Sudoku Solving on Sudoku 2x2
1.3Final RewardRainbow
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Rainbow2026.02 | 1.3 | 36.2 | |
| PPO2026.02 | 1.3 | 14.9 | |
| PPO-lagrangian2026.02 | 1.3 | 0.7 | |
| KCAC2026.02 | 1.3 | 9.2 | |
| NSAM(ours)2026.02 | 1.3 | 0.1 | |
| PPO2026.02 | 1.2 | 60 | |
| NSAM(ours)2026.02 | 1.2 | 6.1 | |
| PPO-lagrangian2026.02 | 1.1 | 25 | |
| RC-PPO2026.02 | 0.3 | 11.3 | |
| KCAC2026.02 | -0.4 | 32.2 | |
| PLPG2026.02 | -0.5 | 16.1 | |
| PLPG2026.02 | -0.8 | 5.9 | |
| Rainbow2026.02 | -1.1 | 61.8 | |
| RC-PPO2026.02 | -1.4 | 68.3 |