Offline Reinforcement Learning on hopper medium-replay
113Normalized Score
Proposed
Updated 5d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2023.10 | 113 | |
2026.02 | 103.1 | |
2023.10 | 102.5 | |
2026.05 | 102.2 | |
2026.05 | 102 | |
2026.02 | 101.9 | |
2026.02 | 100.5 | |
2026.05 | 100.4 | |
2026.02 | 99.9 | |
2026.02 | 97.5 | |
2026.05 | 95.7 | |
2026.05 | 95.4 | |
2023.10 | 94.7 | |
2026.02 | 94.7 | |
2026.05 | 94.2 | |
2021.06 | 94.1 | |
2026.05 | 93.9 | |
2026.05 | 93.4 | |
2026.05 | 92.1 | |
2023.10 | 89.5 | |
2026.02 | 84.43 | |
2026.02 | 83.99 | |
2026.05 | 82.7 | |
2021.06 | 77.3 | |
2026.02 | 75.22 | |
2021.06 | 71 | |
2026.02 | 70.06 | |
2024.02 | 63.7 | |
2026.05 | 60.9 | |
2026.02 | 56.96 | |
2024.02 | 52.1 | |
2024.02 | 50.8 | |
2026.02 | 50.79 | |
2024.02 | 48.6 | |
2021.06 | 48.6 | |
2026.02 | 46.7 | |
2023.10 | 44.4 | |
2026.02 | 39.22 | |
2024.02 | 38.7 | |
2023.10 | 36.4 | |
2026.02 | 35.9 | |
2023.10 | 33.7 | |
2023.10 | 33.1 | |
2026.02 | 33.03 | |
2023.10 | 32.6 | |
2026.02 | 30.17 | |
2021.06 | 21.2 | |
2024.02 | 7.7 | |
2025.12 | 7.4 | |
2025.12 | 5.6 | |
2025.12 | 4.6 | |
2025.12 | 4.1 | |
2025.12 | 3.7 | |
2025.12 | 3.5 | |
2025.12 | 2.3 |