Off-policy prediction on RW inverted
0.035Tail-average RMSETETD
Evaluation Results
| Method | Links | |
|---|---|---|
| TETDalpha=0.01, tail-average window=final 10% of update steps2026.05 | 0.035 | |
| RETDalpha=0.01, tail-average window=final 10% of update steps2026.05 | 0.046 | |
| ETDalpha=0.01, tail-average window=final 10% of update steps2026.05 | 0.047 | |
| CETDalpha=0.01, tail-average window=final 10% of update steps2026.05 | 0.047 | |
| TDalpha=0.01, tail-average window=final 10% of update steps2026.05 | 0.097 | |
| TDRCalpha=0.01, tail-average window=final 10% of update steps2026.05 | 0.103 | |
| TDCalpha=0.01, tail-average window=final 10% of update steps2026.05 | 0.113 | |
| GTD2alpha=0.01, tail-average window=final 10% of update steps2026.05 | 0.176 |