ResearchBenchmarksContinuous Control on MuJoCo Biased Pendulum (Hard Constraint)Follow0C.V RatePPOLag-0.0040.0230.050.077Jun 28, 2024Evaluation ResultsMethodMethodLinksC.V RateReturnPPOLagCost Knowledge=KnownCost Knowledge=Known2024.060717.43RLSFCost Knowledge=InferredCost Knowledge=Inferred2024.060—SIMKCCost Knowledge=KnownCost Knowledge=Known2024.060.1983.27