N-Queens Problem on N=10
1Final RewardNSAM(ours)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| NSAM(ours)2026.02 | 1 | 1.5 | |
| PPO2026.02 | -0.6 | 100 | |
| KCAC2026.02 | -0.8 | 100 | |
| PPO-lagrangian2026.02 | -1 | 100 | |
| Rainbow2026.02 | -1.2 | 100 | |
| PLPG2026.02 | -1.6 | 98.2 | |
| RC-PPO2026.02 | -1.7 | 100 |
Loading the SOTA2 catalog…