ResearchBenchmarksContinuous Control on MuJoCo Ant 10-p v4Follow92.7Normalized ReturnIQL23.12441.18759.2577.313Feb 11, 2026Evaluation ResultsMethodMethodLinksNormalized ReturnIQL2026.0292.7Flex-f-Q2026.0291.1Flex-f-DICE2026.0281.5Opti-DICE2026.0274.9TD3BC2026.0232.3CQL2026.0225.8