Offline Reinforcement Learning on D4RL Medium-Replay Walker2d
97Normalized Score
PSPO
Updated 23d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.05 | 97 | |
2026.05 | 95.6 | |
2026.05 | 89.7 | |
2026.05 | 89.2 | |
2026.05 | 85.3 | |
2023.06 | 82.6 | |
2023.06 | 82.6 | |
2025.12 | 81.5 | |
2025.12 | 81.2 | |
2023.06 | 80.7 | |
2026.05 | 79.9 | |
2025.12 | 79.8 | |
2023.06 | 79.3 | |
2025.12 | 78.8 | |
2023.06 | 77.2 | |
2023.06 | 77.2 | |
2023.05 | 77 | |
2026.05 | 76.8 | |
2023.06 | 75 | |
2025.12 | 75 | |
2023.06 | 73.9 | |
2023.06 | 73.7 | |
2023.06 | 73.4 | |
2023.05 | 73.11 | |
2023.06 | 72.3 | |
2023.05 | 72.07 | |
2025.12 | 71.8 | |
2023.05 | 71.27 | |
2023.06 | 70.9 | |
2023.05 | 68.79 | |
2023.06 | 66.8 | |
2023.06 | 66.6 | |
2025.12 | 66.6 | |
2023.06 | 66.6 | |
2025.09 | 66.36 | |
2023.06 | 61.2 | |
2025.12 | 61.2 | |
2023.05 | 59.92 | |
2025.12 | 56 | |
2025.09 | 54.87 | |
2023.06 | 49.8 | |
2026.05 | 40.8 | |
2023.06 | 26 | |
2025.12 | 26 | |
2025.12 | 15.5 | |
2025.12 | 14.1 | |
2023.05 | 10.3 | |
2025.12 | 9.5 | |
2025.12 | 9 | |
2025.12 | 6.9 | |
2025.12 | 2.9 | |
2025.12 | 2 |