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

BallCircle on Bullet-Safety-Gym (Normalized Metrics)

89Normalized Reward

Reference policy (πref)

15.1634.3353.572.67Apr 29, 2026May 2, 2026May 6, 2026May 9, 2026May 13, 2026May 16, 2026May 20, 2026
Updated 13d ago

Evaluation Results

MethodLinks
893.73
2026.05
720.7
2026.05
710.35
2026.05
651.82
2026.05
590.82
2026.04
340
2026.04
3147
2026.05
180.21