Metraipolis › archive › dc_eecbbe88a15b

Agent Priors-guided Policy Learning — arXiv:2609.35690

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35690
License (as archived)
CC0-1.0
Archived
2026-10-08T00:17:38.970Z
SHA-256 of the archived text
77287b0e84045309a406197b6de8a0ba3de527483a07eaef7c27fb8f2ccc373d
Stable URL of this page
https://metraipolis.com/documento/dc_eecbbe88a15b

How to cite

Agent Priors-guided Policy Learning — arXiv:2609.35690 — arXiv (en), https://arxiv.org/abs/2609.35690 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eecbbe88a15b (Metraipolis archive dc_eecbbe88a15b, sha256 77287b0e84045309a406197b6de8a0ba3de527483a07eaef7c27fb8f2ccc373d)
BibTeX
@misc{dceecbbe88a15b,
  title = {Agent Priors-guided Policy Learning — arXiv:2609.35690},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35690},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eecbbe88a15b; sha256 77287b0e84045309a406197b6de8a0ba3de527483a07eaef7c27fb8f2ccc373d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35690. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Robots that learn from a few demonstrations often require two forms of generalization. Compositional generalization recombines skills to solve new tasks, and skill generalization lets the learned policy behind each skill work in new situations. The two depend on each other, yet information is lost between composition and the skills it calls. Where a skill works is determined by the structure its policy is trained with, while composition sees the skill only through a separate description, such as a name, an instruction, or a symbolic operator, that omits this structure. Our key idea is to use each policy's structural prior as part of the interface between composition and the skill. A structural prior states what a behavior depends on, for example that a grasp depends only on the gripper's pose relative to the object. Built into training, it shapes where the policy generalizes; stated in language, it tells composition where the policy applies. We instantiate this idea in Agent Priors-guided Policy Learning (APPL). A construction agent segments complete demonstrations into reusable skills, proposes several structural priors for each skill, and trains and verifies one policy per prior. A runtime agent then selects among these prior-specific policies and composes them toward new task goals using their interfaces. Across MetaWorld and long-horizon ManiSkill tasks, APPL improves out-of-distribution skill generalization and enables previously unseen skill compositions; ablating the interface information substantially reduces performance. These results support the use of training-time structural assumptions as a bridge between skill learning and skill composition.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.35690 — 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 2026-10-07T23:52:16.629Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).