ResearchBenchmarksOff-policy prediction on Baird (Final RMSPBE)Follow0.0082Final RMSPBEGTD2-MP-0.5449923.1890546.923110.657146May 17, 2026Evaluation ResultsMethodMethodLinksFinal RMSPBEGTD2-MP2026.050.0082TDC2026.050.0104BA-TDRC2026.050.0136TDRC2026.050.0137GTD22026.050.0308TD2026.0513.838