Offline Policy Evaluation on D4RL Hopper medium-replay
13RMSEOPERA
Evaluation results
| Method | Links | |
|---|---|---|
| OPERAEstimator Category=Multi-OPE Estimator2024.05 | 13 | |
| BestOPEEstimator Category=Multi-OPE Estimator2024.05 | 15.5 | |
| AvgOPEEstimator Category=Multi-OPE Estimator2024.05 | 60.7 | |
| BVFTEstimator Category=Multi-OPE Estimator2024.05 | 61.2 | |
| DREstimator Category=Single OPE Estimator2024.05 | 112.7 | |
| MBEstimator Category=Single OPE Estimator2024.05 | 298.7 | |
| Dual-DICEEstimator Category=Single OPE Estimator2024.05 | 1,565.2 |