Sudoku Solving on Sudoku 4x4
2.1Final RewardNSAM(ours)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| NSAM(ours)2026.02 | 2.1 | 0.006 | |
| KCAC2026.02 | 1 | 0.912 | |
| PLPG2026.02 | -2.2 | 0.157 | |
| Rainbow2026.02 | -2.6 | 1 | |
| PPO2026.02 | -2.6 | 1 | |
| PPO-lagrangian2026.02 | -3.4 | 1 | |
| RC-PPO2026.02 | -3.8 | 0.999 |