Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safe Reinforcement Learning on Safety Gymnasium Humanoid (C=25)
Loading...
6,496.85
Return
CSPO
2,264.6116
3,363.3658
4,462.12
5,560.8742
Jun 12, 2026
Return
Cost
Updated 1mo ago
Evaluation Results
Method
Method
Links
Return
Cost
CSPO
2026.06
6,496.85
18
CPPOPID
2026.06
6,417.05
26.4
PPO-Lag
2026.06
6,414.56
25.49
IPO
2026.06
6,270.25
30.4
CPO
2026.06
6,213.15
18.3
APPO
2026.06
6,092.95
25.3
EPO
2026.06
5,745.65
13.1
P3O
2026.06
5,684.22
22
C-TRPO
2026.06
5,450.52
15.9
FOCOPS
2026.06
5,295.88
26.7
PCPO
2026.06
4,706.07
14.7
CUP
2026.06
2,427.39
18.9
Feedback
Search any
task
Search any
task