Offline Reinforcement Learning on D4RL Medium-Replay HalfCheetah
95.8Normalized Score
Adaptive Policy Selection and Fine-Tuning
Updated 23d ago
Evaluation Results
| Method | Links | |
|---|---|---|
| 95.8 | ||
2026.05 | 84.7 | |
2026.05 | 84.7 | |
2026.05 | 78.4 | |
2025.12 | 77.6 | |
2025.12 | 77.2 | |
2025.12 | 76.2 | |
2026.05 | 75.4 | |
2026.03 | 74.4 | |
2025.12 | 72.9 | |
2025.12 | 72.1 | |
2025.12 | 72.1 | |
2025.12 | 71.7 | |
2026.03 | 71.7 | |
2023.10 | 71.7 | |
2026.05 | 71.7 | |
2023.10 | 71.5 | |
2023.10 | 70.4 | |
2025.12 | 69.5 | |
2023.10 | 68.9 | |
2026.03 | 68.7 | |
2026.05 | 68.7 | |
2026.05 | 68.4 | |
2025.12 | 67.6 | |
2026.03 | 67.6 | |
2026.05 | 67.6 | |
2025.12 | 67.3 | |
2025.12 | 66.4 | |
2025.12 | 65.5 | |
2025.12 | 64.6 | |
2026.03 | 62 | |
2026.05 | 62 | |
2025.12 | 61.3 | |
2023.10 | 61.3 | |
2025.12 | 55.1 | |
2025.12 | 55.1 | |
2023.10 | 55.1 | |
2026.03 | 51.4 | |
2026.05 | 51.4 | |
2023.10 | 48 | |
2023.06 | 45.5 | |
2026.02 | 45.5 | |
2023.06 | 45.5 | |
2025.12 | 45.3 | |
2026.03 | 45.3 | |
2026.05 | 45.3 | |
2025.12 | 45.1 | |
2026.02 | 44.6 | |
2024.04 | 44.5 | |
2026.03 | 44.5 | |
2026.05 | 44.5 | |
2023.10 | 44.4 | |
2023.06 | 44.2 | |
2023.10 | 44.2 | |
2025.12 | 44 | |
2025.12 | 43.5 | |
2025.12 | 43.4 | |
2024.04 | 42.3 | |
2023.06 | 42.2 | |
2025.12 | 42.2 | |
2023.06 | 41.9 | |
2023.06 | 41.9 | |
2024.04 | 41.5 | |
2023.06 | 41.1 | |
2025.12 | 41.1 | |
2026.02 | 41.1 | |
2026.02 | 41.1 | |
2023.06 | 40.8 | |
2023.06 | 40.8 | |
2024.04 | 40.5 | |
2023.06 | 40.2 | |
2024.04 | 39.8 | |
2026.02 | 39.8 | |
2023.06 | 39.6 | |
2023.06 | 39.4 | |
2023.06 | 39.3 | |
2025.12 | 39.3 | |
2026.02 | 39.1 | |
2023.06 | 39.1 | |
2023.06 | 39 | |
2026.02 | 37.8 | |
2023.06 | 36.6 | |
2023.06 | 36.6 | |
2025.12 | 36.6 | |
2025.12 | 36.6 | |
2023.06 | 36.6 | |
2024.04 | 35.7 | |
2026.02 | 35.6 | |
2024.04 | 33.6 | |
2025.12 | 28.9 | |
2025.12 | 27.9 | |
2025.12 | 27.8 | |
2025.12 | 26.1 | |
2025.12 | 24.2 | |
2025.12 | 21.3 | |
2025.12 | 19.7 | |
2026.02 | 15.2 |