Research map / Reinforcement learning / Policy gradient and actor-critic
Confounding-Robust Policy Improvement
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 nominal-propensity IPW policy learning while unobserved confounding is present | IPW policy learning · Synthetic data | regret relative to the never-treat baseline | Hurt |
| Use causal-forest CATE estimates to choose treatment under unobserved confounding | Direct comparison policy · Synthetic data | regret relative to the never-treat baseline | Hurt |
| Optimize worst-case regret over an uncertainty set of propensity weights | Confounding-robust policy · WHI observational study evaluated on the clinical trial | regret relative to a baseline | Helped |
| Use budgeted rather than pointwise propensity-weight uncertainty (ablation) | Confounding-robust policy · Policy optimization under local confounding | conservativeness | Helped |
Closest papers by meaning
- Towards Safe Policy Learning under Partial Identifiability: A Causal Approach (AAAI 2024 · similarity 0.90)
- Towards Estimating Bounds on the Effect of Policies under Unobserved Confounding (NeurIPS 2024 · similarity 0.88)
- Predictive Performance Comparison of Decision Policies Under Confounding (ICML 2024 · similarity 0.88)
- When to Act and When to Ask: Policy Learning With Deferral Under Hidden Confounding (NeurIPS 2024 · similarity 0.88)
- Distributionally Robust Policy Learning under Concept Drifts (ICML 2025 · similarity 0.87)
- Confounding-Robust Deferral Policy Learning (AAAI 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.