DTRC achieves strong goal-conditioned control performance relative to planning and direct-policy baselines. Held-out diagnostics on the four LeWM tasks show consistent short-range temporal calibration, task-dependent long-range and directional structure, and positive transition-level progress. Temporal supervision improves the same flow-policy parameterization across all four LeWM tasks, while the resulting policy acts directly without iterative trajectory search at test time.

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/2610.08960 — 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 2026-10-08T10:50:37.632Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).