Metraipolis › archive › dc_184691f503cf

ReF-HIL: Shaping the Critic around Human Action Neighborhoods for Efficient Human-in-the-Loop Reinforcement Learning — arXiv:2609.37131

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.37131
License (as archived): CC0-1.0
Archived: 2026-10-07T19:15:32.279Z
SHA-256 of the archived text: 829032c13f8641d00c552f8a139187ab383bea80cdcd4e09d3b511024d86b605
Stable URL of this page: https://metraipolis.com/documento/dc_184691f503cf

How to cite

ReF-HIL: Shaping the Critic around Human Action Neighborhoods for Efficient Human-in-the-Loop Reinforcement Learning — arXiv:2609.37131 — arXiv (en), https://arxiv.org/abs/2609.37131 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_184691f503cf (Metraipolis archive dc_184691f503cf, sha256 829032c13f8641d00c552f8a139187ab383bea80cdcd4e09d3b511024d86b605)

BibTeX

@misc{dc184691f503cf,
  title = {ReF-HIL: Shaping the Critic around Human Action Neighborhoods for Efficient Human-in-the-Loop Reinforcement Learning — arXiv:2609.37131},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37131},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_184691f503cf; sha256 829032c13f8641d00c552f8a139187ab383bea80cdcd4e09d3b511024d86b605},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37131. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Human-in-the-loop reinforcement learning (HIL-RL) offers a promising route to efficient training of robotic manipulation policies by combining autonomous learning with human demonstrations and online corrections. However, insufficient use of successful human experience in value learning prolongs costly real-world training, while persistent imitation penalties can limit value-driven policy improvement. To address these limitations, we propose ReF-HIL, an efficient HIL-RL framework that uses human guidance to accelerate the learning process. Human-Reference-Guided Value Shaping learns an independent value reference from successful human experience to guide online value learning, while incorporating local corrective feedback. A Human Action Fence defines a learned human-action neighborhood, allowing value-driven optimization for better performance without imitation penalties inside while constraining policy and value updates outside. Experiments on five diverse and challenging real-world manipulation tasks demonstrate improved overall learning efficiency and higher success rates compared with the evaluated baselines. Specifically, ReF-HIL reaches 90% autonomous success in only 18-63 minutes of active training and achieves final success rates of 91.7-100%. These results highlight the potential of human-guided reinforcement learning to acquire reliable manipulation skills efficiently in the real world. Project website: this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.37131 — 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 2026-10-07T18:40:59.484Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).