Research map / Reinforcement learning / Policy gradient and actor-critic
Off-Policy Evaluation and Learning for External Validity under a Covariate Shift
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 DRCS instead of DM | OPE on SatImage · SatImage, behavior (a) | MSE: 0.042 -> 0.107 | Hurt |
| Use DRCS instead of IPWCS-R | OPE on SatImage · SatImage, behavior (b) | MSE: 0.093 -> 0.096 | Hurt |
| Use DRCS instead of IPWCS-R | OPE on SatImage · SatImage, behavior (c) | MSE: 0.022 -> 0.154 | Hurt |
| Use DRCS instead of the strongest listed baseline | OPE on Vehicle · Vehicle, behaviors (a), (b), and (c) | MSE: 0.038 -> 0.029; 0.089 -> 0.019; 0.210 -> 0.037 | Helped |
| Use DRCS instead of the strongest listed baseline | OPL on SatImage · SatImage, behaviors (a), (b), and (c) | RWD: 0.658 -> 0.723; 0.641 -> 0.710; 0.465 -> 0.652 | Helped |
| Use DRCS instead of DM | OPL on Vehicle · Vehicle, behaviors (a), (b), and (c) | RWD: 0.411 -> 0.496; 0.393 -> 0.510; 0.313 -> 0.480 | Helped |
| Use cross-fitting with the doubly robust estimator | DRCS · OPE under covariate shift | asymptotic MSE | Helped |
| Estimate the covariate density ratio and include it in OPE | Off-policy evaluation under covariate shift · Covariate-shifted evaluation data | consistency | Helped |
Closest papers by meaning
- OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators (NeurIPS 2024 · similarity 0.87)
- Off-Policy Evaluation under Nonignorable Missing Data (ICML 2025 · similarity 0.87)
- Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation (ICLR 2024 · similarity 0.86)
- Off-policy estimation with adaptively collected data: the power of online learning (NeurIPS 2024 · similarity 0.86)
- Two-way Deconfounder for Off-policy Evaluation in Causal Reinforcement Learning (NeurIPS 2024 · similarity 0.86)
- Log-Sum-Exponential Estimator for Off-Policy Evaluation and Learning (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.