Research map / Reinforcement learning / Policy gradient and actor-critic
Data-Efficient Off-Policy Policy Evaluation for Reinforcement 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 weighted importance weights in the doubly robust estimator | Doubly robust off-policy evaluation · Gridworld, ModelFail, ModelWin | mean squared error | Helped |
| Blend WDR with the approximate model using off-policy j-step returns | MAGIC · Hybrid | mean squared error | Helped |
| Blend WDR with the approximate model using off-policy j-step returns | MAGIC · Gridworld, ModelFail, ModelWin | mean squared error | Mixed |
| Restrict blending to the approximate model and WDR, without intermediate j-step returns (ablation) | MAGIC-B · Hybrid | mean squared error | Hurt |
| Use the approximate model instead of WDR | Off-policy evaluation · ModelWin | mean squared error | Helped |
| Use WDR instead of the approximate model | Off-policy evaluation · ModelFail | mean squared error | Helped |
Closest papers by meaning
- More Efficient Off-Policy Evaluation through Regularized Targeted Learning (ICML 2019 · similarity 0.93)
- Doubly Optimal Policy Evaluation for Reinforcement Learning (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 Policy Evaluation with Offline Data Informed Behavior Policy Design (ICML 2024 · similarity 0.90)
- Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPs (ICLR 2025 · similarity 0.89)
- Efficient Multi-Policy Evaluation for Reinforcement Learning (AAAI 2025 · similarity 0.88)
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.