ResearchBenchmarksOff-policy prediction on Baird's counterexampleFollow0.0128Steady-state AUC ErrorGTD2-MP-1.1369686.62396614.384922.145834May 16, 2026May 17, 2026Evaluation ResultsMethodMethodLinksSteady-state AUC ErrorGTD2-MP2026.050.0128BA-TDRC2026.050.0151TDC2026.050.0153TDRC2026.050.0162GTD22026.050.1244GTD22026.051.887GTD2-MP2026.051.933STHTD-MP2026.051.946TDC2026.052.13STHTD2026.052.66HTD2026.054.341TDRC2026.055.672ETD2026.056.903TD2026.0512.203TD2026.0528.757