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

Offline Reinforcement Learning on Ant-Kinematic

90.34Normalized Score

TABB

3.042425.706248.3771.0338May 21, 2026
Updated 12d ago

Evaluation Results

MethodLinks
2026.05
90.34
2026.05
87.05
2026.05
83.67
2026.05
76.04
2026.05
67.91
2026.05
65.1
2026.05
63.98
2026.05
59.6
2026.05
59.12
2026.05
57.8
2026.05
54.44
2026.05
54.2
2026.05
54.1
2026.05
53.87
2026.05
51.7
2026.05
50.93
2026.05
50.86
2026.05
50.56
2026.05
50
2026.05
49.5
2026.05
47.72
2026.05
46.89
2026.05
46.04
2026.05
45.4
2026.05
44.98
2026.05
44.7
2026.05
44.57
2026.05
43.7
2026.05
42.3
2026.05
42
2026.05
41.85
2026.05
37.2
2026.05
37
2026.05
36.86
2026.05
36.5
2026.05
36
2026.05
33.3
2026.05
31.7
2026.05
29.71
2026.05
29.26
2026.05
25.55
2026.05
24.62
2026.05
24.4
2026.05
22.88
2026.05
22.1
2026.05
20.9
2026.05
19.5
2026.05
19.1
2026.05
19
2026.05
19
2026.05
18.7
2026.05
17.8
2026.05
14.5
2026.05
6.4