bluemsi/2nd
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[G1-Sync] Manual knowledge update

Browse Source
This commit is contained in:
Antigravity Agent
2026-04-30 22:42:02 +09:00
parent 0bd4f19e38
commit c36c0644a1
4888 changed files with 18470 additions and 18602 deletions
Download Patch File Download Diff File Expand all files Collapse all files
10_Wiki/Topics/RL_Neuroscience.md
+3 -3
View File
@@ -1,5 +1,5 @@
---
id: P-REINFORCE-AI-003
id: [[P-Reinforce]]-AI-003
category: "10_Wiki/💡 Topics/AI"
confidence_score: 0.98
tags: [ai, rl, neuroscience, brain]
@@ -21,9 +21,9 @@ github_commit: "batch-reinforce-04"
## ⚠️ 모순 및 업데이트 (Contradictions & RL Update)
- **과거 데이터와의 충돌:** 단순 조건 반사 모델에서 미래 가치를 예측하는 '계산적 에이전트' 모델로 확장.
- **정책 변화:** P-Reinforce 엔진의 핵심 로직(Self-Optimization)을 뒷받침하는 이론적 근거로 최상단 배치.
- **정책 변화:** P-Reinforce 엔진의 핵심 로직(Self-[[Optimization]])을 뒷받침하는 이론적 근거로 최상단 배치.
## 🔗 지식 연결 (Graph)
- **Parent:** 10_Wiki/💡 Topics/AI
- **Related:** [[Dopamine]], [[Operant_Conditioning]], [[Reinforcement-Learning]]
- **Raw Source:** 00_Raw/2026-04-20/Computational Neuroscience of Reinforcement Learning.md
- **Raw Source:** 00_Raw/2026-04-20/[[Computational Neuroscience of Reinforcement Learning]].md