List your company

Constrained Reinforcement Learning on MuJoCo Ant (eval)

3,177.6RewardFOCOPS
2,873.7122,952.6063,031.53,110.394Apr 17, 2025

Evaluation results

MethodLinks
FOCOPSKnowledge Level=Oracle2025.043,177.612.7—
CUPKnowledge Level=Oracle2025.043,119.75.1—
TRPO-SauteKnowledge Level=Oracle2025.043,10217—
TraCeSKnowledge Level=Zero Knowledge2025.042,885.419.54,657