List your company

High-Dimensional Locomotion on Ant v4 (test)

4,129.57RewardSAC
863.971,711.772,559.573,407.37May 7, 2026

Evaluation results

MethodLinks
SACDiscounting Variant=AdaGamma2026.054,129.57
SACDiscounting Variant=Uncertainty2026.053,620.87
SACDiscounting Variant=Fixed-γ2026.053,101.48
SACDiscounting Variant=CrossValidate2026.051,399.44
PPODiscounting Variant=AdaGamma2026.051,172.47
PPODiscounting Variant=CrossValidate2026.051,036.33
PPODiscounting Variant=Uncertainty2026.051,018.51
PPODiscounting Variant=Fixed-γ2026.05989.57