List your company

Constrained Offline Reinforcement Learning on DSRL CarCircle1

0.73Normalized ReturnBCQ-Lag
-0.00840.18330.3750.5667Dec 9, 2025

Evaluation results

MethodLinks
BCQ-Lag2025.120.735.25
BC-All2025.120.724.39
COptiDICE2025.120.75.72
CDT2025.120.61.73
MPDiffusernum_samples=162025.120.50.85
BC-Safe2025.120.371.38
CPQ2025.120.022.29