Research map / Reinforcement learning / Policy gradient and actor-critic
A Minimax Approach for Optimal Intervention Policy Learning with Two-Stage Outcomes
Chenyang Li, Hao Mei, Yue Liu
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 |
|---|---|---|---|
| use principal-strata minimax estimator instead of plain OR uplift | OR · ML-1M | policy return: 111,510 -> 136,268 | Improved |
| use principal-strata minimax estimator instead of plain IPS | IPS · ML-1M | policy return: 112,620 -> 147,381 | Improved |
| use principal-strata minimax estimator instead of plain DR | DR · ML-1M | policy return: 104,230 -> 150,442 | Improved |
| use principal-strata minimax estimator instead of plain OR | OR · Jester | policy return: 102,985 -> 147,923 | Improved |
| use principal-strata minimax estimator instead of plain IPS | IPS · Jester | policy return: 83,555 -> 131,291 | Improved |
| use principal-strata minimax estimator instead of plain DR | DR · Jester | policy return: 99,916 -> 131,465 | Improved |
| use uplift (causal) estimation instead of naive outcome-based allocation | NAIVE · ML-1M | policy return: 42,670 -> 111,510 | Improved |
| use uplift (causal) estimation instead of naive outcome-based allocation | NAIVE · Jester | policy return: 77,310 -> 102,985 | Improved |
Closest papers by meaning
- Reflective Prompted Policy Optimization: Trajectory-Grounded Revision and Salience Bias (NeurIPS 2026 · similarity 0.87)
- Policy Learning for Balancing Short-Term and Long-Term Rewards (ICML 2024 · similarity 0.87)
- A Minimaximalist Approach to Reinforcement Learning from Human Feedback (ICML 2024 · similarity 0.85)
- Variational Counterfactual Intervention Planning to Achieve Target Outcomes (ICML 2025 · similarity 0.85)
- Towards Safe Policy Learning under Partial Identifiability: A Causal Approach (AAAI 2024 · similarity 0.85)
- Refining Minimax Regret for Unsupervised Environment Design (ICML 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.
