Metraipolis › archive › dc_31d8528232df

GUILD: Guided Iterative Data Collection for Imitation Learning — arXiv:2611.05368

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.05368
License (as archived)
CC0-1.0
Archived
2026-11-04T12:42:55.850Z
SHA-256 of the archived text
bde74f04b196aff46635d751b4c6711deaba8833dbdc560f0efe028f48786782
Stable URL of this page
https://metraipolis.com/documento/dc_31d8528232df

How to cite

GUILD: Guided Iterative Data Collection for Imitation Learning — arXiv:2611.05368 — arXiv (en), https://arxiv.org/abs/2611.05368 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_31d8528232df (Metraipolis archive dc_31d8528232df, sha256 bde74f04b196aff46635d751b4c6711deaba8833dbdc560f0efe028f48786782)
BibTeX
@misc{dc31d8528232df,
  title = {GUILD: Guided Iterative Data Collection for Imitation Learning — arXiv:2611.05368},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05368},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_31d8528232df; sha256 bde74f04b196aff46635d751b4c6711deaba8833dbdc560f0efe028f48786782},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05368. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Imitation learning policies in robotics are trained on datasets collected through costly real-world teleoperation. Often, the data-collection process is unguided, relying on the teleoperator's intuition, resulting in data that contributes little to overall policy performance. Recent work has shown that curating such unguided datasets can substantially improve policy performance, but these approaches operate by filtering existing datasets after collection and therefore do not prevent the acquisition of uninformative data. In this work, we propose GUILD, a novel Guided Data Collection (GDC) method that actively reasons about which data should be collected to maximize downstream policy performance. We introduce an iterative framework that alternates between 1) task proposal and data collection and 2) data evaluation to close the loop. For task proposal, we leverage semantic priors from vision-language models to identify relevant environments, object configurations, and goals for data collection. However, since semantic relevance does not imply policy improvement, we perform data evaluation. By leveraging predictive data attribution we approximate how the collected trajectories influence policy performance on a target deployment setting. This signal is then used as feedback to guide subsequent data collection, closing the data collection loop. We evaluate our approach in simulation and real robot settings, demonstrating that guided data collection substantially improves sample efficiency and deployment performance compared to passive data collection strategies, multiple baselines and experienced roboticists. More information at this https URL

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.05368 — 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 2026-11-04T12:29:47.415Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).