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

Safe Reinforcement Learning on RacecarCircle (test)

0.2364Violation Rate

TRPOADRC

0.2225280.3161640.40980.503436Jan 26, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
0.23643.5417.3
2026.01
0.37997.9223.45
2026.01
0.399421.7835.72
2026.01
0.42084.5624.21
2026.01
0.46177.9427.09
2026.01
0.48728.5727.76
2026.01
0.49428.2224.95
2026.01
0.50527.8725.03
2026.01
0.5092524.51
2026.01
0.513916.134.48
2026.01
0.568221.7740.95
2026.01
0.583230.7250.41