Metraipolis › archive › dc_19fecf79d00e

Representation World Model: Learning States, Transition and Executable Plans in Representation — arXiv:2609.29171

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29171
License (as archived)
CC0-1.0
Archived
2026-10-08T06:44:46.928Z
SHA-256 of the archived text
2fff591e9c1222cc9f7a22356cfbacf072225bde9c09d8958a0a40beeddaefe4
Stable URL of this page
https://metraipolis.com/documento/dc_19fecf79d00e

How to cite

Representation World Model: Learning States, Transition and Executable Plans in Representation — arXiv:2609.29171 — arXiv (en), https://arxiv.org/abs/2609.29171 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_19fecf79d00e (Metraipolis archive dc_19fecf79d00e, sha256 2fff591e9c1222cc9f7a22356cfbacf072225bde9c09d8958a0a40beeddaefe4)
BibTeX
@misc{dc19fecf79d00e,
  title = {Representation World Model: Learning States, Transition and Executable Plans in Representation — arXiv:2609.29171},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29171},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_19fecf79d00e; sha256 2fff591e9c1222cc9f7a22356cfbacf072225bde9c09d8958a0a40beeddaefe4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29171. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We propose the Representation World Model (RWM), which learns states, transitions, and executable plans directly in representation space. Unlike existing world models that typically learn latent representations together with explicit dynamics models and perform planning through search, optimization, or policy-based prediction, RWM directly incorporates planning into the learned representation geometry. RWM learns the representation geometry by applying inverse-dynamics supervision locally along latent paths constructed from endpoint representations, requiring these paths to preserve task-relevant state and transition information. At inference, planning is performed by directly constructing a latent path between the current and goal representations, with inverse dynamics used to recover the corresponding actions, without recursive rollouts or action-space search. Experiments on continuous-control benchmarks demonstrate the effectiveness of RWM for direct planning, while results on robotic manipulation further show its potential to extend to more complex embodied control tasks. These results suggest that planning directly in representation space provides a promising alternative to conventional world-model planning.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in cs.CV).
Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.29171 — 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 2026-10-08T06:09:29.925Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).