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

Offline Reinforcement Learning on MuJoCo Ant

79.25Normalized Score

MOBODY

1.478821.669441.8662.0506May 24, 2026
Updated 8d ago

Evaluation Results

MethodLinks
2026.05
79.25
2026.05
77.6
2026.05
76.97
2026.05
76.43
2026.05
75.51
2026.05
75.43
2026.05
75.24
2026.05
75.19
2026.05
75.08
2026.05
74.92
2026.05
74.29
2026.05
73.65
2026.05
73.51
2026.05
72.06
2026.05
72.02
2026.05
71.46
2026.05
70.66
2026.05
66.39
2026.05
66.22
2026.05
64.83
2026.05
63.78
2026.05
63.76
2026.05
62.95
2026.05
61.12
2026.05
61.06
2026.05
60.97
2026.05
59.95
2026.05
59.61
2026.05
59.49
2026.05
59.31
2026.05
59.07
2026.05
58.47
2026.05
58.46
2026.05
58.4
2026.05
58.01
2026.05
57.51
2026.05
57.21
2026.05
55.73
2026.05
54.91
2026.05
54.75
2026.05
53.29
2026.05
53.12
2026.05
52.49
2026.05
51.08
2026.05
50.57
2026.05
49.94
2026.05
47.18
2026.05
46.6
2026.05
45.29
2026.05
45.07
2026.05
44.72
2026.05
44.01
2026.05
42.24
2026.05
38.52
2026.05
33.85
2026.05
27.05
2026.05
26.85
2026.05
24.13
2026.05
18.5
2026.05
14.53
2026.05
14.5
2026.05
11.94
2026.05
10.44
2026.05
4.47