Safe Reinforcement Learning on Safety Gymnasium CarButton (C=25) benchmark leaderboard · SOTA2 Research

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

1.13ReturnIPO

Evaluation Results

Method	Links
IPO2026.06		1.13	34.7
CPO2026.06		0.85	33.3
CSPO2026.06		0.7	23.4
C-TRPO2026.06		0.65	34.8
FOCOPS2026.06		0.63	37.6
PPO-Lag2026.06		0.52	25.79
APPO2026.06		0.36	24.8
EPO2026.06		0.14	24.2
PCPO2026.06		0.09	35.6
P3O2026.06		-0.14	32.9
CUP2026.06		-0.33	36.2
CPPOPID2026.06		-1.36	32.7