Off-policy prediction on Two-state (RMSVE)
0RMSVEETD
Evaluation Results
| Method | Links | |
|---|---|---|
| ETDProtocol=at the last step, Runs=100 independent2026.05 | 0 | |
| TDCProtocol=at the last step, Runs=100 independent2026.05 | 1.36 | |
| GTD2Protocol=at the last step, Runs=100 independent2026.05 | 2.69 | |
| STHTD-MPProtocol=at the last step, Runs=100 independent2026.05 | 3.97 | |
| STHTDProtocol=at the last step, Runs=100 independent2026.05 | 6.53 | |
| GTD2-MPProtocol=at the last step, Runs=100 independent2026.05 | 6.66 | |
| HTDProtocol=at the last step, Runs=100 independent2026.05 | 17.021 | |
| TDRCProtocol=at the last step, Runs=100 independent2026.05 | 17.731 | |
| TDProtocol=at the last step, Runs=100 independent2026.05 | 42.792 |