Metraipolis › archive › dc_ed042d099dfc

Residual Denoising Enables Sample-Efficient Multi-Agent Coordination on Demand — arXiv:2609.32129

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32129
License (as archived)
CC0-1.0
Archived
2026-10-08T00:16:54.173Z
SHA-256 of the archived text
8e6d07c83f60631db75402ca855e544b740db1841a9af9f054cb297c26ed6ef0
Stable URL of this page
https://metraipolis.com/documento/dc_ed042d099dfc

How to cite

Residual Denoising Enables Sample-Efficient Multi-Agent Coordination on Demand — arXiv:2609.32129 — arXiv (en), https://arxiv.org/abs/2609.32129 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ed042d099dfc (Metraipolis archive dc_ed042d099dfc, sha256 8e6d07c83f60631db75402ca855e544b740db1841a9af9f054cb297c26ed6ef0)
BibTeX
@misc{dced042d099dfc,
  title = {Residual Denoising Enables Sample-Efficient Multi-Agent Coordination on Demand — arXiv:2609.32129},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32129},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ed042d099dfc; sha256 8e6d07c83f60631db75402ca855e544b740db1841a9af9f054cb297c26ed6ef0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32129. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Pretrained robot policies offer strong manipulation skills but are typically limited to single-agent settings, where a robot acts in isolation. In this work, we study how to adapt pretrained single-agent diffusion policies to multi-agent settings using minimal collaborative data, co-optimizing for two key objectives: high coordination performance and single-agent skill retention. To this end, we introduce ALTER, an adaptation method for coordination on demand: the adapted policy coordinates with other robots when deployed in a team while remaining capable of acting independently when operating alone. Execution is decentralized: each robot acts only on its own visual observations, without explicit inter-agent communication. Our method trains a coordination head that predicts a residual denoiser to transform single-agent behavior into coordinated multi-agent behavior when necessary while also preserving single-agent capabilities. To preserve single-agent capabilities, we augment a small number of collaborative demonstrations with self-distilled data generated by the base policy during training of the residual denoiser. In simulation, ALTER achieves higher coordination success over our baselines while retaining much higher source-skill retention. In our hardware experiments, we find similar trends where ALTER better co-optimizes for coordination success and single-agent skill retention than the baselines.

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/2609.32129 — 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 2026-10-07T23:52:16.403Z 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).