blazing8.git - Unnamed repository; edit this file 'description' to name the repository.

Age	Commit message (Expand)	Author
102 min.	Add 2-player PPO training log (500k episodes, 60.4% vs greedy)HEAD main	YurenHao0426
4 hours	Raise entropy floor to 0.02, increase eval games to 2000	haoyuren
5 hours	Change default eval_every from 10000 to 2500	haoyuren
5 hours	Use auto-calibrated collect_batch in Colab notebook	haoyuren
5 hours	Add training curve plots to Colab notebook	haoyuren
5 hours	Add entropy annealing to escape greedy local minimum after warmup	haoyuren
5 hours	Auto-calibrate collect_batch when not specified	haoyuren
5 hours	Fix total_mem → total_memory in Colab GPU check	haoyuren
5 hours	Fix invalid notebook cell schema (markdown with execution_count)	haoyuren
5 hours	Batched game collection for ~7x training speedup	haoyuren
6 hours	Update README and Colab notebook for current rules and features	haoyuren
6 hours	Separate CPU collect / GPU train, add training CSV log	haoyuren
6 hours	Fix SWAP inheritance, stalemate logic, add greedy warmup	haoyuren
14 hours	Improve versus UI: suit colors, AI highlighting, draw tell	haoyuren
14 hours	Update rules: free draw/pass, remove Q in 2-player games	haoyuren
15 hours	Add tqdm progress bar, fix Colab username	haoyuren
15 hours	Add Colab GPU training notebook	haoyuren
15 hours	Initial commit: Blazing Eights RL agent	haoyuren