List your company

Continuous Control on Ant v4

7,518.3Average ReturnSMFP
1,609.19683,143.29094,677.3856,211.4791May 6, 2025Jul 8, 2025Sep 9, 2025Nov 11, 2025Jan 13, 2026Mar 17, 2026May 20, 2026

Evaluation results

MethodLinks
SMFPTraining Time (h)=2.7, Inference Time (ms)=0.42, Inference Steps=12026.057,518.3
DIMETraining Time (h)=3.5, Inference Time (ms)=4.68, Inference Steps=162026.057,103.6
MaxEntDPTraining Time (h)=2.3, Inference Time (ms)=5.62, Inference Steps=202026.055,717.9
DIPOTraining Time (h)=9.6, Inference Time (ms)=5.20, Inference Steps=202026.055,665.9
CSAC2025.055,538.2
SACTraining Time (h)=2.2, Inference Time (ms)=0.13, Inference Steps=12026.055,530.6
SAC2025.055,229.39
TD3Training Time (h)=0.4, Inference Time (ms)=0.27, Inference Steps=12026.054,583.8
QSMTraining Time (h)=0.8, Inference Time (ms)=5.15, Inference Steps=202026.054,206.4
QVPOTraining Time (h)=5.2, Inference Time (ms)=5.77, Inference Steps=202026.054,040.1
SD32025.052,960.61
PPOTraining Time (h)=0.3, Inference Time (ms)=0.22, Inference Steps=12026.052,781.9
TD32025.052,368.35
SPOTraining Time (h)=0.3, Inference Time (ms)=0.32, Inference Steps=12026.052,100.2
PPO2025.051,836.47