Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Offline Reinforcement Learning on hopper medium

3,729Normalized Score

QDFM

-137.512866.2941,870.12,873.906Oct 10, 2023Mar 2, 2024Jul 24, 2024Dec 15, 2024May 8, 2025Sep 29, 2025Feb 21, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
3,729
2026.02
3,618
2026.02
712
2026.02
154
2026.02
113
2026.02
111
2026.02
100.6
2023.10
98.4
2026.02
97.8
2023.10
97.2
2026.02
97.1
2023.10
94.9
2023.10
94.1
2026.02
86.1
2023.10
85.6
2026.02
82.9
2026.02
74.6
2023.10
74.3
2026.02
71.43
2026.02
71.08
2026.02
66.68
2024.02
66.5
2023.10
66.3
2026.02
66.2
2026.02
60.88
2024.02
60.3
2026.02
59.39
2024.02
58
2024.02
57.3
2026.02
56.09
2026.02
55.9
2026.02
55.26
2023.10
54.5
2026.02
53
2023.10
52.1
2026.02
51.62
2024.02
50.7
2026.02
43.4
2025.12
35.2
2026.02
32.4
2025.12
31.6
2025.12
25.5
2025.12
24.2
2024.02
23.3
2025.12
20.6
2025.12
20.3
2025.12
19.3
2026.02
17.3
2026.02
15.3
2026.02
15.2
2026.02
12.4
2026.02
11.2