Policy Ranking on Pendulum benchmark leaderboard · SOTA2 Research

Policy Ranking on Pendulum

0.02RegretFQE

Evaluation Results

Method	Links
FQE2026.06		0.02	0.76
LDT22026.06		0.03	0.72
LNLLsim2026.06		0.08	0.79
MOReL2026.06		0.14	0.69
ROMI2026.06		0.32	0.49
MOPO2026.06		0.36	0.47
VaGraM2026.06		1.18	0.5
HDTwin2026.06		13.85	-0.1