Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safe Reinforcement Learning on Safety Gymnasium Ant (C=25)
Loading...
3,231.6
Return
CSPO
1,668.6256
2,074.3978
2,480.17
2,885.9422
Jun 12, 2026
Return
Cost
Updated 1mo ago
Evaluation Results
Method
Method
Links
Return
Cost
CSPO
2026.06
3,231.6
24.5
CPPOPID
2026.06
3,190
25.3
PPO-Lag
2026.06
3,134.17
24.3
IPO
2026.06
3,123.6
26.6
CPO
2026.06
3,055.8
19.6
C-TRPO
2026.06
3,042.64
18
APPO
2026.06
2,961.36
24.49
FOCOPS
2026.06
2,860.88
26.7
CUP
2026.06
2,839.65
26.6
EPO
2026.06
2,754.55
13.9
P3O
2026.06
2,514.81
23.1
PCPO
2026.06
1,728.74
18.5
Feedback
Search any
task
Search any
task