Research map / Reinforcement learning / Policy gradient and actor-critic
Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modeling
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 |
|---|---|---|---|
| Adding cluster importance weighting plus model-based residual estimation (OffCEM) instead of IPS | OffCEM · Synthetic, n=500 | MSE relative to IPS: OffCEM MSE ratio 0.169 vs IPS (about 83% reduction) | Helped |
| Using OffCEM instead of DR with many actions | OffCEM · Synthetic, |A|=4000 | MSE relative to DR: ratio 0.112 vs DR | Helped |
| Adding cluster importance weighting and regression to MIPS (gradual ablation) (ablation) | MIPS · Synthetic ablation | MSE | Helped |
| Cluster importance weighting alone (no residual model) (ablation) | MIPS-style estimator · Synthetic ablation | MSE | Hurt |
| Regression model with marginal importance weights only (no clustering) (ablation) | MIPS · Synthetic ablation | MSE | Hurt |
| Two-step regression instead of one-step regression within OffCEM (ablation) | OffCEM · Synthetic ablation | MSE | Helped |
| Cluster importance weighting with uniform random clusters and neural regression on real data | OffCEM · EUR-Lex 4K / Wiki10-31K | MSE | Helped |
| Increasing number of unsupported actions (common support violation) | IPS, DR, MIPS · Synthetic | MSE | Mixed |
Closest papers by meaning
- Off-Policy Learning in Large Action Spaces: Optimization Matters More Than Estimation (ICML 2026 · similarity 0.92)
- POTEC: Off-Policy Contextual Bandits for Large Action Spaces via Policy Decomposition (ICLR 2025 · similarity 0.92)
- Optimal and Adaptive Off-policy Evaluation in Contextual Bandits (ICML 2017 · similarity 0.91)
- Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning (NeurIPS 2024 · similarity 0.88)
- Log-Sum-Exponential Estimator for Off-Policy Evaluation and Learning (ICML 2025 · similarity 0.88)
- Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy Evaluation (NeurIPS 2024 · similarity 0.88)
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.