Metraipolis › archive › dc_7fcdaf3e3312

MATCH: Execution-Aware Hierarchical Reinforcement Learning for Vision-and-Language Navigation in Continuous Environment — arXiv:2610.38248

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.38248
License (as archived)
CC0-1.0
Archived
2026-11-01T02:44:11.615Z
SHA-256 of the archived text
81f94643aa1e0b6d34dc84cec880805e5839c364b088206e30012a01b42a089f
Stable URL of this page
https://metraipolis.com/documento/dc_7fcdaf3e3312

How to cite

MATCH: Execution-Aware Hierarchical Reinforcement Learning for Vision-and-Language Navigation in Continuous Environment — arXiv:2610.38248 — arXiv (en), https://arxiv.org/abs/2610.38248 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7fcdaf3e3312 (Metraipolis archive dc_7fcdaf3e3312, sha256 81f94643aa1e0b6d34dc84cec880805e5839c364b088206e30012a01b42a089f)
BibTeX
@misc{dc7fcdaf3e3312,
  title = {MATCH: Execution-Aware Hierarchical Reinforcement Learning for Vision-and-Language Navigation in Continuous Environment — arXiv:2610.38248},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.38248},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7fcdaf3e3312; sha256 81f94643aa1e0b6d34dc84cec880805e5839c364b088206e30012a01b42a089f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38248. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires instruction-consistent planning and reliable execution under collision constraints. Yet many hierarchical approaches optimize the planner while keeping execution fixed. We introduce MATCH, a framework that jointly learns a language-conditioned planner and a goal-conditioned primitive-action executor. An execution-aware topological graph represents start-dependent execution options and integrates executor value estimates with realized outcome memory, enabling the planner to select execution requests and refine their targets through bounded continuous offsets. A transition-aware dense macro reward balances ordered progress along the reference route against execution residual, encouraging executable requests without substituting local success for instruction following. A staged curriculum culminates in synchronized on-policy updates, with the executor learning on planner-generated requests and the planner adapting its requests to the executor's current behavior. With 0.5B parameters, MATCH achieves state-of-the-art performance on the R2R-CE and RxR-CE benchmarks. Preliminary real-robot deployments further demonstrate its practical potential.

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/2610.38248 — 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 2026-11-01T02:16:58.623Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).