Offline Reinforcement Learning on D4RL HalfCheetah Med-Replay v2
52.2Avg Normalized Return
SPOT
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2022.02 | 52.2 | |
2021.06 | 47.7 | |
2021.06 | 47.7 | |
2021.06 | 45.5 | |
2022.02 | 45.5 | |
2022.02 | 44.6 | |
2022.02 | 44.2 | |
2021.06 | 44.1 | |
2021.06 | 42.4 | |
2021.06 | 42.3 | |
2021.06 | 41.9 | |
2022.02 | 40.5 | |
2025.12 | 39.8 | |
2025.12 | 39.6 | |
2025.12 | 38.8 | |
2021.06 | 38.6 | |
2021.06 | 38.4 | |
2022.02 | 38.1 | |
2025.12 | 36.7 | |
2021.06 | 36.6 | |
2022.02 | 36.6 | |
2022.02 | 36.6 | |
2021.06 | 34.9 | |
2025.12 | 33.3 | |
2025.12 | 33 | |
2025.12 | 32.8 | |
2025.12 | 7.8 | |
2025.12 | 5.2 | |
2021.06 | 4.3 |