| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| OBP library avg over 50 datasets | HD-CBREAL | Cumulative Reward0.735 | 72 | 2mo ago | |
| RiverSwim mostly-left policy, T=50 | Model-based bootstrap with pivot CI | Qπ(1, 0) Coverage55.7 | 20 | 2mo ago | |
| KuaiRec slate experiments | FF-DR | Downstream OPE RMSE0.617 | 12 | 1mo ago | |
| Digits (UCI) | MR | MSE0.0006 | 12 | 4mo ago | |
| MIMIC-IV | AugIS | Interval Length0.007 | 11 | 1mo ago | |
| D4RL Half Cheetah | CP-Gen | Interval Length40.07 | 11 | 1mo ago | |
| Sepsis | DM | Interval Length-0.4 | 11 | 1mo ago | |
| Inventory | Point Estimate Error-428.51 | 9 | 1mo ago | ||
| MIMIC-IV Synthetic via VAE (test) | AugDR | Confidence Interval0.719 | 8 | 1mo ago | |
| D4RL Half Cheetah Synthetic via VAE (test) | DR-PPI | Confidence Interval1,820.79 | 8 | 1mo ago | |
| Sepsis Synthetic (test) | AugIS | Confidence Interval-0.001 | 8 | 1mo ago | |
| Inventory (test) | Confidence Interval-2,209.73 | 8 | 1mo ago | ||
| MIMIC-III sepsis MNAR 80% (test) | V_hat(pi)20.02 | 6 | 1mo ago | ||
| MIMIC-III sepsis MNAR 60% (test) | V_hat(pi)10,667.9 | 6 | 1mo ago | ||
| MIMIC-III sepsis MNAR 40% (test) | V_hat(pi)9.55 | 6 | 1mo ago | ||
| MIMIC-III sepsis 40% MNAR 20% (test) | V_hat(pi)10,408.2 | 6 | 1mo ago | ||
| HotpotQA (cross) | ADWM | Correlation Coefficient (rho)0.81 | 6 | 1mo ago | |
| WebShop (iter1) | ADWM | rho0.9 | 6 | 1mo ago | |
| ALFWorld (iter3) | ADWM | Rho0.8 | 6 | 1mo ago | |
| ALFWorld (iter1) | FQE | Rho0.82 | 6 | 1mo ago | |
| ScienceWorld (ETO) | Rho0.97 | 6 | 1mo ago | ||
| HotpotQA (DPO) | ADWM | Rho0.9 | 6 | 1mo ago | |
| CIFAR-100 | MR | MSE0.0007 | 6 | 4mo ago | |
| Mnist | MR | MSE0.0121 | 6 | 4mo ago | |
| SatImage (UCI) | MR | MSE0.0016 | 6 | 4mo ago |