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

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

27.7ReturnPPO-Lag

Evaluation Results

Method	Links
PPO-Lag2026.06		27.7	26.8
IPO2026.06		27.41	27.1
CSPO2026.06		27.11	24
CPO2026.06		26.67	27.4
APPO2026.06		26	24.97
EPO2026.06		25.05	25.2
C-TRPO2026.06		23.07	28.3
P3O2026.06		21.71	25.7
PCPO2026.06		21.43	29.4
FOCOPS2026.06		20.78	31
CUP2026.06		20.46	28.2
CPPOPID2026.06		6.23	24.6