RL: self-play PPO trening siete

BridzikNet (trup + guess/play/value hlavy s maskovanim), self-play
generator so zdielanou sietou na 4 sedadlach a opponent mixingom
(random/heuristicke sedadla pre robustnost), vlastny clipped-PPO
so skalovanim odmien a lr/entropy annealom. Torch je len trenovacia
zavislost na hoste (requirements-rl.txt); checkpointy a logy su
gitignorovane. Spustenie: py -m rl.train.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

.gitignore

@@ -10,3 +10,5 @@ frontend/.vite/
 .env.*
 !.env.example
 geoip/*.mmdb
+rl/runs/
+rl/checkpoints/