Research map / Reinforcement learning / Policy gradient and actor-critic
Learning Robust Decision Policies from Observational Data
Muhammad Osama, Dave Zachariah, Peter Stoica
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Choose treatments by minimizing a conformal upper cost limit instead of minimizing expected cost | Robust policy · Synthetic blood-pressure data | 20% tail cost | Improved |
| Choose treatments by minimizing a conformal upper cost limit instead of minimizing expected cost | Robust policy · Synthetic blood-pressure data | expected cost | Hurt |
| Use a robust policy rather than the past policy | Robust policy · IHDP synthetic outcomes, equal dispersion and higher untreated dispersion | 20% tail cost | Improved |
| Use a robust policy rather than the linear expected-cost policy | IHDP synthetic outcomes, equal dispersion and higher untreated dispersion · IHDP synthetic outcomes | 20% tail cost | Improved |
| Adapt treatment assignment to higher treated-outcome dispersion | Robust policy · IHDP synthetic outcomes, higher treated dispersion | tail cost | Improved |
| Use a linear expected-cost policy when treated outcomes have higher dispersion | Linear policy · IHDP synthetic outcomes, higher treated dispersion | tail cost | Hurt |
| Provide a conformal cost limit for each decision | Robust policy · IHDP test data | exceedance probability: 18.6% vs 20% | Improved |
Closest papers by meaning
- Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse Agents (ICML 2025 · similarity 0.87)
- Towards Safe Policy Learning under Partial Identifiability: A Causal Approach (AAAI 2024 · similarity 0.87)
- When to Act and When to Ask: Policy Learning With Deferral Under Hidden Confounding (NeurIPS 2024 · similarity 0.86)
- Learning with Selectively Labeled Data from Multiple Decision-makers (ICML 2025 · similarity 0.85)
- Distributionally Robust Policy Learning under Concept Drifts (ICML 2025 · similarity 0.85)
- SafeAR: Safe Algorithmic Recourse by Risk-Aware Policies (AAAI 2024 · similarity 0.85)
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.
