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

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

10.15ReturnCSPO

Evaluation Results

Method	Links
CSPO2026.06		10.15	24.4
PPO-Lag2026.06		9.05	24.1
APPO2026.06		9.01	25.2
IPO2026.06		7.92	28.6
CPO2026.06		7.02	25
C-TRPO2026.06		6.5	28.9
EPO2026.06		6.38	24.3
FOCOPS2026.06		5.55	26.8
P3O2026.06		4.16	26.3
CUP2026.06		3.56	30.1
PCPO2026.06		2.61	33.5
CPPOPID2026.06		1.39	24