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

PointButton2 on Safety-Gymnasium

58Normalized Reward

CPQ

-1.2814.1129.544.89Apr 29, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
584.3
2026.04
584.3
2026.04
511.14
2026.04
511.14
2026.04
461.57
2026.04
461.57
2026.04
432.47
2026.04
432.47
2026.04
4198
2026.04
410.98
2026.04
410.98
2026.04
402.66
2026.04
402.66
2026.04
272.02
2026.04
272.02
2026.04
180.64
2026.04
161.1
2026.04
161.1
2026.04
151.51
2026.04
151.51
2026.04
158