Research map / Reinforcement learning / Policy gradient and actor-critic
Optimal Off-Policy Evaluation from Multiple Logging Policies
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use SMRDR, choosing the control variate to minimize variance under stratified sampling instead of using MRDR's iid-sampling objective | OPE with multiple logging policies · optdigits and pendigits | Relative-RMSE: up to 45% reduction in error | Helped |
| Use SMRDR instead of DR | OPE with multiple logging policies · optdigits and pendigits, especially when n1/n2 is small | Relative-RMSE | Helped |
| Use DR instead of SMRDR | OPE with multiple logging policies · optdigits when n1/n2 is large | Relative-RMSE | Helped |
| Choose between IS, IS-Avg, IS-PW, DR-Avg, and DR-PW based on the data instance rather than using a fixed ordering | OPE with multiple logging policies · optdigits | Relative-RMSE | Mixed |
Closest papers by meaning
- State Relevance for Off-Policy Evaluation (ICML 2021 · similarity 0.89)
- Off-policy Evaluation Beyond Overlap: Sharp Partial Identification Under Smoothness (ICML 2024 · similarity 0.89)
- Log-Sum-Exponential Estimator for Off-Policy Evaluation and Learning (ICML 2025 · similarity 0.87)
- Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning (NeurIPS 2024 · similarity 0.86)
- Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation (ICML 2025 · similarity 0.86)
- Off-Policy Evaluation under Nonignorable Missing Data (ICML 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.