List your company

Off-policy prediction on New two-state

4.131Tail-Average RMSERETD
2.5470413.2387723.930534.62223May 2, 2026

Evaluation results

MethodLinks
RETDalpha=0.01, tail-average window=final 10% of update steps2026.054.131
TETDalpha=0.01, tail-average window=final 10% of update steps2026.055.015
GTD2alpha=0.01, tail-average window=final 10% of update steps2026.058.543
TDalpha=0.01, tail-average window=final 10% of update steps2026.058.573
TDCalpha=0.01, tail-average window=final 10% of update steps2026.058.574
TDRCalpha=0.01, tail-average window=final 10% of update steps2026.058.582
CETDalpha=0.01, tail-average window=final 10% of update steps2026.0543.73