feat: complete wikification of War Commander batch 1&2 and final grey dot cleanup

2026-04-27 18:58:22 +09:00
parent 3424166ea2
commit 6b86b0da4c
2706 changed files with 9074 additions and 7273 deletions
@@ -1,6 +1,6 @@
 ---
 id: P-REINFORCE-AUTO-HYPA-001
-category: "[[10_Wiki/💡 Topics/AI]]"
+category: "10_Wiki/💡 Topics/AI"
 confidence_score: 0.98
 tags: [auto-reinforced, hyperparameters, model-tuning, optimization, machine-learning, learning-rate]
 last_reinforced: 2026-04-20
@@ -27,6 +27,6 @@ last_reinforced: 2026-04-20
 - **정책 변화(RL Update)**: 거대 모델(Foundation-Models) 시대에는 한 번의 학습 비용이 너무 커서, 작은 모델에서 최적 값을 찾은 뒤 이를 거대 모델로 확장 적용하는 '스케일링 법칙 기반 튜닝 정책'이 핵심이 됨. (Scaling-Laws와 연결)

 ## 🔗 지식 연결 (Graph)
- [[Optimization]], [[Gradient-Descent]], [[Scaling-Laws]], [[Foundation-Models]], [[Efficiency]]
+- [[Optimization]], [[Gradient-Descent]], Scaling-Laws, [[Foundation-Models]], [[Efficiency]]
 - **Modern Tech/Tools**: Optuna, Ray Tune, Weights & Biases (W&B), Grid Search, Random Search.
 ---