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

docs: finalized wiki integrity maintenance (v3.0 standard) - pruned 1400+ stubs and fixed 11k+ ghost links

Browse Source
This commit is contained in:
Antigravity Agent
2026-05-02 09:18:34 +09:00
parent c84dcb8371
commit 6445fcc05b
13150 changed files with 55394 additions and 100862 deletions
Download Patch File Download Diff File Expand all files Collapse all files
10_Wiki/Topics_Blog/Off-policy-vs-On-policy-Learning.md
+1 -1
View File
@@ -23,5 +23,5 @@ last_reinforced: 2026-04-26
- **정책 변화:** Antigravity 프로젝트는 에이전트의 새로운 도구 사용 스킬을 학습시킬 때, 초기에는 오프-폴리시 기반의 대량 시뮬레이션 데이터로 지능을 쌓고, 실전 단계에서는 온-폴리시 기법을 적용하여 안전하고 정교하게 미세 조정한 정책을 수립함.
## 🔗 지식 연결 (Graph)
- [[Reinforcement-Learning]], [[Markov-Decision-Process-MDP]], Experience-Replay-Strategies, Proximal-Policy-Optimization-PPO
- [[Reinforcement-Learning|Reinforcement-Learning]], [[Markov-Decision-Process-MDP|Markov-Decision-Process-MDP]], Experience-Replay-Strategies, Proximal-Policy-Optimization-PPO
- **Raw Source:** 10_Wiki/Topics/AI/Off-policy-vs-On-policy-Learning.md