Share your thoughts, 1 month free Claude Pro on usSee more

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

27.7Return

PPO-Lag

Updated 1mo ago

Evaluation Results

Method	Links
PPO-Lag 2026.06		27.7	26.8
IPO 2026.06		27.41	27.1
CSPO 2026.06		27.11	24
CPO 2026.06		26.67	27.4
APPO 2026.06		26	24.97
EPO 2026.06		25.05	25.2
C-TRPO 2026.06		23.07	28.3
P3O 2026.06		21.71	25.7
PCPO 2026.06		21.43	29.4
FOCOPS 2026.06		20.78	31
CUP 2026.06		20.46	28.2
CPPOPID 2026.06		6.23	24.6