Research map / Reinforcement learning / Policy gradient and actor-critic
Cost-Effective Incentive Allocation via Structured Counterfactual Inference
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 |
|---|---|---|---|
| Add HSIC regularization to CCPOvIRE (ablation) | CCPOvIRE · Fully-simulated data, binary action | PEHE: 0.0404 ± 0.0011 -> 0.0385 ± 0.0011 | Helped |
| Add HSIC regularization (ablation) | CCPOvSIRE · Fully-simulated data, multiple actions | RMSE: 0.1115 ± 0.0135 -> 0.0970 ± 0.0038 | Helped |
| Use the structured reward assumption (ablation) | CCPOvSIRE · Fully-simulated data, multiple actions | RMSE: 0.1059 ± 0.0165 -> 0.0970 ± 0.0038 | Helped |
| Add HSIC regularization (ablation) | CCPOvSIRE · Fully-simulated data, budget m = 3 | Reward: 0.6069 ± 0.0020 -> 0.6082 ± 0.0013 | Helped |
| Use the structured reward assumption (ablation) | CCPOvSIRE · Fully-simulated data, budget m = 3 | Reward: 0.6074 ± 0.0011 -> 0.6082 ± 0.0013 | Helped |
| Add HSIC regularization (ablation) | CCPOvSIRE · ImageNet semi-simulation | RMSE: 0.2740 ± 0.0255 -> 0.2408 ± 0.0183 | Helped |
| Use the structured reward assumption (ablation) | CCPOvSIRE · ImageNet semi-simulation | RMSE: 0.2712 ± 0.0341 -> 0.2408 ± 0.0183 | Helped |
| Add HSIC regularization (ablation) | CCPOvSIRE · ImageNet semi-simulation, budget m = 1 | Reward: 0.0718 ± 0.0063 -> 0.0934 ± 0.0225 | Helped |
| Use the structured reward assumption (ablation) | CCPOvSIRE · ImageNet semi-simulation, budget m = 1 | Reward: 0.0839 ± 0.0137 -> 0.0934 ± 0.0225 | Helped |
| Add HSIC regularization (ablation) | CCPOvSIRE · ImageNet semi-simulation, budget m = 2 | Reward: 0.1186 ± 0.0198 -> 0.1408 ± 0.0154 | Helped |
| Use the structured reward assumption (ablation) | CCPOvSIRE · ImageNet semi-simulation, budget m = 2 | Reward: 0.1304 ± 0.0112 -> 0.1408 ± 0.0154 | Helped |
| Replace the linear kernel with an RBF kernel (ablation) | CCPOvSIRE · Fully-simulated data | RMSE: 0.0970 ± 0.0038 -> 0.1040 ± 0.0421 | Hurt |
Closest papers by meaning
- A General Framework for Off-Policy Learning with Partially-Observed Reward (ICLR 2025 · similarity 0.87)
- Collective Counterfactual Explanations: Balancing Individual Goals and Collective Dynamics (NeurIPS 2025 · similarity 0.86)
- Incentivized Learning in Principal-Agent Bandit Games (ICML 2024 · similarity 0.86)
- Scalable Neural Incentive Design with Parameterized Mean-Field Approximation (NeurIPS 2025 · similarity 0.85)
- Optimizing the coalition gain in Online Auctions with Greedy Structured Bandits (NeurIPS 2024 · similarity 0.85)
- Causal Logistic Bandits with Counterfactual Fairness Constraints (ICML 2025 · 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.