SCAPE: Scenario-Conditioned Simulation-Augmented Policy Evaluation
Read the original on Hugging Face Trending Papers →SCAPE is a scenario‑conditioned simulation‑augmented policy evaluation framework that predicts real‑world policy performance for specific scenarios using limited paired simulation‑and‑real samples and extensive simulation rollouts. It corrects sim‑to‑real bias in simulation labels before training the prediction model and calibrates prediction uncertainty via conformal prediction. Experiments on autonomous driving and quadruped velocity tracking show SCAPE reduces scenario‑level prediction error, improves testing sample efficiency, narrows calibrated prediction intervals, and generalizes better to out‑of‑distribution scenarios, enabling fine‑grained deployment strategies.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.