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-POLO-001
-category: "[[10_Wiki/💡 Topics/AI]]"
+category: "10_Wiki/💡 Topics/AI"
 confidence_score: 0.98
 tags: [auto-reinforced, reinforcement-learning, optimization, policy-gradient, ai-training]
 last_reinforced: 2026-04-20
@@ -30,6 +30,6 @@ last_reinforced: 2026-04-20
 - **정책 변화(RL Update)**: 정책 최적화 과정에서 발생하는 '보상 해킹(Reward Hacking)'이나 '안전 위배'를 방지하기 위해, 제약 조건을 수식에 직접 포함하는 'Safe RL' 정책이 자율 주행 및 의료 AI 학습의 필수 규정으로 도입됨.

 ## 🔗 지식 연결 (Graph)
- [[Reinforcement Learning (RL)]], [[Policy Gradient Methods]], [[Optimization]], [[Machine Learning]], [[PPO (Proximal Policy Optimization)]]
+- [[Reinforcement Learning (RL)]], Policy Gradient Methods, [[Optimization]], Machine Learning, PPO (Proximal Policy Optimization)
 - **Modern Tech/Tools**: OpenAI Spinning Up, Stable Baselines3, Ray Rllib.
 ---