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

Offline Reinforcement Learning on D4RL walker2d-medium-expert v2

115.4Normalized Score

EDAC-10

2.97632.16361.3590.537Oct 13, 2022May 21, 2023Dec 28, 2023Aug 5, 2024Mar 14, 2025Oct 21, 2025May 30, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.02
115.4
2026.05
114.9
2022.10
114.7
2022.10
114.7
2026.05
114.4
2023.01
113.04
2023.01
113
112.9
2026.05
112.4
2023.01
112
2026.05
112
2022.10
111.9
2022.10
111.9
2026.05
111.9
2023.01
110.1
2026.02
110.1
2026.02
110.1
2023.01
109.6
2026.02
109.6
2022.10
109.1
2022.10
109.1
2026.05
109.1
2023.01
108.8
2023.11
108.2
2023.01
108.1
2026.02
107.9
2022.10
107.5
2022.10
107.5
2023.01
107.5
2026.05
107.5
2022.10
107
2022.10
107
2026.05
101.1
2026.02
96.5
2023.11
95.6
2025.12
95.4
2025.12
90.6
2022.10
90.1
2022.10
90.1
2025.12
85.3
2025.12
78.5
2026.02
77.4
2023.01
74.5
2025.12
63.1
2025.12
61.4
2022.10
56.7
2026.05
56.7
2023.11
44.6
2026.02
43.6
2025.12
35.1
2026.02
22.1
2022.10
9.3
2022.10
9.3
2026.05
7.3