Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safe Reinforcement Learning on Safety Gymnasium CarButton (C=25)
Loading...
1.13
Return
IPO
-1.4596
-0.7873
-0.115
0.5573
Jun 12, 2026
Return
Cost
Updated 1mo ago
Evaluation Results
Method
Method
Links
Return
Cost
IPO
2026.06
1.13
34.7
CPO
2026.06
0.85
33.3
CSPO
2026.06
0.7
23.4
C-TRPO
2026.06
0.65
34.8
FOCOPS
2026.06
0.63
37.6
PPO-Lag
2026.06
0.52
25.79
APPO
2026.06
0.36
24.8
EPO
2026.06
0.14
24.2
PCPO
2026.06
0.09
35.6
P3O
2026.06
-0.14
32.9
CUP
2026.06
-0.33
36.2
CPPOPID
2026.06
-1.36
32.7
Feedback
Search any
task
Search any
task