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

Offline Reinforcement Learning on halfcheetah medium

68.2Normalized Score

Anti-exploration Method

-3.331215.239433.8152.3806Oct 10, 2023Feb 29, 2024Jul 20, 2024Dec 9, 2024Apr 30, 2025Sep 19, 2025Feb 8, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
68.2
2026.02
66.6
2026.02
60.8
2023.10
58.1
2026.02
54.9
2023.10
54.2
2023.10
53.3
2023.10
47.4
2026.02
47.4
2026.02
47.4
2026.02
47
2024.02
44.4
2026.02
43.2
2024.02
42.4
2024.02
42.4
2026.02
42.4
2024.02
42.3
2024.02
42.1
2023.10
41.7
2026.02
41.2
2023.10
40.7
2026.02
40.7
2026.02
39.6
2026.02
38.9
2023.10
38.2
2023.10
37.2
2026.02
36.9
2026.02
36.6
2023.10
27.8
2025.12
26.7
2025.12
24.6
2025.12
22.9
2025.12
22.6
2026.02
20.23
2026.02
19.69
2025.12
18.7
2025.12
17.3
2025.12
16.1
2026.02
4.92
2026.02
2.22
2024.02
1
2026.02
-0.23
2026.02
-0.58