Off-policy prediction on New two-state
4.131Tail-Average RMSERETD
Evaluation Results
| Method | Links | |
|---|---|---|
| RETDalpha=0.01, tail-average window=final 10% of update steps2026.05 | 4.131 | |
| TETDalpha=0.01, tail-average window=final 10% of update steps2026.05 | 5.015 | |
| GTD2alpha=0.01, tail-average window=final 10% of update steps2026.05 | 8.543 | |
| TDalpha=0.01, tail-average window=final 10% of update steps2026.05 | 8.573 | |
| TDCalpha=0.01, tail-average window=final 10% of update steps2026.05 | 8.574 | |
| TDRCalpha=0.01, tail-average window=final 10% of update steps2026.05 | 8.582 | |
| CETDalpha=0.01, tail-average window=final 10% of update steps2026.05 | 43.73 |