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

10_Wiki/Topics/AI/Reinforcement Learning (RL).md

@@ -1,6 +1,6 @@
 ---
 id: P-REINFORCE-AUTO-RL-001
-category: "[[10_Wiki/💡 Topics/AI]]"
+category: "10_Wiki/💡 Topics/AI"
 confidence_score: 0.99
 tags: [auto-reinforced, reinforcement-learning, machine-learning, ai-training, optimization]
 last_reinforced: 2026-04-20
@@ -31,6 +31,6 @@ last_reinforced: 2026-04-20
 - **정책 변화(RL Update)**: 보상만을 쫓는 에이전트가 예상치 못한 위험(Safety Violation)을 저지르는 것을 막기 위해, 수치화된 보상 뒤에 '인간의 윤리적 제약'을 프로그래밍하는 '정렬(Alignment) 정책'이 RL 연구의 최우선 순위로 부상함.
 
 ## 🔗 지식 연결 (Graph)
-- [[Proximal Policy Optimization (PPO)]], [[Policy-Optimization]], [[Ps-Reinforce]], [[Neurobiology of Reward]], [[Game Theory]]
+- [[Proximal Policy Optimization (PPO)]], [[Policy-Optimization]], [[Ps-Reinforce]], Neurobiology of Reward, Game Theory
 - **Modern Tech/Tools**: Gymnasium (OpenAI Gym), DeepMind MuJoCo, Ray Rllib.
 ---