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

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

Browse Source
This commit is contained in:
yesung
2026-04-27 18:58:22 +09:00
parent 3424166ea2
commit 6b86b0da4c
2706 changed files with 9074 additions and 7273 deletions
Download Patch File Download Diff File Expand all files Collapse all files
10_Wiki/Topics/AI/Multi-Agent-Reinforcement-Learning.md
+4 -4
View File
@@ -1,12 +1,12 @@
---
id: RL-MARL-001
category: "[[10_Wiki/💡 Topics/AI]]"
category: "10_Wiki/💡 Topics/AI"
confidence_score: 1.0
tags: [ai, reinforcement-learning, multi-agent, marl, game-theory, coordination]
last_reinforced: 2026-04-26
---
# [[Multi-Agent Reinforcement Learning (MARL, 다중 에이전트 강화학습)]]
# Multi-Agent Reinforcement Learning (MARL, 다중 에이전트 강화학습)
## 📌 한 줄 통찰 (The Karpathy Summary)
> "개별 에이전트의 이기심을 넘어 집단의 하모니를 구축하고, 상호작용의 역동성 속에서 창발적 지능을 발현하라" — 여러 개의 독립적인 학습 주체(Agents)가 동일한 환경에서 동시에 학습하며 서로 협력하거나 경쟁하여 목표를 달성하는 강화학습 체계.
@@ -23,5 +23,5 @@ last_reinforced: 2026-04-26
- **정책 변화:** Antigravity 프로젝트는 여러 협업 AI(Planning Agent, Coding Agent, Review Agent 등)가 상호작용하며 하나의 작업을 완료할 때, 최적의 협업 효율을 도출하기 위해 MARL 기반의 워크플로우 최적화를 연구함.
## 🔗 지식 연결 (Graph)
- [[Reinforcement-Learning]], [[Game-Theory]], [[Monte-Carlo-Tree-Search-MCTS]], [[Graph-Neural-Networks-GNN]]
- **Raw Source:** [[10_Wiki/Topics/AI/Multi-Agent-Reinforcement-Learning.md]]
- [[Reinforcement-Learning]], [[Game-Theory]], [[Monte-Carlo-Tree-Search-MCTS]], Graph-Neural-Networks-GNN
- **Raw Source:** 10_Wiki/Topics/AI/Multi-Agent-Reinforcement-Learning.md