Off-Policy Evaluation on Mnist
0.0121MSEMR
Evaluation Results
| Method | Links | |
|---|---|---|
| MRnumber of evaluation data (n)=1000, number of training data (m)=500, alpha* (target policy parameter)=0.62023.12 | 0.0121 | |
| DMnumber of evaluation data (n)=1000, number of training data (m)=500, alpha* (target policy parameter)=0.62023.12 | 0.1109 | |
| DRosnumber of evaluation data (n)=1000, number of training data (m)=500, alpha* (target policy parameter)=0.62023.12 | 0.2151 | |
| DRnumber of evaluation data (n)=1000, number of training data (m)=500, alpha* (target policy parameter)=0.62023.12 | 0.2617 | |
| SwitchDRnumber of evaluation data (n)=1000, number of training data (m)=500, alpha* (target policy parameter)=0.62023.12 | 0.275 | |
| IPWnumber of evaluation data (n)=1000, number of training data (m)=500, alpha* (target policy parameter)=0.62023.12 | 0.3359 |