Metraipolis › archive › dc_eab5dc3a79dc

Experience-Guided Initiation Search for Learned Skills in Skill Composition — arXiv:2610.11418

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.11418
License (as archived)
CC0-1.0
Archived
2026-10-09T06:33:15.993Z
SHA-256 of the archived text
e5a9ecd0e0e53a418374440484707be866a71e3bdd11f890231e35988ff13c72
Stable URL of this page
https://metraipolis.com/documento/dc_eab5dc3a79dc

How to cite

Experience-Guided Initiation Search for Learned Skills in Skill Composition — arXiv:2610.11418 — arXiv (en), https://arxiv.org/abs/2610.11418 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eab5dc3a79dc (Metraipolis archive dc_eab5dc3a79dc, sha256 e5a9ecd0e0e53a418374440484707be866a71e3bdd11f890231e35988ff13c72)
BibTeX
@misc{dceab5dc3a79dc,
  title = {Experience-Guided Initiation Search for Learned Skills in Skill Composition — arXiv:2610.11418},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.11418},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eab5dc3a79dc; sha256 e5a9ecd0e0e53a418374440484707be866a71e3bdd11f890231e35988ff13c72},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11418. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deploying frozen learned skills, such as Vision-Language-Action (VLA) policies, in new environments requires identifying initiation configurations that support reliable execution. In skill composition, an initiation configuration affects not only the current skill but also the physical state passed to subsequent skills, so successful execution of an individual skill does not necessarily imply successful completion of the composed task. Estimating target-specific capability through extensive rollouts is costly in real-world deployment, while directly reusing historical experience can be unreliable under environment changes. We propose EVIS, an Experience-Guided and Behavior-Validated Initiation Search framework for discovering reliable initiation configurations under limited target interaction. EVIS uses historical execution experience to prioritize promising candidates and target-environment behavior to validate whether they remain effective. We evaluate EVIS on single-skill and two-stage manipulation tasks with frozen VLA policies. EVIS reduces mean target-environment queries and improves reliable candidate discovery under small interaction budgets. These results show that combining historical guidance with target-side behavioral validation can reduce the interaction cost of deploying frozen learned skills in new environments.

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/2610.11418 — 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 2026-10-09T05:55:22.089Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).