Research map / Reinforcement learning / Policy gradient and actor-critic
State Relevance for Off-Policy Evaluation
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 |
|---|---|---|---|
| omit likelihood ratios for estimated irrelevant states with OSIRIS rather than use ordinary IS | IS · Dilly-Dallying Gridworld | RMSE: 6.9 -> 3.6 | Helped |
| use weighted OSIRIS rather than ordinary IS | IS · Dilly-Dallying Gridworld | RMSE: 6.9 -> 3.7 | Helped |
| omit likelihood ratios for estimated irrelevant states with OSIRIS rather than use ordinary IS | IS · Express Gridworld | RMSE: 3.7 -> 3.8 | Hurt |
| use weighted OSIRIS rather than ordinary IS | IS · Express Gridworld | RMSE: 3.7 -> 3.7 | No clear effect |
| omit likelihood ratios for estimated irrelevant states with OSIRIS rather than use ordinary IS | IS · Cart Pole | RMSE: 10211.3 -> 3985.5 | Hurt |
| use weighted OSIRIS rather than ordinary IS | IS · Cart Pole | RMSE: 10211.3 -> 809.2 | Helped |
| omit likelihood ratios for estimated irrelevant states with OSIRIS rather than use ordinary IS | IS · Lunar Lander | RMSE: 771.1 -> 55.3 | Helped |
| use weighted OSIRIS rather than ordinary IS | IS · Lunar Lander | RMSE: 771.1 -> 25.7 | Helped |
Closest papers by meaning
- Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling (ICML 2020 · similarity 0.93)
- Using Options and Covariance Testing for Long Horizon Off-Policy Policy Evaluation (NeurIPS 2017 · similarity 0.92)
- SOPE: Spectrum of Off-Policy Estimators (NeurIPS 2021 · similarity 0.92)
- Off-Policy Evaluation under Nonignorable Missing Data (ICML 2025 · similarity 0.88)
- Off-policy Evaluation Beyond Overlap: Sharp Partial Identification Under Smoothness (ICML 2024 · similarity 0.88)
- Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation (ICML 2025 · similarity 0.87)
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.