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

Offline Reinforcement Learning on D4RL hopper-expert v2

118.9Normalized Score

PhyB

7.93236.74165.5594.359Oct 13, 2022May 21, 2023Dec 28, 2023Aug 5, 2024Mar 14, 2025Oct 21, 2025May 30, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.05
118.9
2023.06
113
2024.06
112.5
2026.05
112.4
2026.05
112.2
2022.10
111.7
2022.10
111.7
2026.05
111.7
2024.06
111.6
2023.06
111.5
2026.05
111.5
2023.06
111.3
2023.06
111.2
2023.06
111.1
2023.06
111
2026.02
110.5
2026.02
110.5
2022.10
110.1
2022.10
110.1
2024.06
109.6
2026.02
107.8
2026.02
107.8
2022.10
107.7
2022.10
107.7
2023.06
107.3
2022.10
106.5
2022.10
106.5
2026.05
106.5
2026.02
106.2
2023.06
106
2023.06
105.8
2026.02
103.6
2023.06
103.3
2026.05
102.3
2023.06
97.5
2025.12
97
2026.02
96.5
2025.12
94.8
2024.06
90.2
2025.12
89.3
2022.10
80.4
2022.10
80.4
2026.05
80.4
2022.10
78.1
2022.10
78.1
2026.02
77
2025.12
70.1
2023.06
65.6
2023.06
64.2
2025.12
62.6
2026.02
62.5
2025.12
59.1
2026.02
54.6
2022.10
50
2026.05
50
2025.12
47.9
2026.05
40.5
2022.10
39.4
2022.10
39.4
2023.06
37.3
2023.06
25.9
2023.06
25.5
2023.06
24.4
2023.06
22.5
2023.06
18.6
2023.06
12.2