List your company
ResearchFormerly WizWand

Policy Ranking on Pendulum

0.02RegretFQE
-0.53323.20096.93510.6691Jun 24, 2026
Updated 4mo ago

Evaluation results

MethodLinks
FQE2026.060.020.76
LDT2Architecture=best-performing from Figure 42026.060.030.72
LNLLsimArchitecture=best-performing from Figure 42026.060.080.79
MOReL2026.060.140.69
ROMI2026.060.320.49
MOPO2026.060.360.47
VaGraM2026.061.180.5
HDTwin2026.0613.85-0.1