Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Offline Safe Reinforcement Learning on DSRL MediumSparse
Loading...
242.75
Reward
CDCP
-14.1924
52.5138
119.22
185.9262
Jul 4, 2026
Reward
Cost
Updated 19d ago
Evaluation Results
Method
Method
Links
Reward
Cost
CDCP
Mode=Multi-task
2026.07
242.75
20.68
MTCOptiDICE
Mode=Multi-task
2026.07
177.55
38.44
MTCDT
Mode=Multi-task
2026.07
70.04
14.6
MTCPQ
Mode=Multi-task
2026.07
-4.31
1.21
Feedback
Search any
task
Search any
task