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

Safe Reinforcement Learning on RacecarGoal

34.03Violation Rate

TRPO

32.156444.803257.4570.0968Jan 26, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
34.036.1622.02
2026.01
47.0812.3130.12
2026.01
49.3311.730.94
2026.01
64.3122.8943.67
2026.01
68.4117.8139.41
2026.01
71.2417.5539.71
2026.01
71.4418.4740.76
2026.01
72.0517.9340.29
2026.01
72.327.1149.02
2026.01
73.3119.1941.57
2026.01
75.2619.9342.57
2026.01
80.8731.1854.24