ResearchBenchmarksOff-policy prediction on Random Walk (Steady-state AUC error)Follow0.0236Steady-state AUC ErrorTD0.0200680.0439090.067750.091591May 16, 2026May 17, 2026Evaluation ResultsMethodMethodLinksSteady-state AUC ErrorTD2026.050.0236BA-TDRC2026.050.0236TDRC2026.050.0237TDC2026.050.0306TD2026.050.0336TDRC2026.050.0337GTD2-MP2026.050.0363STHTD-MP2026.050.0401HTD2026.050.0431ETD2026.050.0462GTD22026.050.0475STHTD2026.050.063GTD2-MP2026.050.1013TDC2026.050.1027GTD22026.050.1119