List your company

Continuous Control on Safety-Gymnasium SafetyAntVelocity (generalization)

45.5Episodic RewardCPO-FOAM
27.71632.33336.9541.567Apr 7, 2026

Evaluation results

MethodLinks
CPO-FOAM2026.0445.518.4
Lagrangian PPO2026.0435.285.4
Vanilla CPO2026.0433.645.2
RCPO2026.0432.872.5
PID-Lagrangian2026.0430.535.8
IPO2026.0428.455.6