List your company

Continuous Control on HalfCheetah-Velocity Safety-Gymnasium (test)

2,468.78RewardPDO
1,609.15761,832.32882,055.52,278.6712Jan 26, 2026

Evaluation results

MethodLinks
PDOAlgorithm=PDO2026.012,468.785.771,000
TRPO-ADRCAlgorithm=TRPO-ADRC2026.012,394.0914.631,000
RCPOAlgorithm=RCPO2026.012,296.82151,000
CUPAlgorithm=CUP2026.012,175.6128.571,000
CPPO-ADRCAlgorithm=CPPO-ADRC2026.012,098.7113.871,000
IPOAlgorithm=IPO2026.011,819.7516.11,000
RCPO-ADRCAlgorithm=RCPO-ADRC2026.011,642.2210.231,000