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>
15 lines
156 B
Plaintext
15 lines
156 B
Plaintext
__pycache__/
|
|
*.pyc
|
|
.venv/
|
|
*.db
|
|
.idea/
|
|
frontend/node_modules/
|
|
frontend/dist/
|
|
frontend/.vite/
|
|
.env
|
|
.env.*
|
|
!.env.example
|
|
geoip/*.mmdb
|
|
rl/runs/
|
|
rl/checkpoints/
|