Research map / Reinforcement learning / Policy gradient and actor-critic
More Efficient Off-Policy Evaluation through Regularized Targeted Learning
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 RLTMLE 2, an ensemble of regularized LTMLE estimators with weight softening, partial horizons, and penalization | Off-policy evaluation · ModelFail, ModelWin, and GridWorld | MSE | Helped |
| Add weight softening (ablation) | WDR · ModelWin | MSE | Helped |
| Add partial horizons and weight softening (ablation) | LTMLE base estimators · ModelWin, low model misspecification | MSE | Helped |
| Add penalization to partial, softened LTMLE (ablation) | LTMLE base estimators · ModelWin, high model misspecification | MSE | Mixed |
| Use partial importance sampling with a shorter horizon (ablation) | LTMLE · Off-policy evaluation | MSE | Mixed |
Closest papers by meaning
- Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning (ICML 2016 · similarity 0.93)
- Doubly Robust Off-policy Value Evaluation for Reinforcement Learning (ICML 2016 · similarity 0.93)
- Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol (NeurIPS 2025 · similarity 0.92)
- Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPs (ICLR 2025 · similarity 0.91)
- Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation (ICML 2025 · similarity 0.91)
- Efficient Multi-Policy Evaluation for Reinforcement Learning (AAAI 2025 · similarity 0.90)
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.