Decision Making on MLGym Battle of Sexes
2PayoffARTS
Evaluation Results
| Method | Links | |
|---|---|---|
| ARTSBase Model=o32026.06 | 2 | |
| Human BestMethod Type=Human Baseline2026.06 | 1.667 | |
| LinearMethod Type=Prior Works2026.06 | 1.448 | |
| MLEvolveMethod Type=Prior Works2026.06 | 1.446 | |
| AIRAMethod Type=Prior Works2026.06 | 1.442 | |
| ARTS*Base Model=Qwen 4B, Test-time trained=true2026.06 | 1.442 | |
| ARTSBase Model=Qwen 4B2026.06 | 1.441 |