Metraipolis › archive › dc_638e6aa2bdc2

Decision-Metric Alignment in Latent World Models: Diagnostics and Action-Conditioned Objectives for MPC Planning — arXiv:2608.18746

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.18746
License (as archived)
CC0-1.0
Archived
2026-10-18T13:53:24.207Z
SHA-256 of the archived text
9544b8d2a8474d0ec853c0344d93c3d1ab0225fe22a16284ecf978415358267f
Stable URL of this page
https://metraipolis.com/documento/dc_638e6aa2bdc2

How to cite

Decision-Metric Alignment in Latent World Models: Diagnostics and Action-Conditioned Objectives for MPC Planning — arXiv:2608.18746 — arXiv (en), https://arxiv.org/abs/2608.18746 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_638e6aa2bdc2 (Metraipolis archive dc_638e6aa2bdc2, sha256 9544b8d2a8474d0ec853c0344d93c3d1ab0225fe22a16284ecf978415358267f)
BibTeX
@misc{dc638e6aa2bdc2,
  title = {Decision-Metric Alignment in Latent World Models: Diagnostics and Action-Conditioned Objectives for MPC Planning — arXiv:2608.18746},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.18746},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_638e6aa2bdc2; sha256 9544b8d2a8474d0ec853c0344d93c3d1ab0225fe22a16284ecf978415358267f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18746. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

JEPA-style latent world models can use Euclidean distance to a goal latent as the cost for model-predictive control (MPC). Strong decoding of task variables, however, does not guarantee that this particular cost ranks candidate action sequences by real task progress. We call the latter property \emph{decision-metric alignment}. We introduce Plan-Real Spearman, which measures latent--real rank agreement on random plans, and CEM-stage Spearman, which measures the same agreement as cross-entropy-method (CEM) search concentrates its proposal. We analyze sufficient conditions under which latent distance preserves real-cost rankings, identifying encoder distortion, terminal rollout error, and candidate margins as the controlling quantities. Guided by the observed empirical alignment gap, DA-LeWM augments LeWM with inverse-dynamics and demonstration-conditioned goal-action heads. Across all our experiments, DA-LeWM accelerates convergence and achieves higher online success than LeWM, while probe scores remain similar. These results show that action-conditioned objectives improve the geometry used by Euclidean-cost, CEM-based latent MPC.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-20 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.18746 — 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 2026-10-18T13:50:58.933Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).