Research map / Reinforcement learning / Policy gradient and actor-critic
More Robust Doubly Robust 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 |
|---|---|---|---|
| Learn the DR model parameters by minimizing the DR estimator variance (MRDR instead of standard DR) | DR for off-policy evaluation · Vehicle, Friendly I | RMSE: 0.0217 -> 0.0202 | Helped |
| Learn the DR model parameters by minimizing the DR estimator variance (MRDR instead of standard DR) | DR for off-policy evaluation · SatImage, Friendly I | RMSE: 0.0071 -> 0.0063 | Helped |
| Learn the DR model parameters by minimizing the DR estimator variance (MRDR instead of standard DR) | DR for off-policy evaluation · PenDigits, Friendly I | RMSE: 0.0056 -> 0.0037 | Helped |
| Learn the DR model parameters by minimizing the DR estimator variance (MRDR instead of standard DR) | DR for off-policy evaluation · Letter, Friendly I | RMSE: 0.0056 -> 0.0044 | Helped |
| Learn the DR model parameters by minimizing the DR estimator variance (MRDR instead of standard DR) | DR for off-policy evaluation · ModelFail, sample size 32 | MSE: 0.18461 -> 0.1698 | Helped |
| Learn the DR model parameters by minimizing the DR estimator variance (MRDR instead of standard DR) | DR for off-policy evaluation · Modelwin, sample size 32 | MSE: 1.55244 -> 1.46778; DM: 0.06182 | Mixed |
| Learn the DR model parameters by minimizing the DR estimator variance (MRDR instead of standard DR) | DR for off-policy evaluation · 4×4 Maze, sample size 128 | MSE: 0.70465 -> 0.57042 | Helped |
| Learn the DR model parameters by minimizing the DR estimator variance (MRDR instead of standard DR) | DR for off-policy evaluation · Mountain Car, sample size 128 | MSE: 16.14661 -> 14.96227 | Helped |
| Learn the DR model parameters by minimizing the DR estimator variance (MRDR instead of standard DR) | DR for off-policy evaluation · Cart Pole, sample size 32 | MSE: 0.34775 -> 0.27208 | Helped |
| Use DM rather than MRDR | Off-policy evaluation · Modelwin, sample size 32 | MSE: 1.46778 -> 0.06182 | Helped |
Closest papers by meaning
- Doubly Robust Off-policy Value Evaluation for Reinforcement Learning (ICML 2016 · similarity 0.95)
- Intrinsically Efficient, Stable, and Bounded Off-Policy Evaluation for Reinforcement Learning (NeurIPS 2019 · similarity 0.92)
- More Efficient Off-Policy Evaluation through Regularized Targeted Learning (ICML 2019 · similarity 0.92)
- Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol (NeurIPS 2025 · similarity 0.89)
- Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation (ICML 2025 · similarity 0.88)
- Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning (NeurIPS 2024 · 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.