What a Data Release Must Preserve for Off-Policy Evaluation
arXiv:2610.15283v1 Announce Type: new Abstract: In off-policy evaluation, merging decision-time histories that matter differently for a specified policy value or comparison can make that evaluation unidentified, even with observed actions and outcomes and known behavior and target policies. We char…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-14 04:00 · arXiv stat.ML
What a Data Release Must Preserve for Off-Policy Evaluation