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

CarCircle on Bullet-Safety-Gym (Normalized Metrics)

0.97Normalized Reward

Reference policy (πref)

0.15880.36940.580.7906Apr 29, 2026May 2, 2026May 6, 2026May 9, 2026May 13, 2026May 16, 2026May 20, 2026
Updated 13d ago

Evaluation Results

MethodLinks
0.974.58
2026.05
0.771.17
2026.05
0.620.91
2026.05
0.591.73
2026.05
0.541.23
2026.04
0.40.11
2026.04
0.220.75
2026.05
0.190.33