refactor(topics): 멀티 에이전트용 지식 재편 — _Common(공통 기본기) + Domain_* 구조
에이전트 8종(대화형/프로그래머 C·S/디자이너/설계자/기획자/QA/PD/PM)에게 [공통 기본 능력 + 롤별 Specialty] 2층으로 지식을 주입하기 위한 재분류. 문서 내용·포맷은 무수정, 폴더 이동만 (6,372개 문서 수 보존 확인). - Topic_Programming → Domain_Programming (내부 구조 보존) - Topic_Graphic → Domain_Design - Topic_Business → Domain_Product - Topic_General → Domain_General - _Common 신설: Math(구 Topic_Math_Specialty), Reasoning(구 General/From_Thinking & Reasoning), Reasoning_Creativity(구 General/From_창의성), Communication(Poetic_Blog_Writing + From_writing) - 타 도메인의 From_* 폴더는 유지 (출처 표기일 뿐, 이미 도메인에 맞게 분류된 문서) - 빈 폴더 정리 (memory/procedures) - 에이전트→폴더 매핑은 workspace의 .astra/agent-knowledge-map.json (9개 에이전트) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Antigravity Agent
@@ -0,0 +1,208 @@
|
||||
---
|
||||
id: wiki-2026-0508-policy-optimization
|
||||
title: Policy Optimization
|
||||
category: 10_Wiki/Topics
|
||||
status: verified
|
||||
canonical_id: self
|
||||
aliases: [policy-gradient, ppo, trpo, grpo, dpo, rlhf-optimization]
|
||||
duplicate_of: none
|
||||
source_trust_level: A
|
||||
confidence_score: 0.9
|
||||
verification_status: applied
|
||||
tags: [reinforcement-learning, ppo, grpo, dpo, rlhf]
|
||||
raw_sources: []
|
||||
last_reinforced: 2026-05-10
|
||||
github_commit: pending
|
||||
tech_stack:
|
||||
language: Python
|
||||
framework: PyTorch / TRL
|
||||
---
|
||||
|
||||
# Policy Optimization
|
||||
|
||||
## 매 한 줄
|
||||
> **"매 policy π_θ 의 reward expectation 의 직접 maximize"**. 매 vanilla PG (REINFORCE) → A2C/A3C → 매 TRPO (trust region) → 매 PPO (clip surrogate, 2017) → 매 GRPO (group-relative, DeepSeek 2024) → 매 DPO (preference, 2023). 매 modern LLM RLHF 의 backbone.
|
||||
|
||||
## 매 핵심
|
||||
|
||||
### 매 algorithm 계보
|
||||
- **매 REINFORCE (1992)**: ∇J = E[∇log π · R]. 매 high variance.
|
||||
- **매 A2C/A3C (2016)**: actor-critic, advantage A = Q - V. 매 lower variance.
|
||||
- **매 TRPO (2015)**: trust region — KL constraint. 매 monotonic improvement guarantee. 매 expensive (Fisher).
|
||||
- **매 PPO (2017, Schulman)**: clipped surrogate r·A vs clip(r, 1-ε, 1+ε)·A. 매 first-order, 매 simple, 매 dominant 2017-2023.
|
||||
- **매 GRPO (2024, DeepSeek)**: PPO 의 critic 의 제거 — 매 group-relative advantage (mean of K samples). 매 efficient for LLM RL.
|
||||
- **매 DPO (2023, Rafailov)**: 매 reward model 의 우회 — 매 preference data 의 closed-form policy update. 매 RLHF simplified.
|
||||
- **매 GSPO, KTO, ORPO** (2024): DPO variants.
|
||||
|
||||
### 매 PPO clip objective
|
||||
```
|
||||
L_CLIP(θ) = E[ min( r·A, clip(r, 1-ε, 1+ε)·A ) ]
|
||||
where r = π_θ(a|s) / π_old(a|s)
|
||||
```
|
||||
|
||||
### 매 GRPO (DeepSeek-Math/R1)
|
||||
```
|
||||
A_i = (R_i - mean(R)) / std(R) # group-relative
|
||||
L = E[ min(r·A, clip(r, 1-ε, 1+ε)·A) - β·KL(π||π_ref) ]
|
||||
```
|
||||
매 critic 의 사용 X — 매 sample group 의 baseline 으로.
|
||||
|
||||
### 매 DPO objective
|
||||
```
|
||||
L_DPO = -E[ log σ( β·log(π(y_w|x)/π_ref(y_w|x)) - β·log(π(y_l|x)/π_ref(y_l|x)) ) ]
|
||||
```
|
||||
매 chosen y_w + rejected y_l 의 directly optimize.
|
||||
|
||||
### 매 응용
|
||||
1. 매 LLM RLHF (PPO → GRPO → DPO).
|
||||
2. 매 robot control (PPO).
|
||||
3. 매 game-playing (OpenAI Five, AlphaStar).
|
||||
4. 매 LLM reasoning (R1-style RL).
|
||||
|
||||
## 💻 패턴
|
||||
|
||||
### PPO — minimal (CleanRL-style)
|
||||
```python
|
||||
import torch, torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
|
||||
class ActorCritic(nn.Module):
|
||||
def __init__(self, obs_dim, act_dim):
|
||||
super().__init__()
|
||||
self.actor = nn.Sequential(nn.Linear(obs_dim, 64), nn.Tanh(),
|
||||
nn.Linear(64, 64), nn.Tanh(),
|
||||
nn.Linear(64, act_dim))
|
||||
self.critic = nn.Sequential(nn.Linear(obs_dim, 64), nn.Tanh(),
|
||||
nn.Linear(64, 64), nn.Tanh(),
|
||||
nn.Linear(64, 1))
|
||||
|
||||
def ppo_update(net, opt, obs, acts, old_logp, advs, returns, eps=0.2, c_v=0.5, c_e=0.01):
|
||||
logits = net.actor(obs)
|
||||
dist = torch.distributions.Categorical(logits=logits)
|
||||
logp = dist.log_prob(acts)
|
||||
ratio = (logp - old_logp).exp()
|
||||
surr1 = ratio * advs
|
||||
surr2 = ratio.clamp(1-eps, 1+eps) * advs
|
||||
pg_loss = -torch.min(surr1, surr2).mean()
|
||||
v = net.critic(obs).squeeze(-1)
|
||||
v_loss = F.mse_loss(v, returns)
|
||||
ent = dist.entropy().mean()
|
||||
loss = pg_loss + c_v * v_loss - c_e * ent
|
||||
opt.zero_grad(); loss.backward()
|
||||
nn.utils.clip_grad_norm_(net.parameters(), 0.5); opt.step()
|
||||
```
|
||||
|
||||
### GAE (Generalized Advantage Estimation)
|
||||
```python
|
||||
def gae(rewards, values, dones, last_v, gamma=0.99, lam=0.95):
|
||||
advs = torch.zeros_like(rewards)
|
||||
g = 0
|
||||
for t in reversed(range(len(rewards))):
|
||||
next_v = last_v if t == len(rewards)-1 else values[t+1]
|
||||
delta = rewards[t] + gamma * next_v * (1 - dones[t]) - values[t]
|
||||
g = delta + gamma * lam * (1 - dones[t]) * g
|
||||
advs[t] = g
|
||||
return advs, advs + values
|
||||
```
|
||||
|
||||
### GRPO — DeepSeek-style (TRL)
|
||||
```python
|
||||
from trl import GRPOConfig, GRPOTrainer
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
|
||||
tok = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
|
||||
|
||||
def reward_fn(prompts, completions, **kwargs):
|
||||
# 매 e.g. correctness check for math problems
|
||||
return [1.0 if check_answer(c) else 0.0 for c in completions]
|
||||
|
||||
config = GRPOConfig(
|
||||
num_generations=8, # 매 group size K
|
||||
learning_rate=1e-6,
|
||||
beta=0.04, # KL penalty
|
||||
max_prompt_length=512, max_completion_length=512,
|
||||
)
|
||||
trainer = GRPOTrainer(model=model, reward_funcs=reward_fn, args=config,
|
||||
train_dataset=ds, processing_class=tok)
|
||||
trainer.train()
|
||||
```
|
||||
|
||||
### DPO (TRL)
|
||||
```python
|
||||
from trl import DPOTrainer, DPOConfig
|
||||
|
||||
# Dataset: {"prompt": str, "chosen": str, "rejected": str}
|
||||
config = DPOConfig(beta=0.1, learning_rate=5e-7, max_length=1024)
|
||||
trainer = DPOTrainer(model=model, ref_model=ref_model, args=config,
|
||||
train_dataset=preference_ds, processing_class=tok)
|
||||
trainer.train()
|
||||
```
|
||||
|
||||
### Reward shaping for GRPO (math + format)
|
||||
```python
|
||||
import re
|
||||
|
||||
def reward_correctness(completions, ground_truth, **k):
|
||||
return [1.0 if extract_answer(c) == gt else 0.0
|
||||
for c, gt in zip(completions, ground_truth)]
|
||||
|
||||
def reward_format(completions, **k):
|
||||
# 매 <think>...</think><answer>...</answer> 의 강요
|
||||
pat = re.compile(r"<think>.*?</think>\s*<answer>.*?</answer>", re.S)
|
||||
return [0.5 if pat.search(c) else 0.0 for c in completions]
|
||||
|
||||
# Combine in TRL: pass as list reward_funcs=[reward_correctness, reward_format]
|
||||
```
|
||||
|
||||
### KL penalty (PPO-RLHF)
|
||||
```python
|
||||
# 매 reference model 매 anchor 의 사용 — 매 RLHF 의 stay close to SFT
|
||||
log_ratio = logp_policy - logp_ref
|
||||
kl = (log_ratio.exp() - 1 - log_ratio).mean() # 매 unbiased k3 estimator
|
||||
loss = pg_loss + beta * kl
|
||||
```
|
||||
|
||||
### TRPO line-search (sketch)
|
||||
```python
|
||||
# 매 modern code 매 PPO 의 사용 — TRPO 매 reference only
|
||||
# 1. compute natural gradient: F^-1 g (Fisher inverse via conjugate gradient)
|
||||
# 2. line-search with KL ≤ δ constraint
|
||||
# 3. accept step if surrogate improves and KL within budget
|
||||
```
|
||||
|
||||
## 매 결정 기준
|
||||
| 상황 | Algorithm |
|
||||
|---|---|
|
||||
| 매 standard RL benchmark (Atari, MuJoCo) | 매 PPO |
|
||||
| 매 LLM RL with verifiable reward | 매 GRPO |
|
||||
| 매 LLM preference data (no reward model) | 매 DPO |
|
||||
| 매 LLM RLHF (with RM) | 매 PPO or GRPO |
|
||||
| 매 sample-efficient continuous control | 매 SAC (off-policy) |
|
||||
| 매 monotonic improvement guarantee | 매 TRPO (rare in practice) |
|
||||
|
||||
**기본값**: 매 PPO (RL benchmark) / GRPO (LLM RL) / DPO (LLM preference).
|
||||
|
||||
## 🔗 Graph
|
||||
- 부모: [[Reinforcement-Learning]] · [[RLHF]]
|
||||
- 변형: [[PPO]] · [[GRPO]] · [[DPO]] · [[TRPO]] · [[A2C]]
|
||||
|
||||
## 🤖 LLM 활용
|
||||
**언제**: 매 PPO 매 baseline RL, 매 GRPO 매 LLM verifiable-reward task (math, code), 매 DPO 매 preference data only 매 사용.
|
||||
**언제 X**: 매 sample-efficiency critical (off-policy: SAC, TD3), 매 ground-truth label exists (supervised 의 사용).
|
||||
|
||||
## ❌ 안티패턴
|
||||
- **매 huge KL divergence allow**: 매 policy 매 ref 보다 collapse → 매 reward hacking.
|
||||
- **매 advantage 의 normalize 안 함**: 매 PPO 매 batch advantage normalization 의 critical.
|
||||
- **매 single epoch only**: 매 PPO 매 multiple epochs (3-10) 의 importance ratio 의 활용.
|
||||
- **매 GRPO without group**: 매 group size 1 → 매 advantage = 0.
|
||||
|
||||
## 🧪 검증 / 중복
|
||||
- Verified (PPO Schulman 2017, GRPO DeepSeek-Math 2024, DPO Rafailov 2023, TRL docs).
|
||||
- 신뢰도 A.
|
||||
|
||||
## 🕓 Changelog
|
||||
| 날짜 | 변경 |
|
||||
|---|---|
|
||||
| 2026-05-08 | Phase 1 |
|
||||
| 2026-05-10 | Manual cleanup — PPO/GRPO/DPO + GAE + TRL patterns |
|
||||
Reference in New Issue
Block a user