Metraipolis › archive › dc_796b016017e6

Latent Energy Action Planning with World Models — arXiv:2609.03294

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03294
License (as archived)
CC0-1.0
Archived
2026-10-17T02:07:49.827Z
SHA-256 of the archived text
aafe2ef85dab4e5848d296ba05e47e264ddd1b3534e6b725388750c18472bf88
Stable URL of this page
https://metraipolis.com/documento/dc_796b016017e6

How to cite

Latent Energy Action Planning with World Models — arXiv:2609.03294 — arXiv (en), https://arxiv.org/abs/2609.03294 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_796b016017e6 (Metraipolis archive dc_796b016017e6, sha256 aafe2ef85dab4e5848d296ba05e47e264ddd1b3534e6b725388750c18472bf88)
BibTeX
@misc{dc796b016017e6,
  title = {Latent Energy Action Planning with World Models — arXiv:2609.03294},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03294},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_796b016017e6; sha256 aafe2ef85dab4e5848d296ba05e47e264ddd1b3534e6b725388750c18472bf88},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03294. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Latent world models support efficient model predictive control from high-dimensional observations, yet optimizing a single learned latent objective can favor action sequences whose decoder-predicted terminal descriptor does not match the goal descriptor. We introduce Latent Energy Action Planning (LEAP), which treats the complete action horizon as a differentiable variable and optimizes it through a frozen LeWorldModel (LeWM). LEAP couples terminal latent goal matching with a terminal-window state energy. Low energy requires the predicted terminal latent to agree with the goal latent and the decoder-predicted terminal descriptor to agree with the goal descriptor. A frozen goal-conditioned proposal initializes the search, a quasi-Newton solver refines actions through the autoregressive rollout, and post-optimization projection enforces the admissible action range. Across four control domains using the officially released LeWM checkpoints, the complete LEAP planning system raises mean success from 77.5% for LeWM planned with the cross-entropy method (LeWM+CEM) to 94.8% under a matched protocol, a 17.3-percentage-point improvement, while retaining the frozen LeWM representation and predictor.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.03294 — 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 2026-10-17T01:47:25.535Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).