Game Performance Evaluation on Gin Rummy vs. fixed expert
34.2Win RateStacked recipe
Evaluation Results
| Method | Links | |
|---|---|---|
| Stacked recipeNotes=this work2026.07 | 34.2 | |
| Self-play championContext=prior best2026.07 | 30 | |
| TRPO baselineTraining steps=2M2026.07 | 22.5 | |
| PPO baselineTraining steps=2M2026.07 | 15 |