Off-policy prediction on Two-state
0.82Tail-average RMSETDRC
Evaluation results
| Method | Links | |
|---|---|---|
| TDRCalpha=0.01, tail-average window=final 10% of update steps2026.05 | 0.82 | |
| TETDalpha=0.01, tail-average window=final 10% of update steps2026.05 | 1.07 | |
| ETDalpha=0.01, tail-average window=final 10% of update steps2026.05 | 1.14 | |
| TDCalpha=0.01, tail-average window=final 10% of update steps2026.05 | 1.38 | |
| GTD2alpha=0.01, tail-average window=final 10% of update steps2026.05 | 1.457 | |
| RETDalpha=0.01, tail-average window=final 10% of update steps2026.05 | 1.63 | |
| CETDalpha=0.01, tail-average window=final 10% of update steps2026.05 | 7.01 |