Metraipolis › archive › dc_8090678eee23

Beyond State-as-Action: Exploiting Command-State Discrepancy for Robot Imitation Learning — arXiv:2609.33145

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33145
License (as archived)
CC0-1.0
Archived
2026-10-08T00:17:04.506Z
SHA-256 of the archived text
a8bd5b6f04977a15870a16d15838bcb49cc6fc67ec514e058428594dafd594e5
Stable URL of this page
https://metraipolis.com/documento/dc_8090678eee23

How to cite

Beyond State-as-Action: Exploiting Command-State Discrepancy for Robot Imitation Learning — arXiv:2609.33145 — arXiv (en), https://arxiv.org/abs/2609.33145 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8090678eee23 (Metraipolis archive dc_8090678eee23, sha256 a8bd5b6f04977a15870a16d15838bcb49cc6fc67ec514e058428594dafd594e5)
BibTeX
@misc{dc8090678eee23,
  title = {Beyond State-as-Action: Exploiting Command-State Discrepancy for Robot Imitation Learning — arXiv:2609.33145},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33145},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8090678eee23; sha256 a8bd5b6f04977a15870a16d15838bcb49cc6fc67ec514e058428594dafd594e5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33145. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Constructing action targets from measured robot motion is an established approach in imitation learning. Under interaction constraints, however, command-state discrepancy may reflect control demands that motion alone does not capture. We investigate when this information matters and how to exploit it. Across three real-robot tasks, task and phase analyses reveal larger supervision gaps under constrained interaction, while selective command retention provides evidence of locally useful command information. Building on these findings, we propose Command-State Discrepancy Weighting (CSDW), which accounts for robot response times and combines subsequent progress, persistent unmet demand, and demand changes into continuous weights for command supervision. The method requires no task-phase annotations or changes to policy architecture or inference. CSDW improves over uniform command supervision on constrained tasks, while methods perform similarly in the less constrained task. Project page: this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.33145 — 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 2026-10-07T23:52:16.455Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).