Research map / Reinforcement learning / Policy gradient and actor-critic
Off-Policy Evaluation with Policy-Dependent Optimization Response
Wenshuo Guo, Michael Jordan, Angela Zhou
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 WDM or GRDR instead of the direct method under outcome-model misspecification | Policy evaluation on synthetic bipartite matching · Synthetic bipartite matching, misspecified outcome model | MSE | Improved |
| Apply the perturbation debiasing method (ablation) | WDM and GRDR policy-value estimators · Synthetic bipartite matching, misspecified setting | MSE | Improved |
| Use WDM or GRDR instead of the direct method | Policy optimization with a logistic treatment policy · Synthetic bipartite matching | Policy value | Improved |
| Use the direct method rather than WDM or GRDR | Policy optimization with a logistic treatment policy · Synthetic bipartite matching | Policy value | Hurt |
| Use WDM or GRDR rather than direct regression under model misspecification | Conditional causal-effect estimation · Synthetic confounded treatment data | Conditional estimation error | Improved |
Closest papers by meaning
- Off-policy estimation with adaptively collected data: the power of online learning (NeurIPS 2024 · similarity 0.88)
- Towards Estimating Bounds on the Effect of Policies under Unobserved Confounding (NeurIPS 2024 · similarity 0.88)
- Two-way Deconfounder for Off-policy Evaluation in Causal Reinforcement Learning (NeurIPS 2024 · similarity 0.88)
- Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy Evaluation (NeurIPS 2024 · similarity 0.87)
- Predictive Performance Comparison of Decision Policies Under Confounding (ICML 2024 · similarity 0.87)
- Off-policy Evaluation Beyond Overlap: Sharp Partial Identification Under Smoothness (ICML 2024 · 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.
