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

Safe Reinforcement Learning on RacecarButton (test)

72.49Violation Rate

TD3Lag

71.494478.214784.93591.6553Jan 26, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
72.4916.3139.65
2026.01
75.8815.7739.47
2026.01
80.0621.3845
2026.01
81.1835.7659.11
2026.01
84.4818.3742.65
2026.01
85.1818.4942.87
2026.01
85.9921.4645.75
2026.01
87.0432.9456.86
2026.01
87.3133.0757.34
2026.01
88.2620.1244.62
2026.01
97.3778.44103.21
2026.01
97.3865.7590.53