List your company
ResearchFormerly WizWand

Off-policy prediction on Random Walk

0.0236Final RMSPBETD
0.0228680.0278090.032750.037691May 17, 2026
Updated 5mo ago

Evaluation results

MethodLinks
TD2026.050.0236
TDRC2026.050.0236
BA-TDRC2026.050.0236
TDC2026.050.029
GTD2-MP2026.050.0339
GTD22026.050.0419