List your company

High-Dimensional Control on SafetyPointGoal1 v0 (test)

28.25RewardSAC
20.314822.374924.43526.4951May 7, 2026

Evaluation results

MethodLinks
SACDiscounting Variant=AdaGamma2026.0528.2529.37
SACDiscounting Variant=Fixed-γ2026.0527.8252.53
SACDiscounting Variant=Uncertainty2026.0527.4737.46
SACDiscounting Variant=CrossValidate2026.0527.3445.84
PPODiscounting Variant=AdaGamma2026.0526.3141.82
PPODiscounting Variant=Uncertainty2026.0522.5951.25
PPODiscounting Variant=Fixed-γ2026.0522.5851.26
PPODiscounting Variant=CrossValidate2026.0520.6254.13