docs: finalized wiki integrity maintenance (v3.0 standard) - pruned 1400+ stubs and fixed 11k+ ghost links
This commit is contained in:
@@ -2,7 +2,7 @@
|
||||
id: RL-ELIG-001
|
||||
category: "10_Wiki/💡 Topics/AI"
|
||||
confidence_score: 1.0
|
||||
tags: [[[Reinforcement-Learning]], ai, eligibility-traces, credit-assignment, temporal-difference]
|
||||
tags: [[Reinforcement-Learning|[Reinforcement-Learning]], ai, eligibility-traces, credit-assignment, temporal-difference]
|
||||
last_reinforced: 2026-04-26
|
||||
---
|
||||
|
||||
@@ -25,5 +25,5 @@ last_reinforced: 2026-04-26
|
||||
- **정책 변화:** Antigravity 에이전트의 다단계 의사결정 모델은 적격성 흔적 원리를 활용하여, 최종 태스크 성공 시 그 과정에서 거쳐온 중간 지식 검색 단계들의 유용성을 소급 평가함.
|
||||
|
||||
## 🔗 지식 연결 (Graph)
|
||||
- [[Temporal-Difference-Learning]], [[Reinforcement-Learning]], Q-Learning-Foundations, [[Monte-Carlo-Methods]]
|
||||
- [[Temporal-Difference-Learning|Temporal-Difference-Learning]], [[Reinforcement-Learning|Reinforcement-Learning]], Q-Learning-Foundations, [[Monte-Carlo-Methods|Monte-Carlo-Methods]]
|
||||
- **Raw Source:** 10_Wiki/Topics/AI/Eligibility-Traces.md
|
||||
|
||||
Reference in New Issue
Block a user