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

Offline Reinforcement Learning on D4RL walker2d medium-replay v2

100.6Normalized Score

Uncertainty-Aware Rank-One MIMO Q Network

0.96826.83452.778.566Oct 13, 2022May 5, 2023Nov 26, 2023Jun 18, 2024Jan 9, 2025Aug 2, 2025Feb 23, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
100.6
2026.02
94
2023.01
91.9
2023.01
91.6
2022.10
87.1
2023.01
81.8
2026.02
81.8
2026.02
81.8
2022.10
79.9
2026.02
77.7
2023.01
77.2
2022.10
76.8
2023.01
73.8
2026.02
73.7
2026.02
70.9
2023.01
66.6
2023.11
61.2
2023.11
49.8
2023.01
49.5
2022.10
40.8
2022.10
40.1
2023.11
39
2025.12
27.7
2023.01
27
2023.01
26
2026.02
23.6
2022.10
20.3
2025.12
17.8
2025.12
15.6
2026.02
15.2
2025.12
12.6
2022.10
12.2
2025.12
11.2
2025.12
10.7
2026.02
7
2025.12
4.8