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

Offline Reinforcement Learning on walker2d medium-replay

99.6Normalized Score

Proposed

-3.98422.90849.876.692Jun 16, 2021Mar 28, 2022Jan 7, 2023Oct 19, 2023Jul 30, 2024May 11, 2025Feb 21, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2023.10
99.6
2026.02
96.3
2026.02
89.7
2026.02
88.7
2023.10
86.5
2026.02
86.2
2026.02
83.6
2026.02
81.8
2025.12
81.2
2025.12
75.9
2025.12
75.7
2026.02
75.11
2023.10
73.9
2026.02
73.8
2026.02
71.98
2026.02
71.9
2021.06
71.6
2021.06
66.4
2026.02
64.68
2025.12
63.9
2026.02
60.7
2024.02
60.2
2026.02
58.49
2024.02
58.2
2023.10
56
2025.12
52.3
2024.02
51.6
2026.02
50.64
2021.06
49.3
2026.02
42.78
2025.12
35.9
2023.10
34.4
2026.02
29.91
2024.02
29.6
2024.02
26.7
2021.06
26.7
2021.06
23.9
2023.10
21.6
2023.10
20.8
2023.10
19.2
2026.02
15.4
2023.10
15
2025.12
4.8
2025.12
4.4
2025.12
4.1
2025.12
3.6
2024.02
3.2
2025.12
3
2025.12
2.9
2025.12
0