Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Offline Safe Reinforcement Learning on DSRL EasySparse
Loading...
326.06
Reward
CDCP
-16.1312
72.7069
161.545
250.3831
Jul 4, 2026
Reward
Cost
Updated 19d ago
Evaluation Results
Method
Method
Links
Reward
Cost
CDCP
Mode=Multi-task
2026.07
326.06
25.21
MTCOptiDICE
Mode=Multi-task
2026.07
242.81
57.44
MTCDT
Mode=Multi-task
2026.07
175.75
36.97
MTCPQ
Mode=Multi-task
2026.07
-2.97
0.33
Feedback
Search any
task
Search any
task