Metraipolis › archive › dc_aea02d021c4e
Efficient Test-Time Adaptation For Robot Policies — arXiv:2610.20318
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.20318
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T14:23:49.701Z
- SHA-256 of the archived text
747c01b64c64674e7338a054f946b03ab037fa0415492e32c95bd48bc8ff85b5- Stable URL of this page
https://metraipolis.com/documento/dc_aea02d021c4e
How to cite
Efficient Test-Time Adaptation For Robot Policies — arXiv:2610.20318 — arXiv (en), https://arxiv.org/abs/2610.20318 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aea02d021c4e (Metraipolis archive dc_aea02d021c4e, sha256 747c01b64c64674e7338a054f946b03ab037fa0415492e32c95bd48bc8ff85b5)
BibTeX
@misc{dcaea02d021c4e,
title = {Efficient Test-Time Adaptation For Robot Policies — arXiv:2610.20318},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.20318},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aea02d021c4e; sha256 747c01b64c64674e7338a054f946b03ab037fa0415492e32c95bd48bc8ff85b5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20318. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reinforcement-learning policies for robot locomotion can fail at deployment when operating conditions shift (e.g., rough or slippery terrain, payload changes, sensing degradation), and retraining or manual recalibration is often infeasible under on-device latency and memory constraints. We study test-time adaptation (TTA) for robotic control: adapting a pretrained policy online and in a self-supervised manner during execution, without access to rewards. Our starting point is a lightweight baseline that updates only the actor using a frozen pretrained critic as a deployment-time performance surrogate. Building on this, we introduce TEMPO, a test-time entropy-regularized, memory-guided policy optimization method that stabilizes critic-driven updates under severe shift. TEMPO combines (i) an entropy-promoting regularizer on the critic's predictive distribution to mitigate overconfident extrapolation, and (ii) a score-based memory, inspired by prioritized replay, that prioritizes low-value ("hard") observations and applies importance sampling to focus limited computation on the most informative deployment conditions. Across Go1, Go2, and G1 in MuJoCo Playground under four representative shifts and multiple architectures, TEMPO yields consistent gains, reaching up to 80% improvement in a single-device setting. We further validate on a physical Unitree Go2 with an added calf payload, where fully on-device adaptation improves performance over the non-adapted baseline across real-world episodes.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.20318 — 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 2026-10-15T13:53:35.956Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).