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

Offline Reinforcement Learning on D4RL Walker2d Medium v2

94.2Normalized Return

PMDB

-3.97621.5124772.488Jun 3, 2021Mar 17, 2022Dec 30, 2022Oct 14, 2023Jul 27, 2024May 11, 2025Feb 23, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2022.10
94.2
2022.10
92.5
2026.02
92.2
2023.01
90.2
2026.02
89.6
2026.02
87.6
2022.02
86.4
2023.01
86.4
2022.02
83.7
2023.01
83.7
2026.02
83.7
2021.06
82.6
2022.02
81.8
2023.01
81.8
2021.06
81.3
2021.06
81.1
2025.12
80.2
2022.10
79.5
2021.06
79.4
2021.06
79
2025.12
78.9
2025.12
78.5
2022.02
78.3
2023.01
78.3
2026.02
78.3
2023.11
77.8
2025.12
77.8
2021.06
77.3
2021.06
77.2
2025.12
75.6
2026.02
75.4
2022.02
75.3
2023.01
75.3
2021.06
74
2022.02
74
2023.01
74
2026.02
73.3
2022.10
72.8
2021.06
72.5
2022.02
72.5
2023.01
72.5
2022.02
72.4
2023.01
72.4
2023.11
71.7
2022.10
70.9
2025.12
70.8
2025.12
69.9
2021.06
66.6
2025.12
63.7
2022.10
59.8
2022.10
59.7
2025.12
51.8
2025.12
49.1
2025.12
48.7
2025.12
47.7
2026.02
47.7
2025.12
44.5
2025.12
43.4
2025.12
43
2026.02
41.2
2021.06
41
2021.06
36.9
2023.11
17.8
2021.06
9.7
2021.06
0.9
2025.12
0
2026.02
-0.2