STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation
NeurIPSSpotlight2025
TL;DR
Off-policy evaluation (OPE) estimates the performance of a target policy using offline data collected from a behavior policy, and is crucial in domains such as robotics or healthcare where direct inte…
Opening excerpt from the authors’ abstract. source
Read the paper
Topics
evaluation diffusion robotics
← All NeurIPS 2025 Spotlight papers · Browse the whole archive