Share your thoughts, 1 month free Claude Pro on usSee more

Off-policy prediction on Baird's counterexample

0.0128Steady-state AUC Error

GTD2-MP

Updated 5d ago

Evaluation Results

Method	Links
GTD2-MP 2026.05		0.0128
BA-TDRC 2026.05		0.0151
TDC 2026.05		0.0153
TDRC 2026.05		0.0162
GTD2 2026.05		0.1244
GTD2 2026.05		1.887
GTD2-MP 2026.05		1.933
STHTD-MP 2026.05		1.946
TDC 2026.05		2.13
STHTD 2026.05		2.66
HTD 2026.05		4.341
TDRC 2026.05		5.672
ETD 2026.05		6.903
TD 2026.05		12.203
TD 2026.05		28.757