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/Best-of-N Sampling.md
+3 -3
View File
@@ -1,8 +1,8 @@
---
id: P-REINFORCE-AI-BEST-OF-N
id: [[P-Reinforce]]-AI-BEST-OF-N
category: "10_Wiki/💡 Topics/AI"
confidence_score: 0.99
tags: [Best-of-N, Sampling, Inference, Reward Model, AI Alignment]
tags: [Best-of-N, Sampling, Inference, Reward Model, AI [[Alignment]]]
last_reinforced: 2026-04-20
---
@@ -23,5 +23,5 @@ last_reinforced: 2026-04-20
- N이 커질수록 품질은 좋아지지만 코스트(비용)와 지연 시간(Latency)이 기하급수적으로 늘어난다. 따라서 서비스의 실시간성 요구도에 따라 N의 적절한 값을 정하는 것이 엔지니어링의 묘미다.
## 🔗 지식 연결 (Graph)
- Related: [[Prompt-Engineering]] , Reinforcement-Learning-from-Human-Feedback-(RLHF)
- Related: [[Prompt-Engineering]] , [[Reinforcement-Learning]]-from-Human-Feedback-(RLHF)
- Metric: Reward-Model-Training