Metraipolis › archive › dc_7115b5fb60a2

Task-Space Imitation Guidance for Efficient Reinforcement Learning — arXiv:2610.07527

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.07527
License (as archived)
CC0-1.0
Archived
2026-10-07T13:12:00.616Z
SHA-256 of the archived text
70095d376b56f912cb6a0038035c81c285ca1028e846f4987d11c9d3749adb2b
Stable URL of this page
https://metraipolis.com/documento/dc_7115b5fb60a2

How to cite

Task-Space Imitation Guidance for Efficient Reinforcement Learning — arXiv:2610.07527 — arXiv (en), https://arxiv.org/abs/2610.07527 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7115b5fb60a2 (Metraipolis archive dc_7115b5fb60a2, sha256 70095d376b56f912cb6a0038035c81c285ca1028e846f4987d11c9d3749adb2b)
BibTeX
@misc{dc7115b5fb60a2,
  title = {Task-Space Imitation Guidance for Efficient Reinforcement Learning — arXiv:2610.07527},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.07527},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7115b5fb60a2; sha256 70095d376b56f912cb6a0038035c81c285ca1028e846f4987d11c9d3749adb2b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07527. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce Task-Space Imitation Guidance for Efficient Reinforcement Learning (TIGER), a reward-construction and pretraining framework for sparse-reward tabletop robotic manipulation. TIGER treats an action-chunked imitation policy not as an executable controller or action prior, but as a local task-space progress estimator: predicted action chunks are converted, using controller-aware action-to-motion mapping, into short-horizon end-effector references, and the RL agent receives dense progress rewards toward these references while the sparse environment reward remains the dominant objective. During pretraining, TIGER uses imitation-guided look-ahead signals to relax conservative value penalties for actions predicted to make task-space progress, reducing off-manifold exploration during early online RL. Across simulation and real-robot experiments, TIGER improves early sample efficiency and reduces measured safety violations while matching or improving final success rates relative to prior RL and IL-RL baselines on the evaluated tasks.

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/2610.07527 — 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 2026-10-07T12:42:33.548Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).