Offline Reinforcement Learning on D4RL Walker-medium-replay v2
91.6Normalized Return
SPOT
Updated 4d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2022.02 | 91.6 | |
2022.10 | 89.2 | |
2022.10 | 87.1 | |
2022.02 | 81.8 | |
2022.10 | 79.9 | |
2025.12 | 78.9 | |
2022.02 | 77.2 | |
2022.10 | 76.8 | |
2025.12 | 76.6 | |
2022.02 | 73.8 | |
2025.12 | 73.3 | |
2025.12 | 72.3 | |
2022.02 | 66.6 | |
2025.12 | 51.6 | |
2022.02 | 49.5 | |
2022.10 | 40.8 | |
2022.10 | 40.1 | |
2025.12 | 34.3 | |
2025.12 | 29.6 | |
2022.02 | 27 | |
2022.02 | 26 | |
2022.10 | 20.3 | |
2022.10 | 12.2 | |
2025.12 | 5.3 | |
2025.12 | 3.2 |