ResearchBenchmarksReinforcement Learning on HalfCheetah (expert)Follow11,708.1TFLOPsRLPD-309.9322,810.1345,930.29,050.266May 7, 2026Evaluation ResultsMethodMethodLinksTFLOPsTraining Time (min)RLPD2026.0511,708.11,006Cal-QL2026.052,618.2681SPEQ O2O2026.05897124SOPE2026.05318.864SACfD2026.05152.330