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

Safe Reinforcement Learning on CarButton (test)

50.16Violation Rate

CPPOADRC

48.167661.616375.06588.5137Jan 26, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
50.1614.834.2
2026.01
53.288.5329.57
2026.01
69.0414.637.11
2026.01
74.2421.944.84
2026.01
85.0945.2768.95
2026.01
89.7759.7784.05
2026.01
98.8764.189.05
2026.01
99.0359.4484.4
2026.01
99.0450.8475.8
2026.01
99.4958.6283.6
2026.01
99.9358.1883.17
2026.01
99.9762.287.2