Metraipolis › archive › dc_8fef2edc8788

Res-HIL: Human-Guided Residual Reinforcement Learning for Sample-Efficient Dexterous Manipulation — arXiv:2609.30023

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30023
License (as archived)
CC0-1.0
Archived
2026-10-08T07:17:06.177Z
SHA-256 of the archived text
23aeb9dce67891fde74d87186e03d16c9dabc34ffed2a7b52355d9e5d8a9a9e5
Stable URL of this page
https://metraipolis.com/documento/dc_8fef2edc8788

How to cite

Res-HIL: Human-Guided Residual Reinforcement Learning for Sample-Efficient Dexterous Manipulation — arXiv:2609.30023 — arXiv (en), https://arxiv.org/abs/2609.30023 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8fef2edc8788 (Metraipolis archive dc_8fef2edc8788, sha256 23aeb9dce67891fde74d87186e03d16c9dabc34ffed2a7b52355d9e5d8a9a9e5)
BibTeX
@misc{dc8fef2edc8788,
  title = {Res-HIL: Human-Guided Residual Reinforcement Learning for Sample-Efficient Dexterous Manipulation — arXiv:2609.30023},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30023},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8fef2edc8788; sha256 23aeb9dce67891fde74d87186e03d16c9dabc34ffed2a7b52355d9e5d8a9a9e5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30023. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Imitation learning enables robots to acquire manipulation skills from demonstrations, but the resulting policies can fail outside the training data, while collecting more demonstrations requires substantial human effort. Human-in-the-loop reinforcement learning uses corrective feedback during online training, but typically learns the complete task policy rather than refining a pretrained imitation policy. We introduce Res-HIL, a human-in-the-loop residual reinforcement learning framework that learns corrective actions on top of a frozen imitation policy. Each human intervention provides two complementary learning signals: direct supervision of the residual policy and reward shaping of preceding autonomous behavior. Res-HIL combines these signals with zero initialization of the residual policy to stabilize and accelerate online learning. We evaluate Res-HIL on five contact-rich manipulation tasks spanning high-precision and long-horizon behaviors. With only 20 initial demonstrations, Res-HIL outperforms state-of-the-art full-policy human-in-the-loop reinforcement learning and residual fine-tuning without human guidance on every task after ten minutes of online training. Res-HIL improves its pretrained base policies and outperforms imitation policies trained with five times more demonstrations. An ablation study shows that direct residual supervision is critical to performance, while intervention-aware reward shaping substantially improves training efficiency.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.30023 — 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 2026-10-08T06:38:53.833Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).