Metraipolis › archive › dc_5e17aee3da63
Faster Imitation by Re-timing Demonstrations Within the Controller Limit — arXiv:2611.00539
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00539
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:45:59.227Z
- SHA-256 of the archived text
701a9170d63c780c00183dfc4059980036505e089f1f80ec3ebb7e9f1dd552db- Stable URL of this page
https://metraipolis.com/documento/dc_5e17aee3da63
How to cite
Faster Imitation by Re-timing Demonstrations Within the Controller Limit — arXiv:2611.00539 — arXiv (en), https://arxiv.org/abs/2611.00539 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5e17aee3da63 (Metraipolis archive dc_5e17aee3da63, sha256 701a9170d63c780c00183dfc4059980036505e089f1f80ec3ebb7e9f1dd552db)
BibTeX
@misc{dc5e17aee3da63,
title = {Faster Imitation by Re-timing Demonstrations Within the Controller Limit — arXiv:2611.00539},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00539},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5e17aee3da63; sha256 701a9170d63c780c00183dfc4059980036505e089f1f80ec3ebb7e9f1dd552db},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00539. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Imitation policies inherit the operator's pace, and re-timing the demonstrations to run faster works only until success collapses at two to three times demonstration speed. Recent methods attribute that collapse to distribution shift and answer it with finer rules for which segments may be sped up; we show it has a mechanical cause that segment selection cannot address. A low-level controller realises only a bounded displacement per control period, so merging consecutive commands produces sums outside that bound: training pairs that promise a transition the plant cannot deliver. The share of such pairs in the re-timed data, which we call the exceed share, tracks where the retrained policy collapses. The rule that follows has a single parameter: merge greedily while the sum stays realisable. Every command is then realisable by construction, the demonstrated geometry is preserved, and the speed-up lands only where the demonstrator left slack. On four simulated robomimic tasks, 200 held-out seeds per cell, a merge cap of two is at or above the frozen policy's success on all four, by 14 points on Square, and shortens the successful episodes. At matched tempo, uniform re-timing loses 9 and 16 points on Can and ToolHang, is within noise on the other two, and reaches zero on the hardest at 2x. Placement also matters: no shuffled, entropy-guided or speed-conditioned alternative beats the rule on three of the four tasks, by margins the exceed share alone does not explain; on the fourth, at a tempo the task absorbs, every placement lands in the same band. The same principle carries to a simulated humanoid whole-body tracker: re-timing 429 reference motions within its velocity envelope succeeds on 71% of clips at 2.3x, against 51% for uniform time scaling at 2x. 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/2611.00539 — 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 2026-11-03T10:39:50.412Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).