List your company

Constrained Offline Reinforcement Learning on DSRL CarGoal1

0.79Normalized ReturnCPQ
0.2180.36650.5150.6635Dec 9, 2025

Evaluation results

MethodLinks
CPQ2025.120.791.42
CDT2025.120.661.21
MPDiffusernum_samples=162025.120.630.92
BCQ-Lag2025.120.470.78
BC-All2025.120.390.33
COptiDICE2025.120.350.54
BC-Safe2025.120.240.28