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

Safe Reinforcement Learning on CarCircle (test)

17.71Violation Rate

TRPOADRC

16.298425.826735.35544.8833Jan 26, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
17.711.9216.22
2026.01
21.357.7418.85
2026.01
39.212.5230.87
2026.01
39.7713.5630.89
2026.01
40.046.4525.52
2026.01
40.676.5824.24
2026.01
46.7315.8533.54
2026.01
48.417.4924.26
2026.01
51.57.7323.82
2026.01
51.8513.5533.49
2026.01
52.7712.2931.24
2026.01
5317.1838.06