Sudoku Solving on Sudoku 3x3
160Final RewardNSAM(ours)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| NSAM(ours)2026.02 | 160 | 0.3 | |
| KCAC2026.02 | 150 | 57.1 | |
| Rainbow2026.02 | 80 | 88.2 | |
| PPO2026.02 | -40 | 99.6 | |
| PPO-lagrangian2026.02 | -40 | 99.9 | |
| PLPG2026.02 | -90 | 8.9 | |
| RC-PPO2026.02 | -230 | 99 |
| Method | Links | ||
|---|---|---|---|
| NSAM(ours)2026.02 | 160 | 0.3 | |
| KCAC2026.02 | 150 | 57.1 | |
| Rainbow2026.02 | 80 | 88.2 | |
| PPO2026.02 | -40 | 99.6 | |
| PPO-lagrangian2026.02 | -40 | 99.9 | |
| PLPG2026.02 | -90 | 8.9 | |
| RC-PPO2026.02 | -230 | 99 |