List your company

Continuous Control on Inverted2DPendulum MuJoCo v5

9,360Max Evaluation ReturnSAC
9,349.69,352.39,3559,357.7May 1, 2026

Evaluation results

MethodLinks
SACTraining steps=1,000,000, Seeds=102026.059,360
TQCTraining steps=1,000,000, Seeds=102026.059,360
SAVGOTraining steps=1,000,000, Seeds=102026.059,360
TD3Training steps=1,000,000, Seeds=102026.059,358
PPOTraining steps=1,000,000, Seeds=102026.059,350