ResearchBenchmarksContinuous Control on MuJoCo Walker2d Hard ConstraintFollow2,947.25ReturnPPOLag2,924.34922,930.29462,936.242,942.1854Jun 28, 2024Evaluation ResultsMethodMethodLinksReturnConstraint Violation RatePPOLagCost Knowledge=KnownCost Knowledge=Known2024.062,947.2516SIMKCCost Knowledge=KnownCost Knowledge=Known2024.062,925.230