Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Offline Safe Reinforcement Learning on DSRL HardSparse
Loading...
257.98
Reward
CDCP
-12.9816
57.3642
127.71
198.0558
Jul 4, 2026
Reward
Cost
Updated 19d ago
Evaluation Results
Method
Method
Links
Reward
Cost
CDCP
Mode=Multi-task
2026.07
257.98
24.94
MTCOptiDICE
Mode=Multi-task
2026.07
147.62
32.66
MTCDT
Mode=Multi-task
2026.07
94.26
19.57
MTCPQ
Mode=Multi-task
2026.07
-2.56
0.33
Feedback
Search any
task
Search any
task