List your company

Policy Ranking on Lunarlander

0.45RegretLDT2
-1.49611.639524.77537.9105Jun 24, 2026

Evaluation results

MethodLinks
LDT2Architecture=best-performing from Figure 42026.060.450.97
LNLLsimArchitecture=best-performing from Figure 42026.061.410.98
MOPO2026.061.450.62
FQE2026.062.510.83
ROMI2026.068.50.8
MOReL2026.0621.060.73
VaGraM2026.0625.470.84
HDTwin2026.0649.10.54