Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Constrained Offline Reinforcement Learning on DSRL HalfCheetahVelocity
Loading...
105
Normalized Return
BCQ-Lag
25.96
46.48
67
87.52
Dec 9, 2025
Normalized Return
Cost
Updated 1mo ago
Evaluation Results
Method
Method
Links
Normalized Return
Cost
BCQ-Lag
2025.12
105
18.21
CDT
2025.12
100
0.01
MPDiffuser
num_samples=16
2025.12
98
0.77
BC-All
2025.12
97
13.1
BC-Safe
2025.12
88
0.54
COptiDICE
2025.12
65
0
CPQ
2025.12
29
0.74
Feedback
Search any
task
Search any
task
