List your company
ResearchFormerly WizWand

Safe Reinforcement Learning on Safety Gymnasium CarButton (C=25)

1.13ReturnIPO
-1.4596-0.7873-0.1150.5573Jun 12, 2026
Updated 4mo ago

Evaluation results

MethodLinks
IPO2026.061.1334.7
CPO2026.060.8533.3
CSPO2026.060.723.4
C-TRPO2026.060.6534.8
FOCOPS2026.060.6337.6
PPO-Lag2026.060.5225.79
APPO2026.060.3624.8
EPO2026.060.1424.2
PCPO2026.060.0935.6
P3O2026.06-0.1432.9
CUP2026.06-0.3336.2
CPPOPID2026.06-1.3632.7