Offline Reinforcement Learning on Walker2d Expert
211.31Episodic Return
QDFM
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.02 | 211.31 | - | |
2026.02 | 151.19 | - | |
2026.02 | 71.89 | - | |
2026.02 | 4.57 | - | |
2026.02 | 3.26 | - | |
2026.02 | 1.53 | - | |
2026.02 | -0.2 | - | |
2026.02 | -0.3 | - | |
2026.02 | -0.31 | - | |
2026.02 | -7.5 | - | |
2026.02 | -12.2 | - | |
2026.02 | -12.77 | - | |
2025.12 | - | 8.3 | |
2025.12 | - | 9.3 | |
2025.12 | - | 12.4 | |
2025.12 | - | 13.9 | |
2025.12 | - | 10.2 | |
2025.12 | - | 13.5 | |
2025.12 | - | 18.9 |