ResearchBenchmarksContinuous Control on MuJoCo HalfCheetah 10-p v4Follow80.5Normalized ReturnOpti-DICE13.73231.06648.465.734Feb 11, 2026Evaluation ResultsMethodMethodLinksNormalized ReturnOpti-DICE2026.0280.5Flex-f-Q2026.0280.3Flex-f-DICE2026.0279.4IQL2026.0278.2TD3BC2026.0272.9CQL2026.0216.3