Metraipolis › archive › dc_97ee179bb485

Skill Composition for Legged Robot Reinforcement Learning — arXiv:2609.14647

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.14647
License (as archived): CC0-1.0
Archived: 2026-10-15T22:53:13.535Z
SHA-256 of the archived text: 4f1c4bcb72f0b1924b9170f68703afb714fbb5661fae5a2ba01e6a7983d1366c
Stable URL of this page: https://metraipolis.com/documento/dc_97ee179bb485

How to cite

Skill Composition for Legged Robot Reinforcement Learning — arXiv:2609.14647 — arXiv (en), https://arxiv.org/abs/2609.14647 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_97ee179bb485 (Metraipolis archive dc_97ee179bb485, sha256 4f1c4bcb72f0b1924b9170f68703afb714fbb5661fae5a2ba01e6a7983d1366c)

BibTeX

@misc{dc97ee179bb485,
  title = {Skill Composition for Legged Robot Reinforcement Learning — arXiv:2609.14647},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.14647},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_97ee179bb485; sha256 4f1c4bcb72f0b1924b9170f68703afb714fbb5661fae5a2ba01e6a7983d1366c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14647. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Robots, and humanoid robots in particular, are increasingly competent at individual behaviors, each obtained by training a specialized controller. A specialized skill is quick to train, converges reliably because the problem it faces is narrow, and can be validated on its own, none of which is true of a single end-to-end policy asked to cover everything. What remains fragile is the transition between them. We argue that the composition of independent sub-policies deserves to be treated as a research problem in its own right, rather than as an implementation detail left to whatever mechanism happens to be at hand. Reliable composition is what turns a collection of separate skills into a repertoire that can be used, extended and shared. More fundamentally, if control can be passed between specialized policies safely, and at any moment, the choice of what the robot should do next can be delegated to a component of an entirely different nature, such as a planner, an automaton or a symbolic controller, whose behavior can be inspected in advance. The policies would then only ever have to act, and what the robot can be trusted to do would become verifiable.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.14647 — 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 2026-10-15T22:29:03.704Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).