Offline Reinforcement Learning on D4RL HalfCheetah Medium v2
73.1Average Normalized Return
MOPO
Updated 4d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.02 | 73.1 | |
| 68.6 | ||
2026.02 | 64.1 | |
2023.01 | 61.8 | |
2022.02 | 58.4 | |
2023.01 | 58.4 | |
2026.02 | 57.9 | |
2022.02 | 48.4 | |
2023.01 | 48.4 | |
2022.02 | 48.3 | |
2023.01 | 48.3 | |
2026.02 | 48.3 | |
2022.02 | 47.4 | |
2023.01 | 47.4 | |
2026.02 | 47 | |
2021.06 | 46.9 | |
2021.06 | 46.3 | |
2021.06 | 44.6 | |
2021.06 | 44 | |
2021.06 | 44 | |
2022.02 | 44 | |
2023.01 | 44 | |
2025.12 | 43.6 | |
2022.02 | 43.5 | |
2023.01 | 43.5 | |
2021.06 | 43.1 | |
2025.12 | 43.1 | |
2026.02 | 43 | |
2021.06 | 42.6 | |
2022.02 | 42.6 | |
2022.02 | 42.6 | |
2023.01 | 42.6 | |
2023.01 | 42.6 | |
2025.12 | 42.5 | |
2025.12 | 42.4 | |
2025.12 | 42.4 | |
2026.02 | 42.2 | |
2026.02 | 41.7 | |
2025.12 | 41.5 | |
2025.12 | 41.2 | |
2026.02 | 40.1 | |
2025.12 | 8.5 | |
2025.12 | 1 |