Metraipolis › archive › dc_515f5fb1102f

SCAPE: Scenario-Conditioned Simulation-Augmented Policy Evaluation — arXiv:2608.19425

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.19425
License (as archived)
CC0-1.0
Archived
2026-10-18T11:48:38.553Z
SHA-256 of the archived text
cbed1bc650d9d93ae317b0adb4a14dbf191c25183867ff40d978227b6b7aa7a7
Stable URL of this page
https://metraipolis.com/documento/dc_515f5fb1102f

How to cite

SCAPE: Scenario-Conditioned Simulation-Augmented Policy Evaluation — arXiv:2608.19425 — arXiv (en), https://arxiv.org/abs/2608.19425 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_515f5fb1102f (Metraipolis archive dc_515f5fb1102f, sha256 cbed1bc650d9d93ae317b0adb4a14dbf191c25183867ff40d978227b6b7aa7a7)
BibTeX
@misc{dc515f5fb1102f,
  title = {SCAPE: Scenario-Conditioned Simulation-Augmented Policy Evaluation — arXiv:2608.19425},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.19425},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_515f5fb1102f; sha256 cbed1bc650d9d93ae317b0adb4a14dbf191c25183867ff40d978227b6b7aa7a7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19425. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reliable performance evaluation is a central bottleneck for deploying robot-learning policies in real-world conditions. Real-world testing is faithful but costly and difficult to scale, whereas simulation-based testing scales easily but is inevitably biased by the sim-to-real gap. Existing simulation-augmented methods combine limited real-world rollouts with abundant simulation proxies, but focus on performance averaged over initial conditions and deployment settings. Such population-level averages obscure scenario-specific variation and provide limited guidance about when and where a policy can be safely deployed. We propose SCAPE, a scenario-conditioned simulation-augmented policy evaluation framework that predicts scenario-conditioned real-world policy performance using limited paired sim-and-real samples and large-scale simulation rollouts. SCAPE corrects sim-to-real bias in simulation labels before training the prediction model and calibrates prediction uncertainty through conformal prediction. We validate SCAPE on autonomous driving and quadruped velocity tracking. In sim-to-sim studies, SCAPE reduces scenario-level prediction error by 4.9%/34.7% (driving) and 14.5%/27.7% (quadruped) relative to scene-conditioned neural and aggregate statistical baselines on average. We further evaluate a velocity-tracking policy deployed on a physical Unitree Go2. SCAPE also improves testing sample efficiency, produces narrower calibrated prediction intervals, generalizes better to out-of-distribution scenarios, and enables fine-grained deployment strategies.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-21 in cs.LG).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.19425 — 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 2026-10-18T11:47:43.364Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).