Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Constrained Offline Reinforcement Learning on DSRL CarCircle1

0.73Normalized Return

BCQ-Lag

-0.00840.18330.3750.5667Dec 9, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
0.735.25
2025.12
0.724.39
2025.12
0.75.72
2025.12
0.61.73
2025.12
0.50.85
2025.12
0.371.38
2025.12
0.022.29