Metraipolis › archive › dc_ef41554754df

Learning from an Imitable Teacher: Competition Solution for the MetaFine Challenge — arXiv:2611.00615

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.00615
License (as archived): CC0-1.0
Archived: 2026-11-03T10:25:57.482Z
SHA-256 of the archived text: 6dca664e209396409936deec310b05e50284ff94deb3bd8b5216fe9045e6abfc
Stable URL of this page: https://metraipolis.com/documento/dc_ef41554754df

How to cite

Learning from an Imitable Teacher: Competition Solution for the MetaFine Challenge — arXiv:2611.00615 — arXiv (en), https://arxiv.org/abs/2611.00615 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ef41554754df (Metraipolis archive dc_ef41554754df, sha256 6dca664e209396409936deec310b05e50284ff94deb3bd8b5216fe9045e6abfc)

BibTeX

@misc{dcef41554754df,
  title = {Learning from an Imitable Teacher: Competition Solution for the MetaFine Challenge — arXiv:2611.00615},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00615},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ef41554754df; sha256 6dca664e209396409936deec310b05e50284ff94deb3bd8b5216fe9045e6abfc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00615. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The MetaFine Open Competition (RoboFineMani workshop, CoRL 2026) evaluates fine-grained manipulation beyond binary success. Its five simulated tasks, from grasping a bottle by an instructed part to inserting letter-shaped pegs with 4 mm clearance, are scored on perception under lighting and camera changes, instruction understanding, and behavior. This report presents Team Friday's solution, which got second place with an overall score of 0.947, more than twice the $\pi_0$ baseline. Instead of fine-tuning a large vision-language-action (VLA) model, we train one 19M-parameter policy per task with a separate instruction classifier and focus on the data, all generated in the simulator by a privileged scripted teacher, including its corrections of the student's mistakes. By analyzing failed episodes, we find that a teacher that almost always succeeds can still teach a memoryless student badly: its pauses become stalls, its fixed habits become shortcuts, and it never shows the errors the student makes. Making the teacher \emph{imitable} raised the official score on letter insertion, the hardest task, from 0.44 to 0.82 with 32\% more data and the same architecture, and finally to 0.88. We summarize practical lessons on demonstration data and evaluation, which we hope will help in imitation learning for precise manipulation.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.00615 — 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 2026-11-03T10:19:50.022Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).