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

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