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

Offline Reinforcement Learning on D4RL Hopper-medium-expert v2

111.8Normalized Return

PMDB

3.6431.7259.887.88Feb 13, 2022Oct 16, 2022Jun 18, 2023Feb 18, 2024Oct 20, 2024Jun 22, 2025Feb 23, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2022.10
111.8
2022.10
111.8
2026.02
111.6
2026.02
110.8
2022.10
110.7
2022.10
110.7
2026.02
110.5
2022.02
107.6
2023.01
107.6
2022.10
105.6
2022.10
105.6
2026.02
105.6
2022.02
105.4
2023.01
105.4
2022.02
103.3
2023.01
103.3
2022.02
99.3
2023.01
99.3
2022.02
98
2023.01
98
2026.02
98
2022.10
96.9
2022.10
96.9
2023.01
95.3
2022.02
91.5
2023.01
91.5
2026.02
91.5
2022.10
88.2
2022.10
81.3
2022.10
81.3
2022.10
66.2
2022.10
66.2
2026.02
60.6
2025.12
58.1
2026.02
58.1
2022.02
55.8
2023.01
55.8
2025.12
54
2022.10
53.9
2022.10
53.9
2022.02
52.5
2023.01
52.5
2026.02
50.6
2025.12
49.6
2026.02
44.9
2025.12
17
2025.12
12.5
2025.12
11.6
2025.12
7.8