Offline Reinforcement Learning on D4RL HalfCheetah Med-Replay
72.1Normalized Avg Return
MOPO
Updated 4d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2024.11 | 72.1 | |
2024.11 | 71.7 | |
2024.11 | 66.3 | |
2024.11 | 63.7 | |
2024.11 | 55.5 | |
2023.10 | 53.1 | |
2023.10 | 45.5 | |
2023.10 | 44.2 | |
2024.11 | 43.9 | |
2023.10 | 42.3 | |
2023.10 | 42.2 | |
2023.10 | 41.9 | |
2024.11 | 41.8 | |
2023.10 | 41.3 | |
2023.10 | 41 | |
2023.10 | 40.2 | |
2024.05 | 37.91 | |
2023.10 | 36.6 | |
2023.10 | 36.6 | |
2024.05 | 36.57 |