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

Constrained Offline Reinforcement Learning on DSRL PointCircle1

0.86Normalized Return

COptiDICE

0.3920.51350.6350.7565Dec 9, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
0.865.51
2025.12
0.793.98
2025.12
0.590.69
2025.12
0.580.94
2025.12
0.542.38
2025.12
0.430.75
2025.12
0.410.16