Off-policy prediction on Random Walk (RMSVE)
0.0312RMSVETDRC
Evaluation Results
| Method | Links | |
|---|---|---|
| TDRCProtocol=at the last step, Runs=100 independent2026.05 | 0.0312 | |
| TDProtocol=at the last step, Runs=100 independent2026.05 | 0.0319 | |
| STHTD-MPProtocol=at the last step, Runs=100 independent2026.05 | 0.0394 | |
| HTDProtocol=at the last step, Runs=100 independent2026.05 | 0.0419 | |
| ETDProtocol=at the last step, Runs=100 independent2026.05 | 0.0435 | |
| STHTDProtocol=at the last step, Runs=100 independent2026.05 | 0.0586 | |
| GTD2-MPProtocol=at the last step, Runs=100 independent2026.05 | 0.0605 | |
| GTD2Protocol=at the last step, Runs=100 independent2026.05 | 0.061 | |
| TDCProtocol=at the last step, Runs=100 independent2026.05 | 0.0879 |