| Age | Commit message (Expand) | Author |
|---|---|---|
| 6 hours | Raise entropy floor to 0.02, increase eval games to 2000 | haoyuren |
| 7 hours | Change default eval_every from 10000 to 2500 | haoyuren |
| 7 hours | Add entropy annealing to escape greedy local minimum after warmup | haoyuren |
| 7 hours | Auto-calibrate collect_batch when not specified | haoyuren |
| 7 hours | Batched game collection for ~7x training speedup | haoyuren |
| 7 hours | Separate CPU collect / GPU train, add training CSV log | haoyuren |
| 7 hours | Fix SWAP inheritance, stalemate logic, add greedy warmup | haoyuren |
| 16 hours | Update rules: free draw/pass, remove Q in 2-player games | haoyuren |
| 17 hours | Add tqdm progress bar, fix Colab username | haoyuren |
| 17 hours | Initial commit: Blazing Eights RL agent | haoyuren |
 |
index : blazing8.git | |
| Unnamed repository; edit this file 'description' to name the repository. | Ubuntu |
| summaryrefslogtreecommitdiff |