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

Offline Reinforcement Learning on Halfcheetah-Morph

59.6Normalized Score

TABB

0.11215.5563146.444May 21, 2026
Updated 12d ago

Evaluation Results

MethodLinks
2026.05
59.6
2026.05
53.99
2026.05
46.11
2026.05
44.03
2026.05
43.99
2026.05
43.95
2026.05
43.13
2026.05
43.01
2026.05
42.55
2026.05
42.16
2026.05
41.99
2026.05
41.5
2026.05
41.3
2026.05
41.06
2026.05
40.92
2026.05
40.3
2026.05
39.21
2026.05
35.6
2026.05
35
2026.05
33.6
2026.05
32.85
2026.05
32.1
2026.05
32
2026.05
31.8
2026.05
30.8
2026.05
30.6
2026.05
30.22
2026.05
30
2026.05
29.94
2026.05
29.59
2026.05
26.6
2026.05
25.8
2026.05
21.38
2026.05
20.49
2026.05
19.9
2026.05
19.3
2026.05
16.9
2026.05
12.9
2026.05
9.3
2026.05
9.29
2026.05
9.1
2026.05
8.56
2026.05
8.5
2026.05
8.41
2026.05
8.3
2026.05
8.16
2026.05
7.9
2026.05
7.8
2026.05
7.36
2026.05
5.9
2026.05
4.7
2026.05
4.32
2026.05
3.7
2026.05
2.4