Offline Reinforcement Learning on D4RL Medium-Replay Hopper
110.6Normalized Score
NEUBAY
Updated 4d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2025.12 | 110.6 | |
2025.12 | 109.9 | |
2025.12 | 109.6 | |
2025.12 | 104.4 | |
2025.12 | 104.3 | |
2025.12 | 104 | |
2025.12 | 103.9 | |
2025.12 | 103.9 | |
2025.12 | 103.5 | |
2025.12 | 101 | |
2023.06 | 100 | |
2025.12 | 100 | |
2025.12 | 98.5 | |
2025.12 | 98.3 | |
2025.12 | 98.2 | |
2024.04 | 97.4 | |
2023.06 | 96.8 | |
2025.12 | 96.8 | |
2023.06 | 95.3 | |
2023.06 | 95 | |
2026.02 | 95 | |
2026.02 | 95 | |
2023.06 | 94.7 | |
2025.12 | 94.2 | |
2023.06 | 93.6 | |
2025.12 | 92.8 | |
2025.12 | 92.5 | |
2025.12 | 92.1 | |
2023.06 | 91.5 | |
2023.06 | 89.5 | |
2025.12 | 89.5 | |
2025.12 | 89.5 | |
2026.02 | 89.4 | |
2024.04 | 88.9 | |
2026.02 | 87.8 | |
2023.06 | 86.9 | |
2025.12 | 86.3 | |
2025.12 | 85 | |
2023.05 | 84.54 | |
2023.06 | 84.4 | |
2023.05 | 83.06 | |
2023.06 | 82.7 | |
2025.12 | 82.7 | |
2026.02 | 82.5 | |
2025.12 | 82.4 | |
2024.04 | 82 | |
2026.02 | 81.7 | |
2023.06 | 80.9 | |
2023.06 | 78.3 | |
2023.05 | 73.57 | |
2023.05 | 70.2 | |
2023.05 | 62 | |
2026.02 | 60.9 | |
2023.05 | 57.88 | |
2024.04 | 56.2 | |
2025.12 | 54.9 | |
2025.12 | 53.5 | |
2026.02 | 52.1 | |
2025.12 | 51.6 | |
2025.12 | 51.3 | |
2026.02 | 49.6 | |
2024.04 | 45.6 | |
2025.12 | 40.6 | |
2025.12 | 37.6 | |
2024.04 | 29.8 | |
2024.04 | 29.7 | |
2025.12 | 24.9 | |
2023.06 | 24.3 | |
2023.06 | 22.1 | |
2023.06 | 18.1 | |
2025.12 | 18.1 | |
2023.05 | 11.56 |