Metraipolis › archive › dc_1cee18dc3da9

Scouting the Dynamics Gap: Test-Time Policy Adaptation via Action-Outcome Feedback — arXiv:2609.36107

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36107
License (as archived)
CC0-1.0
Archived
2026-10-07T19:15:04.761Z
SHA-256 of the archived text
26882b8c013722a95e050916b9034c758a06a82ef9ea51331102f792bdf8f784
Stable URL of this page
https://metraipolis.com/documento/dc_1cee18dc3da9

How to cite

Scouting the Dynamics Gap: Test-Time Policy Adaptation via Action-Outcome Feedback — arXiv:2609.36107 — arXiv (en), https://arxiv.org/abs/2609.36107 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1cee18dc3da9 (Metraipolis archive dc_1cee18dc3da9, sha256 26882b8c013722a95e050916b9034c758a06a82ef9ea51331102f792bdf8f784)
BibTeX
@misc{dc1cee18dc3da9,
  title = {Scouting the Dynamics Gap: Test-Time Policy Adaptation via Action-Outcome Feedback — arXiv:2609.36107},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36107},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1cee18dc3da9; sha256 26882b8c013722a95e050916b9034c758a06a82ef9ea51331102f792bdf8f784},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36107. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

While pretrained robotic policies exhibit impressive capabilities in controlled environments, unobserved physical properties and dynamics require these policies to rapidly adapt during deployment. Existing test-time adaptation methods typically rely on sparse scalar rewards, failing to exploit the rich geometric and dynamic feedback from the environment during physical interaction. To address this challenge, we propose SCOUT, a dynamics-aware meta-learning framework that enables manipulation policies to rapidly adapt by continuously revising their internal beliefs about environment dynamics. Our approach couples an action-prediction policy with a forward dynamics model via a shared belief latent space. During meta-training, an inner loop updates this shared belief latent by minimizing the dynamics prediction error against the observed action outcome, while the outer loop optimizes the network for action selection. At deployment, this structure allows the agent to infer and adapt to unknown physical dynamics on the fly. By updating its latent belief based on action-outcome mismatches, the policy automatically adapts without risking catastrophic forgetting. We demonstrate that SCOUT significantly accelerates online adaptation across simulated manipulation benchmarks and achieves robust sim-to-real transfer in the real world. Project webiste can be found here: this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.36107 — 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 2026-10-07T18:40:59.380Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).