TTRL-PPO
| Method | Links | |||||
|---|---|---|---|---|---|---|
2025.12 | 24.4 | 46.7 | 23.3 | - | - | |
2025.12 | 24 | 43.3 | 26.7 | - | 42.85 | |
2025.12 | 23.5 | 40 | 23.3 | - | - | |
2025.12 | 23.5 | 43.3 | 23.3 | - | 38.56 | |
2025.12 | 20.8 | 40 | 23.3 | - | - | |
2025.12 | 20.6 | 40 | 23.3 | - | 41.45 | |
2025.12 | 18.5 | 46.7 | 23.3 | - | - | |
2025.12 | 16 | 46.7 | 23.3 | - | 15.2 | |
2025.12 | 15.6 | 43.3 | 20 | - | - | |
2025.12 | 14.6 | 46.7 | 20 | - | 17.25 | |
2025.12 | 11.9 | 43.3 | 20 | - | - | |
2025.12 | 10.4 | 46.7 | 20 | - | 14.35 | |
2025.12 | 3.8 | 30 | 6.7 | - | - | |
2025.12 | 3.8 | 30 | 6.7 | - | 13.7 | |
2025.12 | 3.5 | 23.3 | 6.7 | - | - | |
2025.12 | 1.7 | 20 | 6.7 | - | 47.62 | |
2025.12 | 1.7 | 23.3 | 6.7 | - | 30.02 | |
2025.12 | 1.5 | 16.7 | 6.7 | - | - |