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

Off-policy prediction on Random Walk (Steady-state AUC error)

0.0236Steady-state AUC Error

TD

Updated 5d ago

Evaluation Results

Method	Links
TD 2026.05		0.0236
BA-TDRC 2026.05		0.0236
TDRC 2026.05		0.0237
TDC 2026.05		0.0306
TD 2026.05		0.0336
TDRC 2026.05		0.0337
GTD2-MP 2026.05		0.0363
STHTD-MP 2026.05		0.0401
HTD 2026.05		0.0431
ETD 2026.05		0.0462
GTD2 2026.05		0.0475
STHTD 2026.05		0.063
GTD2-MP 2026.05		0.1013
TDC 2026.05		0.1027
GTD2 2026.05		0.1119