Offline Reinforcement Learning on Maze2D umaze v1
52.2Normalized Return
PrivORL-j
Updated 4d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2025.12 | 52.2 | |
2025.12 | 49.9 | |
2025.12 | 49.8 | |
2025.12 | 49.3 | |
2025.12 | 45.5 | |
2025.12 | 42.1 | |
2025.12 | 41.2 | |
2025.12 | 39.8 | |
2025.12 | 38.8 | |
2025.12 | 38.7 | |
2025.12 | 32 | |
2025.12 | 28.9 | |
2025.12 | 28.4 | |
2025.12 | 28.2 | |
2025.12 | 26.8 | |
2025.12 | 25.9 | |
2025.12 | 24.6 | |
2025.12 | 11.2 |